From a3ecf6190920a1b995b1736bd974cc0ab9725709 Mon Sep 17 00:00:00 2001 From: Alexandre Gaillet Date: Thu, 26 Apr 2018 17:47:47 +0200 Subject: [PATCH 01/21] MON-160 - AWS monitors updated --- cloud/aws/vpn/README.md | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/cloud/aws/vpn/README.md b/cloud/aws/vpn/README.md index f180994..a37e3c2 100644 --- a/cloud/aws/vpn/README.md +++ b/cloud/aws/vpn/README.md @@ -32,3 +32,11 @@ Inputs | vpn_status_message | Custom message for VPN status monitor | string | `` | no | | vpn_status_silenced | Groups to mute for VPN status monitor | map | `` | no | | vpn_status_timeframe | Monitor timeframe for VPN status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | + +Related documentation +--------------------- + +DataDog documentation: [https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/vpn-metricscollected.html](https://docs.datadoghq.com/integrations/amazon_web_services/) + +AWS VPN metrics documentation: [https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/vpn-metricscollected.html](https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/vpn-metricscollected.html) + From 966a9b5f540e0f1ec843305060303c002b56e524 Mon Sep 17 00:00:00 2001 From: Alexandre Gaillet Date: Fri, 27 Apr 2018 17:04:47 +0200 Subject: [PATCH 02/21] MON-191 - AWS monitors updated with customizable aggregator --- cloud/aws/alb/README.md | 6 ++++ cloud/aws/alb/inputs.tf | 36 +++++++++++++++++++ cloud/aws/alb/monitors-alb.tf | 32 ++++++++--------- cloud/aws/apigateway/README.md | 4 ++- cloud/aws/apigateway/inputs.tf | 18 ++++++++++ cloud/aws/apigateway/monitors-api.tf | 16 ++++----- cloud/aws/elasticsearch/README.md | 3 ++ cloud/aws/elasticsearch/inputs.tf | 18 ++++++++++ .../elasticsearch/monitors-elasticsearch.tf | 14 ++++---- cloud/aws/elb/README.md | 6 ++++ cloud/aws/elb/inputs.tf | 36 +++++++++++++++++++ cloud/aws/elb/monitors-elb.tf | 32 ++++++++--------- cloud/aws/kinesis-firehose/README.md | 2 ++ cloud/aws/kinesis-firehose/inputs.tf | 6 ++++ .../monitors-kinesis-firehose.tf | 4 +-- cloud/aws/rds/README.md | 2 ++ cloud/aws/rds/inputs.tf | 12 +++++++ cloud/aws/rds/monitors-rds.tf | 10 +++--- cloud/aws/vpn/README.md | 1 + cloud/aws/vpn/inputs.tf | 6 ++++ cloud/aws/vpn/monitors-vpn.tf | 4 +-- 21 files changed, 211 insertions(+), 57 deletions(-) diff --git a/cloud/aws/alb/README.md b/cloud/aws/alb/README.md index 027e1fd..64d78db 100644 --- a/cloud/aws/alb/README.md +++ b/cloud/aws/alb/README.md @@ -30,6 +30,7 @@ Inputs | Name | Description | Type | Default | Required | |------|-------------|:----:|:-----:|:-----:| +| alb_no_healthy_instances_aggregator | Monitor aggregator for ALB no healthy instances [available values: min, max, sum or avg] | string | `min` | no | | alb_no_healthy_instances_message | Custom message for ALB no healthy instances monitor | string | `` | no | | alb_no_healthy_instances_silenced | Groups to mute for ALB no healthy instances monitor | map | `` | no | | alb_no_healthy_instances_timeframe | Monitor timeframe for ALB no healthy instances [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_1m` | no | @@ -38,26 +39,31 @@ Inputs | environment | Architecture environment | string | - | yes | | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | +| httpcode_elb_4xx_aggregator | Monitor aggregator for ALB httpcode 4xx [available values: min, max, sum or avg] | string | `min` | no | | httpcode_elb_4xx_message | Custom message for ALB httpcode 4xx monitor | string | `` | no | | httpcode_elb_4xx_silenced | Groups to mute for ALB httpcode 4xx monitor | map | `` | no | | httpcode_elb_4xx_threshold_critical | loadbalancer 4xx critical threshold in percentage | string | `80` | no | | httpcode_elb_4xx_threshold_warning | loadbalancer 4xx warning threshold in percentage | string | `60` | no | | httpcode_elb_4xx_timeframe | Monitor timeframe for ALB httpcode 4xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| httpcode_elb_5xx_aggregator | Monitor aggregator for ALB httpcode 5xx [available values: min, max, sum or avg] | string | `min` | no | | httpcode_elb_5xx_message | Custom message for ALB httpcode 5xx monitor | string | `` | no | | httpcode_elb_5xx_silenced | Groups to mute for ALB httpcode 5xx monitor | map | `` | no | | httpcode_elb_5xx_threshold_critical | loadbalancer 5xxcritical threshold in percentage | string | `80` | no | | httpcode_elb_5xx_threshold_warning | loadbalancer 5xx warning threshold in percentage | string | `60` | no | | httpcode_elb_5xx_timeframe | Monitor timeframe for ALB httpcode 5xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| httpcode_target_4xx_aggregator | Monitor aggregator for ALB target httpcode 4xx [available values: min, max, sum or avg] | string | `min` | no | | httpcode_target_4xx_message | Custom message for ALB target httpcode 4xx monitor | string | `` | no | | httpcode_target_4xx_silenced | Groups to mute for ALB target httpcode 4xx monitor | map | `` | no | | httpcode_target_4xx_threshold_critical | target 4xx critical threshold in percentage | string | `80` | no | | httpcode_target_4xx_threshold_warning | target 4xx warning threshold in percentage | string | `60` | no | | httpcode_target_4xx_timeframe | Monitor timeframe for ALB target httpcode 4xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| httpcode_target_5xx_aggregator | Monitor aggregator for ALB target httpcode 5xx [available values: min, max, sum or avg] | string | `min` | no | | httpcode_target_5xx_message | Custom message for ALB target httpcode 5xx monitor | string | `` | no | | httpcode_target_5xx_silenced | Groups to mute for ALB target httpcode 5xx monitor | map | `` | no | | httpcode_target_5xx_threshold_critical | target 5xx critical threshold in percentage | string | `80` | no | | httpcode_target_5xx_threshold_warning | target 5xx warning threshold in percentage | string | `60` | no | | httpcode_target_5xx_timeframe | Monitor timeframe for ALB target httpcode 5xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| latency_aggregator | Monitor aggregator for ALB latency [available values: min, max, sum or avg] | string | `min` | no | | latency_message | Custom message for ALB latency monitor | string | `` | no | | latency_silenced | Groups to mute for ALB latency monitor | map | `` | no | | latency_threshold_critical | latency critical threshold in milliseconds | string | `1000` | no | diff --git a/cloud/aws/alb/inputs.tf b/cloud/aws/alb/inputs.tf index 585740e..68a057a 100644 --- a/cloud/aws/alb/inputs.tf +++ b/cloud/aws/alb/inputs.tf @@ -38,6 +38,12 @@ variable "alb_no_healthy_instances_message" { default = "" } +variable "alb_no_healthy_instances_aggregator" { + description = "Monitor aggregator for ALB no healthy instances [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "alb_no_healthy_instances_timeframe" { description = "Monitor timeframe for ALB no healthy instances [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -56,6 +62,12 @@ variable "latency_message" { default = "" } +variable "latency_aggregator" { + description = "Monitor aggregator for ALB latency [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "latency_timeframe" { description = "Monitor timeframe for ALB latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -84,6 +96,12 @@ variable "httpcode_elb_4xx_message" { default = "" } +variable "httpcode_elb_4xx_aggregator" { + description = "Monitor aggregator for ALB httpcode 4xx [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "httpcode_elb_4xx_timeframe" { description = "Monitor timeframe for ALB httpcode 4xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -112,6 +130,12 @@ variable "httpcode_target_4xx_message" { default = "" } +variable "httpcode_target_4xx_aggregator" { + description = "Monitor aggregator for ALB target httpcode 4xx [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "httpcode_target_4xx_timeframe" { description = "Monitor timeframe for ALB target httpcode 4xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -140,6 +164,12 @@ variable "httpcode_elb_5xx_message" { default = "" } +variable "httpcode_elb_5xx_aggregator" { + description = "Monitor aggregator for ALB httpcode 5xx [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "httpcode_elb_5xx_timeframe" { description = "Monitor timeframe for ALB httpcode 5xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -168,6 +198,12 @@ variable "httpcode_target_5xx_message" { default = "" } +variable "httpcode_target_5xx_aggregator" { + description = "Monitor aggregator for ALB target httpcode 5xx [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "httpcode_target_5xx_timeframe" { description = "Monitor timeframe for ALB target httpcode 5xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/aws/alb/monitors-alb.tf b/cloud/aws/alb/monitors-alb.tf index 51d2d5b..e9272b2 100644 --- a/cloud/aws/alb/monitors-alb.tf +++ b/cloud/aws/alb/monitors-alb.tf @@ -14,8 +14,8 @@ resource "datadog_monitor" "ALB_no_healthy_instances" { message = "${coalesce(var.alb_no_healthy_instances_message, var.message)}" query = < ${var.latency_threshold_critical} EOF @@ -73,10 +73,10 @@ resource "datadog_monitor" "ALB_httpcode_elb_5xx" { message = "${coalesce(var.httpcode_elb_5xx_message, var.message)}" query = < ${var.httpcode_elb_5xx_threshold_critical} EOF @@ -106,10 +106,10 @@ resource "datadog_monitor" "ALB_httpcode_elb_4xx" { message = "${coalesce(var.httpcode_elb_4xx_message, var.message)}" query = < ${var.httpcode_elb_4xx_threshold_critical} EOF @@ -139,10 +139,10 @@ resource "datadog_monitor" "ALB_httpcode_target_5xx" { message = "${coalesce(var.httpcode_target_5xx_message, var.message)}" query = < ${var.httpcode_target_5xx_threshold_critical} EOF @@ -172,10 +172,10 @@ resource "datadog_monitor" "ALB_httpcode_target_4xx" { message = "${coalesce(var.httpcode_target_4xx_message, var.message)}" query = < ${var.httpcode_target_4xx_threshold_critical} EOF diff --git a/cloud/aws/apigateway/README.md b/cloud/aws/apigateway/README.md index 755cfce..9ec15b9 100644 --- a/cloud/aws/apigateway/README.md +++ b/cloud/aws/apigateway/README.md @@ -31,23 +31,25 @@ Inputs | delay | Delay in seconds for the metric evaluation | string | `900` | no | | environment | Environment | string | - | yes | | filter_tags | Tags used for filtering | string | `*` | no | +| http_4xx_requests_aggregator | Monitor aggregator for API Gateway HTTP 4xx requests [available values: min, max, sum or avg] | string | `min` | no | | http_4xx_requests_message | Custom message for API Gateway HTTP 4xx requests monitor | string | `` | no | | http_4xx_requests_silenced | Groups to mute for API Gateway HTTP 4xx requests monitor | map | `` | no | | http_4xx_requests_threshold_critical | Maximum critical acceptable percent of 4xx errors | string | `30` | no | | http_4xx_requests_threshold_warning | Maximum warning acceptable percent of 4xx errors | string | `15` | no | | http_4xx_requests_timeframe | Monitor timeframe for API HTTP 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| http_5xx_requests_aggregator | Monitor aggregator for API Gateway HTTP 5xx requests [available values: min, max, sum or avg] | string | `min` | no | | http_5xx_requests_message | Custom message for API Gateway HTTP 5xx requests monitor | string | `` | no | | http_5xx_requests_silenced | Groups to mute for API Gateway HTTP 5xx requests monitor | map | `` | no | | http_5xx_requests_threshold_critical | Maximum critical acceptable percent of 5xx errors | string | `20` | no | | http_5xx_requests_threshold_warning | Maximum warning acceptable percent of 5xx errors | string | `10` | no | | http_5xx_requests_timeframe | Monitor timeframe for API HTTP 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| latency_aggregator | Monitor aggregator for API Gateway latency [available values: min, max, sum or avg] | string | `min` | no | | latency_message | Custom message for API Gateway latency monitor | string | `` | no | | latency_silenced | Groups to mute for API Gateway latency monitor | map | `` | no | | latency_threshold_critical | Alerting threshold in milliseconds | string | `800` | no | | latency_threshold_warning | Warning threshold in milliseconds | string | `400` | no | | latency_timeframe | Monitor timeframe for API latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | message | Message sent when a monitor is triggered | string | - | yes | - Related documentation --------------------- diff --git a/cloud/aws/apigateway/inputs.tf b/cloud/aws/apigateway/inputs.tf index 83acd7c..21598f8 100644 --- a/cloud/aws/apigateway/inputs.tf +++ b/cloud/aws/apigateway/inputs.tf @@ -33,6 +33,12 @@ variable "latency_message" { default = "" } +variable "latency_aggregator" { + description = "Monitor aggregator for API Gateway latency [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "latency_timeframe" { description = "Monitor timeframe for API latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -65,6 +71,12 @@ variable "http_5xx_requests_message" { default = "" } +variable "http_5xx_requests_aggregator" { + description = "Monitor aggregator for API Gateway HTTP 5xx requests [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "http_5xx_requests_timeframe" { description = "Monitor timeframe for API HTTP 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -97,6 +109,12 @@ variable "http_4xx_requests_message" { default = "" } +variable "http_4xx_requests_aggregator" { + description = "Monitor aggregator for API Gateway HTTP 4xx requests [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "http_4xx_requests_timeframe" { description = "Monitor timeframe for API HTTP 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/aws/apigateway/monitors-api.tf b/cloud/aws/apigateway/monitors-api.tf index 8fd52a7..602fdfd 100644 --- a/cloud/aws/apigateway/monitors-api.tf +++ b/cloud/aws/apigateway/monitors-api.tf @@ -5,8 +5,8 @@ resource "datadog_monitor" "API_Gateway_latency" { message = "${coalesce(var.latency_message, var.message)}" query = < ${var.latency_threshold_critical} EOF @@ -36,10 +36,10 @@ resource "datadog_monitor" "API_http_5xx_errors_count" { message = "${coalesce(var.http_5xx_requests_message, var.message)}" query = < ${var.http_5xx_requests_threshold_critical} EOF @@ -70,10 +70,10 @@ resource "datadog_monitor" "API_http_4xx_errors_count" { message = "${coalesce(var.http_4xx_requests_message, var.message)}" query = < ${var.http_4xx_requests_threshold_critical} EOF diff --git a/cloud/aws/elasticsearch/README.md b/cloud/aws/elasticsearch/README.md index 0d57cbd..65015e6 100644 --- a/cloud/aws/elasticsearch/README.md +++ b/cloud/aws/elasticsearch/README.md @@ -29,18 +29,21 @@ Inputs | Name | Description | Type | Default | Required | |------|-------------|:----:|:-----:|:-----:| +| cpu_aggregator | Monitor aggregator for ES cluster cpu [available values: min, max, sum or avg] | string | `avg` | no | | cpu_message | Custom message for ES cluster cpu monitor | string | `` | no | | cpu_silenced | Groups to mute for ES cluster cpu monitor | map | `` | no | | cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no | | cpu_threshold_warning | CPU usage in percent (warning threshold) | string | `80` | no | | cpu_timeframe | Monitor timeframe for ES cluster cpu [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | | delay | Delay in seconds for the metric evaluation | string | `900` | no | +| diskspace_aggregator | Monitor aggregator for ES cluster diskspace [available values: min, max, sum or avg] | string | `avg` | no | | diskspace_message | Custom message for ES cluster diskspace monitor | string | `` | no | | diskspace_silenced | Groups to mute for ES cluster diskspace monitor | map | `` | no | | diskspace_threshold_critical | Disk free space in percent (critical threshold) | string | `10` | no | | diskspace_threshold_warning | Disk free space in percent (warning threshold) | string | `20` | no | | diskspace_timeframe | Monitor timeframe for ES cluster diskspace [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | | environment | Architecture Environment | string | - | yes | +| es_cluster_status_aggregator | Monitor aggregator for ES cluster status [available values: min, max, sum or avg] | string | `max` | no | | es_cluster_status_message | Custom message for ES cluster status monitor | string | `` | no | | es_cluster_status_silenced | Groups to mute for ES cluster status monitor | map | `` | no | | es_cluster_status_timeframe | Monitor timeframe for ES cluster status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_30m` | no | diff --git a/cloud/aws/elasticsearch/inputs.tf b/cloud/aws/elasticsearch/inputs.tf index 4d3fb2c..ee010a1 100644 --- a/cloud/aws/elasticsearch/inputs.tf +++ b/cloud/aws/elasticsearch/inputs.tf @@ -38,6 +38,12 @@ variable "es_cluster_status_message" { default = "" } +variable "es_cluster_status_aggregator" { + description = "Monitor aggregator for ES cluster status [available values: min, max, sum or avg]" + type = "string" + default = "max" +} + variable "es_cluster_status_timeframe" { description = "Monitor timeframe for ES cluster status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -60,6 +66,12 @@ variable "diskspace_message" { default = "" } +variable "diskspace_aggregator" { + description = "Monitor aggregator for ES cluster diskspace [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "diskspace_timeframe" { description = "Monitor timeframe for ES cluster diskspace [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -88,6 +100,12 @@ variable "cpu_message" { default = "" } +variable "cpu_aggregator" { + description = "Monitor aggregator for ES cluster cpu [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "cpu_timeframe" { description = "Monitor timeframe for ES cluster cpu [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/aws/elasticsearch/monitors-elasticsearch.tf b/cloud/aws/elasticsearch/monitors-elasticsearch.tf index 47dc1e2..309e0a7 100644 --- a/cloud/aws/elasticsearch/monitors-elasticsearch.tf +++ b/cloud/aws/elasticsearch/monitors-elasticsearch.tf @@ -18,9 +18,9 @@ resource "datadog_monitor" "es_cluster_status" { type = "metric alert" query = <= 2 EOF @@ -52,8 +52,8 @@ resource "datadog_monitor" "es_free_space_low" { type = "metric alert" query = < ${var.cpu_threshold_critical} EOF diff --git a/cloud/aws/elb/README.md b/cloud/aws/elb/README.md index ec188f8..0dbc061 100644 --- a/cloud/aws/elb/README.md +++ b/cloud/aws/elb/README.md @@ -32,31 +32,37 @@ Inputs |------|-------------|:----:|:-----:|:-----:| | artificial_requests_count | Number of false requests used to mitigate false positive in case of low trafic | string | `5` | no | | delay | Delay in seconds for the metric evaluation | string | `900` | no | +| elb_4xx_aggregator | Monitor aggregator for ELB 4xx errors [available values: min, max, sum or avg] | string | `min` | no | | elb_4xx_message | Custom message for ELB 4xx errors monitor | string | `` | no | | elb_4xx_silenced | Groups to mute for ELB 4xx errors monitor | map | `` | no | | elb_4xx_threshold_critical | loadbalancer 4xx critical threshold in percentage | string | `10` | no | | elb_4xx_threshold_warning | loadbalancer 4xx warning threshold in percentage | string | `5` | no | | elb_4xx_timeframe | Monitor timeframe for ELB 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| elb_5xx_aggregator | Monitor aggregator for ELB 5xx errors [available values: min, max, sum or avg] | string | `min` | no | | elb_5xx_message | Custom message for ELB 5xx errors monitor | string | `` | no | | elb_5xx_silenced | Groups to mute for ELB 5xx errors monitor | map | `` | no | | elb_5xx_threshold_critical | loadbalancer 5xx critical threshold in percentage | string | `10` | no | | elb_5xx_threshold_warning | loadbalancer 5xx warning threshold in percentage | string | `5` | no | | elb_5xx_timeframe | Monitor timeframe for ELB 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| elb_backend_4xx_aggregator | Monitor aggregator for ELB backend 4xx errors [available values: min, max, sum or avg] | string | `min` | no | | elb_backend_4xx_message | Custom message for ELB backend 4xx errors monitor | string | `` | no | | elb_backend_4xx_silenced | Groups to mute for ELB backend 4xx errors monitor | map | `` | no | | elb_backend_4xx_threshold_critical | loadbalancer backend 4xx critical threshold in percentage | string | `10` | no | | elb_backend_4xx_threshold_warning | loadbalancer backend 4xx warning threshold in percentage | string | `5` | no | | elb_backend_4xx_timeframe | Monitor timeframe for ELB backend 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| elb_backend_5xx_aggregator | Monitor aggregator for ELB backend 5xx errors [available values: min, max, sum or avg] | string | `min` | no | | elb_backend_5xx_message | Custom message for ELB backend 5xx errors monitor | string | `` | no | | elb_backend_5xx_silenced | Groups to mute for ELB backend 5xx errors monitor | map | `` | no | | elb_backend_5xx_threshold_critical | loadbalancer backend 5xx critical threshold in percentage | string | `10` | no | | elb_backend_5xx_threshold_warning | loadbalancer backend 5xx warning threshold in percentage | string | `5` | no | | elb_backend_5xx_timeframe | Monitor timeframe for ELB backend 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| elb_backend_latency_aggregator | Monitor aggregator for ELB backend latency [available values: min, max, sum or avg] | string | `min` | no | | elb_backend_latency_critical | latency critical threshold in seconds | string | `5` | no | | elb_backend_latency_message | Custom message for ELB backend latency monitor | string | `` | no | | elb_backend_latency_silenced | Groups to mute for ELB backend latency monitor | map | `` | no | | elb_backend_latency_timeframe | Monitor timeframe for ELB backend latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | elb_backend_latency_warning | latency warning threshold in seconds | string | `1` | no | +| elb_no_healthy_instance_aggregator | Monitor aggregator for ELB no healty instance [available values: min, max, sum or avg] | string | `min` | no | | elb_no_healthy_instance_message | Custom message for ELB no healty instance monitor | string | `` | no | | elb_no_healthy_instance_silenced | Groups to mute for ELB no healty instance monitor | map | `` | no | | elb_no_healthy_instance_timeframe | Monitor timeframe for ELB no healty instance [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | diff --git a/cloud/aws/elb/inputs.tf b/cloud/aws/elb/inputs.tf index 4809da0..53dc1fe 100644 --- a/cloud/aws/elb/inputs.tf +++ b/cloud/aws/elb/inputs.tf @@ -37,6 +37,12 @@ variable "elb_no_healthy_instance_message" { default = "" } +variable "elb_no_healthy_instance_aggregator" { + description = "Monitor aggregator for ELB no healty instance [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "elb_no_healthy_instance_timeframe" { description = "Monitor timeframe for ELB no healty instance [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -55,6 +61,12 @@ variable "elb_4xx_message" { default = "" } +variable "elb_4xx_aggregator" { + description = "Monitor aggregator for ELB 4xx errors [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "elb_4xx_timeframe" { description = "Monitor timeframe for ELB 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -83,6 +95,12 @@ variable "elb_5xx_message" { default = "" } +variable "elb_5xx_aggregator" { + description = "Monitor aggregator for ELB 5xx errors [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "elb_5xx_timeframe" { description = "Monitor timeframe for ELB 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -111,6 +129,12 @@ variable "elb_backend_4xx_message" { default = "" } +variable "elb_backend_4xx_aggregator" { + description = "Monitor aggregator for ELB backend 4xx errors [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "elb_backend_4xx_timeframe" { description = "Monitor timeframe for ELB backend 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -139,6 +163,12 @@ variable "elb_backend_5xx_message" { default = "" } +variable "elb_backend_5xx_aggregator" { + description = "Monitor aggregator for ELB backend 5xx errors [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "elb_backend_5xx_timeframe" { description = "Monitor timeframe for ELB backend 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -167,6 +197,12 @@ variable "elb_backend_latency_message" { default = "" } +variable "elb_backend_latency_aggregator" { + description = "Monitor aggregator for ELB backend latency [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "elb_backend_latency_timeframe" { description = "Monitor timeframe for ELB backend latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/aws/elb/monitors-elb.tf b/cloud/aws/elb/monitors-elb.tf index a36f403..1390137 100644 --- a/cloud/aws/elb/monitors-elb.tf +++ b/cloud/aws/elb/monitors-elb.tf @@ -11,8 +11,8 @@ resource "datadog_monitor" "ELB_no_healthy_instances" { message = "${coalesce(var.elb_no_healthy_instance_message, var.message)}" query = < ${var.elb_4xx_threshold_critical} EOF @@ -73,10 +73,10 @@ resource "datadog_monitor" "ELB_too_much_5xx" { message = "${coalesce(var.elb_5xx_message, var.message)}" query = < ${var.elb_5xx_threshold_critical} EOF @@ -108,10 +108,10 @@ resource "datadog_monitor" "ELB_too_much_4xx_backend" { message = "${coalesce(var.elb_backend_4xx_message, var.message)}" query = < ${var.elb_backend_4xx_threshold_critical} EOF @@ -143,10 +143,10 @@ resource "datadog_monitor" "ELB_too_much_5xx_backend" { message = "${coalesce(var.elb_backend_5xx_message, var.message)}" query = < ${var.elb_backend_5xx_threshold_critical} EOF @@ -178,8 +178,8 @@ resource "datadog_monitor" "ELB_backend_latency" { message = "${coalesce(var.elb_backend_latency_message, var.message)}" query = < ${var.elb_backend_latency_critical} EOF diff --git a/cloud/aws/kinesis-firehose/README.md b/cloud/aws/kinesis-firehose/README.md index f4bffe6..21d4214 100644 --- a/cloud/aws/kinesis-firehose/README.md +++ b/cloud/aws/kinesis-firehose/README.md @@ -22,12 +22,14 @@ Creates DataDog monitors with the following checks : Inputs ------ + | Name | Description | Type | Default | Required | |------|-------------|:----:|:-----:|:-----:| | delay | Delay in seconds for the metric evaluation | string | `900` | no | | environment | Environment | string | - | yes | | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | +| incoming_records_aggregator | Monitor aggregator for Kinesis Firehorse incoming records [available values: min, max, sum or avg] | string | `sum` | no | | incoming_records_message | Custom message for Kinesis Firehorse incoming records monitor | string | `` | no | | incoming_records_silenced | Groups to mute for Kinesis Firehorse incoming records monitor | map | `` | no | | incoming_records_timeframe | Monitor timeframe for incoming records metrics evaluation [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | diff --git a/cloud/aws/kinesis-firehose/inputs.tf b/cloud/aws/kinesis-firehose/inputs.tf index 831045e..931b253 100644 --- a/cloud/aws/kinesis-firehose/inputs.tf +++ b/cloud/aws/kinesis-firehose/inputs.tf @@ -38,6 +38,12 @@ variable "incoming_records_message" { default = "" } +variable "incoming_records_aggregator" { + description = "Monitor aggregator for Kinesis Firehorse incoming records [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "incoming_records_timeframe" { description = "Monitor timeframe for incoming records metrics evaluation [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" default = "last_15m" diff --git a/cloud/aws/kinesis-firehose/monitors-kinesis-firehose.tf b/cloud/aws/kinesis-firehose/monitors-kinesis-firehose.tf index 1f1a71b..d5ab13f 100644 --- a/cloud/aws/kinesis-firehose/monitors-kinesis-firehose.tf +++ b/cloud/aws/kinesis-firehose/monitors-kinesis-firehose.tf @@ -14,8 +14,8 @@ resource "datadog_monitor" "firehose_incoming_records" { type = "metric alert" query = <` | no | | cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no | | cpu_threshold_warning | CPU usage in percent (warning threshold) | string | `80` | no | | cpu_timeframe | Monitor timeframe for RDS CPU usage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | | delay | Delay in seconds for the metric evaluation | string | `900` | no | +| diskspace_aggregator | Monitor aggregator for RDS free diskspace [available values: min, max, sum or avg] | string | `avg` | no | | diskspace_message | Custom message for RDS free diskspace monitor | string | `` | no | | diskspace_silenced | Groups to mute for RDS free diskspace monitor | map | `` | no | | diskspace_threshold_critical | Disk free space in percent (critical threshold) | string | `10` | no | diff --git a/cloud/aws/rds/inputs.tf b/cloud/aws/rds/inputs.tf index 37be0e2..e54b16d 100644 --- a/cloud/aws/rds/inputs.tf +++ b/cloud/aws/rds/inputs.tf @@ -38,6 +38,12 @@ variable "cpu_message" { default = "" } +variable "cpu_aggregator" { + description = "Monitor aggregator for RDS CPU usage [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "cpu_timeframe" { description = "Monitor timeframe for RDS CPU usage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -66,6 +72,12 @@ variable "diskspace_message" { default = "" } +variable "diskspace_aggregator" { + description = "Monitor aggregator for RDS free diskspace [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "diskspace_timeframe" { description = "Monitor timeframe for RDS free diskspace [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/aws/rds/monitors-rds.tf b/cloud/aws/rds/monitors-rds.tf index 2717d1d..6c452be 100644 --- a/cloud/aws/rds/monitors-rds.tf +++ b/cloud/aws/rds/monitors-rds.tf @@ -14,8 +14,8 @@ resource "datadog_monitor" "rds_cpu_90_15min" { type = "metric alert" query = < ${var.cpu_threshold_critical} EOF @@ -46,9 +46,9 @@ resource "datadog_monitor" "rds_free_space_low" { type = "metric alert" query = <` | no | | vpn_status_timeframe | Monitor timeframe for VPN status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | diff --git a/cloud/aws/vpn/inputs.tf b/cloud/aws/vpn/inputs.tf index 13314b6..a95f500 100644 --- a/cloud/aws/vpn/inputs.tf +++ b/cloud/aws/vpn/inputs.tf @@ -36,6 +36,12 @@ variable "vpn_status_message" { default = "" } +variable "vpn_status_aggregator" { + description = "Monitor aggregator for VPN status [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "vpn_status_timeframe" { description = "Monitor timeframe for VPN status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/aws/vpn/monitors-vpn.tf b/cloud/aws/vpn/monitors-vpn.tf index 1f94ebf..63c2a89 100644 --- a/cloud/aws/vpn/monitors-vpn.tf +++ b/cloud/aws/vpn/monitors-vpn.tf @@ -11,8 +11,8 @@ resource "datadog_monitor" "VPN_status" { message = "${coalesce(var.vpn_status_message, var.message)}" query = < Date: Fri, 27 Apr 2018 18:26:56 +0200 Subject: [PATCH 03/21] MON-191 - Azure monitors updated with customizable aggregator --- cloud/azure/apimanagement/README.md | 5 + cloud/azure/apimanagement/inputs.tf | 30 +++++ .../monitors-azure-apimanagement.tf | 36 +++--- cloud/azure/app-services/README.md | 5 + cloud/azure/app-services/inputs.tf | 30 +++++ .../app-services/monitors-app_services.tf | 28 ++--- cloud/azure/eventhub/README.md | 3 + cloud/azure/eventhub/inputs.tf | 18 +++ cloud/azure/eventhub/monitors-eventhub.tf | 24 ++-- cloud/azure/iothubs/README.md | 14 +++ cloud/azure/iothubs/inputs.tf | 84 +++++++++++++ cloud/azure/iothubs/monitors-iothubs.tf | 110 +++++++++--------- cloud/azure/redis/README.md | 4 + cloud/azure/redis/inputs.tf | 24 ++++ cloud/azure/redis/monitors-azure-redis.tf | 4 +- cloud/azure/sql-database/README.md | 4 + cloud/azure/sql-database/inputs.tf | 24 ++++ .../monitors-sql-database-basics.tf | 14 +-- cloud/azure/storage/README.md | 9 ++ cloud/azure/storage/inputs.tf | 54 +++++++++ cloud/azure/storage/monitors-azure-storage.tf | 36 +++--- cloud/azure/stream-analytics/README.md | 5 + cloud/azure/stream-analytics/inputs.tf | 30 +++++ .../monitors-stream-analytics.tf | 20 ++-- 24 files changed, 479 insertions(+), 136 deletions(-) diff --git a/cloud/azure/apimanagement/README.md b/cloud/azure/apimanagement/README.md index aa1ec85..1b33552 100644 --- a/cloud/azure/apimanagement/README.md +++ b/cloud/azure/apimanagement/README.md @@ -29,6 +29,7 @@ Inputs |------|-------------|:----:|:-----:|:-----:| | delay | Delay in seconds for the metric evaluation | string | `900` | no | | environment | Architecture environment | string | - | yes | +| failed_requests_aggregator | Monitor aggregator for API Management failed requests [available values: min, max, sum or avg] | string | `sum` | no | | failed_requests_message | Custom message for API Management failed requests monitor | string | `` | no | | failed_requests_silenced | Groups to mute for API Management failed requests monitor | map | `` | no | | failed_requests_threshold_critical | Maximum acceptable percent of failed requests | string | `90` | no | @@ -37,19 +38,23 @@ Inputs | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | | message | Message sent when a Redis monitor is triggered | string | - | yes | +| other_requests_aggregator | Monitor aggregator for API Management other requests [available values: min, max, sum or avg] | string | `sum` | no | | other_requests_message | Custom message for API Management other requests monitor | string | `` | no | | other_requests_silenced | Groups to mute for API Management other requests monitor | map | `` | no | | other_requests_threshold_critical | Maximum acceptable percent of other requests | string | `90` | no | | other_requests_threshold_warning | Warning regarding acceptable percent of other requests | string | `50` | no | | other_requests_timeframe | Monitor timeframe for API Management other requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| status_aggregator | Monitor aggregator for API Management status [available values: min, max, sum or avg] | string | `avg` | no | | status_message | Custom message for API Management status monitor | string | `` | no | | status_silenced | Groups to mute for API Management status monitor | map | `` | no | | status_timeframe | Monitor timeframe for API Management status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| successful_requests_aggregator | Monitor aggregator for API Management successful requests [available values: min, max, sum or avg] | string | `sum` | no | | successful_requests_message | Custom message for API Management successful requests monitor | string | `` | no | | successful_requests_silenced | Groups to mute for API Management successful requests monitor | map | `` | no | | successful_requests_threshold_critical | Minimum acceptable percent of successful requests | string | `10` | no | | successful_requests_threshold_warning | Warning regarding acceptable percent of successful requests | string | `30` | no | | successful_requests_timeframe | Monitor timeframe for API Management successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| unauthorized_requests_aggregator | Monitor aggregator for API Management unauthorized requests [available values: min, max, sum or avg] | string | `sum` | no | | unauthorized_requests_message | Custom message for API Management unauthorized requests monitor | string | `` | no | | unauthorized_requests_silenced | Groups to mute for API Management unauthorized requests monitor | map | `` | no | | unauthorized_requests_threshold_critical | Maximum acceptable percent of unauthorized requests | string | `90` | no | diff --git a/cloud/azure/apimanagement/inputs.tf b/cloud/azure/apimanagement/inputs.tf index 0a91eea..5b690b2 100644 --- a/cloud/azure/apimanagement/inputs.tf +++ b/cloud/azure/apimanagement/inputs.tf @@ -37,6 +37,12 @@ variable "status_message" { default = "" } +variable "status_aggregator" { + description = "Monitor aggregator for API Management status [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "status_timeframe" { description = "Monitor timeframe for API Management status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -55,6 +61,12 @@ variable "failed_requests_message" { default = "" } +variable "failed_requests_aggregator" { + description = "Monitor aggregator for API Management failed requests [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "failed_requests_timeframe" { description = "Monitor timeframe for API Management failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -83,6 +95,12 @@ variable "other_requests_message" { default = "" } +variable "other_requests_aggregator" { + description = "Monitor aggregator for API Management other requests [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "other_requests_timeframe" { description = "Monitor timeframe for API Management other requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -111,6 +129,12 @@ variable "unauthorized_requests_message" { default = "" } +variable "unauthorized_requests_aggregator" { + description = "Monitor aggregator for API Management unauthorized requests [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "unauthorized_requests_timeframe" { description = "Monitor timeframe for API Management unauthorized requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -139,6 +163,12 @@ variable "successful_requests_message" { default = "" } +variable "successful_requests_aggregator" { + description = "Monitor aggregator for API Management successful requests [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "successful_requests_timeframe" { description = "Monitor timeframe for API Management successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/azure/apimanagement/monitors-azure-apimanagement.tf b/cloud/azure/apimanagement/monitors-azure-apimanagement.tf index 1775ed2..7de8dd1 100644 --- a/cloud/azure/apimanagement/monitors-azure-apimanagement.tf +++ b/cloud/azure/apimanagement/monitors-azure-apimanagement.tf @@ -13,8 +13,8 @@ resource "datadog_monitor" "apimgt_status" { message = "${coalesce(var.status_message, var.message)}" query = < ${var.failed_requests_threshold_critical} - EOF + EOF thresholds { critical = "${var.failed_requests_threshold_critical}" @@ -74,11 +74,11 @@ resource "datadog_monitor" "apimgt_other_requests" { message = "${coalesce(var.other_requests_message, var.message)}" query = < ${var.other_requests_threshold_critical} - EOF + EOF thresholds { critical = "${var.other_requests_threshold_critical}" @@ -106,11 +106,11 @@ resource "datadog_monitor" "apimgt_unauthorized_requests" { message = "${coalesce(var.unauthorized_requests_message, var.message)}" query = < ${var.unauthorized_requests_threshold_critical} - EOF + EOF thresholds { critical = "${var.unauthorized_requests_threshold_critical}" @@ -138,11 +138,11 @@ resource "datadog_monitor" "apimgt_successful_requests" { message = "${coalesce(var.successful_requests_message, var.message)}" query = <` | no | | http_4xx_requests_threshold_critical | Maximum critical acceptable percent of 4xx errors | string | `90` | no | | http_4xx_requests_threshold_warning | Warning regarding acceptable percent of 4xx errors | string | `50` | no | | http_4xx_requests_timeframe | Monitor timeframe for App Services 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| http_5xx_requests_aggregator | Monitor aggregator for App Services 5xx requests [available values: min, max, sum or avg] | string | `sum` | no | | http_5xx_requests_message | Custom message for App Services 5xx requests monitor | string | `` | no | | http_5xx_requests_silenced | Groups to mute for App Services 5xx requests monitor | map | `` | no | | http_5xx_requests_threshold_critical | Maximum critical acceptable percent of 5xx errors | string | `90` | no | | http_5xx_requests_threshold_warning | Warning regarding acceptable percent of 5xx errors | string | `50` | no | | http_5xx_requests_timeframe | Monitor timeframe for App Services 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| http_successful_requests_aggregator | Monitor aggregator for App Services successful requests [available values: min, max, sum or avg] | string | `sum` | no | | http_successful_requests_message | Custom message for App Services successful requests monitor | string | `` | no | | http_successful_requests_silenced | Groups to mute for App Services successful requests monitor | map | `` | no | | http_successful_requests_threshold_critical | Minimum critical acceptable percent of 2xx & 3xx requests | string | `10` | no | | http_successful_requests_threshold_warning | Warning regarding acceptable percent of 2xx & 3xx requests | string | `30` | no | | http_successful_requests_timeframe | Monitor timeframe for App Services successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| memory_usage_aggregator | Monitor aggregator for App Services memory usage [available values: min, max, sum or avg] | string | `avg` | no | | memory_usage_message | Custom message for App Services memory usage monitor | string | `` | no | | memory_usage_silenced | Groups to mute for App Services memory usage monitor | map | `` | no | | memory_usage_threshold_critical | Alerting threshold in Mib | string | `1073741824` | no | | memory_usage_threshold_warning | Warning threshold in MiB | string | `536870912` | no | | memory_usage_timeframe | Monitor timeframe for App Services memory usage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | message | Message sent when a monitor is triggered | string | - | yes | +| response_time_aggregator | Monitor aggregator for App Services response time [available values: min, max, sum or avg] | string | `min` | no | | response_time_message | Custom message for App Services response time monitor | string | `` | no | | response_time_silenced | Groups to mute for App Services response time monitor | map | `` | no | | response_time_threshold_critical | Alerting threshold for response time in seconds | string | `10` | no | diff --git a/cloud/azure/app-services/inputs.tf b/cloud/azure/app-services/inputs.tf index d41e977..55d967b 100644 --- a/cloud/azure/app-services/inputs.tf +++ b/cloud/azure/app-services/inputs.tf @@ -35,6 +35,12 @@ variable "response_time_message" { default = "" } +variable "response_time_aggregator" { + description = "Monitor aggregator for App Services response time [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "response_time_timeframe" { description = "Monitor timeframe for App Services response time [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -63,6 +69,12 @@ variable "memory_usage_message" { default = "" } +variable "memory_usage_aggregator" { + description = "Monitor aggregator for App Services memory usage [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "memory_usage_timeframe" { description = "Monitor timeframe for App Services memory usage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -91,6 +103,12 @@ variable "http_4xx_requests_message" { default = "" } +variable "http_4xx_requests_aggregator" { + description = "Monitor aggregator for App Services 4xx requests [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "http_4xx_requests_timeframe" { description = "Monitor timeframe for App Services 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -119,6 +137,12 @@ variable "http_5xx_requests_message" { default = "" } +variable "http_5xx_requests_aggregator" { + description = "Monitor aggregator for App Services 5xx requests [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "http_5xx_requests_timeframe" { description = "Monitor timeframe for App Services 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -147,6 +171,12 @@ variable "http_successful_requests_message" { default = "" } +variable "http_successful_requests_aggregator" { + description = "Monitor aggregator for App Services successful requests [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "http_successful_requests_timeframe" { description = "Monitor timeframe for App Services successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/azure/app-services/monitors-app_services.tf b/cloud/azure/app-services/monitors-app_services.tf index b8f639b..202b76b 100644 --- a/cloud/azure/app-services/monitors-app_services.tf +++ b/cloud/azure/app-services/monitors-app_services.tf @@ -13,8 +13,8 @@ resource "datadog_monitor" "appservices_response_time" { message = "${coalesce(var.response_time_message, var.message)}" query = < ${var.response_time_threshold_critical} EOF @@ -44,8 +44,8 @@ resource "datadog_monitor" "appservices_memory_usage_count" { message = "${coalesce(var.memory_usage_message, var.message)}" query = < ${var.memory_usage_threshold_critical} EOF @@ -75,9 +75,9 @@ resource "datadog_monitor" "appservices_http_5xx_errors_count" { message = "${coalesce(var.http_5xx_requests_message, var.message)}" query = < ${var.http_5xx_requests_threshold_critical} EOF @@ -107,9 +107,9 @@ resource "datadog_monitor" "appservices_http_4xx_errors_count" { message = "${coalesce(var.http_4xx_requests_message, var.message)}" query = < ${var.http_4xx_requests_threshold_critical} EOF @@ -139,10 +139,10 @@ resource "datadog_monitor" "appservices_http_success_status_rate" { message = "${coalesce(var.http_successful_requests_message, var.message)}" query = <` | no | | errors_rate_thresold_critical | Errors ratio (percentage) to trigger the critical alert | string | `90` | no | | errors_rate_thresold_warning | Errors ratio (percentage) to trigger a warning alert | string | `50` | no | | errors_rate_timeframe | Monitor timeframe for Event Hub errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| failed_requests_rate_aggregator | Monitor aggregator for Event Hub failed requests [available values: min, max, sum or avg] | string | `sum` | no | | failed_requests_rate_message | Custom message for Event Hub failed requests monitor | string | `` | no | | failed_requests_rate_silenced | Groups to mute for Event Hub failed requests monitor | map | `` | no | | failed_requests_rate_thresold_critical | Failed requests ratio (percentage) to trigger the critical alert | string | `90` | no | @@ -41,6 +43,7 @@ Inputs | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | | message | Message sent when an alert is triggered | string | - | yes | +| status_aggregator | Monitor aggregator for Event Hub status [available values: min, max, sum or avg] | string | `avg` | no | | status_message | Custom message for Event Hub status monitor | string | `` | no | | status_silenced | Groups to mute for Event Hub status monitor | map | `` | no | | status_timeframe | Monitor timeframe for Event Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | diff --git a/cloud/azure/eventhub/inputs.tf b/cloud/azure/eventhub/inputs.tf index 963be45..1748b6f 100644 --- a/cloud/azure/eventhub/inputs.tf +++ b/cloud/azure/eventhub/inputs.tf @@ -37,6 +37,12 @@ variable "status_message" { default = "" } +variable "status_aggregator" { + description = "Monitor aggregator for Event Hub status [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "status_timeframe" { description = "Monitor timeframe for Event Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -55,6 +61,12 @@ variable "failed_requests_rate_message" { default = "" } +variable "failed_requests_rate_aggregator" { + description = "Monitor aggregator for Event Hub failed requests [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "failed_requests_rate_timeframe" { description = "Monitor timeframe for Event Hub failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -83,6 +95,12 @@ variable "errors_rate_message" { default = "" } +variable "errors_rate_aggregator" { + description = "Monitor aggregator for Event Hub errors [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "errors_rate_timeframe" { description = "Monitor timeframe for Event Hub errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/azure/eventhub/monitors-eventhub.tf b/cloud/azure/eventhub/monitors-eventhub.tf index 21e531b..612b326 100644 --- a/cloud/azure/eventhub/monitors-eventhub.tf +++ b/cloud/azure/eventhub/monitors-eventhub.tf @@ -11,8 +11,8 @@ resource "datadog_monitor" "eventhub_status" { message = "${coalesce(var.status_message, var.message)}" query = < ${var.failed_requests_rate_thresold_critical} - EOF + EOF type = "metric alert" @@ -71,18 +71,18 @@ resource "datadog_monitor" "eventhub_errors" { message = "${coalesce(var.errors_rate_message, var.message)}" query = < ${var.errors_rate_thresold_critical} - EOF + EOF type = "metric alert" diff --git a/cloud/azure/iothubs/README.md b/cloud/azure/iothubs/README.md index 4e6ecd9..8678e3b 100644 --- a/cloud/azure/iothubs/README.md +++ b/cloud/azure/iothubs/README.md @@ -39,70 +39,84 @@ Inputs | Name | Description | Type | Default | Required | |------|-------------|:----:|:-----:|:-----:| | delay | Delay in seconds for the metric evaluation | string | `900` | no | +| dropped_d2c_telemetry_egress_aggregator | Monitor aggregator for IoT Hub failed d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no | | dropped_d2c_telemetry_egress_message | Custom message for IoT Hub dropped d2c telemetry monitor | string | `` | no | | dropped_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Dropped limit (critical threshold) | string | `90` | no | | dropped_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Dropped limit (warning threshold) | string | `50` | no | | dropped_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub dropped d2c telemetry monitor | map | `` | no | | dropped_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub dropped d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | environment | Architecture Environment | string | - | yes | +| failed_c2d_methods_rate_aggregator | Monitor aggregator for IoT Hub failed c2d method [available values: min, max, sum or avg] | string | `sum` | no | | failed_c2d_methods_rate_message | Custom message for IoT Hub failed c2d method monitor | string | `` | no | | failed_c2d_methods_rate_silenced | Groups to mute for IoT Hub failed c2d methods monitor | map | `` | no | | failed_c2d_methods_rate_threshold_critical | C2D Methods Failed rate limit (critical threshold) | string | `90` | no | | failed_c2d_methods_rate_threshold_warning | C2D Methods Failed rate limit (warning threshold) | string | `50` | no | | failed_c2d_methods_rate_timeframe | Monitor timeframe for IoT Hub failed c2d method [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| failed_c2d_twin_read_rate_aggregator | Monitor aggregator for IoT Hub failed c2d twin read [available values: min, max, sum or avg] | string | `sum` | no | | failed_c2d_twin_read_rate_message | Custom message for IoT Hub failed c2d twin read monitor | string | `` | no | | failed_c2d_twin_read_rate_silenced | Groups to mute for IoT Hub failed c2d twin read monitor | map | `` | no | | failed_c2d_twin_read_rate_threshold_critical | C2D Twin Read Failed rate limit (critical threshold) | string | `90` | no | | failed_c2d_twin_read_rate_threshold_warning | C2D Twin Read Failed rate limit (warning threshold) | string | `50` | no | | failed_c2d_twin_read_rate_timeframe | Monitor timeframe for IoT Hub failed c2d twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| failed_c2d_twin_update_rate_aggregator | Monitor aggregator for IoT Hub failed c2d twin update [available values: min, max, sum or avg] | string | `sum` | no | | failed_c2d_twin_update_rate_message | Custom message for IoT Hub failed c2d twin update monitor | string | `` | no | | failed_c2d_twin_update_rate_silenced | Groups to mute for IoT Hub failed c2d twin update monitor | map | `` | no | | failed_c2d_twin_update_rate_threshold_critical | C2D Twin Update Failed rate limit (critical threshold) | string | `90` | no | | failed_c2d_twin_update_rate_threshold_warning | C2D Twin Update Failed rate limit (warning threshold) | string | `50` | no | | failed_c2d_twin_update_rate_timeframe | Monitor timeframe for IoT Hub failed c2d twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| failed_d2c_twin_read_rate_aggregator | Monitor aggregator for IoT Hub failed d2c twin read [available values: min, max, sum or avg] | string | `sum` | no | | failed_d2c_twin_read_rate_message | Custom message for IoT Hub failed d2c twin read monitor | string | `` | no | | failed_d2c_twin_read_rate_silenced | Groups to mute for IoT Hub failed d2c twin read monitor | map | `` | no | | failed_d2c_twin_read_rate_threshold_critical | D2C Twin Read Failed rate limit (critical threshold) | string | `90` | no | | failed_d2c_twin_read_rate_threshold_warning | D2C Twin Read Failed rate limit (warning threshold) | string | `50` | no | | failed_d2c_twin_read_rate_timeframe | Monitor timeframe for IoT Hub failed d2c twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| failed_d2c_twin_update_rate_aggregator | Monitor aggregator for IoT Hub failed d2c twin update [available values: min, max, sum or avg] | string | `sum` | no | | failed_d2c_twin_update_rate_message | Custom message for IoT Hub failed d2c twin update monitor | string | `` | no | | failed_d2c_twin_update_rate_silenced | Groups to mute for IoT Hub failed d2c twin update monitor | map | `` | no | | failed_d2c_twin_update_rate_threshold_critical | D2C Twin Update Failed rate limit (critical threshold) | string | `90` | no | | failed_d2c_twin_update_rate_threshold_warning | D2C Twin Update Failed rate limit (warning threshold) | string | `50` | no | | failed_d2c_twin_update_rate_timeframe | Monitor timeframe for IoT Hub failed d2c twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| failed_jobs_rate_aggregator | Monitor aggregator for IoT Hub failed jobs [available values: min, max, sum or avg] | string | `sum` | no | | failed_jobs_rate_message | Custom message for IoT Hub failed jobs monitor | string | `` | no | | failed_jobs_rate_silenced | Groups to mute for IoT Hub failed jobs monitor | map | `` | no | | failed_jobs_rate_threshold_critical | Jobs Failed rate limit (critical threshold) | string | `90` | no | | failed_jobs_rate_threshold_warning | Jobs Failed rate limit (warning threshold) | string | `50` | no | | failed_jobs_rate_timeframe | Monitor timeframe for IoT Hub failed jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| failed_listjobs_rate_aggregator | Monitor aggregator for IoT Hub failed listjobs jobs [available values: min, max, sum or avg] | string | `sum` | no | | failed_listjobs_rate_message | Custom message for IoT Hub failed list jobs monitor | string | `` | no | | failed_listjobs_rate_silenced | Groups to mute for IoT Hub failed list jobs monitor | map | `` | no | | failed_listjobs_rate_threshold_critical | ListJobs Failed rate limit (critical threshold) | string | `90` | no | | failed_listjobs_rate_threshold_warning | ListJobs Failed rate limit (warning threshold) | string | `50` | no | | failed_listjobs_rate_timeframe | Monitor timeframe for IoT Hub failed list jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| failed_queryjobs_rate_aggregator | Monitor aggregator for IoT Hub failed query jobs [available values: min, max, sum or avg] | string | `sum` | no | | failed_queryjobs_rate_message | Custom message for IoT Hub failed query jobs monitor | string | `` | no | | failed_queryjobs_rate_silenced | Groups to mute for IoT Hub failed query jobs monitor | map | `` | no | | failed_queryjobs_rate_threshold_critical | QueryJobs Failed rate limit (critical threshold) | string | `90` | no | | failed_queryjobs_rate_threshold_warning | QueryJobs Failed rate limit (warning threshold) | string | `50` | no | | failed_queryjobs_rate_timeframe | Monitor timeframe for IoT Hub failed query jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | filter_tags | Tags used for filtering | string | `*` | no | +| invalid_d2c_telemetry_egress_aggregator | Monitor aggregator for IoT Hub invalid d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no | | invalid_d2c_telemetry_egress_message | Custom message for IoT Hub invalid d2c telemetry monitor | string | `` | no | | invalid_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Invalid limit (critical threshold) | string | `90` | no | | invalid_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Invalid limit (warning threshold) | string | `50` | no | | invalid_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub invalid d2c telemetry monitor | map | `` | no | | invalid_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub invalid d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | message | Message sent when an alert is triggered | string | - | yes | +| orphaned_d2c_telemetry_egress_aggregator | Monitor aggregator for IoT Hub orphaned d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no | | orphaned_d2c_telemetry_egress_message | Custom message for IoT Hub orphaned d2c telemetry monitor | string | `` | no | | orphaned_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Orphaned limit (critical threshold) | string | `90` | no | | orphaned_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Orphaned limit (warning threshold) | string | `50` | no | | orphaned_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub orphaned d2c telemetry monitor | map | `` | no | | orphaned_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub orphaned d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| status_aggregator | Monitor aggregator for IoT Hub status [available values: min, max, sum or avg] | string | `avg` | no | | status_message | Custom message for IoT Hub status monitor | string | `` | no | | status_silenced | Groups to mute for IoT Hub status monitor | map | `` | no | | status_timeframe | Monitor timeframe for IoT Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| too_many_d2c_telemetry_ingress_nosent_aggregator | Monitor aggregator for IoT Hub unsent d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no | | too_many_d2c_telemetry_ingress_nosent_message | Custom message for IoT Hub unsent d2c telemetry monitor | string | `` | no | | too_many_d2c_telemetry_ingress_nosent_silenced | Groups to mute for IoT Hub unsent d2c telemetry monitor | map | `` | no | | too_many_d2c_telemetry_ingress_nosent_timeframe | Monitor timeframe for IoT Hub unsent d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| total_devices_aggregator | Monitor aggregator for IoT Hub total devices [available values: min, max, sum or avg] | string | `avg` | no | | total_devices_message | Custom message for IoT Hub total devices monitor | string | `` | no | | total_devices_silenced | Groups to mute for IoT Hub total devices monitor | map | `` | no | | total_devices_timeframe | Monitor timeframe for IoT Hub total devices [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | diff --git a/cloud/azure/iothubs/inputs.tf b/cloud/azure/iothubs/inputs.tf index 47680e2..f4763a9 100644 --- a/cloud/azure/iothubs/inputs.tf +++ b/cloud/azure/iothubs/inputs.tf @@ -32,6 +32,12 @@ variable "status_message" { default = "" } +variable "status_aggregator" { + description = "Monitor aggregator for IoT Hub status [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "status_timeframe" { description = "Monitor timeframe for IoT Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -50,6 +56,12 @@ variable "total_devices_message" { default = "" } +variable "total_devices_aggregator" { + description = "Monitor aggregator for IoT Hub total devices [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "total_devices_timeframe" { description = "Monitor timeframe for IoT Hub total devices [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -68,6 +80,12 @@ variable "too_many_d2c_telemetry_ingress_nosent_message" { default = "" } +variable "too_many_d2c_telemetry_ingress_nosent_aggregator" { + description = "Monitor aggregator for IoT Hub unsent d2c telemetry [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "too_many_d2c_telemetry_ingress_nosent_timeframe" { description = "Monitor timeframe for IoT Hub unsent d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -86,6 +104,12 @@ variable "failed_jobs_rate_message" { default = "" } +variable "failed_jobs_rate_aggregator" { + description = "Monitor aggregator for IoT Hub failed jobs [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "failed_jobs_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -114,6 +138,12 @@ variable "failed_listjobs_rate_message" { default = "" } +variable "failed_listjobs_rate_aggregator" { + description = "Monitor aggregator for IoT Hub failed listjobs jobs [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "failed_listjobs_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed list jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -142,6 +172,12 @@ variable "failed_queryjobs_rate_message" { default = "" } +variable "failed_queryjobs_rate_aggregator" { + description = "Monitor aggregator for IoT Hub failed query jobs [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "failed_queryjobs_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed query jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -170,6 +206,12 @@ variable "failed_c2d_methods_rate_message" { default = "" } +variable "failed_c2d_methods_rate_aggregator" { + description = "Monitor aggregator for IoT Hub failed c2d method [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "failed_c2d_methods_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed c2d method [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -198,6 +240,12 @@ variable "failed_c2d_twin_read_rate_message" { default = "" } +variable "failed_c2d_twin_read_rate_aggregator" { + description = "Monitor aggregator for IoT Hub failed c2d twin read [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "failed_c2d_twin_read_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed c2d twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -226,6 +274,12 @@ variable "failed_c2d_twin_update_rate_message" { default = "" } +variable "failed_c2d_twin_update_rate_aggregator" { + description = "Monitor aggregator for IoT Hub failed c2d twin update [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "failed_c2d_twin_update_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed c2d twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -254,6 +308,12 @@ variable "failed_d2c_twin_read_rate_message" { default = "" } +variable "failed_d2c_twin_read_rate_aggregator" { + description = "Monitor aggregator for IoT Hub failed d2c twin read [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "failed_d2c_twin_read_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed d2c twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -282,6 +342,12 @@ variable "failed_d2c_twin_update_rate_message" { default = "" } +variable "failed_d2c_twin_update_rate_aggregator" { + description = "Monitor aggregator for IoT Hub failed d2c twin update [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "failed_d2c_twin_update_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed d2c twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -310,6 +376,12 @@ variable "dropped_d2c_telemetry_egress_message" { default = "" } +variable "dropped_d2c_telemetry_egress_aggregator" { + description = "Monitor aggregator for IoT Hub failed d2c telemetry [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "dropped_d2c_telemetry_egress_timeframe" { description = "Monitor timeframe for IoT Hub dropped d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -338,6 +410,12 @@ variable "orphaned_d2c_telemetry_egress_message" { default = "" } +variable "orphaned_d2c_telemetry_egress_aggregator" { + description = "Monitor aggregator for IoT Hub orphaned d2c telemetry [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "orphaned_d2c_telemetry_egress_timeframe" { description = "Monitor timeframe for IoT Hub orphaned d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -366,6 +444,12 @@ variable "invalid_d2c_telemetry_egress_message" { default = "" } +variable "invalid_d2c_telemetry_egress_aggregator" { + description = "Monitor aggregator for IoT Hub invalid d2c telemetry [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "invalid_d2c_telemetry_egress_timeframe" { description = "Monitor timeframe for IoT Hub invalid d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/azure/iothubs/monitors-iothubs.tf b/cloud/azure/iothubs/monitors-iothubs.tf index 4a70a02..f4d54b5 100644 --- a/cloud/azure/iothubs/monitors-iothubs.tf +++ b/cloud/azure/iothubs/monitors-iothubs.tf @@ -3,10 +3,10 @@ resource "datadog_monitor" "too_many_jobs_failed" { message = "${coalesce(var.failed_jobs_rate_message, var.message)}" query = < ${var.failed_jobs_rate_threshold_critical} EOF @@ -37,10 +37,10 @@ resource "datadog_monitor" "too_many_list_jobs_failed" { message = "${coalesce(var.failed_listjobs_rate_message, var.message)}" query = < ${var.failed_listjobs_rate_threshold_critical} EOF @@ -71,10 +71,10 @@ resource "datadog_monitor" "too_many_query_jobs_failed" { message = "${coalesce(var.failed_queryjobs_rate_message, var.message)}" query = < ${var.failed_queryjobs_rate_threshold_critical} EOF @@ -105,7 +105,7 @@ resource "datadog_monitor" "status" { message = "${coalesce(var.status_message, var.message)}" query = < ${var.failed_c2d_methods_rate_threshold_critical} EOF @@ -189,10 +189,10 @@ resource "datadog_monitor" "too_many_c2d_twin_read_failed" { message = "${coalesce(var.failed_c2d_twin_read_rate_message, var.message)}" query = < ${var.failed_c2d_twin_read_rate_threshold_critical} EOF @@ -223,10 +223,10 @@ resource "datadog_monitor" "too_many_c2d_twin_update_failed" { message = "${coalesce(var.failed_c2d_twin_update_rate_message, var.message)}" query = < ${var.failed_c2d_twin_update_rate_threshold_critical} EOF @@ -257,10 +257,10 @@ resource "datadog_monitor" "too_many_d2c_twin_read_failed" { message = "${coalesce(var.failed_d2c_twin_read_rate_message, var.message)}" query = < ${var.failed_d2c_twin_read_rate_threshold_critical} EOF @@ -291,10 +291,10 @@ resource "datadog_monitor" "too_many_d2c_twin_update_failed" { message = "${coalesce(var.failed_d2c_twin_update_rate_message, var.message)}" query = < ${var.failed_d2c_twin_update_rate_threshold_critical} EOF @@ -325,12 +325,12 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_dropped" { message = "${coalesce(var.dropped_d2c_telemetry_egress_message, var.message)}" query = < ${var.dropped_d2c_telemetry_egress_rate_threshold_critical} EOF @@ -362,12 +362,12 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_orphaned" { message = "${coalesce(var.orphaned_d2c_telemetry_egress_message, var.message)}" query = < ${var.orphaned_d2c_telemetry_egress_rate_threshold_critical} EOF @@ -399,12 +399,12 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_invalid" { message = "${coalesce(var.invalid_d2c_telemetry_egress_message, var.message)}" query = < ${var.invalid_d2c_telemetry_egress_rate_threshold_critical} EOF @@ -436,9 +436,9 @@ resource "datadog_monitor" "too_many_d2c_telemetry_ingress_nosent" { message = "${coalesce(var.too_many_d2c_telemetry_ingress_nosent_message, var.message)}" query = < 0 EOF diff --git a/cloud/azure/redis/README.md b/cloud/azure/redis/README.md index b8ebdcc..a7786c5 100644 --- a/cloud/azure/redis/README.md +++ b/cloud/azure/redis/README.md @@ -29,6 +29,7 @@ Inputs |------|-------------|:----:|:-----:|:-----:| | delay | Delay in seconds for the metric evaluation | string | `900` | no | | environment | Architecture environment | string | - | yes | +| evictedkeys_limit_aggregator | Monitor aggregator for Redis evicted keys [available values: min, max, sum or avg] | string | `avg` | no | | evictedkeys_limit_message | Custom message for Redis evicted keys monitor | string | `` | no | | evictedkeys_limit_silenced | Groups to mute for Redis evicted keys monitor | map | `` | no | | evictedkeys_limit_threshold_critical | Evicted keys limit (critical threshold) | string | `100` | no | @@ -37,16 +38,19 @@ Inputs | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | | message | Message sent when a Redis monitor is triggered | string | - | yes | +| percent_processor_time_aggregator | Monitor aggregator for Redis processor [available values: min, max, sum or avg] | string | `avg` | no | | percent_processor_time_message | Custom message for Redis processor monitor | string | `` | no | | percent_processor_time_silenced | Groups to mute for Redis processor monitor | map | `` | no | | percent_processor_time_threshold_critical | Processor time percent (critical threshold) | string | `80` | no | | percent_processor_time_threshold_warning | Processor time percent (warning threshold) | string | `60` | no | | percent_processor_time_timeframe | Monitor timeframe for Redis processor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| server_load_rate_aggregator | Monitor aggregator for Redis server load [available values: min, max, sum or avg] | string | `avg` | no | | server_load_rate_message | Custom message for Redis server load monitor | string | `` | no | | server_load_rate_silenced | Groups to mute for Redis server load monitor | map | `` | no | | server_load_rate_threshold_critical | Server CPU load rate (critical threshold) | string | `90` | no | | server_load_rate_threshold_warning | Server CPU load rate (warning threshold) | string | `70` | no | | server_load_rate_timeframe | Monitor timeframe for Redis server load [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| status_aggregator | Monitor aggregator for Redis status [available values: min, max, sum or avg] | string | `avg` | no | | status_message | Custom message for Redis status monitor | string | `` | no | | status_silenced | Groups to mute for Redis status monitor | map | `` | no | | status_timeframe | Monitor timeframe for Redis status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | diff --git a/cloud/azure/redis/inputs.tf b/cloud/azure/redis/inputs.tf index e3c0887..372bfae 100644 --- a/cloud/azure/redis/inputs.tf +++ b/cloud/azure/redis/inputs.tf @@ -37,6 +37,12 @@ variable "status_message" { default = "" } +variable "status_aggregator" { + description = "Monitor aggregator for Redis status [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "status_timeframe" { description = "Monitor timeframe for Redis status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -55,6 +61,12 @@ variable "evictedkeys_limit_message" { default = "" } +variable "evictedkeys_limit_aggregator" { + description = "Monitor aggregator for Redis evicted keys [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "evictedkeys_limit_timeframe" { description = "Monitor timeframe for Redis evicted keys [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -83,6 +95,12 @@ variable "percent_processor_time_message" { default = "" } +variable "percent_processor_time_aggregator" { + description = "Monitor aggregator for Redis processor [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "percent_processor_time_timeframe" { description = "Monitor timeframe for Redis processor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -111,6 +129,12 @@ variable "server_load_rate_message" { default = "" } +variable "server_load_rate_aggregator" { + description = "Monitor aggregator for Redis server load [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "server_load_rate_timeframe" { description = "Monitor timeframe for Redis server load [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/azure/redis/monitors-azure-redis.tf b/cloud/azure/redis/monitors-azure-redis.tf index a61b651..ca726f9 100644 --- a/cloud/azure/redis/monitors-azure-redis.tf +++ b/cloud/azure/redis/monitors-azure-redis.tf @@ -100,8 +100,8 @@ resource "datadog_monitor" "server_load" { message = "${coalesce(var.server_load_rate_message, var.message)}" query = < ${var.server_load_rate_threshold_critical} EOF diff --git a/cloud/azure/sql-database/README.md b/cloud/azure/sql-database/README.md index 8b993bb..705e3d3 100644 --- a/cloud/azure/sql-database/README.md +++ b/cloud/azure/sql-database/README.md @@ -27,21 +27,25 @@ Inputs | Name | Description | Type | Default | Required | |------|-------------|:----:|:-----:|:-----:| +| cpu_aggregator | Monitor aggregator for SQL CPU [available values: min, max, sum or avg] | string | `avg` | no | | cpu_message | Custom message for SQL CPU monitor | string | `` | no | | cpu_silenced | Groups to mute for SQL CPU monitor | map | `` | no | | cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no | | cpu_threshold_warning | CPU usage in percent (warning threshold) | string | `80` | no | | cpu_timeframe | Monitor timeframe for SQL CPU [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | +| deadlock_aggregator | Monitor aggregator for SQL Deadlock [available values: min, max, sum or avg] | string | `sum` | no | | deadlock_message | Custom message for SQL Deadlock monitor | string | `` | no | | deadlock_silenced | Groups to mute for SQL Deadlock monitor | map | `` | no | | deadlock_threshold_critical | Amount of Deadlocks (critical threshold) | string | `1` | no | | deadlock_timeframe | Monitor timeframe for SQL Deadlock [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | delay | Delay in seconds for the metric evaluation | string | `900` | no | +| diskspace_aggregator | Monitor aggregator for SQL disk space [available values: min, max, sum or avg] | string | `avg` | no | | diskspace_message | Custom message for SQL disk space monitor | string | `` | no | | diskspace_silenced | Groups to mute for SQL disk space monitor | map | `` | no | | diskspace_threshold_critical | Disk space used in percent (critical threshold) | string | `90` | no | | diskspace_threshold_warning | Disk space used in percent (warning threshold) | string | `80` | no | | diskspace_timeframe | Monitor timeframe for SQL disk space [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | +| dtu_aggregator | Monitor aggregator for SQL DTU [available values: min, max, sum or avg] | string | `avg` | no | | dtu_message | Custom message for SQL DTU monitor | string | `` | no | | dtu_silenced | Groups to mute for SQL DTU monitor | map | `` | no | | dtu_threshold_critical | Amount of DTU used (critical threshold) | string | `90` | no | diff --git a/cloud/azure/sql-database/inputs.tf b/cloud/azure/sql-database/inputs.tf index 386de15..354c36a 100644 --- a/cloud/azure/sql-database/inputs.tf +++ b/cloud/azure/sql-database/inputs.tf @@ -37,6 +37,12 @@ variable "cpu_message" { default = "" } +variable "cpu_aggregator" { + description = "Monitor aggregator for SQL CPU [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "cpu_timeframe" { description = "Monitor timeframe for SQL CPU [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -65,6 +71,12 @@ variable "diskspace_message" { default = "" } +variable "diskspace_aggregator" { + description = "Monitor aggregator for SQL disk space [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "diskspace_timeframe" { description = "Monitor timeframe for SQL disk space [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -93,6 +105,12 @@ variable "dtu_message" { default = "" } +variable "dtu_aggregator" { + description = "Monitor aggregator for SQL DTU [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "dtu_timeframe" { description = "Monitor timeframe for SQL DTU [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -121,6 +139,12 @@ variable "deadlock_message" { default = "" } +variable "deadlock_aggregator" { + description = "Monitor aggregator for SQL Deadlock [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "deadlock_timeframe" { description = "Monitor timeframe for SQL Deadlock [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/azure/sql-database/monitors-sql-database-basics.tf b/cloud/azure/sql-database/monitors-sql-database-basics.tf index 391db76..2413763 100644 --- a/cloud/azure/sql-database/monitors-sql-database-basics.tf +++ b/cloud/azure/sql-database/monitors-sql-database-basics.tf @@ -11,8 +11,8 @@ resource "datadog_monitor" "sql-database_cpu_90_15min" { message = "${coalesce(var.cpu_message, var.message)}" query = < ${var.cpu_threshold_critical} EOF @@ -44,8 +44,8 @@ resource "datadog_monitor" "sql-database_free_space_low" { type = "metric alert" query = < ${var.diskspace_threshold_critical} EOF @@ -76,7 +76,7 @@ resource "datadog_monitor" "sql-database_dtu_consumption_high" { type = "metric alert" query = < ${var.dtu_threshold_critical} EOF @@ -108,8 +108,8 @@ resource "datadog_monitor" "sql-database_deadlocks_count" { type = "metric alert" query = < ${var.deadlock_threshold_critical} EOF diff --git a/cloud/azure/storage/README.md b/cloud/azure/storage/README.md index e85f146..2973151 100644 --- a/cloud/azure/storage/README.md +++ b/cloud/azure/storage/README.md @@ -32,16 +32,19 @@ Inputs | Name | Description | Type | Default | Required | |------|-------------|:----:|:-----:|:-----:| +| authorization_error_requests_aggregator | Monitor aggregator for Storage authorization errors [available values: min, max, sum or avg] | string | `avg` | no | | authorization_error_requests_message | Custom message for Storage authorization errors monitor | string | `` | no | | authorization_error_requests_silenced | Groups to mute for Storage authorization errors monitor | map | `` | no | | authorization_error_requests_threshold_critical | Maximum acceptable percent of authorization error requests for a storage | string | `90` | no | | authorization_error_requests_threshold_warning | Warning regarding acceptable percent of authorization error requests for a storage | string | `50` | no | | authorization_error_requests_timeframe | Monitor timeframe for Storage authorization errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| availability_aggregator | Monitor aggregator for Storage availability [available values: min, max, sum or avg] | string | `avg` | no | | availability_message | Custom message for Storage availability monitor | string | `` | no | | availability_silenced | Groups to mute for Storage availability monitor | map | `` | no | | availability_threshold_critical | Minimum acceptable percent of availability for a storage | string | `50` | no | | availability_threshold_warning | Warning regarding acceptable percent of availability for a storage | string | `90` | no | | availability_timeframe | Monitor timeframe for Storage availability [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| client_other_error_requests_aggregator | Monitor aggregator for Storage other errors [available values: min, max, sum or avg] | string | `avg` | no | | client_other_error_requests_message | Custom message for Storage other errors monitor | string | `` | no | | client_other_error_requests_silenced | Groups to mute for Storage other errors monitor | map | `` | no | | client_other_error_requests_threshold_critical | Maximum acceptable percent of client other error requests for a storage | string | `90` | no | @@ -51,32 +54,38 @@ Inputs | environment | Architecture environment | string | - | yes | | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | +| latency_aggregator | Monitor aggregator for Storage latency [available values: min, max, sum or avg] | string | `min` | no | | latency_message | Custom message for Storage latency monitor | string | `` | no | | latency_silenced | Groups to mute for Storage latency monitor | map | `` | no | | latency_threshold_critical | Maximum acceptable end to end latency (ms) for a storage | string | `2000` | no | | latency_threshold_warning | Warning regarding acceptable end to end latency (ms) for a storage | string | `1000` | no | | latency_timeframe | Monitor timeframe for Storage latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | message | Message sent when a Redis monitor is triggered | string | - | yes | +| network_error_requests_aggregator | Monitor aggregator for Storage network errors [available values: min, max, sum or avg] | string | `avg` | no | | network_error_requests_message | Custom message for Storage network errors monitor | string | `` | no | | network_error_requests_silenced | Groups to mute for Storage network errors monitor | map | `` | no | | network_error_requests_threshold_critical | Maximum acceptable percent of network error requests for a storage | string | `90` | no | | network_error_requests_threshold_warning | Warning regarding acceptable percent of network error requests for a storage | string | `50` | no | | network_error_requests_timeframe | Monitor timeframe for Storage network errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| server_other_error_requests_aggregator | Monitor aggregator for Storage other errors [available values: min, max, sum or avg] | string | `avg` | no | | server_other_error_requests_message | Custom message for Storage server other errors monitor | string | `` | no | | server_other_error_requests_silenced | Groups to mute for Storage server other errors monitor | map | `` | no | | server_other_error_requests_threshold_critical | Maximum acceptable percent of server other error requests for a storage | string | `90` | no | | server_other_error_requests_threshold_warning | Warning regarding acceptable percent of server other error requests for a storage | string | `50` | no | | server_other_error_requests_timeframe | Monitor timeframe for Storage server other errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| successful_requests_aggregator | Monitor aggregator for Storage sucessful requests [available values: min, max, sum or avg] | string | `avg` | no | | successful_requests_message | Custom message for Storage sucessful requests monitor | string | `` | no | | successful_requests_silenced | Groups to mute for Storage sucessful requests monitor | map | `` | no | | successful_requests_threshold_critical | Minimum acceptable percent of successful requests for a storage | string | `10` | no | | successful_requests_threshold_warning | Warning regarding acceptable percent of successful requests for a storage | string | `30` | no | | successful_requests_timeframe | Monitor timeframe for Storage sucessful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| throttling_error_requests_aggregator | Monitor aggregator for Storage throttling errors [available values: min, max, sum or avg] | string | `avg` | no | | throttling_error_requests_message | Custom message for Storage throttling error monitor | string | `` | no | | throttling_error_requests_silenced | Groups to mute for Storage throttling error monitor | map | `` | no | | throttling_error_requests_threshold_critical | Maximum acceptable percent of throttling error requests for a storage | string | `90` | no | | throttling_error_requests_threshold_warning | Warning regarding acceptable percent of throttling error requests for a storage | string | `50` | no | | throttling_error_requests_timeframe | Monitor timeframe for Storage throttling errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| timeout_error_requests_aggregator | Monitor aggregator for Storage timeout [available values: min, max, sum or avg] | string | `avg` | no | | timeout_error_requests_message | Custom message for Storage timeout monitor | string | `` | no | | timeout_error_requests_silenced | Groups to mute for Storage timeout monitor | map | `` | no | | timeout_error_requests_threshold_critical | Maximum acceptable percent of timeout error requests for a storage | string | `90` | no | diff --git a/cloud/azure/storage/inputs.tf b/cloud/azure/storage/inputs.tf index dfd9ae8..75b6379 100644 --- a/cloud/azure/storage/inputs.tf +++ b/cloud/azure/storage/inputs.tf @@ -37,6 +37,12 @@ variable "availability_message" { default = "" } +variable "availability_aggregator" { + description = "Monitor aggregator for Storage availability [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "availability_timeframe" { description = "Monitor timeframe for Storage availability [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -65,6 +71,12 @@ variable "successful_requests_message" { default = "" } +variable "successful_requests_aggregator" { + description = "Monitor aggregator for Storage sucessful requests [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "successful_requests_timeframe" { description = "Monitor timeframe for Storage sucessful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -93,6 +105,12 @@ variable "latency_message" { default = "" } +variable "latency_aggregator" { + description = "Monitor aggregator for Storage latency [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "latency_timeframe" { description = "Monitor timeframe for Storage latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -121,6 +139,12 @@ variable "timeout_error_requests_message" { default = "" } +variable "timeout_error_requests_aggregator" { + description = "Monitor aggregator for Storage timeout [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "timeout_error_requests_timeframe" { description = "Monitor timeframe for Storage timeout [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -149,6 +173,12 @@ variable "network_error_requests_message" { default = "" } +variable "network_error_requests_aggregator" { + description = "Monitor aggregator for Storage network errors [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "network_error_requests_timeframe" { description = "Monitor timeframe for Storage network errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -177,6 +207,12 @@ variable "throttling_error_requests_message" { default = "" } +variable "throttling_error_requests_aggregator" { + description = "Monitor aggregator for Storage throttling errors [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "throttling_error_requests_timeframe" { description = "Monitor timeframe for Storage throttling errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -205,6 +241,12 @@ variable "server_other_error_requests_message" { default = "" } +variable "server_other_error_requests_aggregator" { + description = "Monitor aggregator for Storage other errors [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "server_other_error_requests_timeframe" { description = "Monitor timeframe for Storage server other errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -233,6 +275,12 @@ variable "client_other_error_requests_message" { default = "" } +variable "client_other_error_requests_aggregator" { + description = "Monitor aggregator for Storage other errors [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "client_other_error_requests_timeframe" { description = "Monitor timeframe for Storage other errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -261,6 +309,12 @@ variable "authorization_error_requests_message" { default = "" } +variable "authorization_error_requests_aggregator" { + description = "Monitor aggregator for Storage authorization errors [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "authorization_error_requests_timeframe" { description = "Monitor timeframe for Storage authorization errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/azure/storage/monitors-azure-storage.tf b/cloud/azure/storage/monitors-azure-storage.tf index 34d5396..8ae7e08 100644 --- a/cloud/azure/storage/monitors-azure-storage.tf +++ b/cloud/azure/storage/monitors-azure-storage.tf @@ -11,8 +11,8 @@ resource "datadog_monitor" "availability" { message = "${coalesce(var.availability_message, var.message)}" query = < ${var.latency_threshold_critical} EOF @@ -104,8 +104,8 @@ resource "datadog_monitor" "timeout_error_requests" { message = "${coalesce(var.timeout_error_requests_message, var.message)}" query = < ${var.timeout_error_requests_threshold_critical} EOF @@ -135,8 +135,8 @@ resource "datadog_monitor" "network_error_requests" { message = "${coalesce(var.network_error_requests_message, var.message)}" query = < ${var.network_error_requests_threshold_critical} EOF @@ -166,8 +166,8 @@ resource "datadog_monitor" "throttling_error_requests" { message = "${coalesce(var.throttling_error_requests_message, var.message)}" query = < ${var.throttling_error_requests_threshold_critical} EOF @@ -197,8 +197,8 @@ resource "datadog_monitor" "server_other_error_requests" { message = "${coalesce(var.server_other_error_requests_message, var.message)}" query = < ${var.server_other_error_requests_threshold_critical} EOF @@ -228,8 +228,8 @@ resource "datadog_monitor" "client_other_error_requests" { message = "${coalesce(var.client_other_error_requests_message, var.message)}" query = < ${var.client_other_error_requests_threshold_critical} EOF @@ -259,8 +259,8 @@ resource "datadog_monitor" "authorization_error_requests" { message = "${coalesce(var.authorization_error_requests_message, var.message)}" query = < ${var.authorization_error_requests_threshold_critical} EOF diff --git a/cloud/azure/stream-analytics/README.md b/cloud/azure/stream-analytics/README.md index 32d5b1d..ddf7441 100644 --- a/cloud/azure/stream-analytics/README.md +++ b/cloud/azure/stream-analytics/README.md @@ -18,6 +18,7 @@ Inputs | Name | Description | Type | Default | Required | |------|-------------|:----:|:-----:|:-----:| +| conversion_errors_aggregator | Monitor aggregator for Stream Analytics conversion errors [available values: min, max, sum or avg] | string | `avg` | no | | conversion_errors_message | Custom message for Stream Analytics conversion errors monitor | string | `` | no | | conversion_errors_silenced | Groups to mute for Stream Analytics conversion errors monitor | map | `` | no | | conversion_errors_threshold_critical | Conversion errors limit (critical threshold) | string | `10` | no | @@ -25,6 +26,7 @@ Inputs | conversion_errors_timeframe | Monitor timeframe for Stream Analytics conversion errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | delay | Delay in seconds for the metric evaluation | string | `900` | no | | environment | Architecture environment | string | - | yes | +| failed_function_requests_aggregator | Monitor aggregator for Stream Analytics failed requests [available values: min, max, sum or avg] | string | `sum` | no | | failed_function_requests_message | Custom message for Stream Analytics failed requests monitor | string | `` | no | | failed_function_requests_silenced | Groups to mute for Stream Analytics failed requests monitor | map | `` | no | | failed_function_requests_threshold_critical | Failed Function Request rate limit (critical threshold) | string | `10` | no | @@ -33,14 +35,17 @@ Inputs | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | | message | Message sent when a Redis monitor is triggered | string | - | yes | +| runtime_errors_aggregator | Monitor aggregator for Stream Analytics runtime errors [available values: min, max, sum or avg] | string | `avg` | no | | runtime_errors_message | Custom message for Stream Analytics runtime errors monitor | string | `` | no | | runtime_errors_silenced | Groups to mute for Stream Analytics runtime errors monitor | map | `` | no | | runtime_errors_threshold_critical | Runtime errors limit (critical threshold) | string | `10` | no | | runtime_errors_threshold_warning | Runtime errors limit (warning threshold) | string | `0` | no | | runtime_errors_timeframe | Monitor timeframe for Stream Analytics runtime errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| status_aggregator | Monitor aggregator for Stream Analytics status [available values: min, max, sum or avg] | string | `avg` | no | | status_message | Custom message for Stream Analytics status monitor | string | `` | no | | status_silenced | Groups to mute for Stream Analytics status monitor | map | `` | no | | status_timeframe | Monitor timeframe for Stream Analytics status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| su_utilization_aggregator | Monitor aggregator for Stream Analytics utilization [available values: min, max, sum or avg] | string | `avg` | no | | su_utilization_message | Custom message for Stream Analytics utilization monitor | string | `` | no | | su_utilization_silenced | Groups to mute for Stream Analytics utilization monitor | map | `` | no | | su_utilization_threshold_critical | Streaming Unit utilization rate limit (critical threshold) | string | `80` | no | diff --git a/cloud/azure/stream-analytics/inputs.tf b/cloud/azure/stream-analytics/inputs.tf index 0c2170c..6878bde 100644 --- a/cloud/azure/stream-analytics/inputs.tf +++ b/cloud/azure/stream-analytics/inputs.tf @@ -37,6 +37,12 @@ variable "status_message" { default = "" } +variable "status_aggregator" { + description = "Monitor aggregator for Stream Analytics status [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "status_timeframe" { description = "Monitor timeframe for Stream Analytics status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -55,6 +61,12 @@ variable "su_utilization_message" { default = "" } +variable "su_utilization_aggregator" { + description = "Monitor aggregator for Stream Analytics utilization [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "su_utilization_timeframe" { description = "Monitor timeframe for Stream Analytics utilization [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -83,6 +95,12 @@ variable "failed_function_requests_message" { default = "" } +variable "failed_function_requests_aggregator" { + description = "Monitor aggregator for Stream Analytics failed requests [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + variable "failed_function_requests_timeframe" { description = "Monitor timeframe for Stream Analytics failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -111,6 +129,12 @@ variable "conversion_errors_message" { default = "" } +variable "conversion_errors_aggregator" { + description = "Monitor aggregator for Stream Analytics conversion errors [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "conversion_errors_timeframe" { description = "Monitor timeframe for Stream Analytics conversion errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -139,6 +163,12 @@ variable "runtime_errors_message" { default = "" } +variable "runtime_errors_aggregator" { + description = "Monitor aggregator for Stream Analytics runtime errors [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "runtime_errors_timeframe" { description = "Monitor timeframe for Stream Analytics runtime errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/azure/stream-analytics/monitors-stream-analytics.tf b/cloud/azure/stream-analytics/monitors-stream-analytics.tf index 51ab80a..693b4f2 100644 --- a/cloud/azure/stream-analytics/monitors-stream-analytics.tf +++ b/cloud/azure/stream-analytics/monitors-stream-analytics.tf @@ -11,7 +11,7 @@ resource "datadog_monitor" "status" { message = "${coalesce(var.status_message, var.message)}" query = < ${var.su_utilization_threshold_critical} EOF @@ -68,9 +68,9 @@ resource "datadog_monitor" "failed_function_requests" { message = "${coalesce(var.failed_function_requests_message, var.message)}" query = < ${var.failed_function_requests_threshold_critical} EOF @@ -101,8 +101,8 @@ resource "datadog_monitor" "conversion_errors" { message = "${coalesce(var.conversion_errors_message, var.message)}" query = < ${var.conversion_errors_threshold_critical} EOF @@ -133,8 +133,8 @@ resource "datadog_monitor" "runtime_errors" { message = "${coalesce(var.runtime_errors_message, var.message)}" query = < ${var.runtime_errors_threshold_critical} EOF From 2ba79aefeafc1cac2a018b41ecb3f5eb6abcfc3b Mon Sep 17 00:00:00 2001 From: Alexandre Gaillet Date: Mon, 30 Apr 2018 15:26:09 +0200 Subject: [PATCH 04/21] MON-191 - General Azure README updated --- cloud/azure/README.md | 100 ++++++- cloud/azure/inputs.tf | 588 ++++++++++++++++++++++++++++++++++++++++ cloud/azure/monitors.tf | 97 +++++++ 3 files changed, 784 insertions(+), 1 deletion(-) diff --git a/cloud/azure/README.md b/cloud/azure/README.md index 1a02600..55ddb36 100644 --- a/cloud/azure/README.md +++ b/cloud/azure/README.md @@ -32,197 +32,295 @@ Inputs | Name | Description | Type | Default | Required | |------|-------------|:----:|:-----:|:-----:| +| apimanagement_failed_requests_aggregator | Monitor aggregator for API Management failed requests [available values: min, max, sum or avg] | string | `sum` | no | | apimanagement_failed_requests_message | Custom message for API Management failed requests monitor | string | `` | no | | apimanagement_failed_requests_silenced | Groups to mute for API Management failed requests monitor | map | `` | no | | apimanagement_failed_requests_threshold_critical | Maximum acceptable percent of failed requests | string | `90` | no | | apimanagement_failed_requests_threshold_warning | Warning regarding acceptable percent of failed requests | string | `50` | no | +| apimanagement_failed_requests_timeframe | Monitor timeframe for API Management failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| apimanagement_other_requests_aggregator | Monitor aggregator for API Management other requests [available values: min, max, sum or avg] | string | `sum` | no | | apimanagement_other_requests_message | Custom message for API Management other requests monitor | string | `` | no | | apimanagement_other_requests_silenced | Groups to mute for API Management other requests monitor | map | `` | no | | apimanagement_other_requests_threshold_critical | Maximum acceptable percent of other requests | string | `90` | no | | apimanagement_other_requests_threshold_warning | Warning regarding acceptable percent of other requests | string | `50` | no | +| apimanagement_other_requests_timeframe | Monitor timeframe for API Management other requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| apimanagement_status_aggregator | Monitor aggregator for API Management status [available values: min, max, sum or avg] | string | `avg` | no | | apimanagement_status_message | Custom message for API Management status monitor | string | `` | no | | apimanagement_status_silenced | Groups to mute for API Management status monitor | map | `` | no | +| apimanagement_status_timeframe | Monitor timeframe for API Management status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| apimanagement_successful_requests_aggregator | Monitor aggregator for API Management successful requests [available values: min, max, sum or avg] | string | `sum` | no | | apimanagement_successful_requests_message | Custom message for API Management successful requests monitor | string | `` | no | | apimanagement_successful_requests_silenced | Groups to mute for API Management successful requests monitor | map | `` | no | | apimanagement_successful_requests_threshold_critical | Minimum acceptable percent of successful requests | string | `10` | no | | apimanagement_successful_requests_threshold_warning | Warning regarding acceptable percent of successful requests | string | `30` | no | +| apimanagement_successful_requests_timeframe | Monitor timeframe for API Management successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| apimanagement_unauthorized_requests_aggregator | Monitor aggregator for API Management unauthorized requests [available values: min, max, sum or avg] | string | `sum` | no | | apimanagement_unauthorized_requests_message | Custom message for API Management unauthorized requests monitor | string | `` | no | | apimanagement_unauthorized_requests_silenced | Groups to mute for API Management unauthorized requests monitor | map | `` | no | | apimanagement_unauthorized_requests_threshold_critical | Maximum acceptable percent of unauthorized requests | string | `90` | no | | apimanagement_unauthorized_requests_threshold_warning | Warning regarding acceptable percent of unauthorized requests | string | `50` | no | +| apimanagement_unauthorized_requests_timeframe | Monitor timeframe for API Management unauthorized requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| appservices_http_4xx_requests_aggregator | Monitor aggregator for App Services 4xx requests [available values: min, max, sum or avg] | string | `sum` | no | | appservices_http_4xx_requests_message | Custom message for App Services 4xx requests monitor | string | `` | no | | appservices_http_4xx_requests_silenced | Groups to mute for App Services 4xx requests monitor | map | `` | no | | appservices_http_4xx_requests_threshold_critical | Maximum critical acceptable percent of 4xx errors | string | `90` | no | | appservices_http_4xx_requests_threshold_warning | Warning regarding acceptable percent of 4xx errors | string | `50` | no | +| appservices_http_4xx_requests_timeframe | Monitor timeframe for App Services 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| appservices_http_5xx_requests_aggregator | Monitor aggregator for App Services 5xx requests [available values: min, max, sum or avg] | string | `sum` | no | | appservices_http_5xx_requests_message | Custom message for App Services 5xx requests monitor | string | `` | no | | appservices_http_5xx_requests_silenced | Groups to mute for App Services 5xx requests monitor | map | `` | no | | appservices_http_5xx_requests_threshold_critical | Maximum critical acceptable percent of 5xx errors | string | `90` | no | | appservices_http_5xx_requests_threshold_warning | Warning regarding acceptable percent of 5xx errors | string | `50` | no | +| appservices_http_5xx_requests_timeframe | Monitor timeframe for App Services 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| appservices_http_successful_requests_aggregator | Monitor aggregator for App Services successful requests [available values: min, max, sum or avg] | string | `sum` | no | | appservices_http_successful_requests_message | Custom message for App Services successful requests monitor | string | `` | no | | appservices_http_successful_requests_silenced | Groups to mute for App Services successful requests monitor | map | `` | no | | appservices_http_successful_requests_threshold_critical | Minimum critical acceptable percent of 2xx & 3xx requests | string | `10` | no | | appservices_http_successful_requests_threshold_warning | Warning regarding acceptable percent of 2xx & 3xx requests | string | `30` | no | +| appservices_http_successful_requests_timeframe | Monitor timeframe for App Services successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| appservices_memory_usage_aggregator | Monitor aggregator for App Services memory usage [available values: min, max, sum or avg] | string | `avg` | no | | appservices_memory_usage_message | Custom message for App Services memory usage monitor | string | `` | no | | appservices_memory_usage_silenced | Groups to mute for App Services memory usage monitor | map | `` | no | | appservices_memory_usage_threshold_critical | Alerting threshold in Mib | string | `1073741824` | no | | appservices_memory_usage_threshold_warning | Warning threshold in MiB | string | `536870912` | no | +| appservices_memory_usage_timeframe | Monitor timeframe for App Services memory usage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| appservices_response_time_aggregator | Monitor aggregator for App Services response time [available values: min, max, sum or avg] | string | `min` | no | | appservices_response_time_message | Custom message for App Services response time monitor | string | `` | no | | appservices_response_time_silenced | Groups to mute for App Services response time monitor | map | `` | no | | appservices_response_time_threshold_critical | Alerting threshold for response time in seconds | string | `10` | no | | appservices_response_time_threshold_warning | Warning threshold for response time in seconds | string | `5` | no | +| appservices_response_time_timeframe | Monitor timeframe for App Services response time [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | delay | Delay in seconds for the metric evaluation | string | `900` | no | | environment | Architecture environment | string | - | yes | +| eventhub_errors_rate_aggregator | Monitor aggregator for Event Hub errors [available values: min, max, sum or avg] | string | `sum` | no | | eventhub_errors_rate_message | Custom message for Event Hub errors monitor | string | `` | no | | eventhub_errors_rate_silenced | Groups to mute for Event Hub errors monitor | map | `` | no | | eventhub_errors_rate_thresold_critical | Errors ratio (percentage) to trigger the critical alert | string | `90` | no | | eventhub_errors_rate_thresold_warning | Errors ratio (percentage) to trigger a warning alert | string | `50` | no | +| eventhub_errors_rate_timeframe | Monitor timeframe for Event Hub errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| eventhub_failed_requests_rate_aggregator | Monitor aggregator for Event Hub failed requests [available values: min, max, sum or avg] | string | `sum` | no | | eventhub_failed_requests_rate_message | Custom message for Event Hub failed requests monitor | string | `` | no | | eventhub_failed_requests_rate_silenced | Groups to mute for Event Hub failed requests monitor | map | `` | no | | eventhub_failed_requests_rate_thresold_critical | Failed requests ratio (percentage) to trigger the critical alert | string | `90` | no | | eventhub_failed_requests_rate_thresold_warning | Failed requests ratio (percentage) to trigger a warning alert | string | `50` | no | +| eventhub_failed_requests_rate_timeframe | Monitor timeframe for Event Hub failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| eventhub_status_aggregator | Monitor aggregator for Event Hub status [available values: min, max, sum or avg] | string | `avg` | no | | eventhub_status_message | Custom message for Event Hub status monitor | string | `` | no | | eventhub_status_silenced | Groups to mute for Event Hub status monitor | map | `` | no | +| eventhub_status_timeframe | Monitor timeframe for Event Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | +| iothub_dropped_d2c_telemetry_egress_aggregator | Monitor aggregator for IoT Hub failed d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no | | iothub_dropped_d2c_telemetry_egress_message | Custom message for IoT Hub dropped d2c telemetry monitor | string | `` | no | | iothub_dropped_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Dropped limit (critical threshold) | string | `90` | no | | iothub_dropped_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Dropped limit (warning threshold) | string | `50` | no | | iothub_dropped_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub dropped d2c telemetry monitor | map | `` | no | +| iothub_dropped_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub dropped d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| iothub_failed_c2d_methods_rate_aggregator | Monitor aggregator for IoT Hub failed c2d method [available values: min, max, sum or avg] | string | `sum` | no | | iothub_failed_c2d_methods_rate_message | Custom message for IoT Hub failed c2d method monitor | string | `` | no | | iothub_failed_c2d_methods_rate_silenced | Groups to mute for IoT Hub failed c2d methods monitor | map | `` | no | | iothub_failed_c2d_methods_rate_threshold_critical | C2D Methods Failed rate limit (critical threshold) | string | `90` | no | | iothub_failed_c2d_methods_rate_threshold_warning | C2D Methods Failed rate limit (warning threshold) | string | `50` | no | +| iothub_failed_c2d_methods_rate_timeframe | Monitor timeframe for IoT Hub failed c2d method [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| iothub_failed_c2d_twin_read_rate_aggregator | Monitor aggregator for IoT Hub failed c2d twin read [available values: min, max, sum or avg] | string | `sum` | no | | iothub_failed_c2d_twin_read_rate_message | Custom message for IoT Hub failed c2d twin read monitor | string | `` | no | | iothub_failed_c2d_twin_read_rate_silenced | Groups to mute for IoT Hub failed c2d twin read monitor | map | `` | no | | iothub_failed_c2d_twin_read_rate_threshold_critical | C2D Twin Read Failed rate limit (critical threshold) | string | `90` | no | | iothub_failed_c2d_twin_read_rate_threshold_warning | C2D Twin Read Failed rate limit (warning threshold) | string | `50` | no | +| iothub_failed_c2d_twin_read_rate_timeframe | Monitor timeframe for IoT Hub failed c2d twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| iothub_failed_c2d_twin_update_rate_aggregator | Monitor aggregator for IoT Hub failed c2d twin update [available values: min, max, sum or avg] | string | `sum` | no | | iothub_failed_c2d_twin_update_rate_message | Custom message for IoT Hub failed c2d twin update monitor | string | `` | no | | iothub_failed_c2d_twin_update_rate_silenced | Groups to mute for IoT Hub failed c2d twin update monitor | map | `` | no | | iothub_failed_c2d_twin_update_rate_threshold_critical | C2D Twin Update Failed rate limit (critical threshold) | string | `90` | no | | iothub_failed_c2d_twin_update_rate_threshold_warning | C2D Twin Update Failed rate limit (warning threshold) | string | `50` | no | +| iothub_failed_c2d_twin_update_rate_timeframe | Monitor timeframe for IoT Hub failed c2d twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| iothub_failed_d2c_twin_read_rate_aggregator | Monitor aggregator for IoT Hub failed d2c twin read [available values: min, max, sum or avg] | string | `sum` | no | | iothub_failed_d2c_twin_read_rate_message | Custom message for IoT Hub failed d2c twin read monitor | string | `` | no | | iothub_failed_d2c_twin_read_rate_silenced | Groups to mute for IoT Hub failed d2c twin read monitor | map | `` | no | | iothub_failed_d2c_twin_read_rate_threshold_critical | D2C Twin Read Failed rate limit (critical threshold) | string | `90` | no | | iothub_failed_d2c_twin_read_rate_threshold_warning | D2C Twin Read Failed rate limit (warning threshold) | string | `50` | no | +| iothub_failed_d2c_twin_read_rate_timeframe | Monitor timeframe for IoT Hub failed d2c twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| iothub_failed_d2c_twin_update_rate_aggregator | Monitor aggregator for IoT Hub failed d2c twin update [available values: min, max, sum or avg] | string | `sum` | no | | iothub_failed_d2c_twin_update_rate_message | Custom message for IoT Hub failed d2c twin update monitor | string | `` | no | | iothub_failed_d2c_twin_update_rate_silenced | Groups to mute for IoT Hub failed d2c twin update monitor | map | `` | no | | iothub_failed_d2c_twin_update_rate_threshold_critical | D2C Twin Update Failed rate limit (critical threshold) | string | `90` | no | | iothub_failed_d2c_twin_update_rate_threshold_warning | D2C Twin Update Failed rate limit (warning threshold) | string | `50` | no | +| iothub_failed_d2c_twin_update_rate_timeframe | Monitor timeframe for IoT Hub failed d2c twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| iothub_failed_jobs_rate_aggregator | Monitor aggregator for IoT Hub failed jobs [available values: min, max, sum or avg] | string | `sum` | no | | iothub_failed_jobs_rate_message | Custom message for IoT Hub failed jobs monitor | string | `` | no | | iothub_failed_jobs_rate_silenced | Groups to mute for IoT Hub failed jobs monitor | map | `` | no | | iothub_failed_jobs_rate_threshold_critical | Jobs Failed rate limit (critical threshold) | string | `90` | no | | iothub_failed_jobs_rate_threshold_warning | Jobs Failed rate limit (warning threshold) | string | `50` | no | +| iothub_failed_jobs_rate_timeframe | Monitor timeframe for IoT Hub failed jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| iothub_failed_listjobs_rate_aggregator | Monitor aggregator for IoT Hub failed listjobs jobs [available values: min, max, sum or avg] | string | `sum` | no | | iothub_failed_listjobs_rate_message | Custom message for IoT Hub failed list jobs monitor | string | `` | no | | iothub_failed_listjobs_rate_silenced | Groups to mute for IoT Hub failed list jobs monitor | map | `` | no | | iothub_failed_listjobs_rate_threshold_critical | ListJobs Failed rate limit (critical threshold) | string | `90` | no | | iothub_failed_listjobs_rate_threshold_warning | ListJobs Failed rate limit (warning threshold) | string | `50` | no | +| iothub_failed_listjobs_rate_timeframe | Monitor timeframe for IoT Hub failed list jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| iothub_failed_queryjobs_rate_aggregator | Monitor aggregator for IoT Hub failed query jobs [available values: min, max, sum or avg] | string | `sum` | no | | iothub_failed_queryjobs_rate_message | Custom message for IoT Hub failed query jobs monitor | string | `` | no | | iothub_failed_queryjobs_rate_silenced | Groups to mute for IoT Hub failed query jobs monitor | map | `` | no | | iothub_failed_queryjobs_rate_threshold_critical | QueryJobs Failed rate limit (critical threshold) | string | `90` | no | | iothub_failed_queryjobs_rate_threshold_warning | QueryJobs Failed rate limit (warning threshold) | string | `50` | no | +| iothub_failed_queryjobs_rate_timeframe | Monitor timeframe for IoT Hub failed query jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| iothub_invalid_d2c_telemetry_egress_aggregator | Monitor aggregator for IoT Hub invalid d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no | | iothub_invalid_d2c_telemetry_egress_message | Custom message for IoT Hub invalid d2c telemetry monitor | string | `` | no | | iothub_invalid_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Invalid limit (critical threshold) | string | `90` | no | | iothub_invalid_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Invalid limit (warning threshold) | string | `50` | no | | iothub_invalid_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub invalid d2c telemetry monitor | map | `` | no | +| iothub_invalid_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub invalid d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| iothub_orphaned_d2c_telemetry_egress_aggregator | Monitor aggregator for IoT Hub orphaned d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no | | iothub_orphaned_d2c_telemetry_egress_message | Custom message for IoT Hub orphaned d2c telemetry monitor | string | `` | no | | iothub_orphaned_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Orphaned limit (critical threshold) | string | `90` | no | | iothub_orphaned_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Orphaned limit (warning threshold) | string | `50` | no | | iothub_orphaned_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub orphaned d2c telemetry monitor | map | `` | no | +| iothub_orphaned_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub orphaned d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| iothub_status_aggregator | Monitor aggregator for IoT Hub status [available values: min, max, sum or avg] | string | `avg` | no | | iothub_status_message | Custom message for IoT Hub status monitor | string | `` | no | | iothub_status_silenced | Groups to mute for IoT Hub status monitor | map | `` | no | +| iothub_status_timeframe | Monitor timeframe for IoT Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| iothub_too_many_d2c_telemetry_ingress_nosent_aggregator | Monitor aggregator for IoT Hub unsent d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no | | iothub_too_many_d2c_telemetry_ingress_nosent_message | Custom message for IoT Hub unsent d2c telemetry monitor | string | `` | no | | iothub_too_many_d2c_telemetry_ingress_nosent_silenced | Groups to mute for IoT Hub unsent d2c telemetry monitor | map | `` | no | +| iothub_too_many_d2c_telemetry_ingress_nosent_timeframe | Monitor timeframe for IoT Hub unsent d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| iothub_total_devices_aggregator | Monitor aggregator for IoT Hub total devices [available values: min, max, sum or avg] | string | `avg` | no | | iothub_total_devices_message | Custom message for IoT Hub total devices monitor | string | `` | no | | iothub_total_devices_silenced | Groups to mute for IoT Hub total devices monitor | map | `` | no | +| iothub_total_devices_timeframe | Monitor timeframe for IoT Hub total devices [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | message | Message sent when a monitor is triggered | string | - | yes | | non_taggable_filter_tags | Tags used for filtering for components without tag support | string | `*` | no | +| redis_evictedkeys_limit_aggregator | Monitor aggregator for Redis evicted keys [available values: min, max, sum or avg] | string | `avg` | no | | redis_evictedkeys_limit_message | Custom message for Redis evicted keys monitor | string | `` | no | | redis_evictedkeys_limit_silenced | Groups to mute for Redis evicted keys monitor | map | `` | no | | redis_evictedkeys_limit_threshold_critical | Evicted keys limit (critical threshold) | string | `100` | no | | redis_evictedkeys_limit_threshold_warning | Evicted keys limit (warning threshold) | string | `0` | no | +| redis_evictedkeys_limit_timeframe | Monitor timeframe for Redis evicted keys [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| redis_percent_processor_time_aggregator | Monitor aggregator for Redis processor [available values: min, max, sum or avg] | string | `avg` | no | | redis_percent_processor_time_message | Custom message for Redis processor monitor | string | `` | no | | redis_percent_processor_time_silenced | Groups to mute for Redis processor monitor | map | `` | no | | redis_percent_processor_time_threshold_critical | Processor time percent (critical threshold) | string | `80` | no | | redis_percent_processor_time_threshold_warning | Processor time percent (warning threshold) | string | `60` | no | +| redis_percent_processor_time_timeframe | Monitor timeframe for Redis processor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| redis_server_load_rate_aggregator | Monitor aggregator for Redis server load [available values: min, max, sum or avg] | string | `avg` | no | | redis_server_load_rate_message | Custom message for Redis server load monitor | string | `` | no | | redis_server_load_rate_silenced | Groups to mute for Redis server load monitor | map | `` | no | | redis_server_load_rate_threshold_critical | Server CPU load rate (critical threshold) | string | `90` | no | | redis_server_load_rate_threshold_warning | Server CPU load rate (warning threshold) | string | `70` | no | +| redis_server_load_rate_timeframe | Monitor timeframe for Redis server load [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| redis_status_aggregator | Monitor aggregator for Redis status [available values: min, max, sum or avg] | string | `avg` | no | | redis_status_message | Custom message for Redis status monitor | string | `` | no | | redis_status_silenced | Groups to mute for Redis status monitor | map | `` | no | +| redis_status_timeframe | Monitor timeframe for Redis status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| servicebus_status_aggregator | Monitor timeframe aggregator for Service Bus status [available values: min, max, sum or avg] | string | `min` | no | | servicebus_status_message | Custom message for Service Bus status monitor | string | `` | no | | servicebus_status_silenced | Groups to mute for Service Bus status monitor | map | `` | no | | servicebus_status_timeframe | Monitor timeframe for Service Bus status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | -| servicebus_status_aggregator | Monitor timeframe aggregator for Service Bus status [available values: min, max, sum or avg] | string | `min` | no | +| sqldatabase_cpu_aggregator | Monitor aggregator for SQL CPU [available values: min, max, sum or avg] | string | `avg` | no | | sqldatabase_cpu_message | Custom message for SQL CPU monitor | string | `` | no | | sqldatabase_cpu_silenced | Groups to mute for SQL CPU monitor | map | `` | no | | sqldatabase_cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no | | sqldatabase_cpu_threshold_warning | CPU usage in percent (warning threshold) | string | `80` | no | +| sqldatabase_cpu_timeframe | Monitor timeframe for SQL CPU [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | +| sqldatabase_deadlock_aggregator | Monitor aggregator for SQL Deadlock [available values: min, max, sum or avg] | string | `sum` | no | | sqldatabase_deadlock_message | Custom message for SQL Deadlock monitor | string | `` | no | | sqldatabase_deadlock_silenced | Groups to mute for SQL Deadlock monitor | map | `` | no | | sqldatabase_deadlock_threshold_critical | Amount of Deadlocks (critical threshold) | string | `1` | no | +| sqldatabase_deadlock_timeframe | Monitor timeframe for SQL Deadlock [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| sqldatabase_diskspace_aggregator | Monitor aggregator for SQL disk space [available values: min, max, sum or avg] | string | `avg` | no | | sqldatabase_diskspace_message | Custom message for SQL disk space monitor | string | `` | no | | sqldatabase_diskspace_silenced | Groups to mute for SQL disk space monitor | map | `` | no | | sqldatabase_diskspace_threshold_critical | Disk space used in percent (critical threshold) | string | `90` | no | | sqldatabase_diskspace_threshold_warning | Disk space used in percent (warning threshold) | string | `80` | no | +| sqldatabase_diskspace_timeframe | Monitor timeframe for SQL disk space [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | +| sqldatabase_dtu_aggregator | Monitor aggregator for SQL DTU [available values: min, max, sum or avg] | string | `avg` | no | | sqldatabase_dtu_message | Custom message for SQL DTU monitor | string | `` | no | | sqldatabase_dtu_silenced | Groups to mute for SQL DTU monitor | map | `` | no | | sqldatabase_dtu_threshold_critical | Amount of DTU used (critical threshold) | string | `90` | no | | sqldatabase_dtu_threshold_warning | Amount of DTU used (warning threshold) | string | `85` | no | +| sqldatabase_dtu_timeframe | Monitor timeframe for SQL DTU [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | +| storage_authorization_error_requests_aggregator | Monitor aggregator for Storage authorization errors [available values: min, max, sum or avg] | string | `avg` | no | | storage_authorization_error_requests_message | Custom message for Storage authorization errors monitor | string | `` | no | | storage_authorization_error_requests_silenced | Groups to mute for Storage authorization errors monitor | map | `` | no | | storage_authorization_error_requests_threshold_critical | Maximum acceptable percent of authorization error requests for a storage | string | `90` | no | | storage_authorization_error_requests_threshold_warning | Warning regarding acceptable percent of authorization error requests for a storage | string | `50` | no | +| storage_authorization_error_requests_timeframe | Monitor timeframe for Storage authorization errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| storage_availability_aggregator | Monitor aggregator for Storage availability [available values: min, max, sum or avg] | string | `avg` | no | | storage_availability_message | Custom message for Storage availability monitor | string | `` | no | | storage_availability_silenced | Groups to mute for Storage availability monitor | map | `` | no | | storage_availability_threshold_critical | Minimum acceptable percent of availability for a storage | string | `50` | no | | storage_availability_threshold_warning | Warning regarding acceptable percent of availability for a storage | string | `90` | no | +| storage_availability_timeframe | Monitor timeframe for Storage availability [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| storage_client_other_error_requests_aggregator | Monitor aggregator for Storage other errors [available values: min, max, sum or avg] | string | `avg` | no | | storage_client_other_error_requests_message | Custom message for Storage other errors monitor | string | `` | no | | storage_client_other_error_requests_silenced | Groups to mute for Storage other errors monitor | map | `` | no | | storage_client_other_error_requests_threshold_critical | Maximum acceptable percent of client other error requests for a storage | string | `90` | no | | storage_client_other_error_requests_threshold_warning | Warning regarding acceptable percent of client other error requests for a storage | string | `50` | no | +| storage_client_other_error_requests_timeframe | Monitor timeframe for Storage other errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| storage_latency_aggregator | Monitor aggregator for Storage latency [available values: min, max, sum or avg] | string | `min` | no | | storage_latency_message | Custom message for Storage latency monitor | string | `` | no | | storage_latency_silenced | Groups to mute for Storage latency monitor | map | `` | no | | storage_latency_threshold_critical | Maximum acceptable end to end latency (ms) for a storage | string | `2000` | no | | storage_latency_threshold_warning | Warning regarding acceptable end to end latency (ms) for a storage | string | `1000` | no | +| storage_latency_timeframe | Monitor timeframe for Storage latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| storage_network_error_requests_aggregator | Monitor aggregator for Storage network errors [available values: min, max, sum or avg] | string | `avg` | no | | storage_network_error_requests_message | Custom message for Storage network errors monitor | string | `` | no | | storage_network_error_requests_silenced | Groups to mute for Storage network errors monitor | map | `` | no | | storage_network_error_requests_threshold_critical | Maximum acceptable percent of network error requests for a storage | string | `90` | no | | storage_network_error_requests_threshold_warning | Warning regarding acceptable percent of network error requests for a storage | string | `50` | no | +| storage_network_error_requests_timeframe | Monitor timeframe for Storage network errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| storage_server_other_error_requests_aggregator | Monitor aggregator for Storage other errors [available values: min, max, sum or avg] | string | `avg` | no | | storage_server_other_error_requests_message | Custom message for Storage server other errors monitor | string | `` | no | | storage_server_other_error_requests_silenced | Groups to mute for Storage server other errors monitor | map | `` | no | | storage_server_other_error_requests_threshold_critical | Maximum acceptable percent of server other error requests for a storage | string | `90` | no | | storage_server_other_error_requests_threshold_warning | Warning regarding acceptable percent of server other error requests for a storage | string | `50` | no | +| storage_server_other_error_requests_timeframe | Monitor timeframe for Storage server other errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| storage_successful_requests_aggregator | Monitor aggregator for Storage sucessful requests [available values: min, max, sum or avg] | string | `avg` | no | | storage_successful_requests_message | Custom message for Storage sucessful requests monitor | string | `` | no | | storage_successful_requests_silenced | Groups to mute for Storage sucessful requests monitor | map | `` | no | | storage_successful_requests_threshold_critical | Minimum acceptable percent of successful requests for a storage | string | `10` | no | | storage_successful_requests_threshold_warning | Warning regarding acceptable percent of successful requests for a storage | string | `30` | no | +| storage_successful_requests_timeframe | Monitor timeframe for Storage sucessful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| storage_throttling_error_requests_aggregator | Monitor aggregator for Storage throttling errors [available values: min, max, sum or avg] | string | `avg` | no | | storage_throttling_error_requests_message | Custom message for Storage throttling error monitor | string | `` | no | | storage_throttling_error_requests_silenced | Groups to mute for Storage throttling error monitor | map | `` | no | | storage_throttling_error_requests_threshold_critical | Maximum acceptable percent of throttling error requests for a storage | string | `90` | no | | storage_throttling_error_requests_threshold_warning | Warning regarding acceptable percent of throttling error requests for a storage | string | `50` | no | +| storage_throttling_error_requests_timeframe | Monitor timeframe for Storage throttling errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| storage_timeout_error_requests_aggregator | Monitor aggregator for Storage timeout [available values: min, max, sum or avg] | string | `avg` | no | | storage_timeout_error_requests_message | Custom message for Storage timeout monitor | string | `` | no | | storage_timeout_error_requests_silenced | Groups to mute for Storage timeout monitor | map | `` | no | | storage_timeout_error_requests_threshold_critical | Maximum acceptable percent of timeout error requests for a storage | string | `90` | no | | storage_timeout_error_requests_threshold_warning | Warning regarding acceptable percent of timeout error requests for a storage | string | `50` | no | +| storage_timeout_error_requests_timeframe | Monitor timeframe for Storage timeout [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| streamanalytics_conversion_errors_aggregator | Monitor aggregator for Stream Analytics conversion errors [available values: min, max, sum or avg] | string | `avg` | no | | streamanalytics_conversion_errors_message | Custom message for Stream Analytics conversion errors monitor | string | `` | no | | streamanalytics_conversion_errors_silenced | Groups to mute for Stream Analytics conversion errors monitor | map | `` | no | | streamanalytics_conversion_errors_threshold_critical | Conversion errors limit (critical threshold) | string | `10` | no | | streamanalytics_conversion_errors_threshold_warning | Conversion errors limit (warning threshold) | string | `0` | no | +| streamanalytics_conversion_errors_timeframe | Monitor timeframe for Stream Analytics conversion errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| streamanalytics_failed_function_requests_aggregator | Monitor aggregator for Stream Analytics failed requests [available values: min, max, sum or avg] | string | `sum` | no | | streamanalytics_failed_function_requests_message | Custom message for Stream Analytics failed requests monitor | string | `` | no | | streamanalytics_failed_function_requests_silenced | Groups to mute for Stream Analytics failed requests monitor | map | `` | no | | streamanalytics_failed_function_requests_threshold_critical | Failed Function Request rate limit (critical threshold) | string | `10` | no | | streamanalytics_failed_function_requests_threshold_warning | Failed Function Request rate limit (warning threshold) | string | `0` | no | +| streamanalytics_failed_function_requests_timeframe | Monitor timeframe for Stream Analytics failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| streamanalytics_runtime_errors_aggregator | Monitor aggregator for Stream Analytics runtime errors [available values: min, max, sum or avg] | string | `avg` | no | | streamanalytics_runtime_errors_message | Custom message for Stream Analytics runtime errors monitor | string | `` | no | | streamanalytics_runtime_errors_silenced | Groups to mute for Stream Analytics runtime errors monitor | map | `` | no | | streamanalytics_runtime_errors_threshold_critical | Runtime errors limit (critical threshold) | string | `10` | no | | streamanalytics_runtime_errors_threshold_warning | Runtime errors limit (warning threshold) | string | `0` | no | +| streamanalytics_runtime_errors_timeframe | Monitor timeframe for Stream Analytics runtime errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| streamanalytics_status_aggregator | Monitor aggregator for Stream Analytics status [available values: min, max, sum or avg] | string | `avg` | no | | streamanalytics_status_message | Custom message for Stream Analytics status monitor | string | `` | no | | streamanalytics_status_silenced | Groups to mute for Stream Analytics status monitor | map | `` | no | +| streamanalytics_status_timeframe | Monitor timeframe for Stream Analytics status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| streamanalytics_su_utilization_aggregator | Monitor aggregator for Stream Analytics utilization [available values: min, max, sum or avg] | string | `avg` | no | | streamanalytics_su_utilization_message | Custom message for Stream Analytics utilization monitor | string | `` | no | | streamanalytics_su_utilization_silenced | Groups to mute for Stream Analytics utilization monitor | map | `` | no | | streamanalytics_su_utilization_threshold_critical | Streaming Unit utilization rate limit (critical threshold) | string | `80` | no | | streamanalytics_su_utilization_threshold_warning | Streaming Unit utilization rate limit (warning threshold) | string | `60` | no | +| streamanalytics_su_utilization_timeframe | Monitor timeframe for Stream Analytics utilization [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | Related documentation --------------------- diff --git a/cloud/azure/inputs.tf b/cloud/azure/inputs.tf index f7b804f..2d5ada3 100644 --- a/cloud/azure/inputs.tf +++ b/cloud/azure/inputs.tf @@ -41,6 +41,18 @@ variable "apimanagement_status_message" { default = "" } +variable "apimanagement_status_aggregator" { + description = "Monitor aggregator for API Management status [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "apimanagement_status_timeframe" { + description = "Monitor timeframe for API Management status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "apimanagement_failed_requests_silenced" { description = "Groups to mute for API Management failed requests monitor" type = "map" @@ -53,6 +65,18 @@ variable "apimanagement_failed_requests_message" { default = "" } +variable "apimanagement_failed_requests_aggregator" { + description = "Monitor aggregator for API Management failed requests [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "apimanagement_failed_requests_timeframe" { + description = "Monitor timeframe for API Management failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "apimanagement_failed_requests_threshold_critical" { description = "Maximum acceptable percent of failed requests" default = 90 @@ -75,6 +99,18 @@ variable "apimanagement_other_requests_message" { default = "" } +variable "apimanagement_other_requests_aggregator" { + description = "Monitor aggregator for API Management other requests [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "apimanagement_other_requests_timeframe" { + description = "Monitor timeframe for API Management other requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "apimanagement_other_requests_threshold_critical" { description = "Maximum acceptable percent of other requests" default = 90 @@ -97,6 +133,18 @@ variable "apimanagement_unauthorized_requests_message" { default = "" } +variable "apimanagement_unauthorized_requests_aggregator" { + description = "Monitor aggregator for API Management unauthorized requests [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "apimanagement_unauthorized_requests_timeframe" { + description = "Monitor timeframe for API Management unauthorized requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "apimanagement_unauthorized_requests_threshold_critical" { description = "Maximum acceptable percent of unauthorized requests" default = 90 @@ -119,6 +167,18 @@ variable "apimanagement_successful_requests_message" { default = "" } +variable "apimanagement_successful_requests_aggregator" { + description = "Monitor aggregator for API Management successful requests [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "apimanagement_successful_requests_timeframe" { + description = "Monitor timeframe for API Management successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "apimanagement_successful_requests_threshold_critical" { description = "Minimum acceptable percent of successful requests" default = 10 @@ -142,6 +202,18 @@ variable "appservices_response_time_message" { default = "" } +variable "appservices_response_time_aggregator" { + description = "Monitor aggregator for App Services response time [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + +variable "appservices_response_time_timeframe" { + description = "Monitor timeframe for App Services response time [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "appservices_response_time_threshold_critical" { default = 10 description = "Alerting threshold for response time in seconds" @@ -164,6 +236,18 @@ variable "appservices_memory_usage_message" { default = "" } +variable "appservices_memory_usage_aggregator" { + description = "Monitor aggregator for App Services memory usage [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "appservices_memory_usage_timeframe" { + description = "Monitor timeframe for App Services memory usage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "appservices_memory_usage_threshold_critical" { default = 1073741824 # 1Gb description = "Alerting threshold in Mib" @@ -186,6 +270,18 @@ variable "appservices_http_4xx_requests_message" { default = "" } +variable "appservices_http_4xx_requests_aggregator" { + description = "Monitor aggregator for App Services 4xx requests [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "appservices_http_4xx_requests_timeframe" { + description = "Monitor timeframe for App Services 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "appservices_http_4xx_requests_threshold_critical" { default = 90 description = "Maximum critical acceptable percent of 4xx errors" @@ -208,6 +304,18 @@ variable "appservices_http_5xx_requests_message" { default = "" } +variable "appservices_http_5xx_requests_aggregator" { + description = "Monitor aggregator for App Services 5xx requests [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "appservices_http_5xx_requests_timeframe" { + description = "Monitor timeframe for App Services 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "appservices_http_5xx_requests_threshold_critical" { default = 90 description = "Maximum critical acceptable percent of 5xx errors" @@ -230,6 +338,18 @@ variable "appservices_http_successful_requests_message" { default = "" } +variable "appservices_http_successful_requests_aggregator" { + description = "Monitor aggregator for App Services successful requests [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "appservices_http_successful_requests_timeframe" { + description = "Monitor timeframe for App Services successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "appservices_http_successful_requests_threshold_critical" { default = 10 description = "Minimum critical acceptable percent of 2xx & 3xx requests" @@ -253,6 +373,18 @@ variable "eventhub_status_message" { default = "" } +variable "eventhub_status_aggregator" { + description = "Monitor aggregator for Event Hub status [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "eventhub_status_timeframe" { + description = "Monitor timeframe for Event Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "eventhub_failed_requests_rate_silenced" { description = "Groups to mute for Event Hub failed requests monitor" type = "map" @@ -265,6 +397,18 @@ variable "eventhub_failed_requests_rate_message" { default = "" } +variable "eventhub_failed_requests_rate_aggregator" { + description = "Monitor aggregator for Event Hub failed requests [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "eventhub_failed_requests_rate_timeframe" { + description = "Monitor timeframe for Event Hub failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "eventhub_failed_requests_rate_thresold_critical" { description = "Failed requests ratio (percentage) to trigger the critical alert" default = 90 @@ -287,6 +431,18 @@ variable "eventhub_errors_rate_message" { default = "" } +variable "eventhub_errors_rate_aggregator" { + description = "Monitor aggregator for Event Hub errors [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "eventhub_errors_rate_timeframe" { + description = "Monitor timeframe for Event Hub errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "eventhub_errors_rate_thresold_critical" { description = "Errors ratio (percentage) to trigger the critical alert" default = 90 @@ -310,6 +466,18 @@ variable "iothub_status_message" { default = "" } +variable "iothub_status_aggregator" { + description = "Monitor aggregator for IoT Hub status [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "iothub_status_timeframe" { + description = "Monitor timeframe for IoT Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "iothub_total_devices_silenced" { description = "Groups to mute for IoT Hub total devices monitor" type = "map" @@ -322,6 +490,18 @@ variable "iothub_total_devices_message" { default = "" } +variable "iothub_total_devices_aggregator" { + description = "Monitor aggregator for IoT Hub total devices [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "iothub_total_devices_timeframe" { + description = "Monitor timeframe for IoT Hub total devices [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "iothub_too_many_d2c_telemetry_ingress_nosent_silenced" { description = "Groups to mute for IoT Hub unsent d2c telemetry monitor" type = "map" @@ -334,6 +514,18 @@ variable "iothub_too_many_d2c_telemetry_ingress_nosent_message" { default = "" } +variable "iothub_too_many_d2c_telemetry_ingress_nosent_aggregator" { + description = "Monitor aggregator for IoT Hub unsent d2c telemetry [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "iothub_too_many_d2c_telemetry_ingress_nosent_timeframe" { + description = "Monitor timeframe for IoT Hub unsent d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "iothub_failed_jobs_rate_silenced" { description = "Groups to mute for IoT Hub failed jobs monitor" type = "map" @@ -346,6 +538,18 @@ variable "iothub_failed_jobs_rate_message" { default = "" } +variable "iothub_failed_jobs_rate_aggregator" { + description = "Monitor aggregator for IoT Hub failed jobs [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "iothub_failed_jobs_rate_timeframe" { + description = "Monitor timeframe for IoT Hub failed jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "iothub_failed_jobs_rate_threshold_warning" { description = "Jobs Failed rate limit (warning threshold)" default = 50 @@ -368,6 +572,18 @@ variable "iothub_failed_listjobs_rate_message" { default = "" } +variable "iothub_failed_listjobs_rate_aggregator" { + description = "Monitor aggregator for IoT Hub failed listjobs jobs [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "iothub_failed_listjobs_rate_timeframe" { + description = "Monitor timeframe for IoT Hub failed list jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "iothub_failed_listjobs_rate_threshold_warning" { description = "ListJobs Failed rate limit (warning threshold)" default = 50 @@ -390,6 +606,18 @@ variable "iothub_failed_queryjobs_rate_message" { default = "" } +variable "iothub_failed_queryjobs_rate_aggregator" { + description = "Monitor aggregator for IoT Hub failed query jobs [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "iothub_failed_queryjobs_rate_timeframe" { + description = "Monitor timeframe for IoT Hub failed query jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "iothub_failed_queryjobs_rate_threshold_warning" { description = "QueryJobs Failed rate limit (warning threshold)" default = 50 @@ -412,6 +640,18 @@ variable "iothub_failed_c2d_methods_rate_message" { default = "" } +variable "iothub_failed_c2d_methods_rate_aggregator" { + description = "Monitor aggregator for IoT Hub failed c2d method [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "iothub_failed_c2d_methods_rate_timeframe" { + description = "Monitor timeframe for IoT Hub failed c2d method [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "iothub_failed_c2d_methods_rate_threshold_warning" { description = "C2D Methods Failed rate limit (warning threshold)" default = 50 @@ -434,6 +674,18 @@ variable "iothub_failed_c2d_twin_read_rate_message" { default = "" } +variable "iothub_failed_c2d_twin_read_rate_aggregator" { + description = "Monitor aggregator for IoT Hub failed c2d twin read [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "iothub_failed_c2d_twin_read_rate_timeframe" { + description = "Monitor timeframe for IoT Hub failed c2d twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "iothub_failed_c2d_twin_read_rate_threshold_warning" { description = "C2D Twin Read Failed rate limit (warning threshold)" default = 50 @@ -456,6 +708,18 @@ variable "iothub_failed_c2d_twin_update_rate_message" { default = "" } +variable "iothub_failed_c2d_twin_update_rate_aggregator" { + description = "Monitor aggregator for IoT Hub failed c2d twin update [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "iothub_failed_c2d_twin_update_rate_timeframe" { + description = "Monitor timeframe for IoT Hub failed c2d twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "iothub_failed_c2d_twin_update_rate_threshold_warning" { description = "C2D Twin Update Failed rate limit (warning threshold)" default = 50 @@ -478,6 +742,18 @@ variable "iothub_failed_d2c_twin_read_rate_message" { default = "" } +variable "iothub_failed_d2c_twin_read_rate_aggregator" { + description = "Monitor aggregator for IoT Hub failed d2c twin read [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "iothub_failed_d2c_twin_read_rate_timeframe" { + description = "Monitor timeframe for IoT Hub failed d2c twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "iothub_failed_d2c_twin_read_rate_threshold_warning" { description = "D2C Twin Read Failed rate limit (warning threshold)" default = 50 @@ -500,6 +776,18 @@ variable "iothub_failed_d2c_twin_update_rate_message" { default = "" } +variable "iothub_failed_d2c_twin_update_rate_aggregator" { + description = "Monitor aggregator for IoT Hub failed d2c twin update [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "iothub_failed_d2c_twin_update_rate_timeframe" { + description = "Monitor timeframe for IoT Hub failed d2c twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "iothub_failed_d2c_twin_update_rate_threshold_warning" { description = "D2C Twin Update Failed rate limit (warning threshold)" default = 50 @@ -522,6 +810,18 @@ variable "iothub_dropped_d2c_telemetry_egress_message" { default = "" } +variable "iothub_dropped_d2c_telemetry_egress_aggregator" { + description = "Monitor aggregator for IoT Hub failed d2c telemetry [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "iothub_dropped_d2c_telemetry_egress_timeframe" { + description = "Monitor timeframe for IoT Hub dropped d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "iothub_dropped_d2c_telemetry_egress_rate_threshold_warning" { description = "D2C Telemetry Dropped limit (warning threshold)" default = 50 @@ -544,6 +844,18 @@ variable "iothub_orphaned_d2c_telemetry_egress_message" { default = "" } +variable "iothub_orphaned_d2c_telemetry_egress_aggregator" { + description = "Monitor aggregator for IoT Hub orphaned d2c telemetry [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "iothub_orphaned_d2c_telemetry_egress_timeframe" { + description = "Monitor timeframe for IoT Hub orphaned d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "iothub_orphaned_d2c_telemetry_egress_rate_threshold_warning" { description = "D2C Telemetry Orphaned limit (warning threshold)" default = 50 @@ -566,6 +878,18 @@ variable "iothub_invalid_d2c_telemetry_egress_message" { default = "" } +variable "iothub_invalid_d2c_telemetry_egress_aggregator" { + description = "Monitor aggregator for IoT Hub invalid d2c telemetry [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "iothub_invalid_d2c_telemetry_egress_timeframe" { + description = "Monitor timeframe for IoT Hub invalid d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "iothub_invalid_d2c_telemetry_egress_rate_threshold_warning" { description = "D2C Telemetry Invalid limit (warning threshold)" default = 50 @@ -589,6 +913,18 @@ variable "redis_status_message" { default = "" } +variable "redis_status_aggregator" { + description = "Monitor aggregator for Redis status [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "redis_status_timeframe" { + description = "Monitor timeframe for Redis status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "redis_evictedkeys_limit_silenced" { description = "Groups to mute for Redis evicted keys monitor" type = "map" @@ -601,6 +937,18 @@ variable "redis_evictedkeys_limit_message" { default = "" } +variable "redis_evictedkeys_limit_aggregator" { + description = "Monitor aggregator for Redis evicted keys [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "redis_evictedkeys_limit_timeframe" { + description = "Monitor timeframe for Redis evicted keys [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "redis_evictedkeys_limit_threshold_warning" { description = "Evicted keys limit (warning threshold)" default = 0 @@ -623,6 +971,18 @@ variable "redis_percent_processor_time_message" { default = "" } +variable "redis_percent_processor_time_aggregator" { + description = "Monitor aggregator for Redis processor [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "redis_percent_processor_time_timeframe" { + description = "Monitor timeframe for Redis processor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "redis_percent_processor_time_threshold_critical" { description = "Processor time percent (critical threshold)" default = 80 @@ -645,6 +1005,18 @@ variable "redis_server_load_rate_message" { default = "" } +variable "redis_server_load_rate_aggregator" { + description = "Monitor aggregator for Redis server load [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "redis_server_load_rate_timeframe" { + description = "Monitor timeframe for Redis server load [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "redis_server_load_rate_threshold_critical" { description = "Server CPU load rate (critical threshold)" default = 90 @@ -692,6 +1064,18 @@ variable "sqldatabase_cpu_message" { default = "" } +variable "sqldatabase_cpu_aggregator" { + description = "Monitor aggregator for SQL CPU [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "sqldatabase_cpu_timeframe" { + description = "Monitor timeframe for SQL CPU [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_15m" +} + variable "sqldatabase_cpu_threshold_warning" { description = "CPU usage in percent (warning threshold)" default = "80" @@ -714,6 +1098,18 @@ variable "sqldatabase_diskspace_message" { default = "" } +variable "sqldatabase_diskspace_aggregator" { + description = "Monitor aggregator for SQL disk space [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "sqldatabase_diskspace_timeframe" { + description = "Monitor timeframe for SQL disk space [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_15m" +} + variable "sqldatabase_diskspace_threshold_warning" { description = "Disk space used in percent (warning threshold)" default = "80" @@ -736,6 +1132,18 @@ variable "sqldatabase_dtu_message" { default = "" } +variable "sqldatabase_dtu_aggregator" { + description = "Monitor aggregator for SQL DTU [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "sqldatabase_dtu_timeframe" { + description = "Monitor timeframe for SQL DTU [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_15m" +} + variable "sqldatabase_dtu_threshold_warning" { description = "Amount of DTU used (warning threshold)" default = "85" @@ -758,6 +1166,18 @@ variable "sqldatabase_deadlock_message" { default = "" } +variable "sqldatabase_deadlock_aggregator" { + description = "Monitor aggregator for SQL Deadlock [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "sqldatabase_deadlock_timeframe" { + description = "Monitor timeframe for SQL Deadlock [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "sqldatabase_deadlock_threshold_critical" { description = "Amount of Deadlocks (critical threshold)" default = "1" @@ -776,6 +1196,18 @@ variable "storage_availability_message" { default = "" } +variable "storage_availability_aggregator" { + description = "Monitor aggregator for Storage availability [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "storage_availability_timeframe" { + description = "Monitor timeframe for Storage availability [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "storage_availability_threshold_critical" { description = "Minimum acceptable percent of availability for a storage" default = 50 @@ -798,6 +1230,18 @@ variable "storage_successful_requests_message" { default = "" } +variable "storage_successful_requests_aggregator" { + description = "Monitor aggregator for Storage sucessful requests [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "storage_successful_requests_timeframe" { + description = "Monitor timeframe for Storage sucessful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "storage_successful_requests_threshold_critical" { description = "Minimum acceptable percent of successful requests for a storage" default = 10 @@ -820,6 +1264,18 @@ variable "storage_latency_message" { default = "" } +variable "storage_latency_aggregator" { + description = "Monitor aggregator for Storage latency [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + +variable "storage_latency_timeframe" { + description = "Monitor timeframe for Storage latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "storage_latency_threshold_critical" { description = "Maximum acceptable end to end latency (ms) for a storage" default = 2000 @@ -842,6 +1298,18 @@ variable "storage_timeout_error_requests_message" { default = "" } +variable "storage_timeout_error_requests_aggregator" { + description = "Monitor aggregator for Storage timeout [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "storage_timeout_error_requests_timeframe" { + description = "Monitor timeframe for Storage timeout [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "storage_timeout_error_requests_threshold_critical" { description = "Maximum acceptable percent of timeout error requests for a storage" default = 90 @@ -864,6 +1332,18 @@ variable "storage_network_error_requests_message" { default = "" } +variable "storage_network_error_requests_aggregator" { + description = "Monitor aggregator for Storage network errors [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "storage_network_error_requests_timeframe" { + description = "Monitor timeframe for Storage network errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "storage_network_error_requests_threshold_critical" { description = "Maximum acceptable percent of network error requests for a storage" default = 90 @@ -886,6 +1366,18 @@ variable "storage_throttling_error_requests_message" { default = "" } +variable "storage_throttling_error_requests_aggregator" { + description = "Monitor aggregator for Storage throttling errors [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "storage_throttling_error_requests_timeframe" { + description = "Monitor timeframe for Storage throttling errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "storage_throttling_error_requests_threshold_critical" { description = "Maximum acceptable percent of throttling error requests for a storage" default = 90 @@ -908,6 +1400,18 @@ variable "storage_server_other_error_requests_message" { default = "" } +variable "storage_server_other_error_requests_aggregator" { + description = "Monitor aggregator for Storage other errors [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "storage_server_other_error_requests_timeframe" { + description = "Monitor timeframe for Storage server other errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "storage_server_other_error_requests_threshold_critical" { description = "Maximum acceptable percent of server other error requests for a storage" default = 90 @@ -930,6 +1434,18 @@ variable "storage_client_other_error_requests_message" { default = "" } +variable "storage_client_other_error_requests_aggregator" { + description = "Monitor aggregator for Storage other errors [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "storage_client_other_error_requests_timeframe" { + description = "Monitor timeframe for Storage other errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "storage_client_other_error_requests_threshold_critical" { description = "Maximum acceptable percent of client other error requests for a storage" default = 90 @@ -952,6 +1468,18 @@ variable "storage_authorization_error_requests_message" { default = "" } +variable "storage_authorization_error_requests_aggregator" { + description = "Monitor aggregator for Storage authorization errors [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "storage_authorization_error_requests_timeframe" { + description = "Monitor timeframe for Storage authorization errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "storage_authorization_error_requests_threshold_critical" { description = "Maximum acceptable percent of authorization error requests for a storage" default = 90 @@ -975,6 +1503,18 @@ variable "streamanalytics_status_message" { default = "" } +variable "streamanalytics_status_aggregator" { + description = "Monitor aggregator for Stream Analytics status [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "streamanalytics_status_timeframe" { + description = "Monitor timeframe for Stream Analytics status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "streamanalytics_su_utilization_silenced" { description = "Groups to mute for Stream Analytics utilization monitor" type = "map" @@ -987,6 +1527,18 @@ variable "streamanalytics_su_utilization_message" { default = "" } +variable "streamanalytics_su_utilization_aggregator" { + description = "Monitor aggregator for Stream Analytics utilization [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "streamanalytics_su_utilization_timeframe" { + description = "Monitor timeframe for Stream Analytics utilization [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "streamanalytics_su_utilization_threshold_warning" { description = "Streaming Unit utilization rate limit (warning threshold)" default = 60 @@ -1009,6 +1561,18 @@ variable "streamanalytics_failed_function_requests_message" { default = "" } +variable "streamanalytics_failed_function_requests_aggregator" { + description = "Monitor aggregator for Stream Analytics failed requests [available values: min, max, sum or avg]" + type = "string" + default = "sum" +} + +variable "streamanalytics_failed_function_requests_timeframe" { + description = "Monitor timeframe for Stream Analytics failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "streamanalytics_failed_function_requests_threshold_warning" { description = "Failed Function Request rate limit (warning threshold)" default = 0 @@ -1031,6 +1595,18 @@ variable "streamanalytics_conversion_errors_message" { default = "" } +variable "streamanalytics_conversion_errors_aggregator" { + description = "Monitor aggregator for Stream Analytics conversion errors [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "streamanalytics_conversion_errors_timeframe" { + description = "Monitor timeframe for Stream Analytics conversion errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "streamanalytics_conversion_errors_threshold_warning" { description = "Conversion errors limit (warning threshold)" default = 0 @@ -1053,6 +1629,18 @@ variable "streamanalytics_runtime_errors_message" { default = "" } +variable "streamanalytics_runtime_errors_aggregator" { + description = "Monitor aggregator for Stream Analytics runtime errors [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + +variable "streamanalytics_runtime_errors_timeframe" { + description = "Monitor timeframe for Stream Analytics runtime errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} + variable "streamanalytics_runtime_errors_threshold_warning" { description = "Runtime errors limit (warning threshold)" default = 0 diff --git a/cloud/azure/monitors.tf b/cloud/azure/monitors.tf index b16988e..a7ccedb 100644 --- a/cloud/azure/monitors.tf +++ b/cloud/azure/monitors.tf @@ -10,20 +10,30 @@ module "apimanagement" { status_silenced = "${var.apimanagement_status_silenced}" status_message = "${var.apimanagement_status_message}" + status_aggregator = "${var.apimanagement_status_aggregator}" + status_timeframe = "${var.apimanagement_status_timeframe}" failed_requests_silenced = "${var.apimanagement_failed_requests_silenced}" failed_requests_message = "${var.apimanagement_failed_requests_message}" + failed_requests_aggregator = "${var.apimanagement_failed_requests_aggregator}" + failed_requests_timeframe = "${var.apimanagement_failed_requests_timeframe}" failed_requests_threshold_critical = "${var.apimanagement_failed_requests_threshold_critical}" failed_requests_threshold_warning = "${var.apimanagement_failed_requests_threshold_warning}" other_requests_silenced = "${var.apimanagement_other_requests_silenced}" other_requests_message = "${var.apimanagement_other_requests_message}" + other_requests_aggregator = "${var.apimanagement_other_requests_aggregator}" + other_requests_timeframe = "${var.apimanagement_other_requests_timeframe}" other_requests_threshold_critical = "${var.apimanagement_other_requests_threshold_critical}" other_requests_threshold_warning = "${var.apimanagement_other_requests_threshold_warning}" successful_requests_silenced = "${var.apimanagement_successful_requests_silenced}" successful_requests_message = "${var.apimanagement_successful_requests_message}" + successful_requests_aggregator = "${var.apimanagement_successful_requests_aggregator}" + successful_requests_timeframe = "${var.apimanagement_successful_requests_timeframe}" successful_requests_threshold_critical = "${var.apimanagement_successful_requests_threshold_critical}" successful_requests_threshold_warning = "${var.apimanagement_successful_requests_threshold_warning}" unauthorized_requests_silenced = "${var.apimanagement_unauthorized_requests_silenced}" unauthorized_requests_message = "${var.apimanagement_unauthorized_requests_message}" + unauthorized_requests_aggregator = "${var.apimanagement_unauthorized_requests_aggregator}" + unauthorized_requests_timeframe = "${var.apimanagement_unauthorized_requests_timeframe}" unauthorized_requests_threshold_critical = "${var.apimanagement_unauthorized_requests_threshold_critical}" unauthorized_requests_threshold_warning = "${var.apimanagement_unauthorized_requests_threshold_warning}" } @@ -40,22 +50,32 @@ module "appservices" { http_successful_requests_silenced = "${var.appservices_http_successful_requests_silenced}" http_successful_requests_message = "${var.appservices_http_successful_requests_message}" + http_successful_requests_aggregator = "${var.appservices_http_successful_requests_aggregator}" + http_successful_requests_timeframe = "${var.appservices_http_successful_requests_timeframe}" http_successful_requests_threshold_critical = "${var.appservices_http_successful_requests_threshold_critical}" http_successful_requests_threshold_warning = "${var.appservices_http_successful_requests_threshold_warning}" http_5xx_requests_silenced = "${var.appservices_http_5xx_requests_silenced}" http_5xx_requests_message = "${var.appservices_http_5xx_requests_message}" + http_5xx_requests_aggregator = "${var.appservices_http_5xx_requests_aggregator}" + http_5xx_requests_timeframe = "${var.appservices_http_5xx_requests_timeframe}" http_5xx_requests_threshold_critical = "${var.appservices_http_5xx_requests_threshold_critical}" http_5xx_requests_threshold_warning = "${var.appservices_http_5xx_requests_threshold_warning}" http_4xx_requests_silenced = "${var.appservices_http_4xx_requests_silenced}" http_4xx_requests_message = "${var.appservices_http_4xx_requests_message}" + http_4xx_requests_aggregator = "${var.appservices_http_4xx_requests_aggregator}" + http_4xx_requests_timeframe = "${var.appservices_http_4xx_requests_timeframe}" http_4xx_requests_threshold_critical = "${var.appservices_http_4xx_requests_threshold_critical}" http_4xx_requests_threshold_warning = "${var.appservices_http_4xx_requests_threshold_warning}" memory_usage_silenced = "${var.appservices_memory_usage_silenced}" memory_usage_message = "${var.appservices_memory_usage_message}" + memory_usage_aggregator = "${var.appservices_memory_usage_aggregator}" + memory_usage_timeframe = "${var.appservices_memory_usage_timeframe}" memory_usage_threshold_critical = "${var.appservices_memory_usage_threshold_critical}" memory_usage_threshold_warning = "${var.appservices_memory_usage_threshold_warning}" response_time_silenced = "${var.appservices_response_time_silenced}" response_time_message = "${var.appservices_response_time_message}" + response_time_aggregator = "${var.appservices_response_time_aggregator}" + response_time_timeframe = "${var.appservices_response_time_timeframe}" response_time_threshold_critical = "${var.appservices_response_time_threshold_critical}" response_time_threshold_warning = "${var.appservices_response_time_threshold_warning}" } @@ -72,12 +92,18 @@ module "eventhub" { status_silenced = "${var.eventhub_status_silenced}" status_message = "${var.eventhub_status_message}" + status_aggregator = "${var.eventhub_status_aggregator}" + status_timeframe = "${var.eventhub_status_timeframe}" errors_rate_silenced = "${var.eventhub_errors_rate_silenced}" errors_rate_message = "${var.eventhub_errors_rate_message}" + errors_rate_aggregator = "${var.eventhub_errors_rate_aggregator}" + errors_rate_timeframe = "${var.eventhub_errors_rate_timeframe}" errors_rate_thresold_critical = "${var.eventhub_errors_rate_thresold_critical}" errors_rate_thresold_warning = "${var.eventhub_errors_rate_thresold_warning}" failed_requests_rate_silenced = "${var.eventhub_failed_requests_rate_silenced}" failed_requests_rate_message = "${var.eventhub_failed_requests_rate_message}" + failed_requests_rate_aggregator = "${var.eventhub_failed_requests_rate_aggregator}" + failed_requests_rate_timeframe = "${var.eventhub_failed_requests_rate_timeframe}" failed_requests_rate_thresold_critical = "${var.eventhub_failed_requests_rate_thresold_critical}" failed_requests_rate_thresold_warning = "${var.eventhub_failed_requests_rate_thresold_warning}" } @@ -93,51 +119,80 @@ module "iothub" { status_silenced = "${var.iothub_status_silenced}" status_message = "${var.iothub_status_message}" + status_aggregator = "${var.iothub_status_aggregator}" + status_timeframe = "${var.iothub_status_timeframe}" total_devices_silenced = "${var.iothub_total_devices_silenced}" total_devices_message = "${var.iothub_total_devices_message}" + total_devices_aggregator = "${var.iothub_total_devices_aggregator}" + total_devices_timeframe = "${var.iothub_total_devices_timeframe}" too_many_d2c_telemetry_ingress_nosent_silenced = "${var.iothub_too_many_d2c_telemetry_ingress_nosent_silenced}" + too_many_d2c_telemetry_ingress_nosent_message = "${var.iothub_too_many_d2c_telemetry_ingress_nosent_message}" + too_many_d2c_telemetry_ingress_nosent_aggregator = "${var.iothub_too_many_d2c_telemetry_ingress_nosent_aggregator}" + too_many_d2c_telemetry_ingress_nosent_timeframe = "${var.iothub_too_many_d2c_telemetry_ingress_nosent_timeframe}" dropped_d2c_telemetry_egress_silenced = "${var.iothub_dropped_d2c_telemetry_egress_silenced}" dropped_d2c_telemetry_egress_message = "${var.iothub_dropped_d2c_telemetry_egress_message}" + dropped_d2c_telemetry_egress_aggregator = "${var.iothub_dropped_d2c_telemetry_egress_aggregator}" + dropped_d2c_telemetry_egress_timeframe = "${var.iothub_dropped_d2c_telemetry_egress_timeframe}" dropped_d2c_telemetry_egress_rate_threshold_critical = "${var.iothub_dropped_d2c_telemetry_egress_rate_threshold_critical}" dropped_d2c_telemetry_egress_rate_threshold_warning = "${var.iothub_dropped_d2c_telemetry_egress_rate_threshold_warning}" failed_c2d_methods_rate_silenced = "${var.iothub_failed_c2d_methods_rate_silenced}" failed_c2d_methods_rate_message = "${var.iothub_failed_c2d_methods_rate_message}" + failed_c2d_methods_rate_aggregator = "${var.iothub_failed_c2d_methods_rate_aggregator}" + failed_c2d_methods_rate_timeframe = "${var.iothub_failed_c2d_methods_rate_timeframe}" failed_c2d_methods_rate_threshold_critical = "${var.iothub_failed_c2d_methods_rate_threshold_critical}" failed_c2d_methods_rate_threshold_warning = "${var.iothub_failed_c2d_methods_rate_threshold_warning}" failed_c2d_twin_read_rate_silenced = "${var.iothub_failed_c2d_twin_read_rate_silenced}" failed_c2d_twin_read_rate_message = "${var.iothub_failed_c2d_twin_read_rate_message}" + failed_c2d_twin_read_rate_aggregator = "${var.iothub_failed_c2d_twin_read_rate_aggregator}" + failed_c2d_twin_read_rate_timeframe = "${var.iothub_failed_c2d_twin_read_rate_timeframe}" failed_c2d_twin_read_rate_threshold_critical = "${var.iothub_failed_c2d_twin_read_rate_threshold_critical}" failed_c2d_twin_read_rate_threshold_warning = "${var.iothub_failed_c2d_twin_read_rate_threshold_warning}" failed_c2d_twin_update_rate_silenced = "${var.iothub_failed_c2d_twin_update_rate_silenced}" failed_c2d_twin_update_rate_message = "${var.iothub_failed_c2d_twin_update_rate_message}" + failed_c2d_twin_update_rate_aggregator = "${var.iothub_failed_c2d_twin_update_rate_aggregator}" + failed_c2d_twin_update_rate_timeframe = "${var.iothub_failed_c2d_twin_update_rate_timeframe}" failed_c2d_twin_update_rate_threshold_critical = "${var.iothub_failed_c2d_twin_update_rate_threshold_critical}" failed_c2d_twin_update_rate_threshold_warning = "${var.iothub_failed_c2d_twin_update_rate_threshold_warning}" failed_d2c_twin_read_rate_silenced = "${var.iothub_failed_d2c_twin_read_rate_silenced}" failed_d2c_twin_read_rate_message = "${var.iothub_failed_d2c_twin_read_rate_message}" + failed_d2c_twin_read_rate_aggregator = "${var.iothub_failed_d2c_twin_read_rate_aggregator}" + failed_d2c_twin_read_rate_timeframe = "${var.iothub_failed_d2c_twin_read_rate_timeframe}" failed_d2c_twin_read_rate_threshold_critical = "${var.iothub_failed_d2c_twin_read_rate_threshold_critical}" failed_d2c_twin_read_rate_threshold_warning = "${var.iothub_failed_d2c_twin_read_rate_threshold_warning}" failed_d2c_twin_update_rate_silenced = "${var.iothub_failed_d2c_twin_update_rate_silenced}" failed_d2c_twin_update_rate_message = "${var.iothub_failed_d2c_twin_update_rate_message}" + failed_d2c_twin_update_rate_aggregator = "${var.iothub_failed_d2c_twin_update_rate_aggregator}" + failed_d2c_twin_update_rate_timeframe = "${var.iothub_failed_d2c_twin_update_rate_timeframe}" failed_d2c_twin_update_rate_threshold_critical = "${var.iothub_failed_d2c_twin_update_rate_threshold_critical}" failed_d2c_twin_update_rate_threshold_warning = "${var.iothub_failed_d2c_twin_update_rate_threshold_warning}" failed_jobs_rate_silenced = "${var.iothub_failed_jobs_rate_silenced}" failed_jobs_rate_message = "${var.iothub_failed_jobs_rate_message}" + failed_jobs_rate_aggregator = "${var.iothub_failed_jobs_rate_aggregator}" + failed_jobs_rate_timeframe = "${var.iothub_failed_jobs_rate_timeframe}" failed_jobs_rate_threshold_critical = "${var.iothub_failed_jobs_rate_threshold_critical}" failed_jobs_rate_threshold_warning = "${var.iothub_failed_jobs_rate_threshold_warning}" failed_listjobs_rate_silenced = "${var.iothub_failed_listjobs_rate_silenced}" failed_listjobs_rate_message = "${var.iothub_failed_listjobs_rate_message}" + failed_listjobs_rate_aggregator = "${var.iothub_failed_listjobs_rate_aggregator}" + failed_listjobs_rate_timeframe = "${var.iothub_failed_listjobs_rate_timeframe}" failed_listjobs_rate_threshold_critical = "${var.iothub_failed_listjobs_rate_threshold_critical}" failed_listjobs_rate_threshold_warning = "${var.iothub_failed_listjobs_rate_threshold_warning}" failed_queryjobs_rate_silenced = "${var.iothub_failed_queryjobs_rate_silenced}" failed_queryjobs_rate_message = "${var.iothub_failed_queryjobs_rate_message}" + failed_queryjobs_rate_aggregator = "${var.iothub_failed_queryjobs_rate_aggregator}" + failed_queryjobs_rate_timeframe = "${var.iothub_failed_queryjobs_rate_timeframe}" failed_queryjobs_rate_threshold_critical = "${var.iothub_failed_queryjobs_rate_threshold_critical}" failed_queryjobs_rate_threshold_warning = "${var.iothub_failed_queryjobs_rate_threshold_warning}" invalid_d2c_telemetry_egress_silenced = "${var.iothub_invalid_d2c_telemetry_egress_silenced}" invalid_d2c_telemetry_egress_message = "${var.iothub_invalid_d2c_telemetry_egress_message}" + invalid_d2c_telemetry_egress_aggregator = "${var.iothub_invalid_d2c_telemetry_egress_aggregator}" + invalid_d2c_telemetry_egress_timeframe = "${var.iothub_invalid_d2c_telemetry_egress_timeframe}" invalid_d2c_telemetry_egress_rate_threshold_critical = "${var.iothub_invalid_d2c_telemetry_egress_rate_threshold_critical}" invalid_d2c_telemetry_egress_rate_threshold_warning = "${var.iothub_invalid_d2c_telemetry_egress_rate_threshold_warning}" orphaned_d2c_telemetry_egress_silenced = "${var.iothub_orphaned_d2c_telemetry_egress_silenced}" orphaned_d2c_telemetry_egress_message = "${var.iothub_orphaned_d2c_telemetry_egress_message}" + orphaned_d2c_telemetry_egress_aggregator = "${var.iothub_orphaned_d2c_telemetry_egress_aggregator}" + orphaned_d2c_telemetry_egress_timeframe = "${var.iothub_orphaned_d2c_telemetry_egress_timeframe}" orphaned_d2c_telemetry_egress_rate_threshold_critical = "${var.iothub_orphaned_d2c_telemetry_egress_rate_threshold_critical}" orphaned_d2c_telemetry_egress_rate_threshold_warning = "${var.iothub_orphaned_d2c_telemetry_egress_rate_threshold_warning}" } @@ -154,16 +209,24 @@ module "redis" { status_silenced = "${var.redis_status_silenced}" status_message = "${var.redis_status_message}" + status_aggregator = "${var.redis_status_aggregator}" + status_timeframe = "${var.redis_status_timeframe}" evictedkeys_limit_silenced = "${var.redis_evictedkeys_limit_silenced}" evictedkeys_limit_message = "${var.redis_evictedkeys_limit_message}" + evictedkeys_limit_aggregator = "${var.redis_evictedkeys_limit_aggregator}" + evictedkeys_limit_timeframe = "${var.redis_evictedkeys_limit_timeframe}" evictedkeys_limit_threshold_critical = "${var.redis_evictedkeys_limit_threshold_critical}" evictedkeys_limit_threshold_warning = "${var.redis_evictedkeys_limit_threshold_warning}" percent_processor_time_silenced = "${var.redis_percent_processor_time_silenced}" percent_processor_time_message = "${var.redis_percent_processor_time_message}" + percent_processor_time_aggregator = "${var.redis_percent_processor_time_aggregator}" + percent_processor_time_timeframe = "${var.redis_percent_processor_time_timeframe}" percent_processor_time_threshold_critical = "${var.redis_percent_processor_time_threshold_critical}" percent_processor_time_threshold_warning = "${var.redis_percent_processor_time_threshold_warning}" server_load_rate_silenced = "${var.redis_server_load_rate_silenced}" server_load_rate_message = "${var.redis_server_load_rate_message}" + server_load_rate_aggregator = "${var.redis_server_load_rate_aggregator}" + server_load_rate_timeframe = "${var.redis_server_load_rate_timeframe}" server_load_rate_threshold_critical = "${var.redis_server_load_rate_threshold_critical}" server_load_rate_threshold_warning = "${var.redis_server_load_rate_threshold_warning}" } @@ -196,17 +259,25 @@ module "sqldatabase" { cpu_silenced = "${var.sqldatabase_cpu_silenced}" cpu_message = "${var.sqldatabase_cpu_message}" + cpu_aggregator = "${var.sqldatabase_cpu_aggregator}" + cpu_timeframe = "${var.sqldatabase_cpu_timeframe}" cpu_threshold_critical = "${var.sqldatabase_cpu_threshold_critical}" cpu_threshold_warning = "${var.sqldatabase_cpu_threshold_warning}" deadlock_silenced = "${var.sqldatabase_deadlock_silenced}" deadlock_message = "${var.sqldatabase_deadlock_message}" + deadlock_aggregator = "${var.sqldatabase_deadlock_aggregator}" + deadlock_timeframe = "${var.sqldatabase_deadlock_timeframe}" deadlock_threshold_critical = "${var.sqldatabase_deadlock_threshold_critical}" diskspace_silenced = "${var.sqldatabase_diskspace_silenced}" diskspace_message = "${var.sqldatabase_diskspace_message}" + diskspace_aggregator = "${var.sqldatabase_diskspace_aggregator}" + diskspace_timeframe = "${var.sqldatabase_diskspace_timeframe}" diskspace_threshold_critical = "${var.sqldatabase_diskspace_threshold_critical}" diskspace_threshold_warning = "${var.sqldatabase_diskspace_threshold_warning}" dtu_silenced = "${var.sqldatabase_dtu_silenced}" dtu_message = "${var.sqldatabase_dtu_message}" + dtu_aggregator = "${var.sqldatabase_dtu_aggregator}" + dtu_timeframe = "${var.sqldatabase_dtu_timeframe}" dtu_threshold_critical = "${var.sqldatabase_dtu_threshold_critical}" dtu_threshold_warning = "${var.sqldatabase_dtu_threshold_warning}" } @@ -223,38 +294,56 @@ module "storage" { authorization_error_requests_silenced = "${var.storage_authorization_error_requests_silenced}" authorization_error_requests_message = "${var.storage_authorization_error_requests_message}" + authorization_error_requests_aggregator = "${var.storage_authorization_error_requests_aggregator}" + authorization_error_requests_timeframe = "${var.storage_authorization_error_requests_timeframe}" authorization_error_requests_threshold_critical = "${var.storage_authorization_error_requests_threshold_critical}" authorization_error_requests_threshold_warning = "${var.storage_authorization_error_requests_threshold_warning}" availability_silenced = "${var.storage_availability_silenced}" availability_message = "${var.storage_availability_message}" + availability_aggregator = "${var.storage_availability_aggregator}" + availability_timeframe = "${var.storage_availability_timeframe}" availability_threshold_critical = "${var.storage_availability_threshold_critical}" availability_threshold_warning = "${var.storage_availability_threshold_warning}" client_other_error_requests_silenced = "${var.storage_client_other_error_requests_silenced}" client_other_error_requests_message = "${var.storage_client_other_error_requests_message}" + client_other_error_requests_aggregator = "${var.storage_client_other_error_requests_aggregator}" + client_other_error_requests_timeframe = "${var.storage_client_other_error_requests_timeframe}" client_other_error_requests_threshold_critical = "${var.storage_client_other_error_requests_threshold_critical}" client_other_error_requests_threshold_warning = "${var.storage_client_other_error_requests_threshold_warning}" latency_silenced = "${var.storage_latency_silenced}" latency_message = "${var.storage_latency_message}" + latency_aggregator = "${var.storage_latency_aggregator}" + latency_timeframe = "${var.storage_latency_timeframe}" latency_threshold_critical = "${var.storage_latency_threshold_critical}" latency_threshold_warning = "${var.storage_latency_threshold_warning}" network_error_requests_silenced = "${var.storage_network_error_requests_silenced}" network_error_requests_message = "${var.storage_network_error_requests_message}" + network_error_requests_aggregator = "${var.storage_network_error_requests_aggregator}" + network_error_requests_timeframe = "${var.storage_network_error_requests_timeframe}" network_error_requests_threshold_critical = "${var.storage_network_error_requests_threshold_critical}" network_error_requests_threshold_warning = "${var.storage_network_error_requests_threshold_warning}" server_other_error_requests_silenced = "${var.storage_server_other_error_requests_silenced}" server_other_error_requests_message = "${var.storage_server_other_error_requests_message}" + server_other_error_requests_aggregator = "${var.storage_server_other_error_requests_aggregator}" + server_other_error_requests_timeframe = "${var.storage_server_other_error_requests_timeframe}" server_other_error_requests_threshold_critical = "${var.storage_server_other_error_requests_threshold_critical}" server_other_error_requests_threshold_warning = "${var.storage_server_other_error_requests_threshold_warning}" successful_requests_silenced = "${var.storage_successful_requests_silenced}" successful_requests_message = "${var.storage_successful_requests_message}" + successful_requests_aggregator = "${var.storage_successful_requests_aggregator}" + successful_requests_timeframe = "${var.storage_successful_requests_timeframe}" successful_requests_threshold_critical = "${var.storage_successful_requests_threshold_critical}" successful_requests_threshold_warning = "${var.storage_successful_requests_threshold_warning}" throttling_error_requests_silenced = "${var.storage_throttling_error_requests_silenced}" throttling_error_requests_message = "${var.storage_throttling_error_requests_message}" + throttling_error_requests_aggregator = "${var.storage_throttling_error_requests_aggregator}" + throttling_error_requests_timeframe = "${var.storage_throttling_error_requests_timeframe}" throttling_error_requests_threshold_critical = "${var.storage_throttling_error_requests_threshold_critical}" throttling_error_requests_threshold_warning = "${var.storage_throttling_error_requests_threshold_warning}" timeout_error_requests_silenced = "${var.storage_timeout_error_requests_silenced}" timeout_error_requests_message = "${var.storage_timeout_error_requests_message}" + timeout_error_requests_aggregator = "${var.storage_timeout_error_requests_aggregator}" + timeout_error_requests_timeframe = "${var.storage_timeout_error_requests_timeframe}" timeout_error_requests_threshold_critical = "${var.storage_timeout_error_requests_threshold_critical}" timeout_error_requests_threshold_warning = "${var.storage_timeout_error_requests_threshold_warning}" } @@ -271,18 +360,26 @@ module "streamanalytics" { conversion_errors_silenced = "${var.streamanalytics_conversion_errors_silenced}" conversion_errors_message = "${var.streamanalytics_conversion_errors_message}" + conversion_errors_aggregator = "${var.streamanalytics_conversion_errors_aggregator}" + conversion_errors_timeframe = "${var.streamanalytics_conversion_errors_timeframe}" conversion_errors_threshold_critical = "${var.streamanalytics_conversion_errors_threshold_critical}" conversion_errors_threshold_warning = "${var.streamanalytics_conversion_errors_threshold_warning}" failed_function_requests_silenced = "${var.streamanalytics_failed_function_requests_silenced}" failed_function_requests_message = "${var.streamanalytics_failed_function_requests_message}" + failed_function_requests_aggregator = "${var.streamanalytics_failed_function_requests_aggregator}" + failed_function_requests_timeframe = "${var.streamanalytics_failed_function_requests_timeframe}" failed_function_requests_threshold_critical = "${var.streamanalytics_failed_function_requests_threshold_critical}" failed_function_requests_threshold_warning = "${var.streamanalytics_failed_function_requests_threshold_warning}" runtime_errors_silenced = "${var.streamanalytics_runtime_errors_silenced}" runtime_errors_message = "${var.streamanalytics_runtime_errors_message}" + runtime_errors_aggregator = "${var.streamanalytics_runtime_errors_aggregator}" + runtime_errors_timeframe = "${var.streamanalytics_runtime_errors_timeframe}" runtime_errors_threshold_critical = "${var.streamanalytics_runtime_errors_threshold_critical}" runtime_errors_threshold_warning = "${var.streamanalytics_runtime_errors_threshold_warning}" su_utilization_silenced = "${var.streamanalytics_su_utilization_silenced}" su_utilization_message = "${var.streamanalytics_su_utilization_message}" + su_utilization_aggregator = "${var.streamanalytics_su_utilization_aggregator}" + su_utilization_timeframe = "${var.streamanalytics_su_utilization_timeframe}" su_utilization_threshold_critical = "${var.streamanalytics_su_utilization_threshold_critical}" su_utilization_threshold_warning = "${var.streamanalytics_su_utilization_threshold_warning}" } From e2797f7d712a4733af279cc73e41f0362c3c5b1c Mon Sep 17 00:00:00 2001 From: Alexandre Gaillet Date: Mon, 30 Apr 2018 15:30:19 +0200 Subject: [PATCH 05/21] MON-191 - Mongodb monitors updated with customizable aggregator --- databases/mongodb/README.md | 1 + databases/mongodb/inputs.tf | 6 ++++++ databases/mongodb/monitors-mongo.tf | 4 ++-- 3 files changed, 9 insertions(+), 2 deletions(-) diff --git a/databases/mongodb/README.md b/databases/mongodb/README.md index fc521cd..c5d78e2 100644 --- a/databases/mongodb/README.md +++ b/databases/mongodb/README.md @@ -79,6 +79,7 @@ Inputs | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | | message | Message sent when an alert is triggered | string | - | yes | +| mongodb_replicaset_aggregator | Monitor aggregator for Mongodb replicaset [available values: min, max, sum or avg] | string | `avg` | no | | mongodb_replicaset_message | Custom message for Mongodb replicaset monitor | string | `` | no | | mongodb_replicaset_silenced | Groups to mute for Mongodb replicaset monitor | map | `` | no | | mongodb_replicaset_timeframe | Monitor timeframe for Mongodb replicaset [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | diff --git a/databases/mongodb/inputs.tf b/databases/mongodb/inputs.tf index 46cf5ee..b67f68c 100644 --- a/databases/mongodb/inputs.tf +++ b/databases/mongodb/inputs.tf @@ -36,6 +36,12 @@ variable "mongodb_replicaset_message" { default = "" } +variable "mongodb_replicaset_aggregator" { + description = "Monitor aggregator for Mongodb replicaset [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "mongodb_replicaset_timeframe" { description = "Monitor timeframe for Mongodb replicaset [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/databases/mongodb/monitors-mongo.tf b/databases/mongodb/monitors-mongo.tf index 5357aeb..edac73d 100644 --- a/databases/mongodb/monitors-mongo.tf +++ b/databases/mongodb/monitors-mongo.tf @@ -11,8 +11,8 @@ resource "datadog_monitor" "mongodb_replicaset_state" { message = "${coalesce(var.mongodb_replicaset_message, var.message)}" query = < Date: Mon, 30 Apr 2018 15:35:26 +0200 Subject: [PATCH 06/21] MON-191 - PHP FPM monitors updated with customizable aggregator --- middleware/php-fpm/README.md | 1 + middleware/php-fpm/inputs.tf | 6 ++++++ middleware/php-fpm/monitors-fpm.tf | 8 ++++---- 3 files changed, 11 insertions(+), 4 deletions(-) diff --git a/middleware/php-fpm/README.md b/middleware/php-fpm/README.md index 85b6e3e..49d63eb 100644 --- a/middleware/php-fpm/README.md +++ b/middleware/php-fpm/README.md @@ -30,6 +30,7 @@ Inputs | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | | message | Message sent when an alert is triggered | string | - | yes | +| php_fpm_busy_aggregator | Monitor aggregator for PHP FPM busy worker [available values: min, max, sum or avg] | string | `avg` | no | | php_fpm_busy_message | Custom message for PHP FPM busy worker monitor | string | `` | no | | php_fpm_busy_silenced | Groups to mute for PHP FPM busy worker monitor | map | `` | no | | php_fpm_busy_threshold_critical | php fpm busy critical threshold | string | `0.9` | no | diff --git a/middleware/php-fpm/inputs.tf b/middleware/php-fpm/inputs.tf index b88d5f5..d9946c0 100644 --- a/middleware/php-fpm/inputs.tf +++ b/middleware/php-fpm/inputs.tf @@ -38,6 +38,12 @@ variable "php_fpm_busy_message" { default = "" } +variable "php_fpm_busy_aggregator" { + description = "Monitor aggregator for PHP FPM busy worker [available values: min, max, sum or avg]" + type = "string" + default = "avg" +} + variable "php_fpm_busy_timeframe" { description = "Monitor timeframe for PHP FPM busy worker [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/middleware/php-fpm/monitors-fpm.tf b/middleware/php-fpm/monitors-fpm.tf index f0d9e90..51e8ec0 100644 --- a/middleware/php-fpm/monitors-fpm.tf +++ b/middleware/php-fpm/monitors-fpm.tf @@ -13,10 +13,10 @@ resource "datadog_monitor" "datadog_php_fpm_connect_idle" { type = "metric alert" query = < ${var.php_fpm_busy_threshold_critical} EOF From 4d1e840b7fdf64d71b77476e3c64ac8b862b83b8 Mon Sep 17 00:00:00 2001 From: Alexandre Gaillet Date: Mon, 30 Apr 2018 15:50:58 +0200 Subject: [PATCH 07/21] MON-191 - Generic system monitors updated with customizable aggregator --- cloud/azure/redis/monitors-azure-redis.tf | 10 ++++---- system/generic/README.md | 5 ++++ system/generic/inputs.tf | 30 +++++++++++++++++++++++ system/generic/monitors-system.tf | 26 ++++++++++---------- 4 files changed, 53 insertions(+), 18 deletions(-) diff --git a/cloud/azure/redis/monitors-azure-redis.tf b/cloud/azure/redis/monitors-azure-redis.tf index ca726f9..8c8dcf0 100644 --- a/cloud/azure/redis/monitors-azure-redis.tf +++ b/cloud/azure/redis/monitors-azure-redis.tf @@ -11,7 +11,7 @@ resource "datadog_monitor" "status" { message = "${coalesce(var.status_message, var.message)}" query = < ${var.evictedkeys_limit_threshold_critical} EOF @@ -68,8 +68,8 @@ resource "datadog_monitor" "percent_processor_time" { message = "${coalesce(var.percent_processor_time_message, var.message)}" query = < ${var.percent_processor_time_threshold_critical} EOF diff --git a/system/generic/README.md b/system/generic/README.md index ac23407..1401a7d 100644 --- a/system/generic/README.md +++ b/system/generic/README.md @@ -28,11 +28,13 @@ Inputs | Name | Description | Type | Default | Required | |------|-------------|:----:|:-----:|:-----:| +| cpu_high_aggregator | Monitor aggregator for CPU high [available values: min, max, sum or avg] | string | `min` | no | | cpu_high_message | Custom message for CPU high monitor | string | `` | no | | cpu_high_silenced | Groups to mute for CPU high monitor | map | `` | no | | cpu_high_threshold_critical | CPU high critical threshold | string | `95` | no | | cpu_high_threshold_warning | CPU high warning threshold | string | `80` | no | | cpu_high_timeframe | Monitor timeframe for CPU high [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| cpu_load_aggregator | Monitor aggregator for CPU load ratio [available values: min, max, sum or avg] | string | `min` | no | | cpu_load_message | Custom message for CPU load ratio monitor | string | `` | no | | cpu_load_silenced | Groups to mute for CPU load ratio monitor | map | `` | no | | cpu_load_threshold_critical | CPU load ratio critical threshold | string | `4` | no | @@ -42,16 +44,19 @@ Inputs | environment | Architecture Environment | string | - | yes | | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | +| free_disk_inodes_aggregator | Monitor aggregator for Free disk inodes [available values: min, max, sum or avg] | string | `min` | no | | free_disk_inodes_message | Custom message for Free disk inodes monitor | string | `` | no | | free_disk_inodes_silenced | Groups to mute for Free disk inodes monitor | map | `` | no | | free_disk_inodes_threshold_critical | Free disk space critical threshold | string | `5` | no | | free_disk_inodes_threshold_warning | Free disk space warning threshold | string | `10` | no | | free_disk_inodes_timeframe | Monitor timeframe for Free disk inodes [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| free_disk_space_aggregator | Monitor aggregator for Free diskspace [available values: min, max, sum or avg] | string | `min` | no | | free_disk_space_message | Custom message for Free diskspace monitor | string | `` | no | | free_disk_space_silenced | Groups to mute for Free diskspace monitor | map | `` | no | | free_disk_space_threshold_critical | Free disk space critical threshold | string | `5` | no | | free_disk_space_threshold_warning | Free disk space warning threshold | string | `10` | no | | free_disk_space_timeframe | Monitor timeframe for Free diskspace [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| free_memory_aggregator | Monitor aggregator for Free memory [available values: min, max, sum or avg] | string | `min` | no | | free_memory_message | Custom message for Free memory monitor | string | - | yes | | free_memory_silenced | Groups to mute for Free memory monitor | map | `` | no | | free_memory_threshold_critical | Free disk space critical threshold | string | `5` | no | diff --git a/system/generic/inputs.tf b/system/generic/inputs.tf index 6c66909..8765a36 100644 --- a/system/generic/inputs.tf +++ b/system/generic/inputs.tf @@ -38,6 +38,12 @@ variable "cpu_high_message" { default = "" } +variable "cpu_high_aggregator" { + description = "Monitor aggregator for CPU high [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "cpu_high_timeframe" { description = "Monitor timeframe for CPU high [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -66,6 +72,12 @@ variable "cpu_load_message" { default = "" } +variable "cpu_load_aggregator" { + description = "Monitor aggregator for CPU load ratio [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "cpu_load_timeframe" { description = "Monitor timeframe for CPU load ratio [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -94,6 +106,12 @@ variable "free_disk_space_message" { default = "" } +variable "free_disk_space_aggregator" { + description = "Monitor aggregator for Free diskspace [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "free_disk_space_timeframe" { description = "Monitor timeframe for Free diskspace [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -122,6 +140,12 @@ variable "free_disk_inodes_message" { default = "" } +variable "free_disk_inodes_aggregator" { + description = "Monitor aggregator for Free disk inodes [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "free_disk_inodes_timeframe" { description = "Monitor timeframe for Free disk inodes [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -149,6 +173,12 @@ variable "free_memory_message" { type = "string" } +variable "free_memory_aggregator" { + description = "Monitor aggregator for Free memory [available values: min, max, sum or avg]" + type = "string" + default = "min" +} + variable "free_memory_timeframe" { description = "Monitor timeframe for Free memory [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/system/generic/monitors-system.tf b/system/generic/monitors-system.tf index d737f01..a0e78bc 100644 --- a/system/generic/monitors-system.tf +++ b/system/generic/monitors-system.tf @@ -11,7 +11,7 @@ resource "datadog_monitor" "datadog_cpu_too_high" { message = "${coalesce(var.cpu_high_message, var.message)}" query = < ${var.cpu_high_threshold_critical} EOF @@ -42,9 +42,9 @@ resource "datadog_monitor" "datadog_load_too_high" { message = "${coalesce(var.cpu_load_message, var.message)}" query = < ${var.cpu_load_threshold_critical} EOF @@ -74,9 +74,9 @@ resource "datadog_monitor" "datadog_free_disk_space_too_low" { message = "${coalesce(var.free_disk_space_message, var.message)}" query = < Date: Mon, 30 Apr 2018 16:33:28 +0200 Subject: [PATCH 08/21] MON-191 - Setup latency aggregator to max for AWS ALB, ELB and API gateway monitors --- cloud/aws/alb/README.md | 2 +- cloud/aws/alb/inputs.tf | 2 +- cloud/aws/apigateway/README.md | 3 ++- cloud/aws/apigateway/inputs.tf | 2 +- cloud/aws/elb/README.md | 2 +- cloud/aws/elb/inputs.tf | 2 +- 6 files changed, 7 insertions(+), 6 deletions(-) diff --git a/cloud/aws/alb/README.md b/cloud/aws/alb/README.md index 64d78db..96f6269 100644 --- a/cloud/aws/alb/README.md +++ b/cloud/aws/alb/README.md @@ -63,7 +63,7 @@ Inputs | httpcode_target_5xx_threshold_critical | target 5xx critical threshold in percentage | string | `80` | no | | httpcode_target_5xx_threshold_warning | target 5xx warning threshold in percentage | string | `60` | no | | httpcode_target_5xx_timeframe | Monitor timeframe for ALB target httpcode 5xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| latency_aggregator | Monitor aggregator for ALB latency [available values: min, max, sum or avg] | string | `min` | no | +| latency_aggregator | Monitor aggregator for ALB latency [available values: min, max, sum or avg] | string | `max` | no | | latency_message | Custom message for ALB latency monitor | string | `` | no | | latency_silenced | Groups to mute for ALB latency monitor | map | `` | no | | latency_threshold_critical | latency critical threshold in milliseconds | string | `1000` | no | diff --git a/cloud/aws/alb/inputs.tf b/cloud/aws/alb/inputs.tf index 68a057a..fdead0b 100644 --- a/cloud/aws/alb/inputs.tf +++ b/cloud/aws/alb/inputs.tf @@ -65,7 +65,7 @@ variable "latency_message" { variable "latency_aggregator" { description = "Monitor aggregator for ALB latency [available values: min, max, sum or avg]" type = "string" - default = "min" + default = "max" } variable "latency_timeframe" { diff --git a/cloud/aws/apigateway/README.md b/cloud/aws/apigateway/README.md index 9ec15b9..54e1138 100644 --- a/cloud/aws/apigateway/README.md +++ b/cloud/aws/apigateway/README.md @@ -43,13 +43,14 @@ Inputs | http_5xx_requests_threshold_critical | Maximum critical acceptable percent of 5xx errors | string | `20` | no | | http_5xx_requests_threshold_warning | Maximum warning acceptable percent of 5xx errors | string | `10` | no | | http_5xx_requests_timeframe | Monitor timeframe for API HTTP 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| latency_aggregator | Monitor aggregator for API Gateway latency [available values: min, max, sum or avg] | string | `min` | no | +| latency_aggregator | Monitor aggregator for API Gateway latency [available values: min, max, sum or avg] | string | `max` | no | | latency_message | Custom message for API Gateway latency monitor | string | `` | no | | latency_silenced | Groups to mute for API Gateway latency monitor | map | `` | no | | latency_threshold_critical | Alerting threshold in milliseconds | string | `800` | no | | latency_threshold_warning | Warning threshold in milliseconds | string | `400` | no | | latency_timeframe | Monitor timeframe for API latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | message | Message sent when a monitor is triggered | string | - | yes | + Related documentation --------------------- diff --git a/cloud/aws/apigateway/inputs.tf b/cloud/aws/apigateway/inputs.tf index 21598f8..6890408 100644 --- a/cloud/aws/apigateway/inputs.tf +++ b/cloud/aws/apigateway/inputs.tf @@ -36,7 +36,7 @@ variable "latency_message" { variable "latency_aggregator" { description = "Monitor aggregator for API Gateway latency [available values: min, max, sum or avg]" type = "string" - default = "min" + default = "max" } variable "latency_timeframe" { diff --git a/cloud/aws/elb/README.md b/cloud/aws/elb/README.md index 0dbc061..ab30a8b 100644 --- a/cloud/aws/elb/README.md +++ b/cloud/aws/elb/README.md @@ -56,7 +56,7 @@ Inputs | elb_backend_5xx_threshold_critical | loadbalancer backend 5xx critical threshold in percentage | string | `10` | no | | elb_backend_5xx_threshold_warning | loadbalancer backend 5xx warning threshold in percentage | string | `5` | no | | elb_backend_5xx_timeframe | Monitor timeframe for ELB backend 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| elb_backend_latency_aggregator | Monitor aggregator for ELB backend latency [available values: min, max, sum or avg] | string | `min` | no | +| elb_backend_latency_aggregator | Monitor aggregator for ELB backend latency [available values: min, max, sum or avg] | string | `max` | no | | elb_backend_latency_critical | latency critical threshold in seconds | string | `5` | no | | elb_backend_latency_message | Custom message for ELB backend latency monitor | string | `` | no | | elb_backend_latency_silenced | Groups to mute for ELB backend latency monitor | map | `` | no | diff --git a/cloud/aws/elb/inputs.tf b/cloud/aws/elb/inputs.tf index 53dc1fe..056aeb8 100644 --- a/cloud/aws/elb/inputs.tf +++ b/cloud/aws/elb/inputs.tf @@ -200,7 +200,7 @@ variable "elb_backend_latency_message" { variable "elb_backend_latency_aggregator" { description = "Monitor aggregator for ELB backend latency [available values: min, max, sum or avg]" type = "string" - default = "min" + default = "max" } variable "elb_backend_latency_timeframe" { From 7597b3fec29fc887a5c00672e8ba2fe34fedcda8 Mon Sep 17 00:00:00 2001 From: Alexandre Gaillet Date: Fri, 18 May 2018 17:05:38 +0200 Subject: [PATCH 09/21] MON-191 - Update on firehorse reverted --- cloud/aws/kinesis-firehose/README.md | 1 - cloud/aws/kinesis-firehose/inputs.tf | 6 ------ cloud/aws/kinesis-firehose/monitors-kinesis-firehose.tf | 4 ++-- 3 files changed, 2 insertions(+), 9 deletions(-) diff --git a/cloud/aws/kinesis-firehose/README.md b/cloud/aws/kinesis-firehose/README.md index 21d4214..fafe19b 100644 --- a/cloud/aws/kinesis-firehose/README.md +++ b/cloud/aws/kinesis-firehose/README.md @@ -29,7 +29,6 @@ Inputs | environment | Environment | string | - | yes | | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | -| incoming_records_aggregator | Monitor aggregator for Kinesis Firehorse incoming records [available values: min, max, sum or avg] | string | `sum` | no | | incoming_records_message | Custom message for Kinesis Firehorse incoming records monitor | string | `` | no | | incoming_records_silenced | Groups to mute for Kinesis Firehorse incoming records monitor | map | `` | no | | incoming_records_timeframe | Monitor timeframe for incoming records metrics evaluation [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | diff --git a/cloud/aws/kinesis-firehose/inputs.tf b/cloud/aws/kinesis-firehose/inputs.tf index 931b253..831045e 100644 --- a/cloud/aws/kinesis-firehose/inputs.tf +++ b/cloud/aws/kinesis-firehose/inputs.tf @@ -38,12 +38,6 @@ variable "incoming_records_message" { default = "" } -variable "incoming_records_aggregator" { - description = "Monitor aggregator for Kinesis Firehorse incoming records [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "incoming_records_timeframe" { description = "Monitor timeframe for incoming records metrics evaluation [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" default = "last_15m" diff --git a/cloud/aws/kinesis-firehose/monitors-kinesis-firehose.tf b/cloud/aws/kinesis-firehose/monitors-kinesis-firehose.tf index d5ab13f..1f1a71b 100644 --- a/cloud/aws/kinesis-firehose/monitors-kinesis-firehose.tf +++ b/cloud/aws/kinesis-firehose/monitors-kinesis-firehose.tf @@ -14,8 +14,8 @@ resource "datadog_monitor" "firehose_incoming_records" { type = "metric alert" query = < Date: Tue, 22 May 2018 14:41:47 +0200 Subject: [PATCH 10/21] MON-191 - Merge diff from MON-198 --- cloud/aws/alb/inputs.tf | 12 ++++++------ cloud/aws/apigateway/inputs.tf | 6 +++--- cloud/aws/elb/inputs.tf | 10 +++++----- system/generic/inputs.tf | 4 ++-- 4 files changed, 16 insertions(+), 16 deletions(-) diff --git a/cloud/aws/alb/inputs.tf b/cloud/aws/alb/inputs.tf index fdead0b..de2c7cd 100644 --- a/cloud/aws/alb/inputs.tf +++ b/cloud/aws/alb/inputs.tf @@ -47,7 +47,7 @@ variable "alb_no_healthy_instances_aggregator" { variable "alb_no_healthy_instances_timeframe" { description = "Monitor timeframe for ALB no healthy instances [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" - default = "last_1m" + default = "last_5m" } variable "latency_silenced" { @@ -65,7 +65,7 @@ variable "latency_message" { variable "latency_aggregator" { description = "Monitor aggregator for ALB latency [available values: min, max, sum or avg]" type = "string" - default = "max" + default = "min" } variable "latency_timeframe" { @@ -99,7 +99,7 @@ variable "httpcode_elb_4xx_message" { variable "httpcode_elb_4xx_aggregator" { description = "Monitor aggregator for ALB httpcode 4xx [available values: min, max, sum or avg]" type = "string" - default = "min" + default = "sum" } variable "httpcode_elb_4xx_timeframe" { @@ -133,7 +133,7 @@ variable "httpcode_target_4xx_message" { variable "httpcode_target_4xx_aggregator" { description = "Monitor aggregator for ALB target httpcode 4xx [available values: min, max, sum or avg]" type = "string" - default = "min" + default = "sum" } variable "httpcode_target_4xx_timeframe" { @@ -167,7 +167,7 @@ variable "httpcode_elb_5xx_message" { variable "httpcode_elb_5xx_aggregator" { description = "Monitor aggregator for ALB httpcode 5xx [available values: min, max, sum or avg]" type = "string" - default = "min" + default = "sum" } variable "httpcode_elb_5xx_timeframe" { @@ -201,7 +201,7 @@ variable "httpcode_target_5xx_message" { variable "httpcode_target_5xx_aggregator" { description = "Monitor aggregator for ALB target httpcode 5xx [available values: min, max, sum or avg]" type = "string" - default = "min" + default = "sum" } variable "httpcode_target_5xx_timeframe" { diff --git a/cloud/aws/apigateway/inputs.tf b/cloud/aws/apigateway/inputs.tf index 6890408..461fd1c 100644 --- a/cloud/aws/apigateway/inputs.tf +++ b/cloud/aws/apigateway/inputs.tf @@ -36,7 +36,7 @@ variable "latency_message" { variable "latency_aggregator" { description = "Monitor aggregator for API Gateway latency [available values: min, max, sum or avg]" type = "string" - default = "max" + default = "min" } variable "latency_timeframe" { @@ -74,7 +74,7 @@ variable "http_5xx_requests_message" { variable "http_5xx_requests_aggregator" { description = "Monitor aggregator for API Gateway HTTP 5xx requests [available values: min, max, sum or avg]" type = "string" - default = "min" + default = "sum" } variable "http_5xx_requests_timeframe" { @@ -112,7 +112,7 @@ variable "http_4xx_requests_message" { variable "http_4xx_requests_aggregator" { description = "Monitor aggregator for API Gateway HTTP 4xx requests [available values: min, max, sum or avg]" type = "string" - default = "min" + default = "sum" } variable "http_4xx_requests_timeframe" { diff --git a/cloud/aws/elb/inputs.tf b/cloud/aws/elb/inputs.tf index 056aeb8..d311ca3 100644 --- a/cloud/aws/elb/inputs.tf +++ b/cloud/aws/elb/inputs.tf @@ -64,7 +64,7 @@ variable "elb_4xx_message" { variable "elb_4xx_aggregator" { description = "Monitor aggregator for ELB 4xx errors [available values: min, max, sum or avg]" type = "string" - default = "min" + default = "sum" } variable "elb_4xx_timeframe" { @@ -98,7 +98,7 @@ variable "elb_5xx_message" { variable "elb_5xx_aggregator" { description = "Monitor aggregator for ELB 5xx errors [available values: min, max, sum or avg]" type = "string" - default = "min" + default = "sum" } variable "elb_5xx_timeframe" { @@ -132,7 +132,7 @@ variable "elb_backend_4xx_message" { variable "elb_backend_4xx_aggregator" { description = "Monitor aggregator for ELB backend 4xx errors [available values: min, max, sum or avg]" type = "string" - default = "min" + default = "sum" } variable "elb_backend_4xx_timeframe" { @@ -166,7 +166,7 @@ variable "elb_backend_5xx_message" { variable "elb_backend_5xx_aggregator" { description = "Monitor aggregator for ELB backend 5xx errors [available values: min, max, sum or avg]" type = "string" - default = "min" + default = "sum" } variable "elb_backend_5xx_timeframe" { @@ -200,7 +200,7 @@ variable "elb_backend_latency_message" { variable "elb_backend_latency_aggregator" { description = "Monitor aggregator for ELB backend latency [available values: min, max, sum or avg]" type = "string" - default = "max" + default = "min" } variable "elb_backend_latency_timeframe" { diff --git a/system/generic/inputs.tf b/system/generic/inputs.tf index 8765a36..fec8a81 100644 --- a/system/generic/inputs.tf +++ b/system/generic/inputs.tf @@ -47,7 +47,7 @@ variable "cpu_high_aggregator" { variable "cpu_high_timeframe" { description = "Monitor timeframe for CPU high [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" - default = "last_5m" + default = "last_10m" } variable "cpu_high_threshold_warning" { @@ -182,7 +182,7 @@ variable "free_memory_aggregator" { variable "free_memory_timeframe" { description = "Monitor timeframe for Free memory [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" - default = "last_1m" + default = "last_15m" } variable "free_memory_threshold_warning" { From 437e230514c7a4d7b7441649cf317838619a7392 Mon Sep 17 00:00:00 2001 From: Alexandre Gaillet Date: Tue, 22 May 2018 18:22:19 +0200 Subject: [PATCH 11/21] MON-191 - Space aggregator hard coded for AWS monitors --- cloud/aws/alb/README.md | 30 +++++----- cloud/aws/alb/inputs.tf | 52 +++++------------ cloud/aws/alb/monitors-alb.tf | 56 +++++++++---------- cloud/aws/apigateway/README.md | 4 +- cloud/aws/apigateway/inputs.tf | 16 +----- cloud/aws/apigateway/monitors-api.tf | 16 +++--- cloud/aws/elasticsearch/README.md | 6 +- cloud/aws/elasticsearch/inputs.tf | 12 ++-- .../elasticsearch/monitors-elasticsearch.tf | 14 ++--- cloud/aws/elb/README.md | 8 +-- cloud/aws/elb/inputs.tf | 32 ++--------- cloud/aws/elb/monitors-elb.tf | 32 +++++------ .../monitors-kinesis-firehose.tf | 8 +-- cloud/aws/rds/README.md | 4 +- cloud/aws/rds/inputs.tf | 8 +-- cloud/aws/rds/monitors-rds.tf | 10 ++-- cloud/aws/vpn/README.md | 2 +- cloud/aws/vpn/inputs.tf | 4 +- cloud/aws/vpn/monitors-vpn.tf | 4 +- 19 files changed, 124 insertions(+), 194 deletions(-) diff --git a/cloud/aws/alb/README.md b/cloud/aws/alb/README.md index 96f6269..679a2e1 100644 --- a/cloud/aws/alb/README.md +++ b/cloud/aws/alb/README.md @@ -30,44 +30,40 @@ Inputs | Name | Description | Type | Default | Required | |------|-------------|:----:|:-----:|:-----:| -| alb_no_healthy_instances_aggregator | Monitor aggregator for ALB no healthy instances [available values: min, max, sum or avg] | string | `min` | no | | alb_no_healthy_instances_message | Custom message for ALB no healthy instances monitor | string | `` | no | | alb_no_healthy_instances_silenced | Groups to mute for ALB no healthy instances monitor | map | `` | no | -| alb_no_healthy_instances_timeframe | Monitor timeframe for ALB no healthy instances [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_1m` | no | +| alb_no_healthy_instances_time_aggregator | Monitor aggregator for ALB no healthy instances [available values: min, max or avg] | string | `min` | no | +| alb_no_healthy_instances_timeframe | Monitor timeframe for ALB no healthy instances [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | artificial_requests_count | Number of false requests used to mitigate false positive in case of low trafic | string | `5` | no | | delay | Delay in seconds for the metric evaluation | string | `900` | no | | environment | Architecture environment | string | - | yes | | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | -| httpcode_elb_4xx_aggregator | Monitor aggregator for ALB httpcode 4xx [available values: min, max, sum or avg] | string | `min` | no | -| httpcode_elb_4xx_message | Custom message for ALB httpcode 4xx monitor | string | `` | no | -| httpcode_elb_4xx_silenced | Groups to mute for ALB httpcode 4xx monitor | map | `` | no | -| httpcode_elb_4xx_threshold_critical | loadbalancer 4xx critical threshold in percentage | string | `80` | no | -| httpcode_elb_4xx_threshold_warning | loadbalancer 4xx warning threshold in percentage | string | `60` | no | -| httpcode_elb_4xx_timeframe | Monitor timeframe for ALB httpcode 4xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| httpcode_elb_5xx_aggregator | Monitor aggregator for ALB httpcode 5xx [available values: min, max, sum or avg] | string | `min` | no | -| httpcode_elb_5xx_message | Custom message for ALB httpcode 5xx monitor | string | `` | no | -| httpcode_elb_5xx_silenced | Groups to mute for ALB httpcode 5xx monitor | map | `` | no | -| httpcode_elb_5xx_threshold_critical | loadbalancer 5xxcritical threshold in percentage | string | `80` | no | -| httpcode_elb_5xx_threshold_warning | loadbalancer 5xx warning threshold in percentage | string | `60` | no | -| httpcode_elb_5xx_timeframe | Monitor timeframe for ALB httpcode 5xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| httpcode_target_4xx_aggregator | Monitor aggregator for ALB target httpcode 4xx [available values: min, max, sum or avg] | string | `min` | no | +| httpcode_alb_4xx_message | Custom message for ALB httpcode 4xx monitor | string | `` | no | +| httpcode_alb_4xx_silenced | Groups to mute for ALB httpcode 4xx monitor | map | `` | no | +| httpcode_alb_4xx_threshold_critical | loadbalancer 4xx critical threshold in percentage | string | `80` | no | +| httpcode_alb_4xx_threshold_warning | loadbalancer 4xx warning threshold in percentage | string | `60` | no | +| httpcode_alb_4xx_timeframe | Monitor timeframe for ALB httpcode 4xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| httpcode_alb_5xx_message | Custom message for ALB httpcode 5xx monitor | string | `` | no | +| httpcode_alb_5xx_silenced | Groups to mute for ALB httpcode 5xx monitor | map | `` | no | +| httpcode_alb_5xx_threshold_critical | loadbalancer 5xxcritical threshold in percentage | string | `80` | no | +| httpcode_alb_5xx_threshold_warning | loadbalancer 5xx warning threshold in percentage | string | `60` | no | +| httpcode_alb_5xx_timeframe | Monitor timeframe for ALB httpcode 5xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | httpcode_target_4xx_message | Custom message for ALB target httpcode 4xx monitor | string | `` | no | | httpcode_target_4xx_silenced | Groups to mute for ALB target httpcode 4xx monitor | map | `` | no | | httpcode_target_4xx_threshold_critical | target 4xx critical threshold in percentage | string | `80` | no | | httpcode_target_4xx_threshold_warning | target 4xx warning threshold in percentage | string | `60` | no | | httpcode_target_4xx_timeframe | Monitor timeframe for ALB target httpcode 4xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| httpcode_target_5xx_aggregator | Monitor aggregator for ALB target httpcode 5xx [available values: min, max, sum or avg] | string | `min` | no | | httpcode_target_5xx_message | Custom message for ALB target httpcode 5xx monitor | string | `` | no | | httpcode_target_5xx_silenced | Groups to mute for ALB target httpcode 5xx monitor | map | `` | no | | httpcode_target_5xx_threshold_critical | target 5xx critical threshold in percentage | string | `80` | no | | httpcode_target_5xx_threshold_warning | target 5xx warning threshold in percentage | string | `60` | no | | httpcode_target_5xx_timeframe | Monitor timeframe for ALB target httpcode 5xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| latency_aggregator | Monitor aggregator for ALB latency [available values: min, max, sum or avg] | string | `max` | no | | latency_message | Custom message for ALB latency monitor | string | `` | no | | latency_silenced | Groups to mute for ALB latency monitor | map | `` | no | | latency_threshold_critical | latency critical threshold in milliseconds | string | `1000` | no | | latency_threshold_warning | latency warning threshold in milliseconds | string | `500` | no | +| latency_time_aggregator | Monitor aggregator for ALB latency [available values: min, max or avg] | string | `min` | no | | latency_timeframe | Monitor timeframe for ALB latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | message | Message sent when a monitor is triggered | string | - | yes | diff --git a/cloud/aws/alb/inputs.tf b/cloud/aws/alb/inputs.tf index de2c7cd..584c299 100644 --- a/cloud/aws/alb/inputs.tf +++ b/cloud/aws/alb/inputs.tf @@ -38,8 +38,8 @@ variable "alb_no_healthy_instances_message" { default = "" } -variable "alb_no_healthy_instances_aggregator" { - description = "Monitor aggregator for ALB no healthy instances [available values: min, max, sum or avg]" +variable "alb_no_healthy_instances_time_aggregator" { + description = "Monitor aggregator for ALB no healthy instances [available values: min, max or avg]" type = "string" default = "min" } @@ -62,8 +62,8 @@ variable "latency_message" { default = "" } -variable "latency_aggregator" { - description = "Monitor aggregator for ALB latency [available values: min, max, sum or avg]" +variable "latency_time_aggregator" { + description = "Monitor aggregator for ALB latency [available values: min, max or avg]" type = "string" default = "min" } @@ -84,36 +84,30 @@ variable "latency_threshold_warning" { description = "latency warning threshold in milliseconds" } -variable "httpcode_elb_4xx_silenced" { +variable "httpcode_alb_4xx_silenced" { description = "Groups to mute for ALB httpcode 4xx monitor" type = "map" default = {} } -variable "httpcode_elb_4xx_message" { +variable "httpcode_alb_4xx_message" { description = "Custom message for ALB httpcode 4xx monitor" type = "string" default = "" } -variable "httpcode_elb_4xx_aggregator" { - description = "Monitor aggregator for ALB httpcode 4xx [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - -variable "httpcode_elb_4xx_timeframe" { +variable "httpcode_alb_4xx_timeframe" { description = "Monitor timeframe for ALB httpcode 4xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" default = "last_5m" } -variable "httpcode_elb_4xx_threshold_critical" { +variable "httpcode_alb_4xx_threshold_critical" { default = 80 description = "loadbalancer 4xx critical threshold in percentage" } -variable "httpcode_elb_4xx_threshold_warning" { +variable "httpcode_alb_4xx_threshold_warning" { default = 60 description = "loadbalancer 4xx warning threshold in percentage" } @@ -130,12 +124,6 @@ variable "httpcode_target_4xx_message" { default = "" } -variable "httpcode_target_4xx_aggregator" { - description = "Monitor aggregator for ALB target httpcode 4xx [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "httpcode_target_4xx_timeframe" { description = "Monitor timeframe for ALB target httpcode 4xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -152,36 +140,30 @@ variable "httpcode_target_4xx_threshold_warning" { description = "target 4xx warning threshold in percentage" } -variable "httpcode_elb_5xx_silenced" { +variable "httpcode_alb_5xx_silenced" { description = "Groups to mute for ALB httpcode 5xx monitor" type = "map" default = {} } -variable "httpcode_elb_5xx_message" { +variable "httpcode_alb_5xx_message" { description = "Custom message for ALB httpcode 5xx monitor" type = "string" default = "" } -variable "httpcode_elb_5xx_aggregator" { - description = "Monitor aggregator for ALB httpcode 5xx [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - -variable "httpcode_elb_5xx_timeframe" { +variable "httpcode_alb_5xx_timeframe" { description = "Monitor timeframe for ALB httpcode 5xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" default = "last_5m" } -variable "httpcode_elb_5xx_threshold_critical" { +variable "httpcode_alb_5xx_threshold_critical" { default = 80 description = "loadbalancer 5xxcritical threshold in percentage" } -variable "httpcode_elb_5xx_threshold_warning" { +variable "httpcode_alb_5xx_threshold_warning" { default = 60 description = "loadbalancer 5xx warning threshold in percentage" } @@ -198,12 +180,6 @@ variable "httpcode_target_5xx_message" { default = "" } -variable "httpcode_target_5xx_aggregator" { - description = "Monitor aggregator for ALB target httpcode 5xx [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "httpcode_target_5xx_timeframe" { description = "Monitor timeframe for ALB target httpcode 5xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/aws/alb/monitors-alb.tf b/cloud/aws/alb/monitors-alb.tf index e9272b2..72fb533 100644 --- a/cloud/aws/alb/monitors-alb.tf +++ b/cloud/aws/alb/monitors-alb.tf @@ -14,8 +14,8 @@ resource "datadog_monitor" "ALB_no_healthy_instances" { message = "${coalesce(var.alb_no_healthy_instances_message, var.message)}" query = < ${var.latency_threshold_critical} EOF @@ -67,26 +67,26 @@ resource "datadog_monitor" "ALB_latency" { tags = ["env:${var.environment}", "resource:alb", "team:aws", "provider:aws"] } -resource "datadog_monitor" "ALB_httpcode_elb_5xx" { +resource "datadog_monitor" "ALB_httpcode_5xx" { name = "[${var.environment}] ALB HTTP code 5xx {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}" type = "metric alert" - message = "${coalesce(var.httpcode_elb_5xx_message, var.message)}" + message = "${coalesce(var.httpcode_alb_5xx_message, var.message)}" query = < ${var.httpcode_elb_5xx_threshold_critical} + ) > ${var.httpcode_alb_5xx_threshold_critical} EOF evaluation_delay = "${var.delay}" new_host_delay = "${var.delay}" thresholds { - critical = "${var.httpcode_elb_5xx_threshold_critical}" - warning = "${var.httpcode_elb_5xx_threshold_warning}" + critical = "${var.httpcode_alb_5xx_threshold_critical}" + warning = "${var.httpcode_alb_5xx_threshold_warning}" } notify_no_data = false @@ -95,31 +95,31 @@ resource "datadog_monitor" "ALB_httpcode_elb_5xx" { timeout_h = 0 include_tags = true - silenced = "${var.httpcode_elb_5xx_silenced}" + silenced = "${var.httpcode_alb_5xx_silenced}" tags = ["env:${var.environment}", "resource:alb", "team:aws", "provider:aws"] } -resource "datadog_monitor" "ALB_httpcode_elb_4xx" { +resource "datadog_monitor" "ALB_httpcode_4xx" { name = "[${var.environment}] ALB HTTP code 4xx {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}" type = "metric alert" - message = "${coalesce(var.httpcode_elb_4xx_message, var.message)}" + message = "${coalesce(var.httpcode_alb_4xx_message, var.message)}" query = < ${var.httpcode_elb_4xx_threshold_critical} + ) > ${var.httpcode_alb_4xx_threshold_critical} EOF evaluation_delay = "${var.delay}" new_host_delay = "${var.delay}" thresholds { - critical = "${var.httpcode_elb_4xx_threshold_critical}" - warning = "${var.httpcode_elb_4xx_threshold_warning}" + critical = "${var.httpcode_alb_4xx_threshold_critical}" + warning = "${var.httpcode_alb_4xx_threshold_warning}" } notify_no_data = false @@ -128,7 +128,7 @@ resource "datadog_monitor" "ALB_httpcode_elb_4xx" { timeout_h = 0 include_tags = true - silenced = "${var.httpcode_elb_4xx_silenced}" + silenced = "${var.httpcode_alb_4xx_silenced}" tags = ["env:${var.environment}", "resource:alb", "team:aws", "provider:aws"] } @@ -139,10 +139,10 @@ resource "datadog_monitor" "ALB_httpcode_target_5xx" { message = "${coalesce(var.httpcode_target_5xx_message, var.message)}" query = < ${var.httpcode_target_5xx_threshold_critical} EOF @@ -172,10 +172,10 @@ resource "datadog_monitor" "ALB_httpcode_target_4xx" { message = "${coalesce(var.httpcode_target_4xx_message, var.message)}" query = < ${var.httpcode_target_4xx_threshold_critical} EOF diff --git a/cloud/aws/apigateway/README.md b/cloud/aws/apigateway/README.md index 54e1138..63e8b9b 100644 --- a/cloud/aws/apigateway/README.md +++ b/cloud/aws/apigateway/README.md @@ -31,19 +31,17 @@ Inputs | delay | Delay in seconds for the metric evaluation | string | `900` | no | | environment | Environment | string | - | yes | | filter_tags | Tags used for filtering | string | `*` | no | -| http_4xx_requests_aggregator | Monitor aggregator for API Gateway HTTP 4xx requests [available values: min, max, sum or avg] | string | `min` | no | | http_4xx_requests_message | Custom message for API Gateway HTTP 4xx requests monitor | string | `` | no | | http_4xx_requests_silenced | Groups to mute for API Gateway HTTP 4xx requests monitor | map | `` | no | | http_4xx_requests_threshold_critical | Maximum critical acceptable percent of 4xx errors | string | `30` | no | | http_4xx_requests_threshold_warning | Maximum warning acceptable percent of 4xx errors | string | `15` | no | | http_4xx_requests_timeframe | Monitor timeframe for API HTTP 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| http_5xx_requests_aggregator | Monitor aggregator for API Gateway HTTP 5xx requests [available values: min, max, sum or avg] | string | `min` | no | | http_5xx_requests_message | Custom message for API Gateway HTTP 5xx requests monitor | string | `` | no | | http_5xx_requests_silenced | Groups to mute for API Gateway HTTP 5xx requests monitor | map | `` | no | | http_5xx_requests_threshold_critical | Maximum critical acceptable percent of 5xx errors | string | `20` | no | | http_5xx_requests_threshold_warning | Maximum warning acceptable percent of 5xx errors | string | `10` | no | | http_5xx_requests_timeframe | Monitor timeframe for API HTTP 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| latency_aggregator | Monitor aggregator for API Gateway latency [available values: min, max, sum or avg] | string | `max` | no | +| latency_time_aggregator | Monitor aggregator for API Gateway latency [available values: min, max or avg] | string | `min` | no | | latency_message | Custom message for API Gateway latency monitor | string | `` | no | | latency_silenced | Groups to mute for API Gateway latency monitor | map | `` | no | | latency_threshold_critical | Alerting threshold in milliseconds | string | `800` | no | diff --git a/cloud/aws/apigateway/inputs.tf b/cloud/aws/apigateway/inputs.tf index 461fd1c..1430ab5 100644 --- a/cloud/aws/apigateway/inputs.tf +++ b/cloud/aws/apigateway/inputs.tf @@ -33,8 +33,8 @@ variable "latency_message" { default = "" } -variable "latency_aggregator" { - description = "Monitor aggregator for API Gateway latency [available values: min, max, sum or avg]" +variable "latency_time_aggregator" { + description = "Monitor aggregator for API Gateway latency [available values: min, max or avg]" type = "string" default = "min" } @@ -71,12 +71,6 @@ variable "http_5xx_requests_message" { default = "" } -variable "http_5xx_requests_aggregator" { - description = "Monitor aggregator for API Gateway HTTP 5xx requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "http_5xx_requests_timeframe" { description = "Monitor timeframe for API HTTP 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -109,12 +103,6 @@ variable "http_4xx_requests_message" { default = "" } -variable "http_4xx_requests_aggregator" { - description = "Monitor aggregator for API Gateway HTTP 4xx requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "http_4xx_requests_timeframe" { description = "Monitor timeframe for API HTTP 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/aws/apigateway/monitors-api.tf b/cloud/aws/apigateway/monitors-api.tf index 602fdfd..a7ff9cd 100644 --- a/cloud/aws/apigateway/monitors-api.tf +++ b/cloud/aws/apigateway/monitors-api.tf @@ -5,8 +5,8 @@ resource "datadog_monitor" "API_Gateway_latency" { message = "${coalesce(var.latency_message, var.message)}" query = < ${var.latency_threshold_critical} EOF @@ -36,10 +36,10 @@ resource "datadog_monitor" "API_http_5xx_errors_count" { message = "${coalesce(var.http_5xx_requests_message, var.message)}" query = < ${var.http_5xx_requests_threshold_critical} EOF @@ -70,10 +70,10 @@ resource "datadog_monitor" "API_http_4xx_errors_count" { message = "${coalesce(var.http_4xx_requests_message, var.message)}" query = < ${var.http_4xx_requests_threshold_critical} EOF diff --git a/cloud/aws/elasticsearch/README.md b/cloud/aws/elasticsearch/README.md index 65015e6..641adac 100644 --- a/cloud/aws/elasticsearch/README.md +++ b/cloud/aws/elasticsearch/README.md @@ -29,23 +29,23 @@ Inputs | Name | Description | Type | Default | Required | |------|-------------|:----:|:-----:|:-----:| -| cpu_aggregator | Monitor aggregator for ES cluster cpu [available values: min, max, sum or avg] | string | `avg` | no | | cpu_message | Custom message for ES cluster cpu monitor | string | `` | no | | cpu_silenced | Groups to mute for ES cluster cpu monitor | map | `` | no | | cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no | | cpu_threshold_warning | CPU usage in percent (warning threshold) | string | `80` | no | +| cpu_time_aggregator | Monitor aggregator for ES cluster cpu [available values: min, max or avg] | string | `avg` | no | | cpu_timeframe | Monitor timeframe for ES cluster cpu [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | | delay | Delay in seconds for the metric evaluation | string | `900` | no | -| diskspace_aggregator | Monitor aggregator for ES cluster diskspace [available values: min, max, sum or avg] | string | `avg` | no | | diskspace_message | Custom message for ES cluster diskspace monitor | string | `` | no | | diskspace_silenced | Groups to mute for ES cluster diskspace monitor | map | `` | no | | diskspace_threshold_critical | Disk free space in percent (critical threshold) | string | `10` | no | | diskspace_threshold_warning | Disk free space in percent (warning threshold) | string | `20` | no | +| diskspace_time_aggregator | Monitor aggregator for ES cluster diskspace [available values: min, max or avg] | string | `avg` | no | | diskspace_timeframe | Monitor timeframe for ES cluster diskspace [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | | environment | Architecture Environment | string | - | yes | -| es_cluster_status_aggregator | Monitor aggregator for ES cluster status [available values: min, max, sum or avg] | string | `max` | no | | es_cluster_status_message | Custom message for ES cluster status monitor | string | `` | no | | es_cluster_status_silenced | Groups to mute for ES cluster status monitor | map | `` | no | +| es_cluster_status_time_aggregator | Monitor aggregator for ES cluster status [available values: min, max or avg] | string | `max` | no | | es_cluster_status_timeframe | Monitor timeframe for ES cluster status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_30m` | no | | es_cluster_volume_size | ElasticSearch Domain volume size (in GB) | string | - | yes | | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | diff --git a/cloud/aws/elasticsearch/inputs.tf b/cloud/aws/elasticsearch/inputs.tf index ee010a1..3f1a3e3 100644 --- a/cloud/aws/elasticsearch/inputs.tf +++ b/cloud/aws/elasticsearch/inputs.tf @@ -38,8 +38,8 @@ variable "es_cluster_status_message" { default = "" } -variable "es_cluster_status_aggregator" { - description = "Monitor aggregator for ES cluster status [available values: min, max, sum or avg]" +variable "es_cluster_status_time_aggregator" { + description = "Monitor aggregator for ES cluster status [available values: min, max or avg]" type = "string" default = "max" } @@ -66,8 +66,8 @@ variable "diskspace_message" { default = "" } -variable "diskspace_aggregator" { - description = "Monitor aggregator for ES cluster diskspace [available values: min, max, sum or avg]" +variable "diskspace_time_aggregator" { + description = "Monitor aggregator for ES cluster diskspace [available values: min, max or avg]" type = "string" default = "avg" } @@ -100,8 +100,8 @@ variable "cpu_message" { default = "" } -variable "cpu_aggregator" { - description = "Monitor aggregator for ES cluster cpu [available values: min, max, sum or avg]" +variable "cpu_time_aggregator" { + description = "Monitor aggregator for ES cluster cpu [available values: min, max or avg]" type = "string" default = "avg" } diff --git a/cloud/aws/elasticsearch/monitors-elasticsearch.tf b/cloud/aws/elasticsearch/monitors-elasticsearch.tf index 309e0a7..3f51e75 100644 --- a/cloud/aws/elasticsearch/monitors-elasticsearch.tf +++ b/cloud/aws/elasticsearch/monitors-elasticsearch.tf @@ -18,9 +18,9 @@ resource "datadog_monitor" "es_cluster_status" { type = "metric alert" query = <= 2 EOF @@ -52,8 +52,8 @@ resource "datadog_monitor" "es_free_space_low" { type = "metric alert" query = < ${var.cpu_threshold_critical} EOF diff --git a/cloud/aws/elb/README.md b/cloud/aws/elb/README.md index ab30a8b..f39031d 100644 --- a/cloud/aws/elb/README.md +++ b/cloud/aws/elb/README.md @@ -32,37 +32,33 @@ Inputs |------|-------------|:----:|:-----:|:-----:| | artificial_requests_count | Number of false requests used to mitigate false positive in case of low trafic | string | `5` | no | | delay | Delay in seconds for the metric evaluation | string | `900` | no | -| elb_4xx_aggregator | Monitor aggregator for ELB 4xx errors [available values: min, max, sum or avg] | string | `min` | no | | elb_4xx_message | Custom message for ELB 4xx errors monitor | string | `` | no | | elb_4xx_silenced | Groups to mute for ELB 4xx errors monitor | map | `` | no | | elb_4xx_threshold_critical | loadbalancer 4xx critical threshold in percentage | string | `10` | no | | elb_4xx_threshold_warning | loadbalancer 4xx warning threshold in percentage | string | `5` | no | | elb_4xx_timeframe | Monitor timeframe for ELB 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| elb_5xx_aggregator | Monitor aggregator for ELB 5xx errors [available values: min, max, sum or avg] | string | `min` | no | | elb_5xx_message | Custom message for ELB 5xx errors monitor | string | `` | no | | elb_5xx_silenced | Groups to mute for ELB 5xx errors monitor | map | `` | no | | elb_5xx_threshold_critical | loadbalancer 5xx critical threshold in percentage | string | `10` | no | | elb_5xx_threshold_warning | loadbalancer 5xx warning threshold in percentage | string | `5` | no | | elb_5xx_timeframe | Monitor timeframe for ELB 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| elb_backend_4xx_aggregator | Monitor aggregator for ELB backend 4xx errors [available values: min, max, sum or avg] | string | `min` | no | | elb_backend_4xx_message | Custom message for ELB backend 4xx errors monitor | string | `` | no | | elb_backend_4xx_silenced | Groups to mute for ELB backend 4xx errors monitor | map | `` | no | | elb_backend_4xx_threshold_critical | loadbalancer backend 4xx critical threshold in percentage | string | `10` | no | | elb_backend_4xx_threshold_warning | loadbalancer backend 4xx warning threshold in percentage | string | `5` | no | | elb_backend_4xx_timeframe | Monitor timeframe for ELB backend 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| elb_backend_5xx_aggregator | Monitor aggregator for ELB backend 5xx errors [available values: min, max, sum or avg] | string | `min` | no | | elb_backend_5xx_message | Custom message for ELB backend 5xx errors monitor | string | `` | no | | elb_backend_5xx_silenced | Groups to mute for ELB backend 5xx errors monitor | map | `` | no | | elb_backend_5xx_threshold_critical | loadbalancer backend 5xx critical threshold in percentage | string | `10` | no | | elb_backend_5xx_threshold_warning | loadbalancer backend 5xx warning threshold in percentage | string | `5` | no | | elb_backend_5xx_timeframe | Monitor timeframe for ELB backend 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| elb_backend_latency_aggregator | Monitor aggregator for ELB backend latency [available values: min, max, sum or avg] | string | `max` | no | +| elb_backend_latency_time_aggregator | Monitor aggregator for ELB backend latency [available values: min, max or avg] | string | `min` | no | | elb_backend_latency_critical | latency critical threshold in seconds | string | `5` | no | | elb_backend_latency_message | Custom message for ELB backend latency monitor | string | `` | no | | elb_backend_latency_silenced | Groups to mute for ELB backend latency monitor | map | `` | no | | elb_backend_latency_timeframe | Monitor timeframe for ELB backend latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | elb_backend_latency_warning | latency warning threshold in seconds | string | `1` | no | -| elb_no_healthy_instance_aggregator | Monitor aggregator for ELB no healty instance [available values: min, max, sum or avg] | string | `min` | no | +| elb_no_healthy_instance_time_aggregator | Monitor aggregator for ELB no healty instance [available values: min, max or avg] | string | `min` | no | | elb_no_healthy_instance_message | Custom message for ELB no healty instance monitor | string | `` | no | | elb_no_healthy_instance_silenced | Groups to mute for ELB no healty instance monitor | map | `` | no | | elb_no_healthy_instance_timeframe | Monitor timeframe for ELB no healty instance [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | diff --git a/cloud/aws/elb/inputs.tf b/cloud/aws/elb/inputs.tf index d311ca3..b0f2e80 100644 --- a/cloud/aws/elb/inputs.tf +++ b/cloud/aws/elb/inputs.tf @@ -37,8 +37,8 @@ variable "elb_no_healthy_instance_message" { default = "" } -variable "elb_no_healthy_instance_aggregator" { - description = "Monitor aggregator for ELB no healty instance [available values: min, max, sum or avg]" +variable "elb_no_healthy_instance_time_aggregator" { + description = "Monitor aggregator for ELB no healty instance [available values: min or max]" type = "string" default = "min" } @@ -61,12 +61,6 @@ variable "elb_4xx_message" { default = "" } -variable "elb_4xx_aggregator" { - description = "Monitor aggregator for ELB 4xx errors [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "elb_4xx_timeframe" { description = "Monitor timeframe for ELB 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -95,12 +89,6 @@ variable "elb_5xx_message" { default = "" } -variable "elb_5xx_aggregator" { - description = "Monitor aggregator for ELB 5xx errors [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "elb_5xx_timeframe" { description = "Monitor timeframe for ELB 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -129,12 +117,6 @@ variable "elb_backend_4xx_message" { default = "" } -variable "elb_backend_4xx_aggregator" { - description = "Monitor aggregator for ELB backend 4xx errors [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "elb_backend_4xx_timeframe" { description = "Monitor timeframe for ELB backend 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -163,12 +145,6 @@ variable "elb_backend_5xx_message" { default = "" } -variable "elb_backend_5xx_aggregator" { - description = "Monitor aggregator for ELB backend 5xx errors [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "elb_backend_5xx_timeframe" { description = "Monitor timeframe for ELB backend 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -197,8 +173,8 @@ variable "elb_backend_latency_message" { default = "" } -variable "elb_backend_latency_aggregator" { - description = "Monitor aggregator for ELB backend latency [available values: min, max, sum or avg]" +variable "elb_backend_latency_time_aggregator" { + description = "Monitor aggregator for ELB backend latency [available values: min, max or avg]" type = "string" default = "min" } diff --git a/cloud/aws/elb/monitors-elb.tf b/cloud/aws/elb/monitors-elb.tf index 1390137..ed92f6b 100644 --- a/cloud/aws/elb/monitors-elb.tf +++ b/cloud/aws/elb/monitors-elb.tf @@ -11,8 +11,8 @@ resource "datadog_monitor" "ELB_no_healthy_instances" { message = "${coalesce(var.elb_no_healthy_instance_message, var.message)}" query = < ${var.elb_4xx_threshold_critical} EOF @@ -73,10 +73,10 @@ resource "datadog_monitor" "ELB_too_much_5xx" { message = "${coalesce(var.elb_5xx_message, var.message)}" query = < ${var.elb_5xx_threshold_critical} EOF @@ -108,10 +108,10 @@ resource "datadog_monitor" "ELB_too_much_4xx_backend" { message = "${coalesce(var.elb_backend_4xx_message, var.message)}" query = < ${var.elb_backend_4xx_threshold_critical} EOF @@ -143,10 +143,10 @@ resource "datadog_monitor" "ELB_too_much_5xx_backend" { message = "${coalesce(var.elb_backend_5xx_message, var.message)}" query = < ${var.elb_backend_5xx_threshold_critical} EOF @@ -178,8 +178,8 @@ resource "datadog_monitor" "ELB_backend_latency" { message = "${coalesce(var.elb_backend_latency_message, var.message)}" query = < ${var.elb_backend_latency_critical} EOF diff --git a/cloud/aws/kinesis-firehose/monitors-kinesis-firehose.tf b/cloud/aws/kinesis-firehose/monitors-kinesis-firehose.tf index 1f1a71b..7d73d6d 100644 --- a/cloud/aws/kinesis-firehose/monitors-kinesis-firehose.tf +++ b/cloud/aws/kinesis-firehose/monitors-kinesis-firehose.tf @@ -14,10 +14,10 @@ resource "datadog_monitor" "firehose_incoming_records" { type = "metric alert" query = <` | no | | cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no | | cpu_threshold_warning | CPU usage in percent (warning threshold) | string | `80` | no | | cpu_timeframe | Monitor timeframe for RDS CPU usage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | | delay | Delay in seconds for the metric evaluation | string | `900` | no | -| diskspace_aggregator | Monitor aggregator for RDS free diskspace [available values: min, max, sum or avg] | string | `avg` | no | +| diskspace_time_aggregator | Monitor aggregator for RDS free diskspace [available values: min, max or avg] | string | `avg` | no | | diskspace_message | Custom message for RDS free diskspace monitor | string | `` | no | | diskspace_silenced | Groups to mute for RDS free diskspace monitor | map | `` | no | | diskspace_threshold_critical | Disk free space in percent (critical threshold) | string | `10` | no | diff --git a/cloud/aws/rds/inputs.tf b/cloud/aws/rds/inputs.tf index e54b16d..747a1a3 100644 --- a/cloud/aws/rds/inputs.tf +++ b/cloud/aws/rds/inputs.tf @@ -38,8 +38,8 @@ variable "cpu_message" { default = "" } -variable "cpu_aggregator" { - description = "Monitor aggregator for RDS CPU usage [available values: min, max, sum or avg]" +variable "cpu_time_aggregator" { + description = "Monitor aggregator for RDS CPU usage [available values: min, max or avg]" type = "string" default = "avg" } @@ -72,8 +72,8 @@ variable "diskspace_message" { default = "" } -variable "diskspace_aggregator" { - description = "Monitor aggregator for RDS free diskspace [available values: min, max, sum or avg]" +variable "diskspace_time_aggregator" { + description = "Monitor aggregator for RDS free diskspace [available values: min, max or avg]" type = "string" default = "avg" } diff --git a/cloud/aws/rds/monitors-rds.tf b/cloud/aws/rds/monitors-rds.tf index 6c452be..550a041 100644 --- a/cloud/aws/rds/monitors-rds.tf +++ b/cloud/aws/rds/monitors-rds.tf @@ -14,8 +14,8 @@ resource "datadog_monitor" "rds_cpu_90_15min" { type = "metric alert" query = < ${var.cpu_threshold_critical} EOF @@ -46,9 +46,9 @@ resource "datadog_monitor" "rds_free_space_low" { type = "metric alert" query = <` | no | | vpn_status_timeframe | Monitor timeframe for VPN status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | diff --git a/cloud/aws/vpn/inputs.tf b/cloud/aws/vpn/inputs.tf index a95f500..c1a0969 100644 --- a/cloud/aws/vpn/inputs.tf +++ b/cloud/aws/vpn/inputs.tf @@ -36,8 +36,8 @@ variable "vpn_status_message" { default = "" } -variable "vpn_status_aggregator" { - description = "Monitor aggregator for VPN status [available values: min, max, sum or avg]" +variable "vpn_status_time_aggregator" { + description = "Monitor aggregator for VPN status [available values: min, max or avg]" type = "string" default = "avg" } diff --git a/cloud/aws/vpn/monitors-vpn.tf b/cloud/aws/vpn/monitors-vpn.tf index 63c2a89..3327573 100644 --- a/cloud/aws/vpn/monitors-vpn.tf +++ b/cloud/aws/vpn/monitors-vpn.tf @@ -11,8 +11,8 @@ resource "datadog_monitor" "VPN_status" { message = "${coalesce(var.vpn_status_message, var.message)}" query = < Date: Wed, 23 May 2018 11:04:56 +0200 Subject: [PATCH 12/21] MON-191 - Space aggregator hard coded for Azure monitors --- cloud/azure/README.md | 77 ++---- cloud/azure/apimanagement/README.md | 6 +- cloud/azure/apimanagement/inputs.tf | 28 +- .../monitors-azure-apimanagement.tf | 26 +- cloud/azure/app-services/README.md | 7 +- cloud/azure/app-services/inputs.tf | 26 +- .../app-services/monitors-app_services.tf | 28 +- cloud/azure/eventhub/README.md | 4 +- cloud/azure/eventhub/inputs.tf | 16 +- cloud/azure/eventhub/monitors-eventhub.tf | 20 +- cloud/azure/inputs.tf | 246 ++++-------------- cloud/azure/iothubs/README.md | 16 +- cloud/azure/iothubs/inputs.tf | 76 +----- cloud/azure/iothubs/monitors-iothubs.tf | 114 ++++---- cloud/azure/monitors.tf | 81 +++--- cloud/azure/redis/README.md | 8 +- cloud/azure/redis/inputs.tf | 16 +- cloud/azure/redis/monitors-azure-redis.tf | 18 +- cloud/azure/servicebus/README.md | 2 +- cloud/azure/servicebus/inputs.tf | 4 +- .../azure/servicebus/monitors-service-bus.tf | 4 +- cloud/azure/sql-database/README.md | 7 +- cloud/azure/sql-database/inputs.tf | 18 +- .../monitors-sql-database-basics.tf | 14 +- cloud/azure/storage/README.md | 18 +- cloud/azure/storage/inputs.tf | 36 +-- cloud/azure/storage/monitors-azure-storage.tf | 36 +-- cloud/azure/stream-analytics/README.md | 9 +- cloud/azure/stream-analytics/inputs.tf | 22 +- .../monitors-stream-analytics.tf | 22 +- 30 files changed, 335 insertions(+), 670 deletions(-) diff --git a/cloud/azure/README.md b/cloud/azure/README.md index 55ddb36..253c4ec 100644 --- a/cloud/azure/README.md +++ b/cloud/azure/README.md @@ -32,294 +32,271 @@ Inputs | Name | Description | Type | Default | Required | |------|-------------|:----:|:-----:|:-----:| -| apimanagement_failed_requests_aggregator | Monitor aggregator for API Management failed requests [available values: min, max, sum or avg] | string | `sum` | no | | apimanagement_failed_requests_message | Custom message for API Management failed requests monitor | string | `` | no | | apimanagement_failed_requests_silenced | Groups to mute for API Management failed requests monitor | map | `` | no | | apimanagement_failed_requests_threshold_critical | Maximum acceptable percent of failed requests | string | `90` | no | | apimanagement_failed_requests_threshold_warning | Warning regarding acceptable percent of failed requests | string | `50` | no | | apimanagement_failed_requests_timeframe | Monitor timeframe for API Management failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| apimanagement_other_requests_aggregator | Monitor aggregator for API Management other requests [available values: min, max, sum or avg] | string | `sum` | no | | apimanagement_other_requests_message | Custom message for API Management other requests monitor | string | `` | no | | apimanagement_other_requests_silenced | Groups to mute for API Management other requests monitor | map | `` | no | | apimanagement_other_requests_threshold_critical | Maximum acceptable percent of other requests | string | `90` | no | | apimanagement_other_requests_threshold_warning | Warning regarding acceptable percent of other requests | string | `50` | no | | apimanagement_other_requests_timeframe | Monitor timeframe for API Management other requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| apimanagement_status_aggregator | Monitor aggregator for API Management status [available values: min, max, sum or avg] | string | `avg` | no | | apimanagement_status_message | Custom message for API Management status monitor | string | `` | no | | apimanagement_status_silenced | Groups to mute for API Management status monitor | map | `` | no | +| apimanagement_status_time_aggregator | Monitor aggregator for API Management status [available values: min, max or avg] | string | `avg` | no | | apimanagement_status_timeframe | Monitor timeframe for API Management status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| apimanagement_successful_requests_aggregator | Monitor aggregator for API Management successful requests [available values: min, max, sum or avg] | string | `sum` | no | | apimanagement_successful_requests_message | Custom message for API Management successful requests monitor | string | `` | no | | apimanagement_successful_requests_silenced | Groups to mute for API Management successful requests monitor | map | `` | no | | apimanagement_successful_requests_threshold_critical | Minimum acceptable percent of successful requests | string | `10` | no | | apimanagement_successful_requests_threshold_warning | Warning regarding acceptable percent of successful requests | string | `30` | no | | apimanagement_successful_requests_timeframe | Monitor timeframe for API Management successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| apimanagement_unauthorized_requests_aggregator | Monitor aggregator for API Management unauthorized requests [available values: min, max, sum or avg] | string | `sum` | no | | apimanagement_unauthorized_requests_message | Custom message for API Management unauthorized requests monitor | string | `` | no | | apimanagement_unauthorized_requests_silenced | Groups to mute for API Management unauthorized requests monitor | map | `` | no | | apimanagement_unauthorized_requests_threshold_critical | Maximum acceptable percent of unauthorized requests | string | `90` | no | | apimanagement_unauthorized_requests_threshold_warning | Warning regarding acceptable percent of unauthorized requests | string | `50` | no | | apimanagement_unauthorized_requests_timeframe | Monitor timeframe for API Management unauthorized requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| appservices_http_4xx_requests_aggregator | Monitor aggregator for App Services 4xx requests [available values: min, max, sum or avg] | string | `sum` | no | | appservices_http_4xx_requests_message | Custom message for App Services 4xx requests monitor | string | `` | no | | appservices_http_4xx_requests_silenced | Groups to mute for App Services 4xx requests monitor | map | `` | no | | appservices_http_4xx_requests_threshold_critical | Maximum critical acceptable percent of 4xx errors | string | `90` | no | | appservices_http_4xx_requests_threshold_warning | Warning regarding acceptable percent of 4xx errors | string | `50` | no | | appservices_http_4xx_requests_timeframe | Monitor timeframe for App Services 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| appservices_http_5xx_requests_aggregator | Monitor aggregator for App Services 5xx requests [available values: min, max, sum or avg] | string | `sum` | no | | appservices_http_5xx_requests_message | Custom message for App Services 5xx requests monitor | string | `` | no | | appservices_http_5xx_requests_silenced | Groups to mute for App Services 5xx requests monitor | map | `` | no | | appservices_http_5xx_requests_threshold_critical | Maximum critical acceptable percent of 5xx errors | string | `90` | no | | appservices_http_5xx_requests_threshold_warning | Warning regarding acceptable percent of 5xx errors | string | `50` | no | | appservices_http_5xx_requests_timeframe | Monitor timeframe for App Services 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| appservices_http_successful_requests_aggregator | Monitor aggregator for App Services successful requests [available values: min, max, sum or avg] | string | `sum` | no | | appservices_http_successful_requests_message | Custom message for App Services successful requests monitor | string | `` | no | | appservices_http_successful_requests_silenced | Groups to mute for App Services successful requests monitor | map | `` | no | | appservices_http_successful_requests_threshold_critical | Minimum critical acceptable percent of 2xx & 3xx requests | string | `10` | no | | appservices_http_successful_requests_threshold_warning | Warning regarding acceptable percent of 2xx & 3xx requests | string | `30` | no | | appservices_http_successful_requests_timeframe | Monitor timeframe for App Services successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| appservices_memory_usage_aggregator | Monitor aggregator for App Services memory usage [available values: min, max, sum or avg] | string | `avg` | no | | appservices_memory_usage_message | Custom message for App Services memory usage monitor | string | `` | no | | appservices_memory_usage_silenced | Groups to mute for App Services memory usage monitor | map | `` | no | | appservices_memory_usage_threshold_critical | Alerting threshold in Mib | string | `1073741824` | no | | appservices_memory_usage_threshold_warning | Warning threshold in MiB | string | `536870912` | no | +| appservices_memory_usage_time_aggregator | Monitor aggregator for App Services memory usage [available values: min, max or avg] | string | `avg` | no | | appservices_memory_usage_timeframe | Monitor timeframe for App Services memory usage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| appservices_response_time_aggregator | Monitor aggregator for App Services response time [available values: min, max, sum or avg] | string | `min` | no | | appservices_response_time_message | Custom message for App Services response time monitor | string | `` | no | | appservices_response_time_silenced | Groups to mute for App Services response time monitor | map | `` | no | | appservices_response_time_threshold_critical | Alerting threshold for response time in seconds | string | `10` | no | | appservices_response_time_threshold_warning | Warning threshold for response time in seconds | string | `5` | no | +| appservices_response_time_time_aggregator | Monitor aggregator for App Services response time [available values: min, max or avg] | string | `min` | no | | appservices_response_time_timeframe | Monitor timeframe for App Services response time [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | delay | Delay in seconds for the metric evaluation | string | `900` | no | | environment | Architecture environment | string | - | yes | -| eventhub_errors_rate_aggregator | Monitor aggregator for Event Hub errors [available values: min, max, sum or avg] | string | `sum` | no | | eventhub_errors_rate_message | Custom message for Event Hub errors monitor | string | `` | no | | eventhub_errors_rate_silenced | Groups to mute for Event Hub errors monitor | map | `` | no | | eventhub_errors_rate_thresold_critical | Errors ratio (percentage) to trigger the critical alert | string | `90` | no | | eventhub_errors_rate_thresold_warning | Errors ratio (percentage) to trigger a warning alert | string | `50` | no | | eventhub_errors_rate_timeframe | Monitor timeframe for Event Hub errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| eventhub_failed_requests_rate_aggregator | Monitor aggregator for Event Hub failed requests [available values: min, max, sum or avg] | string | `sum` | no | | eventhub_failed_requests_rate_message | Custom message for Event Hub failed requests monitor | string | `` | no | | eventhub_failed_requests_rate_silenced | Groups to mute for Event Hub failed requests monitor | map | `` | no | | eventhub_failed_requests_rate_thresold_critical | Failed requests ratio (percentage) to trigger the critical alert | string | `90` | no | | eventhub_failed_requests_rate_thresold_warning | Failed requests ratio (percentage) to trigger a warning alert | string | `50` | no | | eventhub_failed_requests_rate_timeframe | Monitor timeframe for Event Hub failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| eventhub_status_aggregator | Monitor aggregator for Event Hub status [available values: min, max, sum or avg] | string | `avg` | no | | eventhub_status_message | Custom message for Event Hub status monitor | string | `` | no | | eventhub_status_silenced | Groups to mute for Event Hub status monitor | map | `` | no | +| eventhub_status_time_aggregator | Monitor aggregator for Event Hub status [available values: min, max or avg] | string | `avg` | no | | eventhub_status_timeframe | Monitor timeframe for Event Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | -| iothub_dropped_d2c_telemetry_egress_aggregator | Monitor aggregator for IoT Hub failed d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no | | iothub_dropped_d2c_telemetry_egress_message | Custom message for IoT Hub dropped d2c telemetry monitor | string | `` | no | | iothub_dropped_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Dropped limit (critical threshold) | string | `90` | no | | iothub_dropped_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Dropped limit (warning threshold) | string | `50` | no | | iothub_dropped_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub dropped d2c telemetry monitor | map | `` | no | | iothub_dropped_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub dropped d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| iothub_failed_c2d_methods_rate_aggregator | Monitor aggregator for IoT Hub failed c2d method [available values: min, max, sum or avg] | string | `sum` | no | | iothub_failed_c2d_methods_rate_message | Custom message for IoT Hub failed c2d method monitor | string | `` | no | | iothub_failed_c2d_methods_rate_silenced | Groups to mute for IoT Hub failed c2d methods monitor | map | `` | no | | iothub_failed_c2d_methods_rate_threshold_critical | C2D Methods Failed rate limit (critical threshold) | string | `90` | no | | iothub_failed_c2d_methods_rate_threshold_warning | C2D Methods Failed rate limit (warning threshold) | string | `50` | no | | iothub_failed_c2d_methods_rate_timeframe | Monitor timeframe for IoT Hub failed c2d method [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| iothub_failed_c2d_twin_read_rate_aggregator | Monitor aggregator for IoT Hub failed c2d twin read [available values: min, max, sum or avg] | string | `sum` | no | | iothub_failed_c2d_twin_read_rate_message | Custom message for IoT Hub failed c2d twin read monitor | string | `` | no | | iothub_failed_c2d_twin_read_rate_silenced | Groups to mute for IoT Hub failed c2d twin read monitor | map | `` | no | | iothub_failed_c2d_twin_read_rate_threshold_critical | C2D Twin Read Failed rate limit (critical threshold) | string | `90` | no | | iothub_failed_c2d_twin_read_rate_threshold_warning | C2D Twin Read Failed rate limit (warning threshold) | string | `50` | no | | iothub_failed_c2d_twin_read_rate_timeframe | Monitor timeframe for IoT Hub failed c2d twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| iothub_failed_c2d_twin_update_rate_aggregator | Monitor aggregator for IoT Hub failed c2d twin update [available values: min, max, sum or avg] | string | `sum` | no | | iothub_failed_c2d_twin_update_rate_message | Custom message for IoT Hub failed c2d twin update monitor | string | `` | no | | iothub_failed_c2d_twin_update_rate_silenced | Groups to mute for IoT Hub failed c2d twin update monitor | map | `` | no | | iothub_failed_c2d_twin_update_rate_threshold_critical | C2D Twin Update Failed rate limit (critical threshold) | string | `90` | no | | iothub_failed_c2d_twin_update_rate_threshold_warning | C2D Twin Update Failed rate limit (warning threshold) | string | `50` | no | | iothub_failed_c2d_twin_update_rate_timeframe | Monitor timeframe for IoT Hub failed c2d twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| iothub_failed_d2c_twin_read_rate_aggregator | Monitor aggregator for IoT Hub failed d2c twin read [available values: min, max, sum or avg] | string | `sum` | no | | iothub_failed_d2c_twin_read_rate_message | Custom message for IoT Hub failed d2c twin read monitor | string | `` | no | | iothub_failed_d2c_twin_read_rate_silenced | Groups to mute for IoT Hub failed d2c twin read monitor | map | `` | no | | iothub_failed_d2c_twin_read_rate_threshold_critical | D2C Twin Read Failed rate limit (critical threshold) | string | `90` | no | | iothub_failed_d2c_twin_read_rate_threshold_warning | D2C Twin Read Failed rate limit (warning threshold) | string | `50` | no | | iothub_failed_d2c_twin_read_rate_timeframe | Monitor timeframe for IoT Hub failed d2c twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| iothub_failed_d2c_twin_update_rate_aggregator | Monitor aggregator for IoT Hub failed d2c twin update [available values: min, max, sum or avg] | string | `sum` | no | | iothub_failed_d2c_twin_update_rate_message | Custom message for IoT Hub failed d2c twin update monitor | string | `` | no | | iothub_failed_d2c_twin_update_rate_silenced | Groups to mute for IoT Hub failed d2c twin update monitor | map | `` | no | | iothub_failed_d2c_twin_update_rate_threshold_critical | D2C Twin Update Failed rate limit (critical threshold) | string | `90` | no | | iothub_failed_d2c_twin_update_rate_threshold_warning | D2C Twin Update Failed rate limit (warning threshold) | string | `50` | no | | iothub_failed_d2c_twin_update_rate_timeframe | Monitor timeframe for IoT Hub failed d2c twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| iothub_failed_jobs_rate_aggregator | Monitor aggregator for IoT Hub failed jobs [available values: min, max, sum or avg] | string | `sum` | no | | iothub_failed_jobs_rate_message | Custom message for IoT Hub failed jobs monitor | string | `` | no | | iothub_failed_jobs_rate_silenced | Groups to mute for IoT Hub failed jobs monitor | map | `` | no | | iothub_failed_jobs_rate_threshold_critical | Jobs Failed rate limit (critical threshold) | string | `90` | no | | iothub_failed_jobs_rate_threshold_warning | Jobs Failed rate limit (warning threshold) | string | `50` | no | | iothub_failed_jobs_rate_timeframe | Monitor timeframe for IoT Hub failed jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| iothub_failed_listjobs_rate_aggregator | Monitor aggregator for IoT Hub failed listjobs jobs [available values: min, max, sum or avg] | string | `sum` | no | | iothub_failed_listjobs_rate_message | Custom message for IoT Hub failed list jobs monitor | string | `` | no | | iothub_failed_listjobs_rate_silenced | Groups to mute for IoT Hub failed list jobs monitor | map | `` | no | | iothub_failed_listjobs_rate_threshold_critical | ListJobs Failed rate limit (critical threshold) | string | `90` | no | | iothub_failed_listjobs_rate_threshold_warning | ListJobs Failed rate limit (warning threshold) | string | `50` | no | | iothub_failed_listjobs_rate_timeframe | Monitor timeframe for IoT Hub failed list jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| iothub_failed_queryjobs_rate_aggregator | Monitor aggregator for IoT Hub failed query jobs [available values: min, max, sum or avg] | string | `sum` | no | | iothub_failed_queryjobs_rate_message | Custom message for IoT Hub failed query jobs monitor | string | `` | no | | iothub_failed_queryjobs_rate_silenced | Groups to mute for IoT Hub failed query jobs monitor | map | `` | no | | iothub_failed_queryjobs_rate_threshold_critical | QueryJobs Failed rate limit (critical threshold) | string | `90` | no | | iothub_failed_queryjobs_rate_threshold_warning | QueryJobs Failed rate limit (warning threshold) | string | `50` | no | | iothub_failed_queryjobs_rate_timeframe | Monitor timeframe for IoT Hub failed query jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| iothub_invalid_d2c_telemetry_egress_aggregator | Monitor aggregator for IoT Hub invalid d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no | | iothub_invalid_d2c_telemetry_egress_message | Custom message for IoT Hub invalid d2c telemetry monitor | string | `` | no | | iothub_invalid_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Invalid limit (critical threshold) | string | `90` | no | | iothub_invalid_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Invalid limit (warning threshold) | string | `50` | no | | iothub_invalid_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub invalid d2c telemetry monitor | map | `` | no | | iothub_invalid_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub invalid d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| iothub_orphaned_d2c_telemetry_egress_aggregator | Monitor aggregator for IoT Hub orphaned d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no | | iothub_orphaned_d2c_telemetry_egress_message | Custom message for IoT Hub orphaned d2c telemetry monitor | string | `` | no | | iothub_orphaned_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Orphaned limit (critical threshold) | string | `90` | no | | iothub_orphaned_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Orphaned limit (warning threshold) | string | `50` | no | | iothub_orphaned_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub orphaned d2c telemetry monitor | map | `` | no | | iothub_orphaned_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub orphaned d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| iothub_status_aggregator | Monitor aggregator for IoT Hub status [available values: min, max, sum or avg] | string | `avg` | no | | iothub_status_message | Custom message for IoT Hub status monitor | string | `` | no | | iothub_status_silenced | Groups to mute for IoT Hub status monitor | map | `` | no | +| iothub_status_time_aggregator | Monitor aggregator for IoT Hub status [available values: min, max or avg] | string | `avg` | no | | iothub_status_timeframe | Monitor timeframe for IoT Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| iothub_too_many_d2c_telemetry_ingress_nosent_aggregator | Monitor aggregator for IoT Hub unsent d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no | | iothub_too_many_d2c_telemetry_ingress_nosent_message | Custom message for IoT Hub unsent d2c telemetry monitor | string | `` | no | | iothub_too_many_d2c_telemetry_ingress_nosent_silenced | Groups to mute for IoT Hub unsent d2c telemetry monitor | map | `` | no | | iothub_too_many_d2c_telemetry_ingress_nosent_timeframe | Monitor timeframe for IoT Hub unsent d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| iothub_total_devices_aggregator | Monitor aggregator for IoT Hub total devices [available values: min, max, sum or avg] | string | `avg` | no | | iothub_total_devices_message | Custom message for IoT Hub total devices monitor | string | `` | no | | iothub_total_devices_silenced | Groups to mute for IoT Hub total devices monitor | map | `` | no | +| iothub_total_devices_time_aggregator | Monitor aggregator for IoT Hub total devices [available values: min, max or avg] | string | `avg` | no | | iothub_total_devices_timeframe | Monitor timeframe for IoT Hub total devices [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | message | Message sent when a monitor is triggered | string | - | yes | | non_taggable_filter_tags | Tags used for filtering for components without tag support | string | `*` | no | -| redis_evictedkeys_limit_aggregator | Monitor aggregator for Redis evicted keys [available values: min, max, sum or avg] | string | `avg` | no | | redis_evictedkeys_limit_message | Custom message for Redis evicted keys monitor | string | `` | no | | redis_evictedkeys_limit_silenced | Groups to mute for Redis evicted keys monitor | map | `` | no | | redis_evictedkeys_limit_threshold_critical | Evicted keys limit (critical threshold) | string | `100` | no | | redis_evictedkeys_limit_threshold_warning | Evicted keys limit (warning threshold) | string | `0` | no | +| redis_evictedkeys_limit_time_aggregator | Monitor aggregator for Redis evicted keys [available values: min, max or avg] | string | `avg` | no | | redis_evictedkeys_limit_timeframe | Monitor timeframe for Redis evicted keys [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| redis_percent_processor_time_aggregator | Monitor aggregator for Redis processor [available values: min, max, sum or avg] | string | `avg` | no | | redis_percent_processor_time_message | Custom message for Redis processor monitor | string | `` | no | | redis_percent_processor_time_silenced | Groups to mute for Redis processor monitor | map | `` | no | | redis_percent_processor_time_threshold_critical | Processor time percent (critical threshold) | string | `80` | no | | redis_percent_processor_time_threshold_warning | Processor time percent (warning threshold) | string | `60` | no | +| redis_percent_processor_time_time_aggregator | Monitor aggregator for Redis processor [available values: min, max or avg] | string | `avg` | no | | redis_percent_processor_time_timeframe | Monitor timeframe for Redis processor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| redis_server_load_rate_aggregator | Monitor aggregator for Redis server load [available values: min, max, sum or avg] | string | `avg` | no | | redis_server_load_rate_message | Custom message for Redis server load monitor | string | `` | no | | redis_server_load_rate_silenced | Groups to mute for Redis server load monitor | map | `` | no | | redis_server_load_rate_threshold_critical | Server CPU load rate (critical threshold) | string | `90` | no | | redis_server_load_rate_threshold_warning | Server CPU load rate (warning threshold) | string | `70` | no | +| redis_server_load_rate_time_aggregator | Monitor aggregator for Redis server load [available values: min, max or avg] | string | `avg` | no | | redis_server_load_rate_timeframe | Monitor timeframe for Redis server load [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| redis_status_aggregator | Monitor aggregator for Redis status [available values: min, max, sum or avg] | string | `avg` | no | | redis_status_message | Custom message for Redis status monitor | string | `` | no | | redis_status_silenced | Groups to mute for Redis status monitor | map | `` | no | +| redis_status_time_aggregator | Monitor aggregator for Redis status [available values: min, max or avg] | string | `avg` | no | | redis_status_timeframe | Monitor timeframe for Redis status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| servicebus_status_aggregator | Monitor timeframe aggregator for Service Bus status [available values: min, max, sum or avg] | string | `min` | no | | servicebus_status_message | Custom message for Service Bus status monitor | string | `` | no | | servicebus_status_silenced | Groups to mute for Service Bus status monitor | map | `` | no | +| servicebus_status_time_aggregator | Monitor aggregator for Service Bus status [available values: min, max or avg] | string | `min` | no | | servicebus_status_timeframe | Monitor timeframe for Service Bus status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | -| sqldatabase_cpu_aggregator | Monitor aggregator for SQL CPU [available values: min, max, sum or avg] | string | `avg` | no | | sqldatabase_cpu_message | Custom message for SQL CPU monitor | string | `` | no | | sqldatabase_cpu_silenced | Groups to mute for SQL CPU monitor | map | `` | no | | sqldatabase_cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no | | sqldatabase_cpu_threshold_warning | CPU usage in percent (warning threshold) | string | `80` | no | +| sqldatabase_cpu_time_aggregator | Monitor aggregator for SQL CPU [available values: min, max or avg] | string | `avg` | no | | sqldatabase_cpu_timeframe | Monitor timeframe for SQL CPU [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | -| sqldatabase_deadlock_aggregator | Monitor aggregator for SQL Deadlock [available values: min, max, sum or avg] | string | `sum` | no | | sqldatabase_deadlock_message | Custom message for SQL Deadlock monitor | string | `` | no | | sqldatabase_deadlock_silenced | Groups to mute for SQL Deadlock monitor | map | `` | no | | sqldatabase_deadlock_threshold_critical | Amount of Deadlocks (critical threshold) | string | `1` | no | | sqldatabase_deadlock_timeframe | Monitor timeframe for SQL Deadlock [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| sqldatabase_diskspace_aggregator | Monitor aggregator for SQL disk space [available values: min, max, sum or avg] | string | `avg` | no | | sqldatabase_diskspace_message | Custom message for SQL disk space monitor | string | `` | no | | sqldatabase_diskspace_silenced | Groups to mute for SQL disk space monitor | map | `` | no | | sqldatabase_diskspace_threshold_critical | Disk space used in percent (critical threshold) | string | `90` | no | | sqldatabase_diskspace_threshold_warning | Disk space used in percent (warning threshold) | string | `80` | no | +| sqldatabase_diskspace_time_aggregator | Monitor aggregator for SQL disk space [available values: min, max or avg] | string | `avg` | no | | sqldatabase_diskspace_timeframe | Monitor timeframe for SQL disk space [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | -| sqldatabase_dtu_aggregator | Monitor aggregator for SQL DTU [available values: min, max, sum or avg] | string | `avg` | no | | sqldatabase_dtu_message | Custom message for SQL DTU monitor | string | `` | no | | sqldatabase_dtu_silenced | Groups to mute for SQL DTU monitor | map | `` | no | | sqldatabase_dtu_threshold_critical | Amount of DTU used (critical threshold) | string | `90` | no | | sqldatabase_dtu_threshold_warning | Amount of DTU used (warning threshold) | string | `85` | no | +| sqldatabase_dtu_time_aggregator | Monitor aggregator for SQL DTU [available values: min, max or avg] | string | `avg` | no | | sqldatabase_dtu_timeframe | Monitor timeframe for SQL DTU [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | -| storage_authorization_error_requests_aggregator | Monitor aggregator for Storage authorization errors [available values: min, max, sum or avg] | string | `avg` | no | | storage_authorization_error_requests_message | Custom message for Storage authorization errors monitor | string | `` | no | | storage_authorization_error_requests_silenced | Groups to mute for Storage authorization errors monitor | map | `` | no | | storage_authorization_error_requests_threshold_critical | Maximum acceptable percent of authorization error requests for a storage | string | `90` | no | | storage_authorization_error_requests_threshold_warning | Warning regarding acceptable percent of authorization error requests for a storage | string | `50` | no | +| storage_authorization_error_requests_time_aggregator | Monitor aggregator for Storage authorization errors [available values: min, max or avg] | string | `avg` | no | | storage_authorization_error_requests_timeframe | Monitor timeframe for Storage authorization errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| storage_availability_aggregator | Monitor aggregator for Storage availability [available values: min, max, sum or avg] | string | `avg` | no | | storage_availability_message | Custom message for Storage availability monitor | string | `` | no | | storage_availability_silenced | Groups to mute for Storage availability monitor | map | `` | no | | storage_availability_threshold_critical | Minimum acceptable percent of availability for a storage | string | `50` | no | | storage_availability_threshold_warning | Warning regarding acceptable percent of availability for a storage | string | `90` | no | +| storage_availability_time_aggregator | Monitor aggregator for Storage availability [available values: min, max or avg] | string | `avg` | no | | storage_availability_timeframe | Monitor timeframe for Storage availability [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| storage_client_other_error_requests_aggregator | Monitor aggregator for Storage other errors [available values: min, max, sum or avg] | string | `avg` | no | | storage_client_other_error_requests_message | Custom message for Storage other errors monitor | string | `` | no | | storage_client_other_error_requests_silenced | Groups to mute for Storage other errors monitor | map | `` | no | | storage_client_other_error_requests_threshold_critical | Maximum acceptable percent of client other error requests for a storage | string | `90` | no | | storage_client_other_error_requests_threshold_warning | Warning regarding acceptable percent of client other error requests for a storage | string | `50` | no | +| storage_client_other_error_requests_time_aggregator | Monitor aggregator for Storage other errors [available values: min, max or avg] | string | `avg` | no | | storage_client_other_error_requests_timeframe | Monitor timeframe for Storage other errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| storage_latency_aggregator | Monitor aggregator for Storage latency [available values: min, max, sum or avg] | string | `min` | no | | storage_latency_message | Custom message for Storage latency monitor | string | `` | no | | storage_latency_silenced | Groups to mute for Storage latency monitor | map | `` | no | | storage_latency_threshold_critical | Maximum acceptable end to end latency (ms) for a storage | string | `2000` | no | | storage_latency_threshold_warning | Warning regarding acceptable end to end latency (ms) for a storage | string | `1000` | no | +| storage_latency_time_aggregator | Monitor aggregator for Storage latency [available values: min, max or avg] | string | `min` | no | | storage_latency_timeframe | Monitor timeframe for Storage latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| storage_network_error_requests_aggregator | Monitor aggregator for Storage network errors [available values: min, max, sum or avg] | string | `avg` | no | | storage_network_error_requests_message | Custom message for Storage network errors monitor | string | `` | no | | storage_network_error_requests_silenced | Groups to mute for Storage network errors monitor | map | `` | no | | storage_network_error_requests_threshold_critical | Maximum acceptable percent of network error requests for a storage | string | `90` | no | | storage_network_error_requests_threshold_warning | Warning regarding acceptable percent of network error requests for a storage | string | `50` | no | +| storage_network_error_requests_time_aggregator | Monitor aggregator for Storage network errors [available values: min, max or avg] | string | `avg` | no | | storage_network_error_requests_timeframe | Monitor timeframe for Storage network errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| storage_server_other_error_requests_aggregator | Monitor aggregator for Storage other errors [available values: min, max, sum or avg] | string | `avg` | no | | storage_server_other_error_requests_message | Custom message for Storage server other errors monitor | string | `` | no | | storage_server_other_error_requests_silenced | Groups to mute for Storage server other errors monitor | map | `` | no | | storage_server_other_error_requests_threshold_critical | Maximum acceptable percent of server other error requests for a storage | string | `90` | no | | storage_server_other_error_requests_threshold_warning | Warning regarding acceptable percent of server other error requests for a storage | string | `50` | no | +| storage_server_other_error_requests_time_aggregator | Monitor aggregator for Storage other errors [available values: min, max or avg] | string | `avg` | no | | storage_server_other_error_requests_timeframe | Monitor timeframe for Storage server other errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| storage_successful_requests_aggregator | Monitor aggregator for Storage sucessful requests [available values: min, max, sum or avg] | string | `avg` | no | | storage_successful_requests_message | Custom message for Storage sucessful requests monitor | string | `` | no | | storage_successful_requests_silenced | Groups to mute for Storage sucessful requests monitor | map | `` | no | | storage_successful_requests_threshold_critical | Minimum acceptable percent of successful requests for a storage | string | `10` | no | | storage_successful_requests_threshold_warning | Warning regarding acceptable percent of successful requests for a storage | string | `30` | no | +| storage_successful_requests_time_aggregator | Monitor aggregator for Storage sucessful requests [available values: min, max or avg] | string | `avg` | no | | storage_successful_requests_timeframe | Monitor timeframe for Storage sucessful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| storage_throttling_error_requests_aggregator | Monitor aggregator for Storage throttling errors [available values: min, max, sum or avg] | string | `avg` | no | | storage_throttling_error_requests_message | Custom message for Storage throttling error monitor | string | `` | no | | storage_throttling_error_requests_silenced | Groups to mute for Storage throttling error monitor | map | `` | no | | storage_throttling_error_requests_threshold_critical | Maximum acceptable percent of throttling error requests for a storage | string | `90` | no | | storage_throttling_error_requests_threshold_warning | Warning regarding acceptable percent of throttling error requests for a storage | string | `50` | no | +| storage_throttling_error_requests_time_aggregator | Monitor aggregator for Storage throttling errors [available values: min, max or avg] | string | `avg` | no | | storage_throttling_error_requests_timeframe | Monitor timeframe for Storage throttling errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| storage_timeout_error_requests_aggregator | Monitor aggregator for Storage timeout [available values: min, max, sum or avg] | string | `avg` | no | | storage_timeout_error_requests_message | Custom message for Storage timeout monitor | string | `` | no | | storage_timeout_error_requests_silenced | Groups to mute for Storage timeout monitor | map | `` | no | | storage_timeout_error_requests_threshold_critical | Maximum acceptable percent of timeout error requests for a storage | string | `90` | no | | storage_timeout_error_requests_threshold_warning | Warning regarding acceptable percent of timeout error requests for a storage | string | `50` | no | +| storage_timeout_error_requests_time_aggregator | Monitor aggregator for Storage timeout [available values: min, max or avg] | string | `avg` | no | | storage_timeout_error_requests_timeframe | Monitor timeframe for Storage timeout [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| streamanalytics_conversion_errors_aggregator | Monitor aggregator for Stream Analytics conversion errors [available values: min, max, sum or avg] | string | `avg` | no | | streamanalytics_conversion_errors_message | Custom message for Stream Analytics conversion errors monitor | string | `` | no | | streamanalytics_conversion_errors_silenced | Groups to mute for Stream Analytics conversion errors monitor | map | `` | no | | streamanalytics_conversion_errors_threshold_critical | Conversion errors limit (critical threshold) | string | `10` | no | | streamanalytics_conversion_errors_threshold_warning | Conversion errors limit (warning threshold) | string | `0` | no | +| streamanalytics_conversion_errors_time_aggregator | Monitor aggregator for Stream Analytics conversion errors [available values: min, max or avg] | string | `avg` | no | | streamanalytics_conversion_errors_timeframe | Monitor timeframe for Stream Analytics conversion errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| streamanalytics_failed_function_requests_aggregator | Monitor aggregator for Stream Analytics failed requests [available values: min, max, sum or avg] | string | `sum` | no | | streamanalytics_failed_function_requests_message | Custom message for Stream Analytics failed requests monitor | string | `` | no | | streamanalytics_failed_function_requests_silenced | Groups to mute for Stream Analytics failed requests monitor | map | `` | no | | streamanalytics_failed_function_requests_threshold_critical | Failed Function Request rate limit (critical threshold) | string | `10` | no | | streamanalytics_failed_function_requests_threshold_warning | Failed Function Request rate limit (warning threshold) | string | `0` | no | | streamanalytics_failed_function_requests_timeframe | Monitor timeframe for Stream Analytics failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| streamanalytics_runtime_errors_aggregator | Monitor aggregator for Stream Analytics runtime errors [available values: min, max, sum or avg] | string | `avg` | no | | streamanalytics_runtime_errors_message | Custom message for Stream Analytics runtime errors monitor | string | `` | no | | streamanalytics_runtime_errors_silenced | Groups to mute for Stream Analytics runtime errors monitor | map | `` | no | | streamanalytics_runtime_errors_threshold_critical | Runtime errors limit (critical threshold) | string | `10` | no | | streamanalytics_runtime_errors_threshold_warning | Runtime errors limit (warning threshold) | string | `0` | no | +| streamanalytics_runtime_errors_time_aggregator | Monitor aggregator for Stream Analytics runtime errors [available values: min, max or avg] | string | `avg` | no | | streamanalytics_runtime_errors_timeframe | Monitor timeframe for Stream Analytics runtime errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| streamanalytics_status_aggregator | Monitor aggregator for Stream Analytics status [available values: min, max, sum or avg] | string | `avg` | no | | streamanalytics_status_message | Custom message for Stream Analytics status monitor | string | `` | no | | streamanalytics_status_silenced | Groups to mute for Stream Analytics status monitor | map | `` | no | +| streamanalytics_status_time_aggregator | Monitor aggregator for Stream Analytics status [available values: min, max or avg] | string | `avg` | no | | streamanalytics_status_timeframe | Monitor timeframe for Stream Analytics status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| streamanalytics_su_utilization_aggregator | Monitor aggregator for Stream Analytics utilization [available values: min, max, sum or avg] | string | `avg` | no | | streamanalytics_su_utilization_message | Custom message for Stream Analytics utilization monitor | string | `` | no | | streamanalytics_su_utilization_silenced | Groups to mute for Stream Analytics utilization monitor | map | `` | no | | streamanalytics_su_utilization_threshold_critical | Streaming Unit utilization rate limit (critical threshold) | string | `80` | no | | streamanalytics_su_utilization_threshold_warning | Streaming Unit utilization rate limit (warning threshold) | string | `60` | no | +| streamanalytics_su_utilization_time_aggregator | Monitor aggregator for Stream Analytics utilization [available values: min, max or avg] | string | `avg` | no | | streamanalytics_su_utilization_timeframe | Monitor timeframe for Stream Analytics utilization [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | Related documentation diff --git a/cloud/azure/apimanagement/README.md b/cloud/azure/apimanagement/README.md index 1b33552..fe75301 100644 --- a/cloud/azure/apimanagement/README.md +++ b/cloud/azure/apimanagement/README.md @@ -29,7 +29,6 @@ Inputs |------|-------------|:----:|:-----:|:-----:| | delay | Delay in seconds for the metric evaluation | string | `900` | no | | environment | Architecture environment | string | - | yes | -| failed_requests_aggregator | Monitor aggregator for API Management failed requests [available values: min, max, sum or avg] | string | `sum` | no | | failed_requests_message | Custom message for API Management failed requests monitor | string | `` | no | | failed_requests_silenced | Groups to mute for API Management failed requests monitor | map | `` | no | | failed_requests_threshold_critical | Maximum acceptable percent of failed requests | string | `90` | no | @@ -38,23 +37,20 @@ Inputs | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | | message | Message sent when a Redis monitor is triggered | string | - | yes | -| other_requests_aggregator | Monitor aggregator for API Management other requests [available values: min, max, sum or avg] | string | `sum` | no | | other_requests_message | Custom message for API Management other requests monitor | string | `` | no | | other_requests_silenced | Groups to mute for API Management other requests monitor | map | `` | no | | other_requests_threshold_critical | Maximum acceptable percent of other requests | string | `90` | no | | other_requests_threshold_warning | Warning regarding acceptable percent of other requests | string | `50` | no | | other_requests_timeframe | Monitor timeframe for API Management other requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| status_aggregator | Monitor aggregator for API Management status [available values: min, max, sum or avg] | string | `avg` | no | | status_message | Custom message for API Management status monitor | string | `` | no | | status_silenced | Groups to mute for API Management status monitor | map | `` | no | +| status_time_aggregator | Monitor aggregator for API Management status [available values: min, max or avg] | string | `avg` | no | | status_timeframe | Monitor timeframe for API Management status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| successful_requests_aggregator | Monitor aggregator for API Management successful requests [available values: min, max, sum or avg] | string | `sum` | no | | successful_requests_message | Custom message for API Management successful requests monitor | string | `` | no | | successful_requests_silenced | Groups to mute for API Management successful requests monitor | map | `` | no | | successful_requests_threshold_critical | Minimum acceptable percent of successful requests | string | `10` | no | | successful_requests_threshold_warning | Warning regarding acceptable percent of successful requests | string | `30` | no | | successful_requests_timeframe | Monitor timeframe for API Management successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| unauthorized_requests_aggregator | Monitor aggregator for API Management unauthorized requests [available values: min, max, sum or avg] | string | `sum` | no | | unauthorized_requests_message | Custom message for API Management unauthorized requests monitor | string | `` | no | | unauthorized_requests_silenced | Groups to mute for API Management unauthorized requests monitor | map | `` | no | | unauthorized_requests_threshold_critical | Maximum acceptable percent of unauthorized requests | string | `90` | no | diff --git a/cloud/azure/apimanagement/inputs.tf b/cloud/azure/apimanagement/inputs.tf index 5b690b2..42ca41c 100644 --- a/cloud/azure/apimanagement/inputs.tf +++ b/cloud/azure/apimanagement/inputs.tf @@ -37,8 +37,8 @@ variable "status_message" { default = "" } -variable "status_aggregator" { - description = "Monitor aggregator for API Management status [available values: min, max, sum or avg]" +variable "status_time_aggregator" { + description = "Monitor aggregator for API Management status [available values: min, max or avg]" type = "string" default = "avg" } @@ -61,12 +61,6 @@ variable "failed_requests_message" { default = "" } -variable "failed_requests_aggregator" { - description = "Monitor aggregator for API Management failed requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "failed_requests_timeframe" { description = "Monitor timeframe for API Management failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -95,12 +89,6 @@ variable "other_requests_message" { default = "" } -variable "other_requests_aggregator" { - description = "Monitor aggregator for API Management other requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "other_requests_timeframe" { description = "Monitor timeframe for API Management other requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -129,12 +117,6 @@ variable "unauthorized_requests_message" { default = "" } -variable "unauthorized_requests_aggregator" { - description = "Monitor aggregator for API Management unauthorized requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "unauthorized_requests_timeframe" { description = "Monitor timeframe for API Management unauthorized requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -163,12 +145,6 @@ variable "successful_requests_message" { default = "" } -variable "successful_requests_aggregator" { - description = "Monitor aggregator for API Management successful requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "successful_requests_timeframe" { description = "Monitor timeframe for API Management successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/azure/apimanagement/monitors-azure-apimanagement.tf b/cloud/azure/apimanagement/monitors-azure-apimanagement.tf index 7de8dd1..6f2d114 100644 --- a/cloud/azure/apimanagement/monitors-azure-apimanagement.tf +++ b/cloud/azure/apimanagement/monitors-azure-apimanagement.tf @@ -13,7 +13,7 @@ resource "datadog_monitor" "apimgt_status" { message = "${coalesce(var.status_message, var.message)}" query = < ${var.failed_requests_threshold_critical} EOF @@ -74,9 +74,9 @@ resource "datadog_monitor" "apimgt_other_requests" { message = "${coalesce(var.other_requests_message, var.message)}" query = < ${var.other_requests_threshold_critical} EOF @@ -106,9 +106,9 @@ resource "datadog_monitor" "apimgt_unauthorized_requests" { message = "${coalesce(var.unauthorized_requests_message, var.message)}" query = < ${var.unauthorized_requests_threshold_critical} EOF @@ -138,9 +138,9 @@ resource "datadog_monitor" "apimgt_successful_requests" { message = "${coalesce(var.successful_requests_message, var.message)}" query = <` | no | | http_4xx_requests_threshold_critical | Maximum critical acceptable percent of 4xx errors | string | `90` | no | | http_4xx_requests_threshold_warning | Warning regarding acceptable percent of 4xx errors | string | `50` | no | | http_4xx_requests_timeframe | Monitor timeframe for App Services 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| http_5xx_requests_aggregator | Monitor aggregator for App Services 5xx requests [available values: min, max, sum or avg] | string | `sum` | no | | http_5xx_requests_message | Custom message for App Services 5xx requests monitor | string | `` | no | | http_5xx_requests_silenced | Groups to mute for App Services 5xx requests monitor | map | `` | no | | http_5xx_requests_threshold_critical | Maximum critical acceptable percent of 5xx errors | string | `90` | no | | http_5xx_requests_threshold_warning | Warning regarding acceptable percent of 5xx errors | string | `50` | no | | http_5xx_requests_timeframe | Monitor timeframe for App Services 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| http_successful_requests_aggregator | Monitor aggregator for App Services successful requests [available values: min, max, sum or avg] | string | `sum` | no | | http_successful_requests_message | Custom message for App Services successful requests monitor | string | `` | no | | http_successful_requests_silenced | Groups to mute for App Services successful requests monitor | map | `` | no | | http_successful_requests_threshold_critical | Minimum critical acceptable percent of 2xx & 3xx requests | string | `10` | no | | http_successful_requests_threshold_warning | Warning regarding acceptable percent of 2xx & 3xx requests | string | `30` | no | | http_successful_requests_timeframe | Monitor timeframe for App Services successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| memory_usage_aggregator | Monitor aggregator for App Services memory usage [available values: min, max, sum or avg] | string | `avg` | no | | memory_usage_message | Custom message for App Services memory usage monitor | string | `` | no | | memory_usage_silenced | Groups to mute for App Services memory usage monitor | map | `` | no | | memory_usage_threshold_critical | Alerting threshold in Mib | string | `1073741824` | no | | memory_usage_threshold_warning | Warning threshold in MiB | string | `536870912` | no | +| memory_usage_time_aggregator | Monitor aggregator for App Services memory usage [available values: min, max or avg] | string | `avg` | no | | memory_usage_timeframe | Monitor timeframe for App Services memory usage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | message | Message sent when a monitor is triggered | string | - | yes | -| response_time_aggregator | Monitor aggregator for App Services response time [available values: min, max, sum or avg] | string | `min` | no | | response_time_message | Custom message for App Services response time monitor | string | `` | no | | response_time_silenced | Groups to mute for App Services response time monitor | map | `` | no | | response_time_threshold_critical | Alerting threshold for response time in seconds | string | `10` | no | | response_time_threshold_warning | Warning threshold for response time in seconds | string | `5` | no | +| response_time_time_aggregator | Monitor aggregator for App Services response time [available values: min, max or avg] | string | `min` | no | | response_time_timeframe | Monitor timeframe for App Services response time [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | Related documentation diff --git a/cloud/azure/app-services/inputs.tf b/cloud/azure/app-services/inputs.tf index 55d967b..29239a6 100644 --- a/cloud/azure/app-services/inputs.tf +++ b/cloud/azure/app-services/inputs.tf @@ -35,8 +35,8 @@ variable "response_time_message" { default = "" } -variable "response_time_aggregator" { - description = "Monitor aggregator for App Services response time [available values: min, max, sum or avg]" +variable "response_time_time_aggregator" { + description = "Monitor aggregator for App Services response time [available values: min, max or avg]" type = "string" default = "min" } @@ -69,8 +69,8 @@ variable "memory_usage_message" { default = "" } -variable "memory_usage_aggregator" { - description = "Monitor aggregator for App Services memory usage [available values: min, max, sum or avg]" +variable "memory_usage_time_aggregator" { + description = "Monitor aggregator for App Services memory usage [available values: min, max or avg]" type = "string" default = "avg" } @@ -103,12 +103,6 @@ variable "http_4xx_requests_message" { default = "" } -variable "http_4xx_requests_aggregator" { - description = "Monitor aggregator for App Services 4xx requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "http_4xx_requests_timeframe" { description = "Monitor timeframe for App Services 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -137,12 +131,6 @@ variable "http_5xx_requests_message" { default = "" } -variable "http_5xx_requests_aggregator" { - description = "Monitor aggregator for App Services 5xx requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "http_5xx_requests_timeframe" { description = "Monitor timeframe for App Services 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -171,12 +159,6 @@ variable "http_successful_requests_message" { default = "" } -variable "http_successful_requests_aggregator" { - description = "Monitor aggregator for App Services successful requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "http_successful_requests_timeframe" { description = "Monitor timeframe for App Services successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/azure/app-services/monitors-app_services.tf b/cloud/azure/app-services/monitors-app_services.tf index 202b76b..df635c3 100644 --- a/cloud/azure/app-services/monitors-app_services.tf +++ b/cloud/azure/app-services/monitors-app_services.tf @@ -13,8 +13,8 @@ resource "datadog_monitor" "appservices_response_time" { message = "${coalesce(var.response_time_message, var.message)}" query = < ${var.response_time_threshold_critical} EOF @@ -44,8 +44,8 @@ resource "datadog_monitor" "appservices_memory_usage_count" { message = "${coalesce(var.memory_usage_message, var.message)}" query = < ${var.memory_usage_threshold_critical} EOF @@ -75,9 +75,9 @@ resource "datadog_monitor" "appservices_http_5xx_errors_count" { message = "${coalesce(var.http_5xx_requests_message, var.message)}" query = < ${var.http_5xx_requests_threshold_critical} EOF @@ -107,9 +107,9 @@ resource "datadog_monitor" "appservices_http_4xx_errors_count" { message = "${coalesce(var.http_4xx_requests_message, var.message)}" query = < ${var.http_4xx_requests_threshold_critical} EOF @@ -139,10 +139,10 @@ resource "datadog_monitor" "appservices_http_success_status_rate" { message = "${coalesce(var.http_successful_requests_message, var.message)}" query = <` | no | | errors_rate_thresold_critical | Errors ratio (percentage) to trigger the critical alert | string | `90` | no | | errors_rate_thresold_warning | Errors ratio (percentage) to trigger a warning alert | string | `50` | no | | errors_rate_timeframe | Monitor timeframe for Event Hub errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| failed_requests_rate_aggregator | Monitor aggregator for Event Hub failed requests [available values: min, max, sum or avg] | string | `sum` | no | | failed_requests_rate_message | Custom message for Event Hub failed requests monitor | string | `` | no | | failed_requests_rate_silenced | Groups to mute for Event Hub failed requests monitor | map | `` | no | | failed_requests_rate_thresold_critical | Failed requests ratio (percentage) to trigger the critical alert | string | `90` | no | @@ -43,9 +41,9 @@ Inputs | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | | message | Message sent when an alert is triggered | string | - | yes | -| status_aggregator | Monitor aggregator for Event Hub status [available values: min, max, sum or avg] | string | `avg` | no | | status_message | Custom message for Event Hub status monitor | string | `` | no | | status_silenced | Groups to mute for Event Hub status monitor | map | `` | no | +| status_time_aggregator | Monitor aggregator for Event Hub status [available values: min, max or avg] | string | `avg` | no | | status_timeframe | Monitor timeframe for Event Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | Related documentation diff --git a/cloud/azure/eventhub/inputs.tf b/cloud/azure/eventhub/inputs.tf index 1748b6f..ac6b733 100644 --- a/cloud/azure/eventhub/inputs.tf +++ b/cloud/azure/eventhub/inputs.tf @@ -37,8 +37,8 @@ variable "status_message" { default = "" } -variable "status_aggregator" { - description = "Monitor aggregator for Event Hub status [available values: min, max, sum or avg]" +variable "status_time_aggregator" { + description = "Monitor aggregator for Event Hub status [available values: min, max or avg]" type = "string" default = "avg" } @@ -61,12 +61,6 @@ variable "failed_requests_rate_message" { default = "" } -variable "failed_requests_rate_aggregator" { - description = "Monitor aggregator for Event Hub failed requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "failed_requests_rate_timeframe" { description = "Monitor timeframe for Event Hub failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -95,12 +89,6 @@ variable "errors_rate_message" { default = "" } -variable "errors_rate_aggregator" { - description = "Monitor aggregator for Event Hub errors [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "errors_rate_timeframe" { description = "Monitor timeframe for Event Hub errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/azure/eventhub/monitors-eventhub.tf b/cloud/azure/eventhub/monitors-eventhub.tf index 612b326..a3d70c3 100644 --- a/cloud/azure/eventhub/monitors-eventhub.tf +++ b/cloud/azure/eventhub/monitors-eventhub.tf @@ -11,7 +11,9 @@ resource "datadog_monitor" "eventhub_status" { message = "${coalesce(var.status_message, var.message)}" query = < ${var.failed_requests_rate_thresold_critical} EOF @@ -71,14 +73,14 @@ resource "datadog_monitor" "eventhub_errors" { message = "${coalesce(var.errors_rate_message, var.message)}" query = < ${var.errors_rate_thresold_critical} diff --git a/cloud/azure/inputs.tf b/cloud/azure/inputs.tf index 2d5ada3..751abd9 100644 --- a/cloud/azure/inputs.tf +++ b/cloud/azure/inputs.tf @@ -41,8 +41,8 @@ variable "apimanagement_status_message" { default = "" } -variable "apimanagement_status_aggregator" { - description = "Monitor aggregator for API Management status [available values: min, max, sum or avg]" +variable "apimanagement_status_time_aggregator" { + description = "Monitor aggregator for API Management status [available values: min, max or avg]" type = "string" default = "avg" } @@ -65,12 +65,6 @@ variable "apimanagement_failed_requests_message" { default = "" } -variable "apimanagement_failed_requests_aggregator" { - description = "Monitor aggregator for API Management failed requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "apimanagement_failed_requests_timeframe" { description = "Monitor timeframe for API Management failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -99,12 +93,6 @@ variable "apimanagement_other_requests_message" { default = "" } -variable "apimanagement_other_requests_aggregator" { - description = "Monitor aggregator for API Management other requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "apimanagement_other_requests_timeframe" { description = "Monitor timeframe for API Management other requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -133,12 +121,6 @@ variable "apimanagement_unauthorized_requests_message" { default = "" } -variable "apimanagement_unauthorized_requests_aggregator" { - description = "Monitor aggregator for API Management unauthorized requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "apimanagement_unauthorized_requests_timeframe" { description = "Monitor timeframe for API Management unauthorized requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -167,12 +149,6 @@ variable "apimanagement_successful_requests_message" { default = "" } -variable "apimanagement_successful_requests_aggregator" { - description = "Monitor aggregator for API Management successful requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "apimanagement_successful_requests_timeframe" { description = "Monitor timeframe for API Management successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -202,8 +178,8 @@ variable "appservices_response_time_message" { default = "" } -variable "appservices_response_time_aggregator" { - description = "Monitor aggregator for App Services response time [available values: min, max, sum or avg]" +variable "appservices_response_time_time_aggregator" { + description = "Monitor aggregator for App Services response time [available values: min, max or avg]" type = "string" default = "min" } @@ -236,8 +212,8 @@ variable "appservices_memory_usage_message" { default = "" } -variable "appservices_memory_usage_aggregator" { - description = "Monitor aggregator for App Services memory usage [available values: min, max, sum or avg]" +variable "appservices_memory_usage_time_aggregator" { + description = "Monitor aggregator for App Services memory usage [available values: min, max or avg]" type = "string" default = "avg" } @@ -270,12 +246,6 @@ variable "appservices_http_4xx_requests_message" { default = "" } -variable "appservices_http_4xx_requests_aggregator" { - description = "Monitor aggregator for App Services 4xx requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "appservices_http_4xx_requests_timeframe" { description = "Monitor timeframe for App Services 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -304,12 +274,6 @@ variable "appservices_http_5xx_requests_message" { default = "" } -variable "appservices_http_5xx_requests_aggregator" { - description = "Monitor aggregator for App Services 5xx requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "appservices_http_5xx_requests_timeframe" { description = "Monitor timeframe for App Services 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -338,12 +302,6 @@ variable "appservices_http_successful_requests_message" { default = "" } -variable "appservices_http_successful_requests_aggregator" { - description = "Monitor aggregator for App Services successful requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "appservices_http_successful_requests_timeframe" { description = "Monitor timeframe for App Services successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -373,8 +331,8 @@ variable "eventhub_status_message" { default = "" } -variable "eventhub_status_aggregator" { - description = "Monitor aggregator for Event Hub status [available values: min, max, sum or avg]" +variable "eventhub_status_time_aggregator" { + description = "Monitor aggregator for Event Hub status [available values: min, max or avg]" type = "string" default = "avg" } @@ -397,12 +355,6 @@ variable "eventhub_failed_requests_rate_message" { default = "" } -variable "eventhub_failed_requests_rate_aggregator" { - description = "Monitor aggregator for Event Hub failed requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "eventhub_failed_requests_rate_timeframe" { description = "Monitor timeframe for Event Hub failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -431,12 +383,6 @@ variable "eventhub_errors_rate_message" { default = "" } -variable "eventhub_errors_rate_aggregator" { - description = "Monitor aggregator for Event Hub errors [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "eventhub_errors_rate_timeframe" { description = "Monitor timeframe for Event Hub errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -466,8 +412,8 @@ variable "iothub_status_message" { default = "" } -variable "iothub_status_aggregator" { - description = "Monitor aggregator for IoT Hub status [available values: min, max, sum or avg]" +variable "iothub_status_time_aggregator" { + description = "Monitor aggregator for IoT Hub status [available values: min, max or avg]" type = "string" default = "avg" } @@ -490,8 +436,8 @@ variable "iothub_total_devices_message" { default = "" } -variable "iothub_total_devices_aggregator" { - description = "Monitor aggregator for IoT Hub total devices [available values: min, max, sum or avg]" +variable "iothub_total_devices_time_aggregator" { + description = "Monitor aggregator for IoT Hub total devices [available values: min, max or avg]" type = "string" default = "avg" } @@ -514,12 +460,6 @@ variable "iothub_too_many_d2c_telemetry_ingress_nosent_message" { default = "" } -variable "iothub_too_many_d2c_telemetry_ingress_nosent_aggregator" { - description = "Monitor aggregator for IoT Hub unsent d2c telemetry [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "iothub_too_many_d2c_telemetry_ingress_nosent_timeframe" { description = "Monitor timeframe for IoT Hub unsent d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -538,12 +478,6 @@ variable "iothub_failed_jobs_rate_message" { default = "" } -variable "iothub_failed_jobs_rate_aggregator" { - description = "Monitor aggregator for IoT Hub failed jobs [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "iothub_failed_jobs_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -572,12 +506,6 @@ variable "iothub_failed_listjobs_rate_message" { default = "" } -variable "iothub_failed_listjobs_rate_aggregator" { - description = "Monitor aggregator for IoT Hub failed listjobs jobs [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "iothub_failed_listjobs_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed list jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -606,12 +534,6 @@ variable "iothub_failed_queryjobs_rate_message" { default = "" } -variable "iothub_failed_queryjobs_rate_aggregator" { - description = "Monitor aggregator for IoT Hub failed query jobs [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "iothub_failed_queryjobs_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed query jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -640,12 +562,6 @@ variable "iothub_failed_c2d_methods_rate_message" { default = "" } -variable "iothub_failed_c2d_methods_rate_aggregator" { - description = "Monitor aggregator for IoT Hub failed c2d method [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "iothub_failed_c2d_methods_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed c2d method [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -674,12 +590,6 @@ variable "iothub_failed_c2d_twin_read_rate_message" { default = "" } -variable "iothub_failed_c2d_twin_read_rate_aggregator" { - description = "Monitor aggregator for IoT Hub failed c2d twin read [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "iothub_failed_c2d_twin_read_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed c2d twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -708,12 +618,6 @@ variable "iothub_failed_c2d_twin_update_rate_message" { default = "" } -variable "iothub_failed_c2d_twin_update_rate_aggregator" { - description = "Monitor aggregator for IoT Hub failed c2d twin update [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "iothub_failed_c2d_twin_update_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed c2d twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -742,12 +646,6 @@ variable "iothub_failed_d2c_twin_read_rate_message" { default = "" } -variable "iothub_failed_d2c_twin_read_rate_aggregator" { - description = "Monitor aggregator for IoT Hub failed d2c twin read [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "iothub_failed_d2c_twin_read_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed d2c twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -776,12 +674,6 @@ variable "iothub_failed_d2c_twin_update_rate_message" { default = "" } -variable "iothub_failed_d2c_twin_update_rate_aggregator" { - description = "Monitor aggregator for IoT Hub failed d2c twin update [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "iothub_failed_d2c_twin_update_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed d2c twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -810,12 +702,6 @@ variable "iothub_dropped_d2c_telemetry_egress_message" { default = "" } -variable "iothub_dropped_d2c_telemetry_egress_aggregator" { - description = "Monitor aggregator for IoT Hub failed d2c telemetry [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "iothub_dropped_d2c_telemetry_egress_timeframe" { description = "Monitor timeframe for IoT Hub dropped d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -844,12 +730,6 @@ variable "iothub_orphaned_d2c_telemetry_egress_message" { default = "" } -variable "iothub_orphaned_d2c_telemetry_egress_aggregator" { - description = "Monitor aggregator for IoT Hub orphaned d2c telemetry [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "iothub_orphaned_d2c_telemetry_egress_timeframe" { description = "Monitor timeframe for IoT Hub orphaned d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -878,12 +758,6 @@ variable "iothub_invalid_d2c_telemetry_egress_message" { default = "" } -variable "iothub_invalid_d2c_telemetry_egress_aggregator" { - description = "Monitor aggregator for IoT Hub invalid d2c telemetry [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "iothub_invalid_d2c_telemetry_egress_timeframe" { description = "Monitor timeframe for IoT Hub invalid d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -913,8 +787,8 @@ variable "redis_status_message" { default = "" } -variable "redis_status_aggregator" { - description = "Monitor aggregator for Redis status [available values: min, max, sum or avg]" +variable "redis_status_time_aggregator" { + description = "Monitor aggregator for Redis status [available values: min, max or avg]" type = "string" default = "avg" } @@ -937,8 +811,8 @@ variable "redis_evictedkeys_limit_message" { default = "" } -variable "redis_evictedkeys_limit_aggregator" { - description = "Monitor aggregator for Redis evicted keys [available values: min, max, sum or avg]" +variable "redis_evictedkeys_limit_time_aggregator" { + description = "Monitor aggregator for Redis evicted keys [available values: min, max or avg]" type = "string" default = "avg" } @@ -971,8 +845,8 @@ variable "redis_percent_processor_time_message" { default = "" } -variable "redis_percent_processor_time_aggregator" { - description = "Monitor aggregator for Redis processor [available values: min, max, sum or avg]" +variable "redis_percent_processor_time_time_aggregator" { + description = "Monitor aggregator for Redis processor [available values: min, max or avg]" type = "string" default = "avg" } @@ -1005,8 +879,8 @@ variable "redis_server_load_rate_message" { default = "" } -variable "redis_server_load_rate_aggregator" { - description = "Monitor aggregator for Redis server load [available values: min, max, sum or avg]" +variable "redis_server_load_rate_time_aggregator" { + description = "Monitor aggregator for Redis server load [available values: min, max or avg]" type = "string" default = "avg" } @@ -1040,8 +914,8 @@ variable "servicebus_status_message" { default = "" } -variable "servicebus_status_aggregator" { - description = "Monitor aggregator for Service Bus status [available values: min, max, sum or avg]" +variable "servicebus_status_time_aggregator" { + description = "Monitor aggregator for Service Bus status [available values: min, max or avg]" type = "string" default = "min" } @@ -1064,8 +938,8 @@ variable "sqldatabase_cpu_message" { default = "" } -variable "sqldatabase_cpu_aggregator" { - description = "Monitor aggregator for SQL CPU [available values: min, max, sum or avg]" +variable "sqldatabase_cpu_time_aggregator" { + description = "Monitor aggregator for SQL CPU [available values: min, max or avg]" type = "string" default = "avg" } @@ -1098,8 +972,8 @@ variable "sqldatabase_diskspace_message" { default = "" } -variable "sqldatabase_diskspace_aggregator" { - description = "Monitor aggregator for SQL disk space [available values: min, max, sum or avg]" +variable "sqldatabase_diskspace_time_aggregator" { + description = "Monitor aggregator for SQL disk space [available values: min, max or avg]" type = "string" default = "avg" } @@ -1132,8 +1006,8 @@ variable "sqldatabase_dtu_message" { default = "" } -variable "sqldatabase_dtu_aggregator" { - description = "Monitor aggregator for SQL DTU [available values: min, max, sum or avg]" +variable "sqldatabase_dtu_time_aggregator" { + description = "Monitor aggregator for SQL DTU [available values: min, max or avg]" type = "string" default = "avg" } @@ -1166,12 +1040,6 @@ variable "sqldatabase_deadlock_message" { default = "" } -variable "sqldatabase_deadlock_aggregator" { - description = "Monitor aggregator for SQL Deadlock [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "sqldatabase_deadlock_timeframe" { description = "Monitor timeframe for SQL Deadlock [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -1196,8 +1064,8 @@ variable "storage_availability_message" { default = "" } -variable "storage_availability_aggregator" { - description = "Monitor aggregator for Storage availability [available values: min, max, sum or avg]" +variable "storage_availability_time_aggregator" { + description = "Monitor aggregator for Storage availability [available values: min, max or avg]" type = "string" default = "avg" } @@ -1230,8 +1098,8 @@ variable "storage_successful_requests_message" { default = "" } -variable "storage_successful_requests_aggregator" { - description = "Monitor aggregator for Storage sucessful requests [available values: min, max, sum or avg]" +variable "storage_successful_requests_time_aggregator" { + description = "Monitor aggregator for Storage sucessful requests [available values: min, max or avg]" type = "string" default = "avg" } @@ -1264,8 +1132,8 @@ variable "storage_latency_message" { default = "" } -variable "storage_latency_aggregator" { - description = "Monitor aggregator for Storage latency [available values: min, max, sum or avg]" +variable "storage_latency_time_aggregator" { + description = "Monitor aggregator for Storage latency [available values: min, max or avg]" type = "string" default = "min" } @@ -1298,8 +1166,8 @@ variable "storage_timeout_error_requests_message" { default = "" } -variable "storage_timeout_error_requests_aggregator" { - description = "Monitor aggregator for Storage timeout [available values: min, max, sum or avg]" +variable "storage_timeout_error_requests_time_aggregator" { + description = "Monitor aggregator for Storage timeout [available values: min, max or avg]" type = "string" default = "avg" } @@ -1332,8 +1200,8 @@ variable "storage_network_error_requests_message" { default = "" } -variable "storage_network_error_requests_aggregator" { - description = "Monitor aggregator for Storage network errors [available values: min, max, sum or avg]" +variable "storage_network_error_requests_time_aggregator" { + description = "Monitor aggregator for Storage network errors [available values: min, max or avg]" type = "string" default = "avg" } @@ -1366,8 +1234,8 @@ variable "storage_throttling_error_requests_message" { default = "" } -variable "storage_throttling_error_requests_aggregator" { - description = "Monitor aggregator for Storage throttling errors [available values: min, max, sum or avg]" +variable "storage_throttling_error_requests_time_aggregator" { + description = "Monitor aggregator for Storage throttling errors [available values: min, max or avg]" type = "string" default = "avg" } @@ -1400,8 +1268,8 @@ variable "storage_server_other_error_requests_message" { default = "" } -variable "storage_server_other_error_requests_aggregator" { - description = "Monitor aggregator for Storage other errors [available values: min, max, sum or avg]" +variable "storage_server_other_error_requests_time_aggregator" { + description = "Monitor aggregator for Storage other errors [available values: min, max or avg]" type = "string" default = "avg" } @@ -1434,8 +1302,8 @@ variable "storage_client_other_error_requests_message" { default = "" } -variable "storage_client_other_error_requests_aggregator" { - description = "Monitor aggregator for Storage other errors [available values: min, max, sum or avg]" +variable "storage_client_other_error_requests_time_aggregator" { + description = "Monitor aggregator for Storage other errors [available values: min, max or avg]" type = "string" default = "avg" } @@ -1468,8 +1336,8 @@ variable "storage_authorization_error_requests_message" { default = "" } -variable "storage_authorization_error_requests_aggregator" { - description = "Monitor aggregator for Storage authorization errors [available values: min, max, sum or avg]" +variable "storage_authorization_error_requests_time_aggregator" { + description = "Monitor aggregator for Storage authorization errors [available values: min, max or avg]" type = "string" default = "avg" } @@ -1503,8 +1371,8 @@ variable "streamanalytics_status_message" { default = "" } -variable "streamanalytics_status_aggregator" { - description = "Monitor aggregator for Stream Analytics status [available values: min, max, sum or avg]" +variable "streamanalytics_status_time_aggregator" { + description = "Monitor aggregator for Stream Analytics status [available values: min, max or avg]" type = "string" default = "avg" } @@ -1527,8 +1395,8 @@ variable "streamanalytics_su_utilization_message" { default = "" } -variable "streamanalytics_su_utilization_aggregator" { - description = "Monitor aggregator for Stream Analytics utilization [available values: min, max, sum or avg]" +variable "streamanalytics_su_utilization_time_aggregator" { + description = "Monitor aggregator for Stream Analytics utilization [available values: min, max or avg]" type = "string" default = "avg" } @@ -1561,12 +1429,6 @@ variable "streamanalytics_failed_function_requests_message" { default = "" } -variable "streamanalytics_failed_function_requests_aggregator" { - description = "Monitor aggregator for Stream Analytics failed requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "streamanalytics_failed_function_requests_timeframe" { description = "Monitor timeframe for Stream Analytics failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -1595,8 +1457,8 @@ variable "streamanalytics_conversion_errors_message" { default = "" } -variable "streamanalytics_conversion_errors_aggregator" { - description = "Monitor aggregator for Stream Analytics conversion errors [available values: min, max, sum or avg]" +variable "streamanalytics_conversion_errors_time_aggregator" { + description = "Monitor aggregator for Stream Analytics conversion errors [available values: min, max or avg]" type = "string" default = "avg" } @@ -1629,8 +1491,8 @@ variable "streamanalytics_runtime_errors_message" { default = "" } -variable "streamanalytics_runtime_errors_aggregator" { - description = "Monitor aggregator for Stream Analytics runtime errors [available values: min, max, sum or avg]" +variable "streamanalytics_runtime_errors_time_aggregator" { + description = "Monitor aggregator for Stream Analytics runtime errors [available values: min, max or avg]" type = "string" default = "avg" } diff --git a/cloud/azure/iothubs/README.md b/cloud/azure/iothubs/README.md index 8678e3b..6190555 100644 --- a/cloud/azure/iothubs/README.md +++ b/cloud/azure/iothubs/README.md @@ -39,86 +39,74 @@ Inputs | Name | Description | Type | Default | Required | |------|-------------|:----:|:-----:|:-----:| | delay | Delay in seconds for the metric evaluation | string | `900` | no | -| dropped_d2c_telemetry_egress_aggregator | Monitor aggregator for IoT Hub failed d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no | | dropped_d2c_telemetry_egress_message | Custom message for IoT Hub dropped d2c telemetry monitor | string | `` | no | | dropped_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Dropped limit (critical threshold) | string | `90` | no | | dropped_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Dropped limit (warning threshold) | string | `50` | no | | dropped_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub dropped d2c telemetry monitor | map | `` | no | | dropped_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub dropped d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | environment | Architecture Environment | string | - | yes | -| failed_c2d_methods_rate_aggregator | Monitor aggregator for IoT Hub failed c2d method [available values: min, max, sum or avg] | string | `sum` | no | | failed_c2d_methods_rate_message | Custom message for IoT Hub failed c2d method monitor | string | `` | no | | failed_c2d_methods_rate_silenced | Groups to mute for IoT Hub failed c2d methods monitor | map | `` | no | | failed_c2d_methods_rate_threshold_critical | C2D Methods Failed rate limit (critical threshold) | string | `90` | no | | failed_c2d_methods_rate_threshold_warning | C2D Methods Failed rate limit (warning threshold) | string | `50` | no | | failed_c2d_methods_rate_timeframe | Monitor timeframe for IoT Hub failed c2d method [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| failed_c2d_twin_read_rate_aggregator | Monitor aggregator for IoT Hub failed c2d twin read [available values: min, max, sum or avg] | string | `sum` | no | | failed_c2d_twin_read_rate_message | Custom message for IoT Hub failed c2d twin read monitor | string | `` | no | | failed_c2d_twin_read_rate_silenced | Groups to mute for IoT Hub failed c2d twin read monitor | map | `` | no | | failed_c2d_twin_read_rate_threshold_critical | C2D Twin Read Failed rate limit (critical threshold) | string | `90` | no | | failed_c2d_twin_read_rate_threshold_warning | C2D Twin Read Failed rate limit (warning threshold) | string | `50` | no | | failed_c2d_twin_read_rate_timeframe | Monitor timeframe for IoT Hub failed c2d twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| failed_c2d_twin_update_rate_aggregator | Monitor aggregator for IoT Hub failed c2d twin update [available values: min, max, sum or avg] | string | `sum` | no | | failed_c2d_twin_update_rate_message | Custom message for IoT Hub failed c2d twin update monitor | string | `` | no | | failed_c2d_twin_update_rate_silenced | Groups to mute for IoT Hub failed c2d twin update monitor | map | `` | no | | failed_c2d_twin_update_rate_threshold_critical | C2D Twin Update Failed rate limit (critical threshold) | string | `90` | no | | failed_c2d_twin_update_rate_threshold_warning | C2D Twin Update Failed rate limit (warning threshold) | string | `50` | no | | failed_c2d_twin_update_rate_timeframe | Monitor timeframe for IoT Hub failed c2d twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| failed_d2c_twin_read_rate_aggregator | Monitor aggregator for IoT Hub failed d2c twin read [available values: min, max, sum or avg] | string | `sum` | no | | failed_d2c_twin_read_rate_message | Custom message for IoT Hub failed d2c twin read monitor | string | `` | no | | failed_d2c_twin_read_rate_silenced | Groups to mute for IoT Hub failed d2c twin read monitor | map | `` | no | | failed_d2c_twin_read_rate_threshold_critical | D2C Twin Read Failed rate limit (critical threshold) | string | `90` | no | | failed_d2c_twin_read_rate_threshold_warning | D2C Twin Read Failed rate limit (warning threshold) | string | `50` | no | | failed_d2c_twin_read_rate_timeframe | Monitor timeframe for IoT Hub failed d2c twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| failed_d2c_twin_update_rate_aggregator | Monitor aggregator for IoT Hub failed d2c twin update [available values: min, max, sum or avg] | string | `sum` | no | | failed_d2c_twin_update_rate_message | Custom message for IoT Hub failed d2c twin update monitor | string | `` | no | | failed_d2c_twin_update_rate_silenced | Groups to mute for IoT Hub failed d2c twin update monitor | map | `` | no | | failed_d2c_twin_update_rate_threshold_critical | D2C Twin Update Failed rate limit (critical threshold) | string | `90` | no | | failed_d2c_twin_update_rate_threshold_warning | D2C Twin Update Failed rate limit (warning threshold) | string | `50` | no | | failed_d2c_twin_update_rate_timeframe | Monitor timeframe for IoT Hub failed d2c twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| failed_jobs_rate_aggregator | Monitor aggregator for IoT Hub failed jobs [available values: min, max, sum or avg] | string | `sum` | no | | failed_jobs_rate_message | Custom message for IoT Hub failed jobs monitor | string | `` | no | | failed_jobs_rate_silenced | Groups to mute for IoT Hub failed jobs monitor | map | `` | no | | failed_jobs_rate_threshold_critical | Jobs Failed rate limit (critical threshold) | string | `90` | no | | failed_jobs_rate_threshold_warning | Jobs Failed rate limit (warning threshold) | string | `50` | no | | failed_jobs_rate_timeframe | Monitor timeframe for IoT Hub failed jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| failed_listjobs_rate_aggregator | Monitor aggregator for IoT Hub failed listjobs jobs [available values: min, max, sum or avg] | string | `sum` | no | | failed_listjobs_rate_message | Custom message for IoT Hub failed list jobs monitor | string | `` | no | | failed_listjobs_rate_silenced | Groups to mute for IoT Hub failed list jobs monitor | map | `` | no | | failed_listjobs_rate_threshold_critical | ListJobs Failed rate limit (critical threshold) | string | `90` | no | | failed_listjobs_rate_threshold_warning | ListJobs Failed rate limit (warning threshold) | string | `50` | no | | failed_listjobs_rate_timeframe | Monitor timeframe for IoT Hub failed list jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| failed_queryjobs_rate_aggregator | Monitor aggregator for IoT Hub failed query jobs [available values: min, max, sum or avg] | string | `sum` | no | | failed_queryjobs_rate_message | Custom message for IoT Hub failed query jobs monitor | string | `` | no | | failed_queryjobs_rate_silenced | Groups to mute for IoT Hub failed query jobs monitor | map | `` | no | | failed_queryjobs_rate_threshold_critical | QueryJobs Failed rate limit (critical threshold) | string | `90` | no | | failed_queryjobs_rate_threshold_warning | QueryJobs Failed rate limit (warning threshold) | string | `50` | no | | failed_queryjobs_rate_timeframe | Monitor timeframe for IoT Hub failed query jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | filter_tags | Tags used for filtering | string | `*` | no | -| invalid_d2c_telemetry_egress_aggregator | Monitor aggregator for IoT Hub invalid d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no | | invalid_d2c_telemetry_egress_message | Custom message for IoT Hub invalid d2c telemetry monitor | string | `` | no | | invalid_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Invalid limit (critical threshold) | string | `90` | no | | invalid_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Invalid limit (warning threshold) | string | `50` | no | | invalid_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub invalid d2c telemetry monitor | map | `` | no | | invalid_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub invalid d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | message | Message sent when an alert is triggered | string | - | yes | -| orphaned_d2c_telemetry_egress_aggregator | Monitor aggregator for IoT Hub orphaned d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no | | orphaned_d2c_telemetry_egress_message | Custom message for IoT Hub orphaned d2c telemetry monitor | string | `` | no | | orphaned_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Orphaned limit (critical threshold) | string | `90` | no | | orphaned_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Orphaned limit (warning threshold) | string | `50` | no | | orphaned_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub orphaned d2c telemetry monitor | map | `` | no | | orphaned_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub orphaned d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| status_aggregator | Monitor aggregator for IoT Hub status [available values: min, max, sum or avg] | string | `avg` | no | | status_message | Custom message for IoT Hub status monitor | string | `` | no | | status_silenced | Groups to mute for IoT Hub status monitor | map | `` | no | +| status_time_aggregator | Monitor aggregator for IoT Hub status [available values: min, max, sum or avg] | string | `avg` | no | | status_timeframe | Monitor timeframe for IoT Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| too_many_d2c_telemetry_ingress_nosent_aggregator | Monitor aggregator for IoT Hub unsent d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no | | too_many_d2c_telemetry_ingress_nosent_message | Custom message for IoT Hub unsent d2c telemetry monitor | string | `` | no | | too_many_d2c_telemetry_ingress_nosent_silenced | Groups to mute for IoT Hub unsent d2c telemetry monitor | map | `` | no | | too_many_d2c_telemetry_ingress_nosent_timeframe | Monitor timeframe for IoT Hub unsent d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| total_devices_aggregator | Monitor aggregator for IoT Hub total devices [available values: min, max, sum or avg] | string | `avg` | no | | total_devices_message | Custom message for IoT Hub total devices monitor | string | `` | no | | total_devices_silenced | Groups to mute for IoT Hub total devices monitor | map | `` | no | +| total_devices_time_aggregator | Monitor aggregator for IoT Hub total devices [available values: min, max, sum or avg] | string | `avg` | no | | total_devices_timeframe | Monitor timeframe for IoT Hub total devices [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | Related documentation diff --git a/cloud/azure/iothubs/inputs.tf b/cloud/azure/iothubs/inputs.tf index f4763a9..58dbb63 100644 --- a/cloud/azure/iothubs/inputs.tf +++ b/cloud/azure/iothubs/inputs.tf @@ -32,7 +32,7 @@ variable "status_message" { default = "" } -variable "status_aggregator" { +variable "status_time_aggregator" { description = "Monitor aggregator for IoT Hub status [available values: min, max, sum or avg]" type = "string" default = "avg" @@ -56,7 +56,7 @@ variable "total_devices_message" { default = "" } -variable "total_devices_aggregator" { +variable "total_devices_time_aggregator" { description = "Monitor aggregator for IoT Hub total devices [available values: min, max, sum or avg]" type = "string" default = "avg" @@ -80,12 +80,6 @@ variable "too_many_d2c_telemetry_ingress_nosent_message" { default = "" } -variable "too_many_d2c_telemetry_ingress_nosent_aggregator" { - description = "Monitor aggregator for IoT Hub unsent d2c telemetry [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "too_many_d2c_telemetry_ingress_nosent_timeframe" { description = "Monitor timeframe for IoT Hub unsent d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -104,12 +98,6 @@ variable "failed_jobs_rate_message" { default = "" } -variable "failed_jobs_rate_aggregator" { - description = "Monitor aggregator for IoT Hub failed jobs [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "failed_jobs_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -138,12 +126,6 @@ variable "failed_listjobs_rate_message" { default = "" } -variable "failed_listjobs_rate_aggregator" { - description = "Monitor aggregator for IoT Hub failed listjobs jobs [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "failed_listjobs_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed list jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -172,12 +154,6 @@ variable "failed_queryjobs_rate_message" { default = "" } -variable "failed_queryjobs_rate_aggregator" { - description = "Monitor aggregator for IoT Hub failed query jobs [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "failed_queryjobs_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed query jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -206,12 +182,6 @@ variable "failed_c2d_methods_rate_message" { default = "" } -variable "failed_c2d_methods_rate_aggregator" { - description = "Monitor aggregator for IoT Hub failed c2d method [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "failed_c2d_methods_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed c2d method [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -240,12 +210,6 @@ variable "failed_c2d_twin_read_rate_message" { default = "" } -variable "failed_c2d_twin_read_rate_aggregator" { - description = "Monitor aggregator for IoT Hub failed c2d twin read [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "failed_c2d_twin_read_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed c2d twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -274,12 +238,6 @@ variable "failed_c2d_twin_update_rate_message" { default = "" } -variable "failed_c2d_twin_update_rate_aggregator" { - description = "Monitor aggregator for IoT Hub failed c2d twin update [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "failed_c2d_twin_update_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed c2d twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -308,12 +266,6 @@ variable "failed_d2c_twin_read_rate_message" { default = "" } -variable "failed_d2c_twin_read_rate_aggregator" { - description = "Monitor aggregator for IoT Hub failed d2c twin read [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "failed_d2c_twin_read_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed d2c twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -342,12 +294,6 @@ variable "failed_d2c_twin_update_rate_message" { default = "" } -variable "failed_d2c_twin_update_rate_aggregator" { - description = "Monitor aggregator for IoT Hub failed d2c twin update [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "failed_d2c_twin_update_rate_timeframe" { description = "Monitor timeframe for IoT Hub failed d2c twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -376,12 +322,6 @@ variable "dropped_d2c_telemetry_egress_message" { default = "" } -variable "dropped_d2c_telemetry_egress_aggregator" { - description = "Monitor aggregator for IoT Hub failed d2c telemetry [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "dropped_d2c_telemetry_egress_timeframe" { description = "Monitor timeframe for IoT Hub dropped d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -410,12 +350,6 @@ variable "orphaned_d2c_telemetry_egress_message" { default = "" } -variable "orphaned_d2c_telemetry_egress_aggregator" { - description = "Monitor aggregator for IoT Hub orphaned d2c telemetry [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "orphaned_d2c_telemetry_egress_timeframe" { description = "Monitor timeframe for IoT Hub orphaned d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -444,12 +378,6 @@ variable "invalid_d2c_telemetry_egress_message" { default = "" } -variable "invalid_d2c_telemetry_egress_aggregator" { - description = "Monitor aggregator for IoT Hub invalid d2c telemetry [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "invalid_d2c_telemetry_egress_timeframe" { description = "Monitor timeframe for IoT Hub invalid d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/azure/iothubs/monitors-iothubs.tf b/cloud/azure/iothubs/monitors-iothubs.tf index f4d54b5..bb81de9 100644 --- a/cloud/azure/iothubs/monitors-iothubs.tf +++ b/cloud/azure/iothubs/monitors-iothubs.tf @@ -3,10 +3,10 @@ resource "datadog_monitor" "too_many_jobs_failed" { message = "${coalesce(var.failed_jobs_rate_message, var.message)}" query = < ${var.failed_jobs_rate_threshold_critical} EOF @@ -37,10 +37,10 @@ resource "datadog_monitor" "too_many_list_jobs_failed" { message = "${coalesce(var.failed_listjobs_rate_message, var.message)}" query = < ${var.failed_listjobs_rate_threshold_critical} EOF @@ -71,10 +71,10 @@ resource "datadog_monitor" "too_many_query_jobs_failed" { message = "${coalesce(var.failed_queryjobs_rate_message, var.message)}" query = < ${var.failed_queryjobs_rate_threshold_critical} EOF @@ -105,7 +105,9 @@ resource "datadog_monitor" "status" { message = "${coalesce(var.status_message, var.message)}" query = < ${var.failed_c2d_methods_rate_threshold_critical} EOF @@ -189,10 +193,10 @@ resource "datadog_monitor" "too_many_c2d_twin_read_failed" { message = "${coalesce(var.failed_c2d_twin_read_rate_message, var.message)}" query = < ${var.failed_c2d_twin_read_rate_threshold_critical} EOF @@ -223,10 +227,10 @@ resource "datadog_monitor" "too_many_c2d_twin_update_failed" { message = "${coalesce(var.failed_c2d_twin_update_rate_message, var.message)}" query = < ${var.failed_c2d_twin_update_rate_threshold_critical} EOF @@ -257,10 +261,10 @@ resource "datadog_monitor" "too_many_d2c_twin_read_failed" { message = "${coalesce(var.failed_d2c_twin_read_rate_message, var.message)}" query = < ${var.failed_d2c_twin_read_rate_threshold_critical} EOF @@ -291,10 +295,10 @@ resource "datadog_monitor" "too_many_d2c_twin_update_failed" { message = "${coalesce(var.failed_d2c_twin_update_rate_message, var.message)}" query = < ${var.failed_d2c_twin_update_rate_threshold_critical} EOF @@ -325,12 +329,12 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_dropped" { message = "${coalesce(var.dropped_d2c_telemetry_egress_message, var.message)}" query = < ${var.dropped_d2c_telemetry_egress_rate_threshold_critical} EOF @@ -362,12 +366,12 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_orphaned" { message = "${coalesce(var.orphaned_d2c_telemetry_egress_message, var.message)}" query = < ${var.orphaned_d2c_telemetry_egress_rate_threshold_critical} EOF @@ -399,12 +403,12 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_invalid" { message = "${coalesce(var.invalid_d2c_telemetry_egress_message, var.message)}" query = < ${var.invalid_d2c_telemetry_egress_rate_threshold_critical} EOF @@ -436,9 +440,9 @@ resource "datadog_monitor" "too_many_d2c_telemetry_ingress_nosent" { message = "${coalesce(var.too_many_d2c_telemetry_ingress_nosent_message, var.message)}" query = < 0 EOF diff --git a/cloud/azure/monitors.tf b/cloud/azure/monitors.tf index a7ccedb..b3d6dda 100644 --- a/cloud/azure/monitors.tf +++ b/cloud/azure/monitors.tf @@ -10,29 +10,25 @@ module "apimanagement" { status_silenced = "${var.apimanagement_status_silenced}" status_message = "${var.apimanagement_status_message}" - status_aggregator = "${var.apimanagement_status_aggregator}" + status_time_aggregator = "${var.apimanagement_status_time_aggregator}" status_timeframe = "${var.apimanagement_status_timeframe}" failed_requests_silenced = "${var.apimanagement_failed_requests_silenced}" failed_requests_message = "${var.apimanagement_failed_requests_message}" - failed_requests_aggregator = "${var.apimanagement_failed_requests_aggregator}" failed_requests_timeframe = "${var.apimanagement_failed_requests_timeframe}" failed_requests_threshold_critical = "${var.apimanagement_failed_requests_threshold_critical}" failed_requests_threshold_warning = "${var.apimanagement_failed_requests_threshold_warning}" other_requests_silenced = "${var.apimanagement_other_requests_silenced}" other_requests_message = "${var.apimanagement_other_requests_message}" - other_requests_aggregator = "${var.apimanagement_other_requests_aggregator}" other_requests_timeframe = "${var.apimanagement_other_requests_timeframe}" other_requests_threshold_critical = "${var.apimanagement_other_requests_threshold_critical}" other_requests_threshold_warning = "${var.apimanagement_other_requests_threshold_warning}" successful_requests_silenced = "${var.apimanagement_successful_requests_silenced}" successful_requests_message = "${var.apimanagement_successful_requests_message}" - successful_requests_aggregator = "${var.apimanagement_successful_requests_aggregator}" successful_requests_timeframe = "${var.apimanagement_successful_requests_timeframe}" successful_requests_threshold_critical = "${var.apimanagement_successful_requests_threshold_critical}" successful_requests_threshold_warning = "${var.apimanagement_successful_requests_threshold_warning}" unauthorized_requests_silenced = "${var.apimanagement_unauthorized_requests_silenced}" unauthorized_requests_message = "${var.apimanagement_unauthorized_requests_message}" - unauthorized_requests_aggregator = "${var.apimanagement_unauthorized_requests_aggregator}" unauthorized_requests_timeframe = "${var.apimanagement_unauthorized_requests_timeframe}" unauthorized_requests_threshold_critical = "${var.apimanagement_unauthorized_requests_threshold_critical}" unauthorized_requests_threshold_warning = "${var.apimanagement_unauthorized_requests_threshold_warning}" @@ -50,31 +46,28 @@ module "appservices" { http_successful_requests_silenced = "${var.appservices_http_successful_requests_silenced}" http_successful_requests_message = "${var.appservices_http_successful_requests_message}" - http_successful_requests_aggregator = "${var.appservices_http_successful_requests_aggregator}" http_successful_requests_timeframe = "${var.appservices_http_successful_requests_timeframe}" http_successful_requests_threshold_critical = "${var.appservices_http_successful_requests_threshold_critical}" http_successful_requests_threshold_warning = "${var.appservices_http_successful_requests_threshold_warning}" http_5xx_requests_silenced = "${var.appservices_http_5xx_requests_silenced}" http_5xx_requests_message = "${var.appservices_http_5xx_requests_message}" - http_5xx_requests_aggregator = "${var.appservices_http_5xx_requests_aggregator}" http_5xx_requests_timeframe = "${var.appservices_http_5xx_requests_timeframe}" http_5xx_requests_threshold_critical = "${var.appservices_http_5xx_requests_threshold_critical}" http_5xx_requests_threshold_warning = "${var.appservices_http_5xx_requests_threshold_warning}" http_4xx_requests_silenced = "${var.appservices_http_4xx_requests_silenced}" http_4xx_requests_message = "${var.appservices_http_4xx_requests_message}" - http_4xx_requests_aggregator = "${var.appservices_http_4xx_requests_aggregator}" http_4xx_requests_timeframe = "${var.appservices_http_4xx_requests_timeframe}" http_4xx_requests_threshold_critical = "${var.appservices_http_4xx_requests_threshold_critical}" http_4xx_requests_threshold_warning = "${var.appservices_http_4xx_requests_threshold_warning}" memory_usage_silenced = "${var.appservices_memory_usage_silenced}" memory_usage_message = "${var.appservices_memory_usage_message}" - memory_usage_aggregator = "${var.appservices_memory_usage_aggregator}" + memory_usage_time_aggregator = "${var.appservices_memory_usage_time_aggregator}" memory_usage_timeframe = "${var.appservices_memory_usage_timeframe}" memory_usage_threshold_critical = "${var.appservices_memory_usage_threshold_critical}" memory_usage_threshold_warning = "${var.appservices_memory_usage_threshold_warning}" response_time_silenced = "${var.appservices_response_time_silenced}" response_time_message = "${var.appservices_response_time_message}" - response_time_aggregator = "${var.appservices_response_time_aggregator}" + response_time_time_aggregator = "${var.appservices_response_time_time_aggregator}" response_time_timeframe = "${var.appservices_response_time_timeframe}" response_time_threshold_critical = "${var.appservices_response_time_threshold_critical}" response_time_threshold_warning = "${var.appservices_response_time_threshold_warning}" @@ -92,17 +85,15 @@ module "eventhub" { status_silenced = "${var.eventhub_status_silenced}" status_message = "${var.eventhub_status_message}" - status_aggregator = "${var.eventhub_status_aggregator}" + status_time_aggregator = "${var.eventhub_status_time_aggregator}" status_timeframe = "${var.eventhub_status_timeframe}" errors_rate_silenced = "${var.eventhub_errors_rate_silenced}" errors_rate_message = "${var.eventhub_errors_rate_message}" - errors_rate_aggregator = "${var.eventhub_errors_rate_aggregator}" errors_rate_timeframe = "${var.eventhub_errors_rate_timeframe}" errors_rate_thresold_critical = "${var.eventhub_errors_rate_thresold_critical}" errors_rate_thresold_warning = "${var.eventhub_errors_rate_thresold_warning}" failed_requests_rate_silenced = "${var.eventhub_failed_requests_rate_silenced}" failed_requests_rate_message = "${var.eventhub_failed_requests_rate_message}" - failed_requests_rate_aggregator = "${var.eventhub_failed_requests_rate_aggregator}" failed_requests_rate_timeframe = "${var.eventhub_failed_requests_rate_timeframe}" failed_requests_rate_thresold_critical = "${var.eventhub_failed_requests_rate_thresold_critical}" failed_requests_rate_thresold_warning = "${var.eventhub_failed_requests_rate_thresold_warning}" @@ -119,79 +110,67 @@ module "iothub" { status_silenced = "${var.iothub_status_silenced}" status_message = "${var.iothub_status_message}" - status_aggregator = "${var.iothub_status_aggregator}" + status_time_aggregator = "${var.iothub_status_time_aggregator}" status_timeframe = "${var.iothub_status_timeframe}" total_devices_silenced = "${var.iothub_total_devices_silenced}" total_devices_message = "${var.iothub_total_devices_message}" - total_devices_aggregator = "${var.iothub_total_devices_aggregator}" + total_devices_time_aggregator = "${var.iothub_total_devices_time_aggregator}" total_devices_timeframe = "${var.iothub_total_devices_timeframe}" too_many_d2c_telemetry_ingress_nosent_silenced = "${var.iothub_too_many_d2c_telemetry_ingress_nosent_silenced}" too_many_d2c_telemetry_ingress_nosent_message = "${var.iothub_too_many_d2c_telemetry_ingress_nosent_message}" - too_many_d2c_telemetry_ingress_nosent_aggregator = "${var.iothub_too_many_d2c_telemetry_ingress_nosent_aggregator}" too_many_d2c_telemetry_ingress_nosent_timeframe = "${var.iothub_too_many_d2c_telemetry_ingress_nosent_timeframe}" dropped_d2c_telemetry_egress_silenced = "${var.iothub_dropped_d2c_telemetry_egress_silenced}" dropped_d2c_telemetry_egress_message = "${var.iothub_dropped_d2c_telemetry_egress_message}" - dropped_d2c_telemetry_egress_aggregator = "${var.iothub_dropped_d2c_telemetry_egress_aggregator}" dropped_d2c_telemetry_egress_timeframe = "${var.iothub_dropped_d2c_telemetry_egress_timeframe}" dropped_d2c_telemetry_egress_rate_threshold_critical = "${var.iothub_dropped_d2c_telemetry_egress_rate_threshold_critical}" dropped_d2c_telemetry_egress_rate_threshold_warning = "${var.iothub_dropped_d2c_telemetry_egress_rate_threshold_warning}" failed_c2d_methods_rate_silenced = "${var.iothub_failed_c2d_methods_rate_silenced}" failed_c2d_methods_rate_message = "${var.iothub_failed_c2d_methods_rate_message}" - failed_c2d_methods_rate_aggregator = "${var.iothub_failed_c2d_methods_rate_aggregator}" failed_c2d_methods_rate_timeframe = "${var.iothub_failed_c2d_methods_rate_timeframe}" failed_c2d_methods_rate_threshold_critical = "${var.iothub_failed_c2d_methods_rate_threshold_critical}" failed_c2d_methods_rate_threshold_warning = "${var.iothub_failed_c2d_methods_rate_threshold_warning}" failed_c2d_twin_read_rate_silenced = "${var.iothub_failed_c2d_twin_read_rate_silenced}" failed_c2d_twin_read_rate_message = "${var.iothub_failed_c2d_twin_read_rate_message}" - failed_c2d_twin_read_rate_aggregator = "${var.iothub_failed_c2d_twin_read_rate_aggregator}" failed_c2d_twin_read_rate_timeframe = "${var.iothub_failed_c2d_twin_read_rate_timeframe}" failed_c2d_twin_read_rate_threshold_critical = "${var.iothub_failed_c2d_twin_read_rate_threshold_critical}" failed_c2d_twin_read_rate_threshold_warning = "${var.iothub_failed_c2d_twin_read_rate_threshold_warning}" failed_c2d_twin_update_rate_silenced = "${var.iothub_failed_c2d_twin_update_rate_silenced}" failed_c2d_twin_update_rate_message = "${var.iothub_failed_c2d_twin_update_rate_message}" - failed_c2d_twin_update_rate_aggregator = "${var.iothub_failed_c2d_twin_update_rate_aggregator}" failed_c2d_twin_update_rate_timeframe = "${var.iothub_failed_c2d_twin_update_rate_timeframe}" failed_c2d_twin_update_rate_threshold_critical = "${var.iothub_failed_c2d_twin_update_rate_threshold_critical}" failed_c2d_twin_update_rate_threshold_warning = "${var.iothub_failed_c2d_twin_update_rate_threshold_warning}" failed_d2c_twin_read_rate_silenced = "${var.iothub_failed_d2c_twin_read_rate_silenced}" failed_d2c_twin_read_rate_message = "${var.iothub_failed_d2c_twin_read_rate_message}" - failed_d2c_twin_read_rate_aggregator = "${var.iothub_failed_d2c_twin_read_rate_aggregator}" failed_d2c_twin_read_rate_timeframe = "${var.iothub_failed_d2c_twin_read_rate_timeframe}" failed_d2c_twin_read_rate_threshold_critical = "${var.iothub_failed_d2c_twin_read_rate_threshold_critical}" failed_d2c_twin_read_rate_threshold_warning = "${var.iothub_failed_d2c_twin_read_rate_threshold_warning}" failed_d2c_twin_update_rate_silenced = "${var.iothub_failed_d2c_twin_update_rate_silenced}" failed_d2c_twin_update_rate_message = "${var.iothub_failed_d2c_twin_update_rate_message}" - failed_d2c_twin_update_rate_aggregator = "${var.iothub_failed_d2c_twin_update_rate_aggregator}" failed_d2c_twin_update_rate_timeframe = "${var.iothub_failed_d2c_twin_update_rate_timeframe}" failed_d2c_twin_update_rate_threshold_critical = "${var.iothub_failed_d2c_twin_update_rate_threshold_critical}" failed_d2c_twin_update_rate_threshold_warning = "${var.iothub_failed_d2c_twin_update_rate_threshold_warning}" failed_jobs_rate_silenced = "${var.iothub_failed_jobs_rate_silenced}" failed_jobs_rate_message = "${var.iothub_failed_jobs_rate_message}" - failed_jobs_rate_aggregator = "${var.iothub_failed_jobs_rate_aggregator}" failed_jobs_rate_timeframe = "${var.iothub_failed_jobs_rate_timeframe}" failed_jobs_rate_threshold_critical = "${var.iothub_failed_jobs_rate_threshold_critical}" failed_jobs_rate_threshold_warning = "${var.iothub_failed_jobs_rate_threshold_warning}" failed_listjobs_rate_silenced = "${var.iothub_failed_listjobs_rate_silenced}" failed_listjobs_rate_message = "${var.iothub_failed_listjobs_rate_message}" - failed_listjobs_rate_aggregator = "${var.iothub_failed_listjobs_rate_aggregator}" failed_listjobs_rate_timeframe = "${var.iothub_failed_listjobs_rate_timeframe}" failed_listjobs_rate_threshold_critical = "${var.iothub_failed_listjobs_rate_threshold_critical}" failed_listjobs_rate_threshold_warning = "${var.iothub_failed_listjobs_rate_threshold_warning}" failed_queryjobs_rate_silenced = "${var.iothub_failed_queryjobs_rate_silenced}" failed_queryjobs_rate_message = "${var.iothub_failed_queryjobs_rate_message}" - failed_queryjobs_rate_aggregator = "${var.iothub_failed_queryjobs_rate_aggregator}" failed_queryjobs_rate_timeframe = "${var.iothub_failed_queryjobs_rate_timeframe}" failed_queryjobs_rate_threshold_critical = "${var.iothub_failed_queryjobs_rate_threshold_critical}" failed_queryjobs_rate_threshold_warning = "${var.iothub_failed_queryjobs_rate_threshold_warning}" invalid_d2c_telemetry_egress_silenced = "${var.iothub_invalid_d2c_telemetry_egress_silenced}" invalid_d2c_telemetry_egress_message = "${var.iothub_invalid_d2c_telemetry_egress_message}" - invalid_d2c_telemetry_egress_aggregator = "${var.iothub_invalid_d2c_telemetry_egress_aggregator}" invalid_d2c_telemetry_egress_timeframe = "${var.iothub_invalid_d2c_telemetry_egress_timeframe}" invalid_d2c_telemetry_egress_rate_threshold_critical = "${var.iothub_invalid_d2c_telemetry_egress_rate_threshold_critical}" invalid_d2c_telemetry_egress_rate_threshold_warning = "${var.iothub_invalid_d2c_telemetry_egress_rate_threshold_warning}" orphaned_d2c_telemetry_egress_silenced = "${var.iothub_orphaned_d2c_telemetry_egress_silenced}" orphaned_d2c_telemetry_egress_message = "${var.iothub_orphaned_d2c_telemetry_egress_message}" - orphaned_d2c_telemetry_egress_aggregator = "${var.iothub_orphaned_d2c_telemetry_egress_aggregator}" orphaned_d2c_telemetry_egress_timeframe = "${var.iothub_orphaned_d2c_telemetry_egress_timeframe}" orphaned_d2c_telemetry_egress_rate_threshold_critical = "${var.iothub_orphaned_d2c_telemetry_egress_rate_threshold_critical}" orphaned_d2c_telemetry_egress_rate_threshold_warning = "${var.iothub_orphaned_d2c_telemetry_egress_rate_threshold_warning}" @@ -209,23 +188,23 @@ module "redis" { status_silenced = "${var.redis_status_silenced}" status_message = "${var.redis_status_message}" - status_aggregator = "${var.redis_status_aggregator}" + status_time_aggregator = "${var.redis_status_time_aggregator}" status_timeframe = "${var.redis_status_timeframe}" evictedkeys_limit_silenced = "${var.redis_evictedkeys_limit_silenced}" evictedkeys_limit_message = "${var.redis_evictedkeys_limit_message}" - evictedkeys_limit_aggregator = "${var.redis_evictedkeys_limit_aggregator}" + evictedkeys_limit_time_aggregator = "${var.redis_evictedkeys_limit_time_aggregator}" evictedkeys_limit_timeframe = "${var.redis_evictedkeys_limit_timeframe}" evictedkeys_limit_threshold_critical = "${var.redis_evictedkeys_limit_threshold_critical}" evictedkeys_limit_threshold_warning = "${var.redis_evictedkeys_limit_threshold_warning}" percent_processor_time_silenced = "${var.redis_percent_processor_time_silenced}" percent_processor_time_message = "${var.redis_percent_processor_time_message}" - percent_processor_time_aggregator = "${var.redis_percent_processor_time_aggregator}" + percent_processor_time_time_aggregator = "${var.redis_percent_processor_time_time_aggregator}" percent_processor_time_timeframe = "${var.redis_percent_processor_time_timeframe}" percent_processor_time_threshold_critical = "${var.redis_percent_processor_time_threshold_critical}" percent_processor_time_threshold_warning = "${var.redis_percent_processor_time_threshold_warning}" server_load_rate_silenced = "${var.redis_server_load_rate_silenced}" server_load_rate_message = "${var.redis_server_load_rate_message}" - server_load_rate_aggregator = "${var.redis_server_load_rate_aggregator}" + server_load_rate_time_aggregator = "${var.redis_server_load_rate_time_aggregator}" server_load_rate_timeframe = "${var.redis_server_load_rate_timeframe}" server_load_rate_threshold_critical = "${var.redis_server_load_rate_threshold_critical}" server_load_rate_threshold_warning = "${var.redis_server_load_rate_threshold_warning}" @@ -241,10 +220,10 @@ module "servicebus" { filter_tags_use_defaults = "${var.filter_tags_use_defaults}" filter_tags_custom = "${var.filter_tags_custom}" - status_silenced = "${var.servicebus_status_silenced}" - status_message = "${var.servicebus_status_message}" - status_timeframe = "${var.servicebus_status_timeframe}" - status_timeframe_aggregator = "${var.servicebus_status_aggregator}" + status_silenced = "${var.servicebus_status_silenced}" + status_message = "${var.servicebus_status_message}" + status_timeframe = "${var.servicebus_status_timeframe}" + status_timeframe_time_aggregator = "${var.servicebus_status_time_aggregator}" } module "sqldatabase" { @@ -259,24 +238,23 @@ module "sqldatabase" { cpu_silenced = "${var.sqldatabase_cpu_silenced}" cpu_message = "${var.sqldatabase_cpu_message}" - cpu_aggregator = "${var.sqldatabase_cpu_aggregator}" + cpu_time_aggregator = "${var.sqldatabase_cpu_time_aggregator}" cpu_timeframe = "${var.sqldatabase_cpu_timeframe}" cpu_threshold_critical = "${var.sqldatabase_cpu_threshold_critical}" cpu_threshold_warning = "${var.sqldatabase_cpu_threshold_warning}" deadlock_silenced = "${var.sqldatabase_deadlock_silenced}" deadlock_message = "${var.sqldatabase_deadlock_message}" - deadlock_aggregator = "${var.sqldatabase_deadlock_aggregator}" deadlock_timeframe = "${var.sqldatabase_deadlock_timeframe}" deadlock_threshold_critical = "${var.sqldatabase_deadlock_threshold_critical}" diskspace_silenced = "${var.sqldatabase_diskspace_silenced}" diskspace_message = "${var.sqldatabase_diskspace_message}" - diskspace_aggregator = "${var.sqldatabase_diskspace_aggregator}" + diskspace_time_aggregator = "${var.sqldatabase_diskspace_time_aggregator}" diskspace_timeframe = "${var.sqldatabase_diskspace_timeframe}" diskspace_threshold_critical = "${var.sqldatabase_diskspace_threshold_critical}" diskspace_threshold_warning = "${var.sqldatabase_diskspace_threshold_warning}" dtu_silenced = "${var.sqldatabase_dtu_silenced}" dtu_message = "${var.sqldatabase_dtu_message}" - dtu_aggregator = "${var.sqldatabase_dtu_aggregator}" + dtu_time_aggregator = "${var.sqldatabase_dtu_time_aggregator}" dtu_timeframe = "${var.sqldatabase_dtu_timeframe}" dtu_threshold_critical = "${var.sqldatabase_dtu_threshold_critical}" dtu_threshold_warning = "${var.sqldatabase_dtu_threshold_warning}" @@ -294,55 +272,55 @@ module "storage" { authorization_error_requests_silenced = "${var.storage_authorization_error_requests_silenced}" authorization_error_requests_message = "${var.storage_authorization_error_requests_message}" - authorization_error_requests_aggregator = "${var.storage_authorization_error_requests_aggregator}" + authorization_error_requests_time_aggregator = "${var.storage_authorization_error_requests_time_aggregator}" authorization_error_requests_timeframe = "${var.storage_authorization_error_requests_timeframe}" authorization_error_requests_threshold_critical = "${var.storage_authorization_error_requests_threshold_critical}" authorization_error_requests_threshold_warning = "${var.storage_authorization_error_requests_threshold_warning}" availability_silenced = "${var.storage_availability_silenced}" availability_message = "${var.storage_availability_message}" - availability_aggregator = "${var.storage_availability_aggregator}" + availability_time_aggregator = "${var.storage_availability_time_aggregator}" availability_timeframe = "${var.storage_availability_timeframe}" availability_threshold_critical = "${var.storage_availability_threshold_critical}" availability_threshold_warning = "${var.storage_availability_threshold_warning}" client_other_error_requests_silenced = "${var.storage_client_other_error_requests_silenced}" client_other_error_requests_message = "${var.storage_client_other_error_requests_message}" - client_other_error_requests_aggregator = "${var.storage_client_other_error_requests_aggregator}" + client_other_error_requests_time_aggregator = "${var.storage_client_other_error_requests_time_aggregator}" client_other_error_requests_timeframe = "${var.storage_client_other_error_requests_timeframe}" client_other_error_requests_threshold_critical = "${var.storage_client_other_error_requests_threshold_critical}" client_other_error_requests_threshold_warning = "${var.storage_client_other_error_requests_threshold_warning}" latency_silenced = "${var.storage_latency_silenced}" latency_message = "${var.storage_latency_message}" - latency_aggregator = "${var.storage_latency_aggregator}" + latency_time_aggregator = "${var.storage_latency_time_aggregator}" latency_timeframe = "${var.storage_latency_timeframe}" latency_threshold_critical = "${var.storage_latency_threshold_critical}" latency_threshold_warning = "${var.storage_latency_threshold_warning}" network_error_requests_silenced = "${var.storage_network_error_requests_silenced}" network_error_requests_message = "${var.storage_network_error_requests_message}" - network_error_requests_aggregator = "${var.storage_network_error_requests_aggregator}" + network_error_requests_time_aggregator = "${var.storage_network_error_requests_time_aggregator}" network_error_requests_timeframe = "${var.storage_network_error_requests_timeframe}" network_error_requests_threshold_critical = "${var.storage_network_error_requests_threshold_critical}" network_error_requests_threshold_warning = "${var.storage_network_error_requests_threshold_warning}" server_other_error_requests_silenced = "${var.storage_server_other_error_requests_silenced}" server_other_error_requests_message = "${var.storage_server_other_error_requests_message}" - server_other_error_requests_aggregator = "${var.storage_server_other_error_requests_aggregator}" + server_other_error_requests_time_aggregator = "${var.storage_server_other_error_requests_time_aggregator}" server_other_error_requests_timeframe = "${var.storage_server_other_error_requests_timeframe}" server_other_error_requests_threshold_critical = "${var.storage_server_other_error_requests_threshold_critical}" server_other_error_requests_threshold_warning = "${var.storage_server_other_error_requests_threshold_warning}" successful_requests_silenced = "${var.storage_successful_requests_silenced}" successful_requests_message = "${var.storage_successful_requests_message}" - successful_requests_aggregator = "${var.storage_successful_requests_aggregator}" + successful_requests_time_aggregator = "${var.storage_successful_requests_time_aggregator}" successful_requests_timeframe = "${var.storage_successful_requests_timeframe}" successful_requests_threshold_critical = "${var.storage_successful_requests_threshold_critical}" successful_requests_threshold_warning = "${var.storage_successful_requests_threshold_warning}" throttling_error_requests_silenced = "${var.storage_throttling_error_requests_silenced}" throttling_error_requests_message = "${var.storage_throttling_error_requests_message}" - throttling_error_requests_aggregator = "${var.storage_throttling_error_requests_aggregator}" + throttling_error_requests_time_aggregator = "${var.storage_throttling_error_requests_time_aggregator}" throttling_error_requests_timeframe = "${var.storage_throttling_error_requests_timeframe}" throttling_error_requests_threshold_critical = "${var.storage_throttling_error_requests_threshold_critical}" throttling_error_requests_threshold_warning = "${var.storage_throttling_error_requests_threshold_warning}" timeout_error_requests_silenced = "${var.storage_timeout_error_requests_silenced}" timeout_error_requests_message = "${var.storage_timeout_error_requests_message}" - timeout_error_requests_aggregator = "${var.storage_timeout_error_requests_aggregator}" + timeout_error_requests_time_aggregator = "${var.storage_timeout_error_requests_time_aggregator}" timeout_error_requests_timeframe = "${var.storage_timeout_error_requests_timeframe}" timeout_error_requests_threshold_critical = "${var.storage_timeout_error_requests_threshold_critical}" timeout_error_requests_threshold_warning = "${var.storage_timeout_error_requests_threshold_warning}" @@ -360,25 +338,24 @@ module "streamanalytics" { conversion_errors_silenced = "${var.streamanalytics_conversion_errors_silenced}" conversion_errors_message = "${var.streamanalytics_conversion_errors_message}" - conversion_errors_aggregator = "${var.streamanalytics_conversion_errors_aggregator}" + conversion_errors_time_aggregator = "${var.streamanalytics_conversion_errors_time_aggregator}" conversion_errors_timeframe = "${var.streamanalytics_conversion_errors_timeframe}" conversion_errors_threshold_critical = "${var.streamanalytics_conversion_errors_threshold_critical}" conversion_errors_threshold_warning = "${var.streamanalytics_conversion_errors_threshold_warning}" failed_function_requests_silenced = "${var.streamanalytics_failed_function_requests_silenced}" failed_function_requests_message = "${var.streamanalytics_failed_function_requests_message}" - failed_function_requests_aggregator = "${var.streamanalytics_failed_function_requests_aggregator}" failed_function_requests_timeframe = "${var.streamanalytics_failed_function_requests_timeframe}" failed_function_requests_threshold_critical = "${var.streamanalytics_failed_function_requests_threshold_critical}" failed_function_requests_threshold_warning = "${var.streamanalytics_failed_function_requests_threshold_warning}" runtime_errors_silenced = "${var.streamanalytics_runtime_errors_silenced}" runtime_errors_message = "${var.streamanalytics_runtime_errors_message}" - runtime_errors_aggregator = "${var.streamanalytics_runtime_errors_aggregator}" + runtime_errors_time_aggregator = "${var.streamanalytics_runtime_errors_time_aggregator}" runtime_errors_timeframe = "${var.streamanalytics_runtime_errors_timeframe}" runtime_errors_threshold_critical = "${var.streamanalytics_runtime_errors_threshold_critical}" runtime_errors_threshold_warning = "${var.streamanalytics_runtime_errors_threshold_warning}" su_utilization_silenced = "${var.streamanalytics_su_utilization_silenced}" su_utilization_message = "${var.streamanalytics_su_utilization_message}" - su_utilization_aggregator = "${var.streamanalytics_su_utilization_aggregator}" + su_utilization_time_aggregator = "${var.streamanalytics_su_utilization_time_aggregator}" su_utilization_timeframe = "${var.streamanalytics_su_utilization_timeframe}" su_utilization_threshold_critical = "${var.streamanalytics_su_utilization_threshold_critical}" su_utilization_threshold_warning = "${var.streamanalytics_su_utilization_threshold_warning}" diff --git a/cloud/azure/redis/README.md b/cloud/azure/redis/README.md index a7786c5..a360b29 100644 --- a/cloud/azure/redis/README.md +++ b/cloud/azure/redis/README.md @@ -29,30 +29,30 @@ Inputs |------|-------------|:----:|:-----:|:-----:| | delay | Delay in seconds for the metric evaluation | string | `900` | no | | environment | Architecture environment | string | - | yes | -| evictedkeys_limit_aggregator | Monitor aggregator for Redis evicted keys [available values: min, max, sum or avg] | string | `avg` | no | | evictedkeys_limit_message | Custom message for Redis evicted keys monitor | string | `` | no | | evictedkeys_limit_silenced | Groups to mute for Redis evicted keys monitor | map | `` | no | | evictedkeys_limit_threshold_critical | Evicted keys limit (critical threshold) | string | `100` | no | | evictedkeys_limit_threshold_warning | Evicted keys limit (warning threshold) | string | `0` | no | +| evictedkeys_limit_time_aggregator | Monitor aggregator for Redis evicted keys [available values: min, max or avg] | string | `avg` | no | | evictedkeys_limit_timeframe | Monitor timeframe for Redis evicted keys [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | | message | Message sent when a Redis monitor is triggered | string | - | yes | -| percent_processor_time_aggregator | Monitor aggregator for Redis processor [available values: min, max, sum or avg] | string | `avg` | no | | percent_processor_time_message | Custom message for Redis processor monitor | string | `` | no | | percent_processor_time_silenced | Groups to mute for Redis processor monitor | map | `` | no | | percent_processor_time_threshold_critical | Processor time percent (critical threshold) | string | `80` | no | | percent_processor_time_threshold_warning | Processor time percent (warning threshold) | string | `60` | no | +| percent_processor_time_time_aggregator | Monitor aggregator for Redis processor [available values: min, max or avg] | string | `avg` | no | | percent_processor_time_timeframe | Monitor timeframe for Redis processor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| server_load_rate_aggregator | Monitor aggregator for Redis server load [available values: min, max, sum or avg] | string | `avg` | no | | server_load_rate_message | Custom message for Redis server load monitor | string | `` | no | | server_load_rate_silenced | Groups to mute for Redis server load monitor | map | `` | no | | server_load_rate_threshold_critical | Server CPU load rate (critical threshold) | string | `90` | no | | server_load_rate_threshold_warning | Server CPU load rate (warning threshold) | string | `70` | no | +| server_load_rate_time_aggregator | Monitor aggregator for Redis server load [available values: min, max or avg] | string | `avg` | no | | server_load_rate_timeframe | Monitor timeframe for Redis server load [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| status_aggregator | Monitor aggregator for Redis status [available values: min, max, sum or avg] | string | `avg` | no | | status_message | Custom message for Redis status monitor | string | `` | no | | status_silenced | Groups to mute for Redis status monitor | map | `` | no | +| status_time_aggregator | Monitor aggregator for Redis status [available values: min, max or avg] | string | `avg` | no | | status_timeframe | Monitor timeframe for Redis status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | Related documentation diff --git a/cloud/azure/redis/inputs.tf b/cloud/azure/redis/inputs.tf index 372bfae..4b14102 100644 --- a/cloud/azure/redis/inputs.tf +++ b/cloud/azure/redis/inputs.tf @@ -37,8 +37,8 @@ variable "status_message" { default = "" } -variable "status_aggregator" { - description = "Monitor aggregator for Redis status [available values: min, max, sum or avg]" +variable "status_time_aggregator" { + description = "Monitor aggregator for Redis status [available values: min, max or avg]" type = "string" default = "avg" } @@ -61,8 +61,8 @@ variable "evictedkeys_limit_message" { default = "" } -variable "evictedkeys_limit_aggregator" { - description = "Monitor aggregator for Redis evicted keys [available values: min, max, sum or avg]" +variable "evictedkeys_limit_time_aggregator" { + description = "Monitor aggregator for Redis evicted keys [available values: min, max or avg]" type = "string" default = "avg" } @@ -95,8 +95,8 @@ variable "percent_processor_time_message" { default = "" } -variable "percent_processor_time_aggregator" { - description = "Monitor aggregator for Redis processor [available values: min, max, sum or avg]" +variable "percent_processor_time_time_aggregator" { + description = "Monitor aggregator for Redis processor [available values: min, max or avg]" type = "string" default = "avg" } @@ -129,8 +129,8 @@ variable "server_load_rate_message" { default = "" } -variable "server_load_rate_aggregator" { - description = "Monitor aggregator for Redis server load [available values: min, max, sum or avg]" +variable "server_load_rate_time_aggregator" { + description = "Monitor aggregator for Redis server load [available values: min, max or avg]" type = "string" default = "avg" } diff --git a/cloud/azure/redis/monitors-azure-redis.tf b/cloud/azure/redis/monitors-azure-redis.tf index 8c8dcf0..274f8f9 100644 --- a/cloud/azure/redis/monitors-azure-redis.tf +++ b/cloud/azure/redis/monitors-azure-redis.tf @@ -11,8 +11,10 @@ resource "datadog_monitor" "status" { message = "${coalesce(var.status_message, var.message)}" query = < ${var.evictedkeys_limit_threshold_critical} EOF @@ -68,8 +70,8 @@ resource "datadog_monitor" "percent_processor_time" { message = "${coalesce(var.percent_processor_time_message, var.message)}" query = < ${var.percent_processor_time_threshold_critical} EOF @@ -100,8 +102,8 @@ resource "datadog_monitor" "server_load" { message = "${coalesce(var.server_load_rate_message, var.message)}" query = < ${var.server_load_rate_threshold_critical} EOF diff --git a/cloud/azure/servicebus/README.md b/cloud/azure/servicebus/README.md index 461ee40..672193d 100644 --- a/cloud/azure/servicebus/README.md +++ b/cloud/azure/servicebus/README.md @@ -32,7 +32,7 @@ Inputs | status_message | Custom message for Service Bus status monitor | string | `` | no | | status_silenced | Groups to mute for Service Bus status monitor | map | `` | no | | status_timeframe | Monitor timeframe for Service Bus status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | -| status_aggregator | Monitor aggregator for Service Bus status [available values: min, max, sum or avg] | string | `min` | no | +| status_time_aggregator | Monitor aggregator for Service Bus status [available values: min, max or avg] | string | `min` | no | Related documentation --------------------- diff --git a/cloud/azure/servicebus/inputs.tf b/cloud/azure/servicebus/inputs.tf index 6ea0587..55c2a12 100644 --- a/cloud/azure/servicebus/inputs.tf +++ b/cloud/azure/servicebus/inputs.tf @@ -37,8 +37,8 @@ variable "status_message" { default = "" } -variable "status_aggregator" { - description = "Monitor aggregator for Service Bus status [available values: min, max, sum or avg]" +variable "status_time_aggregator" { + description = "Monitor aggregator for Service Bus status [available values: min, max or avg]" type = "string" default = "min" } diff --git a/cloud/azure/servicebus/monitors-service-bus.tf b/cloud/azure/servicebus/monitors-service-bus.tf index 607d99b..a72e27f 100644 --- a/cloud/azure/servicebus/monitors-service-bus.tf +++ b/cloud/azure/servicebus/monitors-service-bus.tf @@ -11,8 +11,8 @@ resource "datadog_monitor" "servicebus_status" { message = "${coalesce(var.status_message, var.message)}" query = <` | no | | cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no | | cpu_threshold_warning | CPU usage in percent (warning threshold) | string | `80` | no | | cpu_timeframe | Monitor timeframe for SQL CPU [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | -| deadlock_aggregator | Monitor aggregator for SQL Deadlock [available values: min, max, sum or avg] | string | `sum` | no | | deadlock_message | Custom message for SQL Deadlock monitor | string | `` | no | | deadlock_silenced | Groups to mute for SQL Deadlock monitor | map | `` | no | | deadlock_threshold_critical | Amount of Deadlocks (critical threshold) | string | `1` | no | | deadlock_timeframe | Monitor timeframe for SQL Deadlock [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | delay | Delay in seconds for the metric evaluation | string | `900` | no | -| diskspace_aggregator | Monitor aggregator for SQL disk space [available values: min, max, sum or avg] | string | `avg` | no | +| diskspace_time_aggregator | Monitor aggregator for SQL disk space [available values: min, max or avg] | string | `avg` | no | | diskspace_message | Custom message for SQL disk space monitor | string | `` | no | | diskspace_silenced | Groups to mute for SQL disk space monitor | map | `` | no | | diskspace_threshold_critical | Disk space used in percent (critical threshold) | string | `90` | no | | diskspace_threshold_warning | Disk space used in percent (warning threshold) | string | `80` | no | | diskspace_timeframe | Monitor timeframe for SQL disk space [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | -| dtu_aggregator | Monitor aggregator for SQL DTU [available values: min, max, sum or avg] | string | `avg` | no | +| dtu_time_aggregator | Monitor aggregator for SQL DTU [available values: min, max or avg] | string | `avg` | no | | dtu_message | Custom message for SQL DTU monitor | string | `` | no | | dtu_silenced | Groups to mute for SQL DTU monitor | map | `` | no | | dtu_threshold_critical | Amount of DTU used (critical threshold) | string | `90` | no | diff --git a/cloud/azure/sql-database/inputs.tf b/cloud/azure/sql-database/inputs.tf index 354c36a..4ce6680 100644 --- a/cloud/azure/sql-database/inputs.tf +++ b/cloud/azure/sql-database/inputs.tf @@ -37,8 +37,8 @@ variable "cpu_message" { default = "" } -variable "cpu_aggregator" { - description = "Monitor aggregator for SQL CPU [available values: min, max, sum or avg]" +variable "cpu_time_aggregator" { + description = "Monitor aggregator for SQL CPU [available values: min, max or avg]" type = "string" default = "avg" } @@ -71,8 +71,8 @@ variable "diskspace_message" { default = "" } -variable "diskspace_aggregator" { - description = "Monitor aggregator for SQL disk space [available values: min, max, sum or avg]" +variable "diskspace_time_aggregator" { + description = "Monitor aggregator for SQL disk space [available values: min, max or avg]" type = "string" default = "avg" } @@ -105,8 +105,8 @@ variable "dtu_message" { default = "" } -variable "dtu_aggregator" { - description = "Monitor aggregator for SQL DTU [available values: min, max, sum or avg]" +variable "dtu_time_aggregator" { + description = "Monitor aggregator for SQL DTU [available values: min, max or avg]" type = "string" default = "avg" } @@ -139,12 +139,6 @@ variable "deadlock_message" { default = "" } -variable "deadlock_aggregator" { - description = "Monitor aggregator for SQL Deadlock [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "deadlock_timeframe" { description = "Monitor timeframe for SQL Deadlock [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/azure/sql-database/monitors-sql-database-basics.tf b/cloud/azure/sql-database/monitors-sql-database-basics.tf index 2413763..089e960 100644 --- a/cloud/azure/sql-database/monitors-sql-database-basics.tf +++ b/cloud/azure/sql-database/monitors-sql-database-basics.tf @@ -11,8 +11,8 @@ resource "datadog_monitor" "sql-database_cpu_90_15min" { message = "${coalesce(var.cpu_message, var.message)}" query = < ${var.cpu_threshold_critical} EOF @@ -44,8 +44,8 @@ resource "datadog_monitor" "sql-database_free_space_low" { type = "metric alert" query = < ${var.diskspace_threshold_critical} EOF @@ -76,7 +76,7 @@ resource "datadog_monitor" "sql-database_dtu_consumption_high" { type = "metric alert" query = < ${var.dtu_threshold_critical} EOF @@ -108,8 +108,8 @@ resource "datadog_monitor" "sql-database_deadlocks_count" { type = "metric alert" query = < ${var.deadlock_threshold_critical} EOF diff --git a/cloud/azure/storage/README.md b/cloud/azure/storage/README.md index 2973151..72cf5ae 100644 --- a/cloud/azure/storage/README.md +++ b/cloud/azure/storage/README.md @@ -32,19 +32,19 @@ Inputs | Name | Description | Type | Default | Required | |------|-------------|:----:|:-----:|:-----:| -| authorization_error_requests_aggregator | Monitor aggregator for Storage authorization errors [available values: min, max, sum or avg] | string | `avg` | no | +| authorization_error_requests_time_aggregator | Monitor aggregator for Storage authorization errors [available values: min, max, sum or avg] | string | `avg` | no | | authorization_error_requests_message | Custom message for Storage authorization errors monitor | string | `` | no | | authorization_error_requests_silenced | Groups to mute for Storage authorization errors monitor | map | `` | no | | authorization_error_requests_threshold_critical | Maximum acceptable percent of authorization error requests for a storage | string | `90` | no | | authorization_error_requests_threshold_warning | Warning regarding acceptable percent of authorization error requests for a storage | string | `50` | no | | authorization_error_requests_timeframe | Monitor timeframe for Storage authorization errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| availability_aggregator | Monitor aggregator for Storage availability [available values: min, max, sum or avg] | string | `avg` | no | +| availability_time_aggregator | Monitor aggregator for Storage availability [available values: min, max or avg] | string | `avg` | no | | availability_message | Custom message for Storage availability monitor | string | `` | no | | availability_silenced | Groups to mute for Storage availability monitor | map | `` | no | | availability_threshold_critical | Minimum acceptable percent of availability for a storage | string | `50` | no | | availability_threshold_warning | Warning regarding acceptable percent of availability for a storage | string | `90` | no | | availability_timeframe | Monitor timeframe for Storage availability [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| client_other_error_requests_aggregator | Monitor aggregator for Storage other errors [available values: min, max, sum or avg] | string | `avg` | no | +| client_other_error_requests_time_aggregator | Monitor aggregator for Storage other errors [available values: min, max or avg] | string | `avg` | no | | client_other_error_requests_message | Custom message for Storage other errors monitor | string | `` | no | | client_other_error_requests_silenced | Groups to mute for Storage other errors monitor | map | `` | no | | client_other_error_requests_threshold_critical | Maximum acceptable percent of client other error requests for a storage | string | `90` | no | @@ -54,38 +54,38 @@ Inputs | environment | Architecture environment | string | - | yes | | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | -| latency_aggregator | Monitor aggregator for Storage latency [available values: min, max, sum or avg] | string | `min` | no | +| latency_time_aggregator | Monitor aggregator for Storage latency [available values: min, max or avg] | string | `min` | no | | latency_message | Custom message for Storage latency monitor | string | `` | no | | latency_silenced | Groups to mute for Storage latency monitor | map | `` | no | | latency_threshold_critical | Maximum acceptable end to end latency (ms) for a storage | string | `2000` | no | | latency_threshold_warning | Warning regarding acceptable end to end latency (ms) for a storage | string | `1000` | no | | latency_timeframe | Monitor timeframe for Storage latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | message | Message sent when a Redis monitor is triggered | string | - | yes | -| network_error_requests_aggregator | Monitor aggregator for Storage network errors [available values: min, max, sum or avg] | string | `avg` | no | +| network_error_requests_time_aggregator | Monitor aggregator for Storage network errors [available values: min, max or avg] | string | `avg` | no | | network_error_requests_message | Custom message for Storage network errors monitor | string | `` | no | | network_error_requests_silenced | Groups to mute for Storage network errors monitor | map | `` | no | | network_error_requests_threshold_critical | Maximum acceptable percent of network error requests for a storage | string | `90` | no | | network_error_requests_threshold_warning | Warning regarding acceptable percent of network error requests for a storage | string | `50` | no | | network_error_requests_timeframe | Monitor timeframe for Storage network errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| server_other_error_requests_aggregator | Monitor aggregator for Storage other errors [available values: min, max, sum or avg] | string | `avg` | no | +| server_other_error_requests_time_aggregator | Monitor aggregator for Storage other errors [available values: min, max or avg] | string | `avg` | no | | server_other_error_requests_message | Custom message for Storage server other errors monitor | string | `` | no | | server_other_error_requests_silenced | Groups to mute for Storage server other errors monitor | map | `` | no | | server_other_error_requests_threshold_critical | Maximum acceptable percent of server other error requests for a storage | string | `90` | no | | server_other_error_requests_threshold_warning | Warning regarding acceptable percent of server other error requests for a storage | string | `50` | no | | server_other_error_requests_timeframe | Monitor timeframe for Storage server other errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| successful_requests_aggregator | Monitor aggregator for Storage sucessful requests [available values: min, max, sum or avg] | string | `avg` | no | +| successful_requests_time_aggregator | Monitor aggregator for Storage sucessful requests [available values: min, max or avg] | string | `avg` | no | | successful_requests_message | Custom message for Storage sucessful requests monitor | string | `` | no | | successful_requests_silenced | Groups to mute for Storage sucessful requests monitor | map | `` | no | | successful_requests_threshold_critical | Minimum acceptable percent of successful requests for a storage | string | `10` | no | | successful_requests_threshold_warning | Warning regarding acceptable percent of successful requests for a storage | string | `30` | no | | successful_requests_timeframe | Monitor timeframe for Storage sucessful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| throttling_error_requests_aggregator | Monitor aggregator for Storage throttling errors [available values: min, max, sum or avg] | string | `avg` | no | +| throttling_error_requests_time_aggregator | Monitor aggregator for Storage throttling errors [available values: min, max or avg] | string | `avg` | no | | throttling_error_requests_message | Custom message for Storage throttling error monitor | string | `` | no | | throttling_error_requests_silenced | Groups to mute for Storage throttling error monitor | map | `` | no | | throttling_error_requests_threshold_critical | Maximum acceptable percent of throttling error requests for a storage | string | `90` | no | | throttling_error_requests_threshold_warning | Warning regarding acceptable percent of throttling error requests for a storage | string | `50` | no | | throttling_error_requests_timeframe | Monitor timeframe for Storage throttling errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| timeout_error_requests_aggregator | Monitor aggregator for Storage timeout [available values: min, max, sum or avg] | string | `avg` | no | +| timeout_error_requests_time_aggregator | Monitor aggregator for Storage timeout [available values: min, max or avg] | string | `avg` | no | | timeout_error_requests_message | Custom message for Storage timeout monitor | string | `` | no | | timeout_error_requests_silenced | Groups to mute for Storage timeout monitor | map | `` | no | | timeout_error_requests_threshold_critical | Maximum acceptable percent of timeout error requests for a storage | string | `90` | no | diff --git a/cloud/azure/storage/inputs.tf b/cloud/azure/storage/inputs.tf index 75b6379..72668a4 100644 --- a/cloud/azure/storage/inputs.tf +++ b/cloud/azure/storage/inputs.tf @@ -37,8 +37,8 @@ variable "availability_message" { default = "" } -variable "availability_aggregator" { - description = "Monitor aggregator for Storage availability [available values: min, max, sum or avg]" +variable "availability_time_aggregator" { + description = "Monitor aggregator for Storage availability [available values: min, max or avg]" type = "string" default = "avg" } @@ -71,8 +71,8 @@ variable "successful_requests_message" { default = "" } -variable "successful_requests_aggregator" { - description = "Monitor aggregator for Storage sucessful requests [available values: min, max, sum or avg]" +variable "successful_requests_time_aggregator" { + description = "Monitor aggregator for Storage sucessful requests [available values: min, max or avg]" type = "string" default = "avg" } @@ -105,8 +105,8 @@ variable "latency_message" { default = "" } -variable "latency_aggregator" { - description = "Monitor aggregator for Storage latency [available values: min, max, sum or avg]" +variable "latency_time_aggregator" { + description = "Monitor aggregator for Storage latency [available values: min, max or avg]" type = "string" default = "min" } @@ -139,8 +139,8 @@ variable "timeout_error_requests_message" { default = "" } -variable "timeout_error_requests_aggregator" { - description = "Monitor aggregator for Storage timeout [available values: min, max, sum or avg]" +variable "timeout_error_requests_time_aggregator" { + description = "Monitor aggregator for Storage timeout [available values: min, max or avg]" type = "string" default = "avg" } @@ -173,8 +173,8 @@ variable "network_error_requests_message" { default = "" } -variable "network_error_requests_aggregator" { - description = "Monitor aggregator for Storage network errors [available values: min, max, sum or avg]" +variable "network_error_requests_time_aggregator" { + description = "Monitor aggregator for Storage network errors [available values: min, max or avg]" type = "string" default = "avg" } @@ -207,8 +207,8 @@ variable "throttling_error_requests_message" { default = "" } -variable "throttling_error_requests_aggregator" { - description = "Monitor aggregator for Storage throttling errors [available values: min, max, sum or avg]" +variable "throttling_error_requests_time_aggregator" { + description = "Monitor aggregator for Storage throttling errors [available values: min, max or avg]" type = "string" default = "avg" } @@ -241,8 +241,8 @@ variable "server_other_error_requests_message" { default = "" } -variable "server_other_error_requests_aggregator" { - description = "Monitor aggregator for Storage other errors [available values: min, max, sum or avg]" +variable "server_other_error_requests_time_aggregator" { + description = "Monitor aggregator for Storage other errors [available values: min, max or avg]" type = "string" default = "avg" } @@ -275,8 +275,8 @@ variable "client_other_error_requests_message" { default = "" } -variable "client_other_error_requests_aggregator" { - description = "Monitor aggregator for Storage other errors [available values: min, max, sum or avg]" +variable "client_other_error_requests_time_aggregator" { + description = "Monitor aggregator for Storage other errors [available values: min, max or avg]" type = "string" default = "avg" } @@ -309,8 +309,8 @@ variable "authorization_error_requests_message" { default = "" } -variable "authorization_error_requests_aggregator" { - description = "Monitor aggregator for Storage authorization errors [available values: min, max, sum or avg]" +variable "authorization_error_requests_time_aggregator" { + description = "Monitor aggregator for Storage authorization errors [available values: min, max or avg]" type = "string" default = "avg" } diff --git a/cloud/azure/storage/monitors-azure-storage.tf b/cloud/azure/storage/monitors-azure-storage.tf index 8ae7e08..71f8870 100644 --- a/cloud/azure/storage/monitors-azure-storage.tf +++ b/cloud/azure/storage/monitors-azure-storage.tf @@ -11,8 +11,8 @@ resource "datadog_monitor" "availability" { message = "${coalesce(var.availability_message, var.message)}" query = < ${var.latency_threshold_critical} EOF @@ -104,8 +104,8 @@ resource "datadog_monitor" "timeout_error_requests" { message = "${coalesce(var.timeout_error_requests_message, var.message)}" query = < ${var.timeout_error_requests_threshold_critical} EOF @@ -135,8 +135,8 @@ resource "datadog_monitor" "network_error_requests" { message = "${coalesce(var.network_error_requests_message, var.message)}" query = < ${var.network_error_requests_threshold_critical} EOF @@ -166,8 +166,8 @@ resource "datadog_monitor" "throttling_error_requests" { message = "${coalesce(var.throttling_error_requests_message, var.message)}" query = < ${var.throttling_error_requests_threshold_critical} EOF @@ -197,8 +197,8 @@ resource "datadog_monitor" "server_other_error_requests" { message = "${coalesce(var.server_other_error_requests_message, var.message)}" query = < ${var.server_other_error_requests_threshold_critical} EOF @@ -228,8 +228,8 @@ resource "datadog_monitor" "client_other_error_requests" { message = "${coalesce(var.client_other_error_requests_message, var.message)}" query = < ${var.client_other_error_requests_threshold_critical} EOF @@ -259,8 +259,8 @@ resource "datadog_monitor" "authorization_error_requests" { message = "${coalesce(var.authorization_error_requests_message, var.message)}" query = < ${var.authorization_error_requests_threshold_critical} EOF diff --git a/cloud/azure/stream-analytics/README.md b/cloud/azure/stream-analytics/README.md index ddf7441..f848f20 100644 --- a/cloud/azure/stream-analytics/README.md +++ b/cloud/azure/stream-analytics/README.md @@ -18,15 +18,14 @@ Inputs | Name | Description | Type | Default | Required | |------|-------------|:----:|:-----:|:-----:| -| conversion_errors_aggregator | Monitor aggregator for Stream Analytics conversion errors [available values: min, max, sum or avg] | string | `avg` | no | | conversion_errors_message | Custom message for Stream Analytics conversion errors monitor | string | `` | no | | conversion_errors_silenced | Groups to mute for Stream Analytics conversion errors monitor | map | `` | no | | conversion_errors_threshold_critical | Conversion errors limit (critical threshold) | string | `10` | no | | conversion_errors_threshold_warning | Conversion errors limit (warning threshold) | string | `0` | no | +| conversion_errors_time_aggregator | Monitor aggregator for Stream Analytics conversion errors [available values: min, max or avg] | string | `avg` | no | | conversion_errors_timeframe | Monitor timeframe for Stream Analytics conversion errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | delay | Delay in seconds for the metric evaluation | string | `900` | no | | environment | Architecture environment | string | - | yes | -| failed_function_requests_aggregator | Monitor aggregator for Stream Analytics failed requests [available values: min, max, sum or avg] | string | `sum` | no | | failed_function_requests_message | Custom message for Stream Analytics failed requests monitor | string | `` | no | | failed_function_requests_silenced | Groups to mute for Stream Analytics failed requests monitor | map | `` | no | | failed_function_requests_threshold_critical | Failed Function Request rate limit (critical threshold) | string | `10` | no | @@ -35,21 +34,21 @@ Inputs | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | | message | Message sent when a Redis monitor is triggered | string | - | yes | -| runtime_errors_aggregator | Monitor aggregator for Stream Analytics runtime errors [available values: min, max, sum or avg] | string | `avg` | no | | runtime_errors_message | Custom message for Stream Analytics runtime errors monitor | string | `` | no | | runtime_errors_silenced | Groups to mute for Stream Analytics runtime errors monitor | map | `` | no | | runtime_errors_threshold_critical | Runtime errors limit (critical threshold) | string | `10` | no | | runtime_errors_threshold_warning | Runtime errors limit (warning threshold) | string | `0` | no | +| runtime_errors_time_aggregator | Monitor aggregator for Stream Analytics runtime errors [available values: min, max or avg] | string | `avg` | no | | runtime_errors_timeframe | Monitor timeframe for Stream Analytics runtime errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| status_aggregator | Monitor aggregator for Stream Analytics status [available values: min, max, sum or avg] | string | `avg` | no | | status_message | Custom message for Stream Analytics status monitor | string | `` | no | | status_silenced | Groups to mute for Stream Analytics status monitor | map | `` | no | +| status_time_aggregator | Monitor aggregator for Stream Analytics status [available values: min, max or avg] | string | `avg` | no | | status_timeframe | Monitor timeframe for Stream Analytics status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| su_utilization_aggregator | Monitor aggregator for Stream Analytics utilization [available values: min, max, sum or avg] | string | `avg` | no | | su_utilization_message | Custom message for Stream Analytics utilization monitor | string | `` | no | | su_utilization_silenced | Groups to mute for Stream Analytics utilization monitor | map | `` | no | | su_utilization_threshold_critical | Streaming Unit utilization rate limit (critical threshold) | string | `80` | no | | su_utilization_threshold_warning | Streaming Unit utilization rate limit (warning threshold) | string | `60` | no | +| su_utilization_time_aggregator | Monitor aggregator for Stream Analytics utilization [available values: min, max or avg] | string | `avg` | no | | su_utilization_timeframe | Monitor timeframe for Stream Analytics utilization [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | Related documentation diff --git a/cloud/azure/stream-analytics/inputs.tf b/cloud/azure/stream-analytics/inputs.tf index 6878bde..2e07ded 100644 --- a/cloud/azure/stream-analytics/inputs.tf +++ b/cloud/azure/stream-analytics/inputs.tf @@ -37,8 +37,8 @@ variable "status_message" { default = "" } -variable "status_aggregator" { - description = "Monitor aggregator for Stream Analytics status [available values: min, max, sum or avg]" +variable "status_time_aggregator" { + description = "Monitor aggregator for Stream Analytics status [available values: min, max or avg]" type = "string" default = "avg" } @@ -61,8 +61,8 @@ variable "su_utilization_message" { default = "" } -variable "su_utilization_aggregator" { - description = "Monitor aggregator for Stream Analytics utilization [available values: min, max, sum or avg]" +variable "su_utilization_time_aggregator" { + description = "Monitor aggregator for Stream Analytics utilization [available values: min, max or avg]" type = "string" default = "avg" } @@ -95,12 +95,6 @@ variable "failed_function_requests_message" { default = "" } -variable "failed_function_requests_aggregator" { - description = "Monitor aggregator for Stream Analytics failed requests [available values: min, max, sum or avg]" - type = "string" - default = "sum" -} - variable "failed_function_requests_timeframe" { description = "Monitor timeframe for Stream Analytics failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" @@ -129,8 +123,8 @@ variable "conversion_errors_message" { default = "" } -variable "conversion_errors_aggregator" { - description = "Monitor aggregator for Stream Analytics conversion errors [available values: min, max, sum or avg]" +variable "conversion_errors_time_aggregator" { + description = "Monitor aggregator for Stream Analytics conversion errors [available values: min, max or avg]" type = "string" default = "avg" } @@ -163,8 +157,8 @@ variable "runtime_errors_message" { default = "" } -variable "runtime_errors_aggregator" { - description = "Monitor aggregator for Stream Analytics runtime errors [available values: min, max, sum or avg]" +variable "runtime_errors_time_aggregator" { + description = "Monitor aggregator for Stream Analytics runtime errors [available values: min, max or avg]" type = "string" default = "avg" } diff --git a/cloud/azure/stream-analytics/monitors-stream-analytics.tf b/cloud/azure/stream-analytics/monitors-stream-analytics.tf index 693b4f2..b14d31f 100644 --- a/cloud/azure/stream-analytics/monitors-stream-analytics.tf +++ b/cloud/azure/stream-analytics/monitors-stream-analytics.tf @@ -11,7 +11,9 @@ resource "datadog_monitor" "status" { message = "${coalesce(var.status_message, var.message)}" query = < ${var.su_utilization_threshold_critical} EOF @@ -68,9 +70,9 @@ resource "datadog_monitor" "failed_function_requests" { message = "${coalesce(var.failed_function_requests_message, var.message)}" query = < ${var.failed_function_requests_threshold_critical} EOF @@ -101,8 +103,8 @@ resource "datadog_monitor" "conversion_errors" { message = "${coalesce(var.conversion_errors_message, var.message)}" query = < ${var.conversion_errors_threshold_critical} EOF @@ -133,8 +135,8 @@ resource "datadog_monitor" "runtime_errors" { message = "${coalesce(var.runtime_errors_message, var.message)}" query = < ${var.runtime_errors_threshold_critical} EOF From 9a26a51284a8db1c146bd0c131cbf3f993d4c440 Mon Sep 17 00:00:00 2001 From: Alexandre Gaillet Date: Wed, 23 May 2018 11:13:01 +0200 Subject: [PATCH 13/21] MON-191 - Space aggregator hard coded for mongodb, php-fpm and systemd monitors --- databases/mongodb/README.md | 2 +- databases/mongodb/inputs.tf | 4 ++-- databases/mongodb/monitors-mongo.tf | 4 ++-- middleware/php-fpm/README.md | 2 +- middleware/php-fpm/inputs.tf | 4 ++-- middleware/php-fpm/monitors-fpm.tf | 8 ++++---- system/generic/README.md | 10 +++++----- system/generic/inputs.tf | 20 ++++++++++---------- system/generic/monitors-system.tf | 26 +++++++++++++------------- 9 files changed, 40 insertions(+), 40 deletions(-) diff --git a/databases/mongodb/README.md b/databases/mongodb/README.md index c5d78e2..cbb2a64 100644 --- a/databases/mongodb/README.md +++ b/databases/mongodb/README.md @@ -79,7 +79,7 @@ Inputs | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | | message | Message sent when an alert is triggered | string | - | yes | -| mongodb_replicaset_aggregator | Monitor aggregator for Mongodb replicaset [available values: min, max, sum or avg] | string | `avg` | no | +| mongodb_replicaset_time_aggregator | Monitor aggregator for Mongodb replicaset [available values: min, max or avg] | string | `avg` | no | | mongodb_replicaset_message | Custom message for Mongodb replicaset monitor | string | `` | no | | mongodb_replicaset_silenced | Groups to mute for Mongodb replicaset monitor | map | `` | no | | mongodb_replicaset_timeframe | Monitor timeframe for Mongodb replicaset [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | diff --git a/databases/mongodb/inputs.tf b/databases/mongodb/inputs.tf index b67f68c..a3d8f59 100644 --- a/databases/mongodb/inputs.tf +++ b/databases/mongodb/inputs.tf @@ -36,8 +36,8 @@ variable "mongodb_replicaset_message" { default = "" } -variable "mongodb_replicaset_aggregator" { - description = "Monitor aggregator for Mongodb replicaset [available values: min, max, sum or avg]" +variable "mongodb_replicaset_time_aggregator" { + description = "Monitor aggregator for Mongodb replicaset [available values: min, max or avg]" type = "string" default = "avg" } diff --git a/databases/mongodb/monitors-mongo.tf b/databases/mongodb/monitors-mongo.tf index edac73d..aaa2549 100644 --- a/databases/mongodb/monitors-mongo.tf +++ b/databases/mongodb/monitors-mongo.tf @@ -11,8 +11,8 @@ resource "datadog_monitor" "mongodb_replicaset_state" { message = "${coalesce(var.mongodb_replicaset_message, var.message)}" query = <` | no | | php_fpm_busy_threshold_critical | php fpm busy critical threshold | string | `0.9` | no | diff --git a/middleware/php-fpm/inputs.tf b/middleware/php-fpm/inputs.tf index d9946c0..c35f5dc 100644 --- a/middleware/php-fpm/inputs.tf +++ b/middleware/php-fpm/inputs.tf @@ -38,8 +38,8 @@ variable "php_fpm_busy_message" { default = "" } -variable "php_fpm_busy_aggregator" { - description = "Monitor aggregator for PHP FPM busy worker [available values: min, max, sum or avg]" +variable "php_fpm_busy_time_aggregator" { + description = "Monitor aggregator for PHP FPM busy worker [available values: min, max or avg]" type = "string" default = "avg" } diff --git a/middleware/php-fpm/monitors-fpm.tf b/middleware/php-fpm/monitors-fpm.tf index 51e8ec0..8273490 100644 --- a/middleware/php-fpm/monitors-fpm.tf +++ b/middleware/php-fpm/monitors-fpm.tf @@ -13,10 +13,10 @@ resource "datadog_monitor" "datadog_php_fpm_connect_idle" { type = "metric alert" query = < ${var.php_fpm_busy_threshold_critical} EOF diff --git a/system/generic/README.md b/system/generic/README.md index 1401a7d..05b4268 100644 --- a/system/generic/README.md +++ b/system/generic/README.md @@ -28,13 +28,13 @@ Inputs | Name | Description | Type | Default | Required | |------|-------------|:----:|:-----:|:-----:| -| cpu_high_aggregator | Monitor aggregator for CPU high [available values: min, max, sum or avg] | string | `min` | no | +| cpu_high_time_aggregator | Monitor aggregator for CPU high [available values: min, max or avg] | string | `min` | no | | cpu_high_message | Custom message for CPU high monitor | string | `` | no | | cpu_high_silenced | Groups to mute for CPU high monitor | map | `` | no | | cpu_high_threshold_critical | CPU high critical threshold | string | `95` | no | | cpu_high_threshold_warning | CPU high warning threshold | string | `80` | no | | cpu_high_timeframe | Monitor timeframe for CPU high [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| cpu_load_aggregator | Monitor aggregator for CPU load ratio [available values: min, max, sum or avg] | string | `min` | no | +| cpu_load_time_aggregator | Monitor aggregator for CPU load ratio [available values: min, max or avg] | string | `min` | no | | cpu_load_message | Custom message for CPU load ratio monitor | string | `` | no | | cpu_load_silenced | Groups to mute for CPU load ratio monitor | map | `` | no | | cpu_load_threshold_critical | CPU load ratio critical threshold | string | `4` | no | @@ -44,19 +44,19 @@ Inputs | environment | Architecture Environment | string | - | yes | | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | -| free_disk_inodes_aggregator | Monitor aggregator for Free disk inodes [available values: min, max, sum or avg] | string | `min` | no | +| free_disk_inodes_time_aggregator | Monitor aggregator for Free disk inodes [available values: min, max or avg] | string | `min` | no | | free_disk_inodes_message | Custom message for Free disk inodes monitor | string | `` | no | | free_disk_inodes_silenced | Groups to mute for Free disk inodes monitor | map | `` | no | | free_disk_inodes_threshold_critical | Free disk space critical threshold | string | `5` | no | | free_disk_inodes_threshold_warning | Free disk space warning threshold | string | `10` | no | | free_disk_inodes_timeframe | Monitor timeframe for Free disk inodes [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| free_disk_space_aggregator | Monitor aggregator for Free diskspace [available values: min, max, sum or avg] | string | `min` | no | +| free_disk_space_time_aggregator | Monitor aggregator for Free diskspace [available values: min, max or avg] | string | `min` | no | | free_disk_space_message | Custom message for Free diskspace monitor | string | `` | no | | free_disk_space_silenced | Groups to mute for Free diskspace monitor | map | `` | no | | free_disk_space_threshold_critical | Free disk space critical threshold | string | `5` | no | | free_disk_space_threshold_warning | Free disk space warning threshold | string | `10` | no | | free_disk_space_timeframe | Monitor timeframe for Free diskspace [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| free_memory_aggregator | Monitor aggregator for Free memory [available values: min, max, sum or avg] | string | `min` | no | +| free_memory_time_aggregator | Monitor aggregator for Free memory [available values: min, max or avg] | string | `min` | no | | free_memory_message | Custom message for Free memory monitor | string | - | yes | | free_memory_silenced | Groups to mute for Free memory monitor | map | `` | no | | free_memory_threshold_critical | Free disk space critical threshold | string | `5` | no | diff --git a/system/generic/inputs.tf b/system/generic/inputs.tf index fec8a81..f55e02c 100644 --- a/system/generic/inputs.tf +++ b/system/generic/inputs.tf @@ -38,8 +38,8 @@ variable "cpu_high_message" { default = "" } -variable "cpu_high_aggregator" { - description = "Monitor aggregator for CPU high [available values: min, max, sum or avg]" +variable "cpu_high_time_aggregator" { + description = "Monitor aggregator for CPU high [available values: min, max or avg]" type = "string" default = "min" } @@ -72,8 +72,8 @@ variable "cpu_load_message" { default = "" } -variable "cpu_load_aggregator" { - description = "Monitor aggregator for CPU load ratio [available values: min, max, sum or avg]" +variable "cpu_load_time_aggregator" { + description = "Monitor aggregator for CPU load ratio [available values: min, max or avg]" type = "string" default = "min" } @@ -106,8 +106,8 @@ variable "free_disk_space_message" { default = "" } -variable "free_disk_space_aggregator" { - description = "Monitor aggregator for Free diskspace [available values: min, max, sum or avg]" +variable "free_disk_space_time_aggregator" { + description = "Monitor aggregator for Free diskspace [available values: min, max or avg]" type = "string" default = "min" } @@ -140,8 +140,8 @@ variable "free_disk_inodes_message" { default = "" } -variable "free_disk_inodes_aggregator" { - description = "Monitor aggregator for Free disk inodes [available values: min, max, sum or avg]" +variable "free_disk_inodes_time_aggregator" { + description = "Monitor aggregator for Free disk inodes [available values: min, max or avg]" type = "string" default = "min" } @@ -173,8 +173,8 @@ variable "free_memory_message" { type = "string" } -variable "free_memory_aggregator" { - description = "Monitor aggregator for Free memory [available values: min, max, sum or avg]" +variable "free_memory_time_aggregator" { + description = "Monitor aggregator for Free memory [available values: min, max or avg]" type = "string" default = "min" } diff --git a/system/generic/monitors-system.tf b/system/generic/monitors-system.tf index a0e78bc..f62a56a 100644 --- a/system/generic/monitors-system.tf +++ b/system/generic/monitors-system.tf @@ -11,7 +11,7 @@ resource "datadog_monitor" "datadog_cpu_too_high" { message = "${coalesce(var.cpu_high_message, var.message)}" query = < ${var.cpu_high_threshold_critical} EOF @@ -42,9 +42,9 @@ resource "datadog_monitor" "datadog_load_too_high" { message = "${coalesce(var.cpu_load_message, var.message)}" query = < ${var.cpu_load_threshold_critical} EOF @@ -74,9 +74,9 @@ resource "datadog_monitor" "datadog_free_disk_space_too_low" { message = "${coalesce(var.free_disk_space_message, var.message)}" query = < Date: Thu, 14 Jun 2018 10:07:09 +0200 Subject: [PATCH 14/21] MON-191 - Wrong variable in elb latency timeframe fixed --- cloud/aws/elb/monitors-elb.tf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/cloud/aws/elb/monitors-elb.tf b/cloud/aws/elb/monitors-elb.tf index ed92f6b..befc3bc 100644 --- a/cloud/aws/elb/monitors-elb.tf +++ b/cloud/aws/elb/monitors-elb.tf @@ -178,7 +178,7 @@ resource "datadog_monitor" "ELB_backend_latency" { message = "${coalesce(var.elb_backend_latency_message, var.message)}" query = < ${var.elb_backend_latency_critical} EOF From d783400d6b6993e7d3937ec5716e6d6493a766da Mon Sep 17 00:00:00 2001 From: Quentin Manfroi Date: Wed, 27 Jun 2018 18:21:37 +0200 Subject: [PATCH 15/21] MON-191 update operators and readme --- cloud/aws/alb/README.md | Bin 5447 -> 5448 bytes cloud/aws/alb/monitors-alb.tf | 20 ++-- cloud/aws/apigateway/README.md | Bin 3446 -> 3447 bytes cloud/aws/apigateway/monitors-api.tf | 10 +- cloud/aws/elasticsearch/README.md | Bin 3483 -> 3484 bytes cloud/aws/elasticsearch/inputs.tf | 4 +- cloud/aws/elb/README.md | 83 +++++++------- cloud/aws/elb/monitors-elb.tf | 18 +-- cloud/aws/kinesis-firehose/README.md | Bin 1861 -> 1862 bytes cloud/aws/rds/README.md | Bin 2749 -> 2750 bytes cloud/aws/rds/inputs.tf | 4 +- cloud/aws/vpn/README.md | Bin 1948 -> 1932 bytes cloud/aws/vpn/inputs.tf | 2 +- cloud/azure/README.md | 47 ++++---- cloud/azure/apimanagement/README.md | Bin 4575 -> 4576 bytes cloud/azure/apimanagement/inputs.tf | 2 +- cloud/azure/app-services/README.md | Bin 4795 -> 4796 bytes cloud/azure/app-services/inputs.tf | 2 +- cloud/azure/eventhub/README.md | Bin 3171 -> 3172 bytes cloud/azure/eventhub/inputs.tf | 2 +- cloud/azure/inputs.tf | 46 ++++---- cloud/azure/iothubs/README.md | 153 +++++++++++++------------ cloud/azure/iothubs/inputs.tf | 4 +- cloud/azure/redis/README.md | Bin 4155 -> 4156 bytes cloud/azure/redis/inputs.tf | 6 +- cloud/azure/servicebus/README.md | Bin 2048 -> 2034 bytes cloud/azure/servicebus/inputs.tf | 2 +- cloud/azure/sql-database/README.md | Bin 3885 -> 3853 bytes cloud/azure/sql-database/inputs.tf | 4 +- cloud/azure/storage/README.md | 19 +-- cloud/azure/storage/inputs.tf | 16 +-- cloud/azure/stream-analytics/README.md | Bin 4685 -> 4686 bytes cloud/azure/stream-analytics/inputs.tf | 8 +- common/alerting-message/README.md | Bin 1428 -> 1545 bytes common/alerting-message/output.tf | 1 + databases/mongodb/README.md | 3 +- databases/mongodb/inputs.tf | 2 +- middleware/apache/README.md | 25 ++-- middleware/nginx/README.md | 25 ++-- middleware/php-fpm/README.md | 37 +++--- system/generic/README.md | 81 ++++++------- system/generic/inputs.tf | 18 +-- 42 files changed, 327 insertions(+), 317 deletions(-) diff --git a/cloud/aws/alb/README.md b/cloud/aws/alb/README.md index 679a2e173c1d7e4bb6a9b6dae231843c098c0e4d..f4bb659c4cefec4b355cea932ec128106a48fa9e 100644 GIT binary patch delta 9 QcmX@EbwX={yC@?A027%4@c;k- delta 7 OcmX@1bzEzMyC?t+xdQM2 diff --git a/cloud/aws/alb/monitors-alb.tf b/cloud/aws/alb/monitors-alb.tf index 72fb533..96e122d 100644 --- a/cloud/aws/alb/monitors-alb.tf +++ b/cloud/aws/alb/monitors-alb.tf @@ -16,7 +16,7 @@ resource "datadog_monitor" "ALB_no_healthy_instances" { query = < ${var.latency_threshold_critical} EOF @@ -75,8 +75,8 @@ resource "datadog_monitor" "ALB_httpcode_5xx" { query = < ${var.httpcode_alb_5xx_threshold_critical} EOF @@ -108,8 +108,8 @@ resource "datadog_monitor" "ALB_httpcode_4xx" { query = < ${var.httpcode_alb_4xx_threshold_critical} EOF @@ -141,8 +141,8 @@ resource "datadog_monitor" "ALB_httpcode_target_5xx" { query = < ${var.httpcode_target_5xx_threshold_critical} EOF @@ -174,8 +174,8 @@ resource "datadog_monitor" "ALB_httpcode_target_4xx" { query = < ${var.httpcode_target_4xx_threshold_critical} EOF diff --git a/cloud/aws/apigateway/README.md b/cloud/aws/apigateway/README.md index 63e8b9b31a8ef9bcb16faaac1bda8867b04d3006..8e242edefac16edeeeb91ea45d6dae991d7c27ad 100644 GIT binary patch delta 23 fcmew+^<8SidydUToSBT1KXcS?zRoqDiID*Sg^vlO delta 21 dcmew^^-XHSdydH=T+N%`b7V4ZzRfk82>^1y35Eaw diff --git a/cloud/aws/apigateway/monitors-api.tf b/cloud/aws/apigateway/monitors-api.tf index a7ff9cd..b6bee79 100644 --- a/cloud/aws/apigateway/monitors-api.tf +++ b/cloud/aws/apigateway/monitors-api.tf @@ -6,7 +6,7 @@ resource "datadog_monitor" "API_Gateway_latency" { query = < ${var.latency_threshold_critical} EOF @@ -38,8 +38,8 @@ resource "datadog_monitor" "API_http_5xx_errors_count" { query = < ${var.http_5xx_requests_threshold_critical} EOF @@ -72,8 +72,8 @@ resource "datadog_monitor" "API_http_4xx_errors_count" { query = < ${var.http_4xx_requests_threshold_critical} EOF diff --git a/cloud/aws/elasticsearch/README.md b/cloud/aws/elasticsearch/README.md index 641adac463ceaf57a6a50de386a07edf4aeb6093..e0582596616d0e414e71e97635bf1a365e09e210 100644 GIT binary patch delta 35 rcmbO&Jx6*&1q*X-X5M5*7U9i(ET5PrALHbke20~5^9*)oHbw>j+UE-o delta 33 mcmbOuJzIK11q*XxS^8u~7U9i(ET5RboQtfYn`f{yvjG6WJqp` | no | -| elb_4xx_threshold_critical | loadbalancer 4xx critical threshold in percentage | string | `10` | no | -| elb_4xx_threshold_warning | loadbalancer 4xx warning threshold in percentage | string | `5` | no | -| elb_4xx_timeframe | Monitor timeframe for ELB 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| elb_5xx_message | Custom message for ELB 5xx errors monitor | string | `` | no | -| elb_5xx_silenced | Groups to mute for ELB 5xx errors monitor | map | `` | no | -| elb_5xx_threshold_critical | loadbalancer 5xx critical threshold in percentage | string | `10` | no | -| elb_5xx_threshold_warning | loadbalancer 5xx warning threshold in percentage | string | `5` | no | -| elb_5xx_timeframe | Monitor timeframe for ELB 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| elb_backend_4xx_message | Custom message for ELB backend 4xx errors monitor | string | `` | no | -| elb_backend_4xx_silenced | Groups to mute for ELB backend 4xx errors monitor | map | `` | no | -| elb_backend_4xx_threshold_critical | loadbalancer backend 4xx critical threshold in percentage | string | `10` | no | -| elb_backend_4xx_threshold_warning | loadbalancer backend 4xx warning threshold in percentage | string | `5` | no | -| elb_backend_4xx_timeframe | Monitor timeframe for ELB backend 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| elb_backend_5xx_message | Custom message for ELB backend 5xx errors monitor | string | `` | no | -| elb_backend_5xx_silenced | Groups to mute for ELB backend 5xx errors monitor | map | `` | no | -| elb_backend_5xx_threshold_critical | loadbalancer backend 5xx critical threshold in percentage | string | `10` | no | -| elb_backend_5xx_threshold_warning | loadbalancer backend 5xx warning threshold in percentage | string | `5` | no | -| elb_backend_5xx_timeframe | Monitor timeframe for ELB backend 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| elb_backend_latency_time_aggregator | Monitor aggregator for ELB backend latency [available values: min, max or avg] | string | `min` | no | -| elb_backend_latency_critical | latency critical threshold in seconds | string | `5` | no | -| elb_backend_latency_message | Custom message for ELB backend latency monitor | string | `` | no | -| elb_backend_latency_silenced | Groups to mute for ELB backend latency monitor | map | `` | no | -| elb_backend_latency_timeframe | Monitor timeframe for ELB backend latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| elb_backend_latency_warning | latency warning threshold in seconds | string | `1` | no | -| elb_no_healthy_instance_time_aggregator | Monitor aggregator for ELB no healty instance [available values: min, max or avg] | string | `min` | no | -| elb_no_healthy_instance_message | Custom message for ELB no healty instance monitor | string | `` | no | -| elb_no_healthy_instance_silenced | Groups to mute for ELB no healty instance monitor | map | `` | no | -| elb_no_healthy_instance_timeframe | Monitor timeframe for ELB no healty instance [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| environment | Architecture Environment | string | - | yes | -| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | -| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | -| message | Message sent when an alert is triggered | string | - | yes | +Inputs +------ + +| Name | Description | Type | Default | Required | +|------|-------------|:----:|:-----:|:-----:| +| artificial_requests_count | Number of false requests used to mitigate false positive in case of low trafic | string | `5` | no | +| delay | Delay in seconds for the metric evaluation | string | `900` | no | +| elb_4xx_message | Custom message for ELB 4xx errors monitor | string | `` | no | +| elb_4xx_silenced | Groups to mute for ELB 4xx errors monitor | map | `` | no | +| elb_4xx_threshold_critical | loadbalancer 4xx critical threshold in percentage | string | `10` | no | +| elb_4xx_threshold_warning | loadbalancer 4xx warning threshold in percentage | string | `5` | no | +| elb_4xx_timeframe | Monitor timeframe for ELB 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| elb_5xx_message | Custom message for ELB 5xx errors monitor | string | `` | no | +| elb_5xx_silenced | Groups to mute for ELB 5xx errors monitor | map | `` | no | +| elb_5xx_threshold_critical | loadbalancer 5xx critical threshold in percentage | string | `10` | no | +| elb_5xx_threshold_warning | loadbalancer 5xx warning threshold in percentage | string | `5` | no | +| elb_5xx_timeframe | Monitor timeframe for ELB 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| elb_backend_4xx_message | Custom message for ELB backend 4xx errors monitor | string | `` | no | +| elb_backend_4xx_silenced | Groups to mute for ELB backend 4xx errors monitor | map | `` | no | +| elb_backend_4xx_threshold_critical | loadbalancer backend 4xx critical threshold in percentage | string | `10` | no | +| elb_backend_4xx_threshold_warning | loadbalancer backend 4xx warning threshold in percentage | string | `5` | no | +| elb_backend_4xx_timeframe | Monitor timeframe for ELB backend 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| elb_backend_5xx_message | Custom message for ELB backend 5xx errors monitor | string | `` | no | +| elb_backend_5xx_silenced | Groups to mute for ELB backend 5xx errors monitor | map | `` | no | +| elb_backend_5xx_threshold_critical | loadbalancer backend 5xx critical threshold in percentage | string | `10` | no | +| elb_backend_5xx_threshold_warning | loadbalancer backend 5xx warning threshold in percentage | string | `5` | no | +| elb_backend_5xx_timeframe | Monitor timeframe for ELB backend 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| elb_backend_latency_critical | latency critical threshold in seconds | string | `5` | no | +| elb_backend_latency_message | Custom message for ELB backend latency monitor | string | `` | no | +| elb_backend_latency_silenced | Groups to mute for ELB backend latency monitor | map | `` | no | +| elb_backend_latency_time_aggregator | Monitor aggregator for ELB backend latency [available values: min, max or avg] | string | `min` | no | +| elb_backend_latency_timeframe | Monitor timeframe for ELB backend latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| elb_backend_latency_warning | latency warning threshold in seconds | string | `1` | no | +| elb_no_healthy_instance_message | Custom message for ELB no healty instance monitor | string | `` | no | +| elb_no_healthy_instance_silenced | Groups to mute for ELB no healty instance monitor | map | `` | no | +| elb_no_healthy_instance_time_aggregator | Monitor aggregator for ELB no healty instance [available values: min or max] | string | `min` | no | +| elb_no_healthy_instance_timeframe | Monitor timeframe for ELB no healty instance [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| environment | Architecture Environment | string | - | yes | +| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | +| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | +| message | Message sent when an alert is triggered | string | - | yes | + diff --git a/cloud/aws/elb/monitors-elb.tf b/cloud/aws/elb/monitors-elb.tf index befc3bc..fbb2267 100644 --- a/cloud/aws/elb/monitors-elb.tf +++ b/cloud/aws/elb/monitors-elb.tf @@ -40,8 +40,8 @@ resource "datadog_monitor" "ELB_too_much_4xx" { query = < ${var.elb_4xx_threshold_critical} EOF @@ -75,8 +75,8 @@ resource "datadog_monitor" "ELB_too_much_5xx" { query = < ${var.elb_5xx_threshold_critical} EOF @@ -110,8 +110,8 @@ resource "datadog_monitor" "ELB_too_much_4xx_backend" { query = < ${var.elb_backend_4xx_threshold_critical} EOF @@ -145,8 +145,8 @@ resource "datadog_monitor" "ELB_too_much_5xx_backend" { query = < ${var.elb_backend_5xx_threshold_critical} EOF @@ -179,7 +179,7 @@ resource "datadog_monitor" "ELB_backend_latency" { query = < ${var.elb_backend_latency_critical} EOF diff --git a/cloud/aws/kinesis-firehose/README.md b/cloud/aws/kinesis-firehose/README.md index fafe19bbf77b75daa3de8e083d794e2ea7d51779..77f7c43343f0ff810b20aeb913f7774b6892c27b 100644 GIT binary patch delta 9 QcmX@gcZ_d?D?1|t01>|er2qf` delta 7 OcmX@cca(2~D?0!TcLJmU diff --git a/cloud/aws/rds/README.md b/cloud/aws/rds/README.md index 740e4d23418538e31a0ec1721214cbc838c9b066..d00bbbd150158fadefa16f374efb69b915dfd19b 100644 GIT binary patch delta 49 zcmdlhx=(aNG}GoQOp%O}s~VG}Gh_%;{W-W$6hDH41t83Y&wO5*a7!vizBBz|Jyx16u|&P;Rmzo9Jdu M)^^6tChVQe06MG^Z2$lO diff --git a/cloud/aws/rds/inputs.tf b/cloud/aws/rds/inputs.tf index 747a1a3..934bc80 100644 --- a/cloud/aws/rds/inputs.tf +++ b/cloud/aws/rds/inputs.tf @@ -41,7 +41,7 @@ variable "cpu_message" { variable "cpu_time_aggregator" { description = "Monitor aggregator for RDS CPU usage [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "cpu_timeframe" { @@ -75,7 +75,7 @@ variable "diskspace_message" { variable "diskspace_time_aggregator" { description = "Monitor aggregator for RDS free diskspace [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "diskspace_timeframe" { diff --git a/cloud/aws/vpn/README.md b/cloud/aws/vpn/README.md index 4be0db7af1b724388ed0d73201380a604b7f6092..40dd3d5fb64763b06368ef5f38b891f62efae761 100644 GIT binary patch delta 85 zcmbQk-^0J*6C($gE*Nl4{>NxM*@#JRaw3!OH;lix8FPflWvoV8B;McFIUZEMP{kV zrOdWKkxk5=Kynd_`D8y<`N`i|WO)+H(i0SF6!P*FYIrCAW)1>M`?7=rNqN={K+U|H JFR<=r1ONxJA8h~t diff --git a/cloud/aws/vpn/inputs.tf b/cloud/aws/vpn/inputs.tf index c1a0969..b791f51 100644 --- a/cloud/aws/vpn/inputs.tf +++ b/cloud/aws/vpn/inputs.tf @@ -39,7 +39,7 @@ variable "vpn_status_message" { variable "vpn_status_time_aggregator" { description = "Monitor aggregator for VPN status [available values: min, max or avg]" type = "string" - default = "avg" + default = "max" } variable "vpn_status_timeframe" { diff --git a/cloud/azure/README.md b/cloud/azure/README.md index 253c4ec..b94b3aa 100644 --- a/cloud/azure/README.md +++ b/cloud/azure/README.md @@ -44,7 +44,7 @@ Inputs | apimanagement_other_requests_timeframe | Monitor timeframe for API Management other requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | apimanagement_status_message | Custom message for API Management status monitor | string | `` | no | | apimanagement_status_silenced | Groups to mute for API Management status monitor | map | `` | no | -| apimanagement_status_time_aggregator | Monitor aggregator for API Management status [available values: min, max or avg] | string | `avg` | no | +| apimanagement_status_time_aggregator | Monitor aggregator for API Management status [available values: min, max or avg] | string | `max` | no | | apimanagement_status_timeframe | Monitor timeframe for API Management status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | apimanagement_successful_requests_message | Custom message for API Management successful requests monitor | string | `` | no | | apimanagement_successful_requests_silenced | Groups to mute for API Management successful requests monitor | map | `` | no | @@ -75,7 +75,7 @@ Inputs | appservices_memory_usage_silenced | Groups to mute for App Services memory usage monitor | map | `` | no | | appservices_memory_usage_threshold_critical | Alerting threshold in Mib | string | `1073741824` | no | | appservices_memory_usage_threshold_warning | Warning threshold in MiB | string | `536870912` | no | -| appservices_memory_usage_time_aggregator | Monitor aggregator for App Services memory usage [available values: min, max or avg] | string | `avg` | no | +| appservices_memory_usage_time_aggregator | Monitor aggregator for App Services memory usage [available values: min, max or avg] | string | `min` | no | | appservices_memory_usage_timeframe | Monitor timeframe for App Services memory usage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | appservices_response_time_message | Custom message for App Services response time monitor | string | `` | no | | appservices_response_time_silenced | Groups to mute for App Services response time monitor | map | `` | no | @@ -97,7 +97,7 @@ Inputs | eventhub_failed_requests_rate_timeframe | Monitor timeframe for Event Hub failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | eventhub_status_message | Custom message for Event Hub status monitor | string | `` | no | | eventhub_status_silenced | Groups to mute for Event Hub status monitor | map | `` | no | -| eventhub_status_time_aggregator | Monitor aggregator for Event Hub status [available values: min, max or avg] | string | `avg` | no | +| eventhub_status_time_aggregator | Monitor aggregator for Event Hub status [available values: min, max or avg] | string | `max` | no | | eventhub_status_timeframe | Monitor timeframe for Event Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | @@ -158,14 +158,14 @@ Inputs | iothub_orphaned_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub orphaned d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | iothub_status_message | Custom message for IoT Hub status monitor | string | `` | no | | iothub_status_silenced | Groups to mute for IoT Hub status monitor | map | `` | no | -| iothub_status_time_aggregator | Monitor aggregator for IoT Hub status [available values: min, max or avg] | string | `avg` | no | +| iothub_status_time_aggregator | Monitor aggregator for IoT Hub status [available values: min, max or avg] | string | `max` | no | | iothub_status_timeframe | Monitor timeframe for IoT Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | iothub_too_many_d2c_telemetry_ingress_nosent_message | Custom message for IoT Hub unsent d2c telemetry monitor | string | `` | no | | iothub_too_many_d2c_telemetry_ingress_nosent_silenced | Groups to mute for IoT Hub unsent d2c telemetry monitor | map | `` | no | | iothub_too_many_d2c_telemetry_ingress_nosent_timeframe | Monitor timeframe for IoT Hub unsent d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | iothub_total_devices_message | Custom message for IoT Hub total devices monitor | string | `` | no | | iothub_total_devices_silenced | Groups to mute for IoT Hub total devices monitor | map | `` | no | -| iothub_total_devices_time_aggregator | Monitor aggregator for IoT Hub total devices [available values: min, max or avg] | string | `avg` | no | +| iothub_total_devices_time_aggregator | Monitor aggregator for IoT Hub total devices [available values: min, max or avg] | string | `min` | no | | iothub_total_devices_timeframe | Monitor timeframe for IoT Hub total devices [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | message | Message sent when a monitor is triggered | string | - | yes | | non_taggable_filter_tags | Tags used for filtering for components without tag support | string | `*` | no | @@ -179,27 +179,27 @@ Inputs | redis_percent_processor_time_silenced | Groups to mute for Redis processor monitor | map | `` | no | | redis_percent_processor_time_threshold_critical | Processor time percent (critical threshold) | string | `80` | no | | redis_percent_processor_time_threshold_warning | Processor time percent (warning threshold) | string | `60` | no | -| redis_percent_processor_time_time_aggregator | Monitor aggregator for Redis processor [available values: min, max or avg] | string | `avg` | no | +| redis_percent_processor_time_time_aggregator | Monitor aggregator for Redis processor [available values: min, max or avg] | string | `min` | no | | redis_percent_processor_time_timeframe | Monitor timeframe for Redis processor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | redis_server_load_rate_message | Custom message for Redis server load monitor | string | `` | no | | redis_server_load_rate_silenced | Groups to mute for Redis server load monitor | map | `` | no | | redis_server_load_rate_threshold_critical | Server CPU load rate (critical threshold) | string | `90` | no | | redis_server_load_rate_threshold_warning | Server CPU load rate (warning threshold) | string | `70` | no | -| redis_server_load_rate_time_aggregator | Monitor aggregator for Redis server load [available values: min, max or avg] | string | `avg` | no | +| redis_server_load_rate_time_aggregator | Monitor aggregator for Redis server load [available values: min, max or avg] | string | `min` | no | | redis_server_load_rate_timeframe | Monitor timeframe for Redis server load [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | redis_status_message | Custom message for Redis status monitor | string | `` | no | | redis_status_silenced | Groups to mute for Redis status monitor | map | `` | no | -| redis_status_time_aggregator | Monitor aggregator for Redis status [available values: min, max or avg] | string | `avg` | no | +| redis_status_time_aggregator | Monitor aggregator for Redis status [available values: min, max or avg] | string | `max` | no | | redis_status_timeframe | Monitor timeframe for Redis status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | servicebus_status_message | Custom message for Service Bus status monitor | string | `` | no | | servicebus_status_silenced | Groups to mute for Service Bus status monitor | map | `` | no | -| servicebus_status_time_aggregator | Monitor aggregator for Service Bus status [available values: min, max or avg] | string | `min` | no | +| servicebus_status_time_aggregator | Monitor aggregator for Service Bus status [available values: min, max or avg] | string | `max` | no | | servicebus_status_timeframe | Monitor timeframe for Service Bus status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | | sqldatabase_cpu_message | Custom message for SQL CPU monitor | string | `` | no | | sqldatabase_cpu_silenced | Groups to mute for SQL CPU monitor | map | `` | no | | sqldatabase_cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no | | sqldatabase_cpu_threshold_warning | CPU usage in percent (warning threshold) | string | `80` | no | -| sqldatabase_cpu_time_aggregator | Monitor aggregator for SQL CPU [available values: min, max or avg] | string | `avg` | no | +| sqldatabase_cpu_time_aggregator | Monitor aggregator for SQL CPU [available values: min, max or avg] | string | `min` | no | | sqldatabase_cpu_timeframe | Monitor timeframe for SQL CPU [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | | sqldatabase_deadlock_message | Custom message for SQL Deadlock monitor | string | `` | no | | sqldatabase_deadlock_silenced | Groups to mute for SQL Deadlock monitor | map | `` | no | @@ -209,7 +209,7 @@ Inputs | sqldatabase_diskspace_silenced | Groups to mute for SQL disk space monitor | map | `` | no | | sqldatabase_diskspace_threshold_critical | Disk space used in percent (critical threshold) | string | `90` | no | | sqldatabase_diskspace_threshold_warning | Disk space used in percent (warning threshold) | string | `80` | no | -| sqldatabase_diskspace_time_aggregator | Monitor aggregator for SQL disk space [available values: min, max or avg] | string | `avg` | no | +| sqldatabase_diskspace_time_aggregator | Monitor aggregator for SQL disk space [available values: min, max or avg] | string | `max` | no | | sqldatabase_diskspace_timeframe | Monitor timeframe for SQL disk space [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | | sqldatabase_dtu_message | Custom message for SQL DTU monitor | string | `` | no | | sqldatabase_dtu_silenced | Groups to mute for SQL DTU monitor | map | `` | no | @@ -221,19 +221,19 @@ Inputs | storage_authorization_error_requests_silenced | Groups to mute for Storage authorization errors monitor | map | `` | no | | storage_authorization_error_requests_threshold_critical | Maximum acceptable percent of authorization error requests for a storage | string | `90` | no | | storage_authorization_error_requests_threshold_warning | Warning regarding acceptable percent of authorization error requests for a storage | string | `50` | no | -| storage_authorization_error_requests_time_aggregator | Monitor aggregator for Storage authorization errors [available values: min, max or avg] | string | `avg` | no | +| storage_authorization_error_requests_time_aggregator | Monitor aggregator for Storage authorization errors [available values: min, max or avg] | string | `min` | no | | storage_authorization_error_requests_timeframe | Monitor timeframe for Storage authorization errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | storage_availability_message | Custom message for Storage availability monitor | string | `` | no | | storage_availability_silenced | Groups to mute for Storage availability monitor | map | `` | no | | storage_availability_threshold_critical | Minimum acceptable percent of availability for a storage | string | `50` | no | | storage_availability_threshold_warning | Warning regarding acceptable percent of availability for a storage | string | `90` | no | -| storage_availability_time_aggregator | Monitor aggregator for Storage availability [available values: min, max or avg] | string | `avg` | no | +| storage_availability_time_aggregator | Monitor aggregator for Storage availability [available values: min, max or avg] | string | `max` | no | | storage_availability_timeframe | Monitor timeframe for Storage availability [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | storage_client_other_error_requests_message | Custom message for Storage other errors monitor | string | `` | no | | storage_client_other_error_requests_silenced | Groups to mute for Storage other errors monitor | map | `` | no | | storage_client_other_error_requests_threshold_critical | Maximum acceptable percent of client other error requests for a storage | string | `90` | no | | storage_client_other_error_requests_threshold_warning | Warning regarding acceptable percent of client other error requests for a storage | string | `50` | no | -| storage_client_other_error_requests_time_aggregator | Monitor aggregator for Storage other errors [available values: min, max or avg] | string | `avg` | no | +| storage_client_other_error_requests_time_aggregator | Monitor aggregator for Storage other errors [available values: min, max or avg] | string | `min` | no | | storage_client_other_error_requests_timeframe | Monitor timeframe for Storage other errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | storage_latency_message | Custom message for Storage latency monitor | string | `` | no | | storage_latency_silenced | Groups to mute for Storage latency monitor | map | `` | no | @@ -245,37 +245,37 @@ Inputs | storage_network_error_requests_silenced | Groups to mute for Storage network errors monitor | map | `` | no | | storage_network_error_requests_threshold_critical | Maximum acceptable percent of network error requests for a storage | string | `90` | no | | storage_network_error_requests_threshold_warning | Warning regarding acceptable percent of network error requests for a storage | string | `50` | no | -| storage_network_error_requests_time_aggregator | Monitor aggregator for Storage network errors [available values: min, max or avg] | string | `avg` | no | +| storage_network_error_requests_time_aggregator | Monitor aggregator for Storage network errors [available values: min, max or avg] | string | `min` | no | | storage_network_error_requests_timeframe | Monitor timeframe for Storage network errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | storage_server_other_error_requests_message | Custom message for Storage server other errors monitor | string | `` | no | | storage_server_other_error_requests_silenced | Groups to mute for Storage server other errors monitor | map | `` | no | | storage_server_other_error_requests_threshold_critical | Maximum acceptable percent of server other error requests for a storage | string | `90` | no | | storage_server_other_error_requests_threshold_warning | Warning regarding acceptable percent of server other error requests for a storage | string | `50` | no | -| storage_server_other_error_requests_time_aggregator | Monitor aggregator for Storage other errors [available values: min, max or avg] | string | `avg` | no | +| storage_server_other_error_requests_time_aggregator | Monitor aggregator for Storage other errors [available values: min, max or avg] | string | `min` | no | | storage_server_other_error_requests_timeframe | Monitor timeframe for Storage server other errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | storage_successful_requests_message | Custom message for Storage sucessful requests monitor | string | `` | no | | storage_successful_requests_silenced | Groups to mute for Storage sucessful requests monitor | map | `` | no | | storage_successful_requests_threshold_critical | Minimum acceptable percent of successful requests for a storage | string | `10` | no | | storage_successful_requests_threshold_warning | Warning regarding acceptable percent of successful requests for a storage | string | `30` | no | -| storage_successful_requests_time_aggregator | Monitor aggregator for Storage sucessful requests [available values: min, max or avg] | string | `avg` | no | +| storage_successful_requests_time_aggregator | Monitor aggregator for Storage sucessful requests [available values: min, max or avg] | string | `max` | no | | storage_successful_requests_timeframe | Monitor timeframe for Storage sucessful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | storage_throttling_error_requests_message | Custom message for Storage throttling error monitor | string | `` | no | | storage_throttling_error_requests_silenced | Groups to mute for Storage throttling error monitor | map | `` | no | | storage_throttling_error_requests_threshold_critical | Maximum acceptable percent of throttling error requests for a storage | string | `90` | no | | storage_throttling_error_requests_threshold_warning | Warning regarding acceptable percent of throttling error requests for a storage | string | `50` | no | -| storage_throttling_error_requests_time_aggregator | Monitor aggregator for Storage throttling errors [available values: min, max or avg] | string | `avg` | no | +| storage_throttling_error_requests_time_aggregator | Monitor aggregator for Storage throttling errors [available values: min, max or avg] | string | `min` | no | | storage_throttling_error_requests_timeframe | Monitor timeframe for Storage throttling errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | storage_timeout_error_requests_message | Custom message for Storage timeout monitor | string | `` | no | | storage_timeout_error_requests_silenced | Groups to mute for Storage timeout monitor | map | `` | no | | storage_timeout_error_requests_threshold_critical | Maximum acceptable percent of timeout error requests for a storage | string | `90` | no | | storage_timeout_error_requests_threshold_warning | Warning regarding acceptable percent of timeout error requests for a storage | string | `50` | no | -| storage_timeout_error_requests_time_aggregator | Monitor aggregator for Storage timeout [available values: min, max or avg] | string | `avg` | no | +| storage_timeout_error_requests_time_aggregator | Monitor aggregator for Storage timeout [available values: min, max or avg] | string | `min` | no | | storage_timeout_error_requests_timeframe | Monitor timeframe for Storage timeout [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | streamanalytics_conversion_errors_message | Custom message for Stream Analytics conversion errors monitor | string | `` | no | | streamanalytics_conversion_errors_silenced | Groups to mute for Stream Analytics conversion errors monitor | map | `` | no | | streamanalytics_conversion_errors_threshold_critical | Conversion errors limit (critical threshold) | string | `10` | no | | streamanalytics_conversion_errors_threshold_warning | Conversion errors limit (warning threshold) | string | `0` | no | -| streamanalytics_conversion_errors_time_aggregator | Monitor aggregator for Stream Analytics conversion errors [available values: min, max or avg] | string | `avg` | no | +| streamanalytics_conversion_errors_time_aggregator | Monitor aggregator for Stream Analytics conversion errors [available values: min, max or avg] | string | `min` | no | | streamanalytics_conversion_errors_timeframe | Monitor timeframe for Stream Analytics conversion errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | streamanalytics_failed_function_requests_message | Custom message for Stream Analytics failed requests monitor | string | `` | no | | streamanalytics_failed_function_requests_silenced | Groups to mute for Stream Analytics failed requests monitor | map | `` | no | @@ -286,17 +286,17 @@ Inputs | streamanalytics_runtime_errors_silenced | Groups to mute for Stream Analytics runtime errors monitor | map | `` | no | | streamanalytics_runtime_errors_threshold_critical | Runtime errors limit (critical threshold) | string | `10` | no | | streamanalytics_runtime_errors_threshold_warning | Runtime errors limit (warning threshold) | string | `0` | no | -| streamanalytics_runtime_errors_time_aggregator | Monitor aggregator for Stream Analytics runtime errors [available values: min, max or avg] | string | `avg` | no | +| streamanalytics_runtime_errors_time_aggregator | Monitor aggregator for Stream Analytics runtime errors [available values: min, max or avg] | string | `min` | no | | streamanalytics_runtime_errors_timeframe | Monitor timeframe for Stream Analytics runtime errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | streamanalytics_status_message | Custom message for Stream Analytics status monitor | string | `` | no | | streamanalytics_status_silenced | Groups to mute for Stream Analytics status monitor | map | `` | no | -| streamanalytics_status_time_aggregator | Monitor aggregator for Stream Analytics status [available values: min, max or avg] | string | `avg` | no | +| streamanalytics_status_time_aggregator | Monitor aggregator for Stream Analytics status [available values: min, max or avg] | string | `max` | no | | streamanalytics_status_timeframe | Monitor timeframe for Stream Analytics status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | streamanalytics_su_utilization_message | Custom message for Stream Analytics utilization monitor | string | `` | no | | streamanalytics_su_utilization_silenced | Groups to mute for Stream Analytics utilization monitor | map | `` | no | | streamanalytics_su_utilization_threshold_critical | Streaming Unit utilization rate limit (critical threshold) | string | `80` | no | | streamanalytics_su_utilization_threshold_warning | Streaming Unit utilization rate limit (warning threshold) | string | `60` | no | -| streamanalytics_su_utilization_time_aggregator | Monitor aggregator for Stream Analytics utilization [available values: min, max or avg] | string | `avg` | no | +| streamanalytics_su_utilization_time_aggregator | Monitor aggregator for Stream Analytics utilization [available values: min, max or avg] | string | `min` | no | | streamanalytics_su_utilization_timeframe | Monitor timeframe for Stream Analytics utilization [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | Related documentation @@ -305,3 +305,4 @@ Related documentation DataDog documentation: [https://docs.datadoghq.com/integrations/azure/](https://docs.datadoghq.com/integrations/azure/) Azure metrics documentation: [https://docs.microsoft.com/en-us/azure/monitoring-and-diagnostics/monitoring-overview-metrics](https://docs.microsoft.com/en-us/azure/monitoring-and-diagnostics/monitoring-overview-metrics) + \ No newline at end of file diff --git a/cloud/azure/apimanagement/README.md b/cloud/azure/apimanagement/README.md index fe753016e373509c718ce21b448230ef64a176e5..d47673f05f6107826d500db46a6b873623ae9e43 100644 GIT binary patch delta 18 Zcmcbw{6KlbY%b>9#EQ-HxE$FT830L%21oz^ delta 16 XcmaE$d|!FPY%b=+vh>aKxE$F5Jjez= diff --git a/cloud/azure/apimanagement/inputs.tf b/cloud/azure/apimanagement/inputs.tf index 42ca41c..2a19b46 100644 --- a/cloud/azure/apimanagement/inputs.tf +++ b/cloud/azure/apimanagement/inputs.tf @@ -40,7 +40,7 @@ variable "status_message" { variable "status_time_aggregator" { description = "Monitor aggregator for API Management status [available values: min, max or avg]" type = "string" - default = "avg" + default = "max" } variable "status_timeframe" { diff --git a/cloud/azure/app-services/README.md b/cloud/azure/app-services/README.md index 22acc220f06ea957d2973a9268877bf3cd3f78e1..cbfd940c6d32898e1a6e77dbace9af0860f7b67d 100644 GIT binary patch delta 22 ecmdn3x<_@xN8ZVLf_#&A@$hZtO8c_cUU@~vY509l9!m;e9( diff --git a/cloud/azure/app-services/inputs.tf b/cloud/azure/app-services/inputs.tf index 29239a6..d038d4b 100644 --- a/cloud/azure/app-services/inputs.tf +++ b/cloud/azure/app-services/inputs.tf @@ -72,7 +72,7 @@ variable "memory_usage_message" { variable "memory_usage_time_aggregator" { description = "Monitor aggregator for App Services memory usage [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "memory_usage_timeframe" { diff --git a/cloud/azure/eventhub/README.md b/cloud/azure/eventhub/README.md index 2a0bb1750d5116032165e85823a302c0145d69c1..53dc2dd6642421e18a03ac1445735c41987f56c7 100644 GIT binary patch delta 18 ZcmaDX@kC;S5*KrBV#Q`vE;}Yh1^_>s1wa4* delta 16 XcmaDN@mOMm5*Kq~S^8#GE;}XwH0lL6 diff --git a/cloud/azure/eventhub/inputs.tf b/cloud/azure/eventhub/inputs.tf index ac6b733..5229093 100644 --- a/cloud/azure/eventhub/inputs.tf +++ b/cloud/azure/eventhub/inputs.tf @@ -40,7 +40,7 @@ variable "status_message" { variable "status_time_aggregator" { description = "Monitor aggregator for Event Hub status [available values: min, max or avg]" type = "string" - default = "avg" + default = "max" } variable "status_timeframe" { diff --git a/cloud/azure/inputs.tf b/cloud/azure/inputs.tf index 751abd9..35acc9d 100644 --- a/cloud/azure/inputs.tf +++ b/cloud/azure/inputs.tf @@ -44,7 +44,7 @@ variable "apimanagement_status_message" { variable "apimanagement_status_time_aggregator" { description = "Monitor aggregator for API Management status [available values: min, max or avg]" type = "string" - default = "avg" + default = "max" } variable "apimanagement_status_timeframe" { @@ -215,7 +215,7 @@ variable "appservices_memory_usage_message" { variable "appservices_memory_usage_time_aggregator" { description = "Monitor aggregator for App Services memory usage [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "appservices_memory_usage_timeframe" { @@ -334,7 +334,7 @@ variable "eventhub_status_message" { variable "eventhub_status_time_aggregator" { description = "Monitor aggregator for Event Hub status [available values: min, max or avg]" type = "string" - default = "avg" + default = "max" } variable "eventhub_status_timeframe" { @@ -415,7 +415,7 @@ variable "iothub_status_message" { variable "iothub_status_time_aggregator" { description = "Monitor aggregator for IoT Hub status [available values: min, max or avg]" type = "string" - default = "avg" + default = "max" } variable "iothub_status_timeframe" { @@ -439,7 +439,7 @@ variable "iothub_total_devices_message" { variable "iothub_total_devices_time_aggregator" { description = "Monitor aggregator for IoT Hub total devices [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "iothub_total_devices_timeframe" { @@ -790,7 +790,7 @@ variable "redis_status_message" { variable "redis_status_time_aggregator" { description = "Monitor aggregator for Redis status [available values: min, max or avg]" type = "string" - default = "avg" + default = "max" } variable "redis_status_timeframe" { @@ -848,7 +848,7 @@ variable "redis_percent_processor_time_message" { variable "redis_percent_processor_time_time_aggregator" { description = "Monitor aggregator for Redis processor [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "redis_percent_processor_time_timeframe" { @@ -882,7 +882,7 @@ variable "redis_server_load_rate_message" { variable "redis_server_load_rate_time_aggregator" { description = "Monitor aggregator for Redis server load [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "redis_server_load_rate_timeframe" { @@ -917,7 +917,7 @@ variable "servicebus_status_message" { variable "servicebus_status_time_aggregator" { description = "Monitor aggregator for Service Bus status [available values: min, max or avg]" type = "string" - default = "min" + default = "max" } variable "servicebus_status_timeframe" { @@ -941,7 +941,7 @@ variable "sqldatabase_cpu_message" { variable "sqldatabase_cpu_time_aggregator" { description = "Monitor aggregator for SQL CPU [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "sqldatabase_cpu_timeframe" { @@ -975,7 +975,7 @@ variable "sqldatabase_diskspace_message" { variable "sqldatabase_diskspace_time_aggregator" { description = "Monitor aggregator for SQL disk space [available values: min, max or avg]" type = "string" - default = "avg" + default = "max" } variable "sqldatabase_diskspace_timeframe" { @@ -1067,7 +1067,7 @@ variable "storage_availability_message" { variable "storage_availability_time_aggregator" { description = "Monitor aggregator for Storage availability [available values: min, max or avg]" type = "string" - default = "avg" + default = "max" } variable "storage_availability_timeframe" { @@ -1101,7 +1101,7 @@ variable "storage_successful_requests_message" { variable "storage_successful_requests_time_aggregator" { description = "Monitor aggregator for Storage sucessful requests [available values: min, max or avg]" type = "string" - default = "avg" + default = "max" } variable "storage_successful_requests_timeframe" { @@ -1169,7 +1169,7 @@ variable "storage_timeout_error_requests_message" { variable "storage_timeout_error_requests_time_aggregator" { description = "Monitor aggregator for Storage timeout [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "storage_timeout_error_requests_timeframe" { @@ -1203,7 +1203,7 @@ variable "storage_network_error_requests_message" { variable "storage_network_error_requests_time_aggregator" { description = "Monitor aggregator for Storage network errors [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "storage_network_error_requests_timeframe" { @@ -1237,7 +1237,7 @@ variable "storage_throttling_error_requests_message" { variable "storage_throttling_error_requests_time_aggregator" { description = "Monitor aggregator for Storage throttling errors [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "storage_throttling_error_requests_timeframe" { @@ -1271,7 +1271,7 @@ variable "storage_server_other_error_requests_message" { variable "storage_server_other_error_requests_time_aggregator" { description = "Monitor aggregator for Storage other errors [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "storage_server_other_error_requests_timeframe" { @@ -1305,7 +1305,7 @@ variable "storage_client_other_error_requests_message" { variable "storage_client_other_error_requests_time_aggregator" { description = "Monitor aggregator for Storage other errors [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "storage_client_other_error_requests_timeframe" { @@ -1339,7 +1339,7 @@ variable "storage_authorization_error_requests_message" { variable "storage_authorization_error_requests_time_aggregator" { description = "Monitor aggregator for Storage authorization errors [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "storage_authorization_error_requests_timeframe" { @@ -1374,7 +1374,7 @@ variable "streamanalytics_status_message" { variable "streamanalytics_status_time_aggregator" { description = "Monitor aggregator for Stream Analytics status [available values: min, max or avg]" type = "string" - default = "avg" + default = "max" } variable "streamanalytics_status_timeframe" { @@ -1398,7 +1398,7 @@ variable "streamanalytics_su_utilization_message" { variable "streamanalytics_su_utilization_time_aggregator" { description = "Monitor aggregator for Stream Analytics utilization [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "streamanalytics_su_utilization_timeframe" { @@ -1460,7 +1460,7 @@ variable "streamanalytics_conversion_errors_message" { variable "streamanalytics_conversion_errors_time_aggregator" { description = "Monitor aggregator for Stream Analytics conversion errors [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "streamanalytics_conversion_errors_timeframe" { @@ -1494,7 +1494,7 @@ variable "streamanalytics_runtime_errors_message" { variable "streamanalytics_runtime_errors_time_aggregator" { description = "Monitor aggregator for Stream Analytics runtime errors [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "streamanalytics_runtime_errors_timeframe" { diff --git a/cloud/azure/iothubs/README.md b/cloud/azure/iothubs/README.md index 6190555..ca9982f 100644 --- a/cloud/azure/iothubs/README.md +++ b/cloud/azure/iothubs/README.md @@ -33,85 +33,86 @@ Creates a DataDog monitors with the following checks : * D2C telemetry egress fallback count check * D2C telemetry ingress no sent count check -Inputs ------- - -| Name | Description | Type | Default | Required | -|------|-------------|:----:|:-----:|:-----:| -| delay | Delay in seconds for the metric evaluation | string | `900` | no | -| dropped_d2c_telemetry_egress_message | Custom message for IoT Hub dropped d2c telemetry monitor | string | `` | no | -| dropped_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Dropped limit (critical threshold) | string | `90` | no | -| dropped_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Dropped limit (warning threshold) | string | `50` | no | -| dropped_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub dropped d2c telemetry monitor | map | `` | no | -| dropped_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub dropped d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| environment | Architecture Environment | string | - | yes | -| failed_c2d_methods_rate_message | Custom message for IoT Hub failed c2d method monitor | string | `` | no | -| failed_c2d_methods_rate_silenced | Groups to mute for IoT Hub failed c2d methods monitor | map | `` | no | -| failed_c2d_methods_rate_threshold_critical | C2D Methods Failed rate limit (critical threshold) | string | `90` | no | -| failed_c2d_methods_rate_threshold_warning | C2D Methods Failed rate limit (warning threshold) | string | `50` | no | -| failed_c2d_methods_rate_timeframe | Monitor timeframe for IoT Hub failed c2d method [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| failed_c2d_twin_read_rate_message | Custom message for IoT Hub failed c2d twin read monitor | string | `` | no | -| failed_c2d_twin_read_rate_silenced | Groups to mute for IoT Hub failed c2d twin read monitor | map | `` | no | -| failed_c2d_twin_read_rate_threshold_critical | C2D Twin Read Failed rate limit (critical threshold) | string | `90` | no | -| failed_c2d_twin_read_rate_threshold_warning | C2D Twin Read Failed rate limit (warning threshold) | string | `50` | no | -| failed_c2d_twin_read_rate_timeframe | Monitor timeframe for IoT Hub failed c2d twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| failed_c2d_twin_update_rate_message | Custom message for IoT Hub failed c2d twin update monitor | string | `` | no | -| failed_c2d_twin_update_rate_silenced | Groups to mute for IoT Hub failed c2d twin update monitor | map | `` | no | -| failed_c2d_twin_update_rate_threshold_critical | C2D Twin Update Failed rate limit (critical threshold) | string | `90` | no | -| failed_c2d_twin_update_rate_threshold_warning | C2D Twin Update Failed rate limit (warning threshold) | string | `50` | no | -| failed_c2d_twin_update_rate_timeframe | Monitor timeframe for IoT Hub failed c2d twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| failed_d2c_twin_read_rate_message | Custom message for IoT Hub failed d2c twin read monitor | string | `` | no | -| failed_d2c_twin_read_rate_silenced | Groups to mute for IoT Hub failed d2c twin read monitor | map | `` | no | -| failed_d2c_twin_read_rate_threshold_critical | D2C Twin Read Failed rate limit (critical threshold) | string | `90` | no | -| failed_d2c_twin_read_rate_threshold_warning | D2C Twin Read Failed rate limit (warning threshold) | string | `50` | no | -| failed_d2c_twin_read_rate_timeframe | Monitor timeframe for IoT Hub failed d2c twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| failed_d2c_twin_update_rate_message | Custom message for IoT Hub failed d2c twin update monitor | string | `` | no | -| failed_d2c_twin_update_rate_silenced | Groups to mute for IoT Hub failed d2c twin update monitor | map | `` | no | -| failed_d2c_twin_update_rate_threshold_critical | D2C Twin Update Failed rate limit (critical threshold) | string | `90` | no | -| failed_d2c_twin_update_rate_threshold_warning | D2C Twin Update Failed rate limit (warning threshold) | string | `50` | no | -| failed_d2c_twin_update_rate_timeframe | Monitor timeframe for IoT Hub failed d2c twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| failed_jobs_rate_message | Custom message for IoT Hub failed jobs monitor | string | `` | no | -| failed_jobs_rate_silenced | Groups to mute for IoT Hub failed jobs monitor | map | `` | no | -| failed_jobs_rate_threshold_critical | Jobs Failed rate limit (critical threshold) | string | `90` | no | -| failed_jobs_rate_threshold_warning | Jobs Failed rate limit (warning threshold) | string | `50` | no | -| failed_jobs_rate_timeframe | Monitor timeframe for IoT Hub failed jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| failed_listjobs_rate_message | Custom message for IoT Hub failed list jobs monitor | string | `` | no | -| failed_listjobs_rate_silenced | Groups to mute for IoT Hub failed list jobs monitor | map | `` | no | -| failed_listjobs_rate_threshold_critical | ListJobs Failed rate limit (critical threshold) | string | `90` | no | -| failed_listjobs_rate_threshold_warning | ListJobs Failed rate limit (warning threshold) | string | `50` | no | -| failed_listjobs_rate_timeframe | Monitor timeframe for IoT Hub failed list jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| failed_queryjobs_rate_message | Custom message for IoT Hub failed query jobs monitor | string | `` | no | -| failed_queryjobs_rate_silenced | Groups to mute for IoT Hub failed query jobs monitor | map | `` | no | -| failed_queryjobs_rate_threshold_critical | QueryJobs Failed rate limit (critical threshold) | string | `90` | no | -| failed_queryjobs_rate_threshold_warning | QueryJobs Failed rate limit (warning threshold) | string | `50` | no | -| failed_queryjobs_rate_timeframe | Monitor timeframe for IoT Hub failed query jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| filter_tags | Tags used for filtering | string | `*` | no | -| invalid_d2c_telemetry_egress_message | Custom message for IoT Hub invalid d2c telemetry monitor | string | `` | no | -| invalid_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Invalid limit (critical threshold) | string | `90` | no | -| invalid_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Invalid limit (warning threshold) | string | `50` | no | -| invalid_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub invalid d2c telemetry monitor | map | `` | no | -| invalid_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub invalid d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| message | Message sent when an alert is triggered | string | - | yes | -| orphaned_d2c_telemetry_egress_message | Custom message for IoT Hub orphaned d2c telemetry monitor | string | `` | no | -| orphaned_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Orphaned limit (critical threshold) | string | `90` | no | -| orphaned_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Orphaned limit (warning threshold) | string | `50` | no | -| orphaned_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub orphaned d2c telemetry monitor | map | `` | no | -| orphaned_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub orphaned d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| status_message | Custom message for IoT Hub status monitor | string | `` | no | -| status_silenced | Groups to mute for IoT Hub status monitor | map | `` | no | -| status_time_aggregator | Monitor aggregator for IoT Hub status [available values: min, max, sum or avg] | string | `avg` | no | -| status_timeframe | Monitor timeframe for IoT Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| too_many_d2c_telemetry_ingress_nosent_message | Custom message for IoT Hub unsent d2c telemetry monitor | string | `` | no | -| too_many_d2c_telemetry_ingress_nosent_silenced | Groups to mute for IoT Hub unsent d2c telemetry monitor | map | `` | no | -| too_many_d2c_telemetry_ingress_nosent_timeframe | Monitor timeframe for IoT Hub unsent d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| total_devices_message | Custom message for IoT Hub total devices monitor | string | `` | no | -| total_devices_silenced | Groups to mute for IoT Hub total devices monitor | map | `` | no | -| total_devices_time_aggregator | Monitor aggregator for IoT Hub total devices [available values: min, max, sum or avg] | string | `avg` | no | -| total_devices_timeframe | Monitor timeframe for IoT Hub total devices [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | - +Inputs +------ + +| Name | Description | Type | Default | Required | +|------|-------------|:----:|:-----:|:-----:| +| delay | Delay in seconds for the metric evaluation | string | `900` | no | +| dropped_d2c_telemetry_egress_message | Custom message for IoT Hub dropped d2c telemetry monitor | string | `` | no | +| dropped_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Dropped limit (critical threshold) | string | `90` | no | +| dropped_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Dropped limit (warning threshold) | string | `50` | no | +| dropped_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub dropped d2c telemetry monitor | map | `` | no | +| dropped_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub dropped d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| environment | Architecture Environment | string | - | yes | +| failed_c2d_methods_rate_message | Custom message for IoT Hub failed c2d method monitor | string | `` | no | +| failed_c2d_methods_rate_silenced | Groups to mute for IoT Hub failed c2d methods monitor | map | `` | no | +| failed_c2d_methods_rate_threshold_critical | C2D Methods Failed rate limit (critical threshold) | string | `90` | no | +| failed_c2d_methods_rate_threshold_warning | C2D Methods Failed rate limit (warning threshold) | string | `50` | no | +| failed_c2d_methods_rate_timeframe | Monitor timeframe for IoT Hub failed c2d method [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| failed_c2d_twin_read_rate_message | Custom message for IoT Hub failed c2d twin read monitor | string | `` | no | +| failed_c2d_twin_read_rate_silenced | Groups to mute for IoT Hub failed c2d twin read monitor | map | `` | no | +| failed_c2d_twin_read_rate_threshold_critical | C2D Twin Read Failed rate limit (critical threshold) | string | `90` | no | +| failed_c2d_twin_read_rate_threshold_warning | C2D Twin Read Failed rate limit (warning threshold) | string | `50` | no | +| failed_c2d_twin_read_rate_timeframe | Monitor timeframe for IoT Hub failed c2d twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| failed_c2d_twin_update_rate_message | Custom message for IoT Hub failed c2d twin update monitor | string | `` | no | +| failed_c2d_twin_update_rate_silenced | Groups to mute for IoT Hub failed c2d twin update monitor | map | `` | no | +| failed_c2d_twin_update_rate_threshold_critical | C2D Twin Update Failed rate limit (critical threshold) | string | `90` | no | +| failed_c2d_twin_update_rate_threshold_warning | C2D Twin Update Failed rate limit (warning threshold) | string | `50` | no | +| failed_c2d_twin_update_rate_timeframe | Monitor timeframe for IoT Hub failed c2d twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| failed_d2c_twin_read_rate_message | Custom message for IoT Hub failed d2c twin read monitor | string | `` | no | +| failed_d2c_twin_read_rate_silenced | Groups to mute for IoT Hub failed d2c twin read monitor | map | `` | no | +| failed_d2c_twin_read_rate_threshold_critical | D2C Twin Read Failed rate limit (critical threshold) | string | `90` | no | +| failed_d2c_twin_read_rate_threshold_warning | D2C Twin Read Failed rate limit (warning threshold) | string | `50` | no | +| failed_d2c_twin_read_rate_timeframe | Monitor timeframe for IoT Hub failed d2c twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| failed_d2c_twin_update_rate_message | Custom message for IoT Hub failed d2c twin update monitor | string | `` | no | +| failed_d2c_twin_update_rate_silenced | Groups to mute for IoT Hub failed d2c twin update monitor | map | `` | no | +| failed_d2c_twin_update_rate_threshold_critical | D2C Twin Update Failed rate limit (critical threshold) | string | `90` | no | +| failed_d2c_twin_update_rate_threshold_warning | D2C Twin Update Failed rate limit (warning threshold) | string | `50` | no | +| failed_d2c_twin_update_rate_timeframe | Monitor timeframe for IoT Hub failed d2c twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| failed_jobs_rate_message | Custom message for IoT Hub failed jobs monitor | string | `` | no | +| failed_jobs_rate_silenced | Groups to mute for IoT Hub failed jobs monitor | map | `` | no | +| failed_jobs_rate_threshold_critical | Jobs Failed rate limit (critical threshold) | string | `90` | no | +| failed_jobs_rate_threshold_warning | Jobs Failed rate limit (warning threshold) | string | `50` | no | +| failed_jobs_rate_timeframe | Monitor timeframe for IoT Hub failed jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| failed_listjobs_rate_message | Custom message for IoT Hub failed list jobs monitor | string | `` | no | +| failed_listjobs_rate_silenced | Groups to mute for IoT Hub failed list jobs monitor | map | `` | no | +| failed_listjobs_rate_threshold_critical | ListJobs Failed rate limit (critical threshold) | string | `90` | no | +| failed_listjobs_rate_threshold_warning | ListJobs Failed rate limit (warning threshold) | string | `50` | no | +| failed_listjobs_rate_timeframe | Monitor timeframe for IoT Hub failed list jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| failed_queryjobs_rate_message | Custom message for IoT Hub failed query jobs monitor | string | `` | no | +| failed_queryjobs_rate_silenced | Groups to mute for IoT Hub failed query jobs monitor | map | `` | no | +| failed_queryjobs_rate_threshold_critical | QueryJobs Failed rate limit (critical threshold) | string | `90` | no | +| failed_queryjobs_rate_threshold_warning | QueryJobs Failed rate limit (warning threshold) | string | `50` | no | +| failed_queryjobs_rate_timeframe | Monitor timeframe for IoT Hub failed query jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| filter_tags | Tags used for filtering | string | `*` | no | +| invalid_d2c_telemetry_egress_message | Custom message for IoT Hub invalid d2c telemetry monitor | string | `` | no | +| invalid_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Invalid limit (critical threshold) | string | `90` | no | +| invalid_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Invalid limit (warning threshold) | string | `50` | no | +| invalid_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub invalid d2c telemetry monitor | map | `` | no | +| invalid_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub invalid d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| message | Message sent when an alert is triggered | string | - | yes | +| orphaned_d2c_telemetry_egress_message | Custom message for IoT Hub orphaned d2c telemetry monitor | string | `` | no | +| orphaned_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Orphaned limit (critical threshold) | string | `90` | no | +| orphaned_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Orphaned limit (warning threshold) | string | `50` | no | +| orphaned_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub orphaned d2c telemetry monitor | map | `` | no | +| orphaned_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub orphaned d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| status_message | Custom message for IoT Hub status monitor | string | `` | no | +| status_silenced | Groups to mute for IoT Hub status monitor | map | `` | no | +| status_time_aggregator | Monitor aggregator for IoT Hub status [available values: min, max, sum or avg] | string | `max` | no | +| status_timeframe | Monitor timeframe for IoT Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| too_many_d2c_telemetry_ingress_nosent_message | Custom message for IoT Hub unsent d2c telemetry monitor | string | `` | no | +| too_many_d2c_telemetry_ingress_nosent_silenced | Groups to mute for IoT Hub unsent d2c telemetry monitor | map | `` | no | +| too_many_d2c_telemetry_ingress_nosent_timeframe | Monitor timeframe for IoT Hub unsent d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| total_devices_message | Custom message for IoT Hub total devices monitor | string | `` | no | +| total_devices_silenced | Groups to mute for IoT Hub total devices monitor | map | `` | no | +| total_devices_time_aggregator | Monitor aggregator for IoT Hub total devices [available values: min, max, sum or avg] | string | `min` | no | +| total_devices_timeframe | Monitor timeframe for IoT Hub total devices [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | + Related documentation --------------------- DataDog documentation: [https://docs.datadoghq.com/integrations/azure_iot_hub](https://docs.datadoghq.com/integrations/azure_iot_hub) Azure IOT Hubs metrics documentation: [https://docs.microsoft.com/en-us/azure/iot-hub/iot-hub-monitor-resource-health](https://docs.microsoft.com/en-us/azure/iot-hub/iot-hub-monitor-resource-health) + \ No newline at end of file diff --git a/cloud/azure/iothubs/inputs.tf b/cloud/azure/iothubs/inputs.tf index 58dbb63..d50ec27 100644 --- a/cloud/azure/iothubs/inputs.tf +++ b/cloud/azure/iothubs/inputs.tf @@ -35,7 +35,7 @@ variable "status_message" { variable "status_time_aggregator" { description = "Monitor aggregator for IoT Hub status [available values: min, max, sum or avg]" type = "string" - default = "avg" + default = "max" } variable "status_timeframe" { @@ -59,7 +59,7 @@ variable "total_devices_message" { variable "total_devices_time_aggregator" { description = "Monitor aggregator for IoT Hub total devices [available values: min, max, sum or avg]" type = "string" - default = "avg" + default = "min" } variable "total_devices_timeframe" { diff --git a/cloud/azure/redis/README.md b/cloud/azure/redis/README.md index a360b29e5410a60d63e49329d9469f6f565328a3..3598fee2366ef2c5e1b0bff050754d05521d04d8 100644 GIT binary patch delta 48 zcmdn3ut#A-C?|7nX5Qpz4&}|&oZFbdoK@TklU4atH&^mZW@OGytk}%Yr^Cd^005N{ B4#NNd delta 46 xcmdm^uv=k6C?|7bS^DH?4&}|&oZFbdoK@TklU4atH&^mZW&{ar=I7I40swX54z2(I diff --git a/cloud/azure/redis/inputs.tf b/cloud/azure/redis/inputs.tf index 4b14102..e006091 100644 --- a/cloud/azure/redis/inputs.tf +++ b/cloud/azure/redis/inputs.tf @@ -40,7 +40,7 @@ variable "status_message" { variable "status_time_aggregator" { description = "Monitor aggregator for Redis status [available values: min, max or avg]" type = "string" - default = "avg" + default = "max" } variable "status_timeframe" { @@ -98,7 +98,7 @@ variable "percent_processor_time_message" { variable "percent_processor_time_time_aggregator" { description = "Monitor aggregator for Redis processor [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "percent_processor_time_timeframe" { @@ -132,7 +132,7 @@ variable "server_load_rate_message" { variable "server_load_rate_time_aggregator" { description = "Monitor aggregator for Redis server load [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "server_load_rate_timeframe" { diff --git a/cloud/azure/servicebus/README.md b/cloud/azure/servicebus/README.md index 672193d41d5ab0a55dfad7aae8e31fecc0308a75..0b0507a7f45853d482e30efc245ae60a3689b064 100644 GIT binary patch delta 87 zcmZn=_{6{AJ0k~|E*Nl4W@0j)Y{sNFIhDzG@@6Kx$)A{tnYd~u>oQACZeq5be1O?= pG8aqOHB&K=jAM=jlG~X* p8F?qMgaMghEFb{`)~!HtJxe)nW?q6qjY3|&LJiQc&Cgi5nE)x68X*7x diff --git a/cloud/azure/servicebus/inputs.tf b/cloud/azure/servicebus/inputs.tf index 55c2a12..0987acd 100644 --- a/cloud/azure/servicebus/inputs.tf +++ b/cloud/azure/servicebus/inputs.tf @@ -40,7 +40,7 @@ variable "status_message" { variable "status_time_aggregator" { description = "Monitor aggregator for Service Bus status [available values: min, max or avg]" type = "string" - default = "min" + default = "max" } variable "status_timeframe" { diff --git a/cloud/azure/sql-database/README.md b/cloud/azure/sql-database/README.md index e46b08d3d015a0c78858fb967c5a49c0174126e3..a1b3a88b7ac30ca9fe6d985de24521965396b153 100644 GIT binary patch delta 216 zcmZ20*DJTdo{57?7Yw*2dodYLu4B@htjO%a##N(`Tu?fhkwba1Co|vVRjeYcV4=wm zxx^=5Vs@A;%n~(uEmH<}Zf0JBLXARRzCz99JeK8?#aM$TXR?M)-p?98S)Ogf-WskX$f%J(t+zP0aS}5N_#Y88-FFsx0D@~XUY(Qplc5y*s za_Zy_T%wa*I9!2poSa*LBolWrklf4Z0d`ADN$KQ#cIC->TuMOE0Inz?xr!?SE+@mL lG1;734B<{09y_3tC?1d@XL%xlq#Ca$GcY_h7x2zu1OVO1OK|`I diff --git a/cloud/azure/sql-database/inputs.tf b/cloud/azure/sql-database/inputs.tf index 4ce6680..38a583a 100644 --- a/cloud/azure/sql-database/inputs.tf +++ b/cloud/azure/sql-database/inputs.tf @@ -40,7 +40,7 @@ variable "cpu_message" { variable "cpu_time_aggregator" { description = "Monitor aggregator for SQL CPU [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "cpu_timeframe" { @@ -74,7 +74,7 @@ variable "diskspace_message" { variable "diskspace_time_aggregator" { description = "Monitor aggregator for SQL disk space [available values: min, max or avg]" type = "string" - default = "avg" + default = "max" } variable "diskspace_timeframe" { diff --git a/cloud/azure/storage/README.md b/cloud/azure/storage/README.md index 72cf5ae..1565478 100644 --- a/cloud/azure/storage/README.md +++ b/cloud/azure/storage/README.md @@ -32,64 +32,64 @@ Inputs | Name | Description | Type | Default | Required | |------|-------------|:----:|:-----:|:-----:| -| authorization_error_requests_time_aggregator | Monitor aggregator for Storage authorization errors [available values: min, max, sum or avg] | string | `avg` | no | | authorization_error_requests_message | Custom message for Storage authorization errors monitor | string | `` | no | | authorization_error_requests_silenced | Groups to mute for Storage authorization errors monitor | map | `` | no | | authorization_error_requests_threshold_critical | Maximum acceptable percent of authorization error requests for a storage | string | `90` | no | | authorization_error_requests_threshold_warning | Warning regarding acceptable percent of authorization error requests for a storage | string | `50` | no | +| authorization_error_requests_time_aggregator | Monitor aggregator for Storage authorization errors [available values: min, max or avg] | string | `min` | no | | authorization_error_requests_timeframe | Monitor timeframe for Storage authorization errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| availability_time_aggregator | Monitor aggregator for Storage availability [available values: min, max or avg] | string | `avg` | no | | availability_message | Custom message for Storage availability monitor | string | `` | no | | availability_silenced | Groups to mute for Storage availability monitor | map | `` | no | | availability_threshold_critical | Minimum acceptable percent of availability for a storage | string | `50` | no | | availability_threshold_warning | Warning regarding acceptable percent of availability for a storage | string | `90` | no | +| availability_time_aggregator | Monitor aggregator for Storage availability [available values: min, max or avg] | string | `max` | no | | availability_timeframe | Monitor timeframe for Storage availability [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| client_other_error_requests_time_aggregator | Monitor aggregator for Storage other errors [available values: min, max or avg] | string | `avg` | no | | client_other_error_requests_message | Custom message for Storage other errors monitor | string | `` | no | | client_other_error_requests_silenced | Groups to mute for Storage other errors monitor | map | `` | no | | client_other_error_requests_threshold_critical | Maximum acceptable percent of client other error requests for a storage | string | `90` | no | | client_other_error_requests_threshold_warning | Warning regarding acceptable percent of client other error requests for a storage | string | `50` | no | +| client_other_error_requests_time_aggregator | Monitor aggregator for Storage other errors [available values: min, max or avg] | string | `min` | no | | client_other_error_requests_timeframe | Monitor timeframe for Storage other errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | delay | Delay in seconds for the metric evaluation | string | `900` | no | | environment | Architecture environment | string | - | yes | | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | -| latency_time_aggregator | Monitor aggregator for Storage latency [available values: min, max or avg] | string | `min` | no | | latency_message | Custom message for Storage latency monitor | string | `` | no | | latency_silenced | Groups to mute for Storage latency monitor | map | `` | no | | latency_threshold_critical | Maximum acceptable end to end latency (ms) for a storage | string | `2000` | no | | latency_threshold_warning | Warning regarding acceptable end to end latency (ms) for a storage | string | `1000` | no | +| latency_time_aggregator | Monitor aggregator for Storage latency [available values: min, max or avg] | string | `min` | no | | latency_timeframe | Monitor timeframe for Storage latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | message | Message sent when a Redis monitor is triggered | string | - | yes | -| network_error_requests_time_aggregator | Monitor aggregator for Storage network errors [available values: min, max or avg] | string | `avg` | no | | network_error_requests_message | Custom message for Storage network errors monitor | string | `` | no | | network_error_requests_silenced | Groups to mute for Storage network errors monitor | map | `` | no | | network_error_requests_threshold_critical | Maximum acceptable percent of network error requests for a storage | string | `90` | no | | network_error_requests_threshold_warning | Warning regarding acceptable percent of network error requests for a storage | string | `50` | no | +| network_error_requests_time_aggregator | Monitor aggregator for Storage network errors [available values: min, max or avg] | string | `min` | no | | network_error_requests_timeframe | Monitor timeframe for Storage network errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| server_other_error_requests_time_aggregator | Monitor aggregator for Storage other errors [available values: min, max or avg] | string | `avg` | no | | server_other_error_requests_message | Custom message for Storage server other errors monitor | string | `` | no | | server_other_error_requests_silenced | Groups to mute for Storage server other errors monitor | map | `` | no | | server_other_error_requests_threshold_critical | Maximum acceptable percent of server other error requests for a storage | string | `90` | no | | server_other_error_requests_threshold_warning | Warning regarding acceptable percent of server other error requests for a storage | string | `50` | no | +| server_other_error_requests_time_aggregator | Monitor aggregator for Storage other errors [available values: min, max or avg] | string | `min` | no | | server_other_error_requests_timeframe | Monitor timeframe for Storage server other errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| successful_requests_time_aggregator | Monitor aggregator for Storage sucessful requests [available values: min, max or avg] | string | `avg` | no | | successful_requests_message | Custom message for Storage sucessful requests monitor | string | `` | no | | successful_requests_silenced | Groups to mute for Storage sucessful requests monitor | map | `` | no | | successful_requests_threshold_critical | Minimum acceptable percent of successful requests for a storage | string | `10` | no | | successful_requests_threshold_warning | Warning regarding acceptable percent of successful requests for a storage | string | `30` | no | +| successful_requests_time_aggregator | Monitor aggregator for Storage sucessful requests [available values: min, max or avg] | string | `max` | no | | successful_requests_timeframe | Monitor timeframe for Storage sucessful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| throttling_error_requests_time_aggregator | Monitor aggregator for Storage throttling errors [available values: min, max or avg] | string | `avg` | no | | throttling_error_requests_message | Custom message for Storage throttling error monitor | string | `` | no | | throttling_error_requests_silenced | Groups to mute for Storage throttling error monitor | map | `` | no | | throttling_error_requests_threshold_critical | Maximum acceptable percent of throttling error requests for a storage | string | `90` | no | | throttling_error_requests_threshold_warning | Warning regarding acceptable percent of throttling error requests for a storage | string | `50` | no | +| throttling_error_requests_time_aggregator | Monitor aggregator for Storage throttling errors [available values: min, max or avg] | string | `min` | no | | throttling_error_requests_timeframe | Monitor timeframe for Storage throttling errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| timeout_error_requests_time_aggregator | Monitor aggregator for Storage timeout [available values: min, max or avg] | string | `avg` | no | | timeout_error_requests_message | Custom message for Storage timeout monitor | string | `` | no | | timeout_error_requests_silenced | Groups to mute for Storage timeout monitor | map | `` | no | | timeout_error_requests_threshold_critical | Maximum acceptable percent of timeout error requests for a storage | string | `90` | no | | timeout_error_requests_threshold_warning | Warning regarding acceptable percent of timeout error requests for a storage | string | `50` | no | +| timeout_error_requests_time_aggregator | Monitor aggregator for Storage timeout [available values: min, max or avg] | string | `min` | no | | timeout_error_requests_timeframe | Monitor timeframe for Storage timeout [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | Related documentation @@ -102,3 +102,4 @@ DataDog blog: [https://www.datadoghq.com/blog/monitor-azure-storage-datadog/](ht Azure Storage metrics documentation: [https://docs.microsoft.com/en-us/azure/storage/common/storage-monitor-storage-account](https://docs.microsoft.com/en-us/azure/storage/common/storage-monitor-storage-account) Azure Storage metrics detailed documentation [https://docs.microsoft.com/en-us/rest/api/storageservices/storage-analytics-metrics-table-schema](https://docs.microsoft.com/en-us/rest/api/storageservices/storage-analytics-metrics-table-schema) + \ No newline at end of file diff --git a/cloud/azure/storage/inputs.tf b/cloud/azure/storage/inputs.tf index 72668a4..a2f527f 100644 --- a/cloud/azure/storage/inputs.tf +++ b/cloud/azure/storage/inputs.tf @@ -40,7 +40,7 @@ variable "availability_message" { variable "availability_time_aggregator" { description = "Monitor aggregator for Storage availability [available values: min, max or avg]" type = "string" - default = "avg" + default = "max" } variable "availability_timeframe" { @@ -74,7 +74,7 @@ variable "successful_requests_message" { variable "successful_requests_time_aggregator" { description = "Monitor aggregator for Storage sucessful requests [available values: min, max or avg]" type = "string" - default = "avg" + default = "max" } variable "successful_requests_timeframe" { @@ -142,7 +142,7 @@ variable "timeout_error_requests_message" { variable "timeout_error_requests_time_aggregator" { description = "Monitor aggregator for Storage timeout [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "timeout_error_requests_timeframe" { @@ -176,7 +176,7 @@ variable "network_error_requests_message" { variable "network_error_requests_time_aggregator" { description = "Monitor aggregator for Storage network errors [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "network_error_requests_timeframe" { @@ -210,7 +210,7 @@ variable "throttling_error_requests_message" { variable "throttling_error_requests_time_aggregator" { description = "Monitor aggregator for Storage throttling errors [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "throttling_error_requests_timeframe" { @@ -244,7 +244,7 @@ variable "server_other_error_requests_message" { variable "server_other_error_requests_time_aggregator" { description = "Monitor aggregator for Storage other errors [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "server_other_error_requests_timeframe" { @@ -278,7 +278,7 @@ variable "client_other_error_requests_message" { variable "client_other_error_requests_time_aggregator" { description = "Monitor aggregator for Storage other errors [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "client_other_error_requests_timeframe" { @@ -312,7 +312,7 @@ variable "authorization_error_requests_message" { variable "authorization_error_requests_time_aggregator" { description = "Monitor aggregator for Storage authorization errors [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "authorization_error_requests_timeframe" { diff --git a/cloud/azure/stream-analytics/README.md b/cloud/azure/stream-analytics/README.md index f848f208438d5b2a7ca53cde03dfc20e6ed55df0..0658fefc36619319f23328be75f3edf427e5fd83 100644 GIT binary patch delta 61 zcmX@Ba!zGK5DRl|X5M6fX1UG9EWYeujxM*{q0-7@2buD>k3zq0-7(oJ?PxEpygJsV1OK<)x H5XA@pMQamL diff --git a/cloud/azure/stream-analytics/inputs.tf b/cloud/azure/stream-analytics/inputs.tf index 2e07ded..615783d 100644 --- a/cloud/azure/stream-analytics/inputs.tf +++ b/cloud/azure/stream-analytics/inputs.tf @@ -40,7 +40,7 @@ variable "status_message" { variable "status_time_aggregator" { description = "Monitor aggregator for Stream Analytics status [available values: min, max or avg]" type = "string" - default = "avg" + default = "max" } variable "status_timeframe" { @@ -64,7 +64,7 @@ variable "su_utilization_message" { variable "su_utilization_time_aggregator" { description = "Monitor aggregator for Stream Analytics utilization [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "su_utilization_timeframe" { @@ -126,7 +126,7 @@ variable "conversion_errors_message" { variable "conversion_errors_time_aggregator" { description = "Monitor aggregator for Stream Analytics conversion errors [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "conversion_errors_timeframe" { @@ -160,7 +160,7 @@ variable "runtime_errors_message" { variable "runtime_errors_time_aggregator" { description = "Monitor aggregator for Stream Analytics runtime errors [available values: min, max or avg]" type = "string" - default = "avg" + default = "min" } variable "runtime_errors_timeframe" { diff --git a/common/alerting-message/README.md b/common/alerting-message/README.md index 067682ee9e8401f463ea72d1bae9d4e0d62ec26a..d9883f98c08d61ed8844977d105aeefd7af1450f 100644 GIT binary patch delta 106 zcmbQj-O01zI*Y1*X-Pq8Niml$1aNWHDEKAjrYh7ZxTF>*7iAWdWaj5h{>vn31e8h4 vNi8bL%uCnJO)V}?Ob4k7$w*a5Pt8j$N-RlDQGkgTmlOe&O}@->kdXlZc?l&R delta 11 ScmeC=nZmu{I?H5l*1Z53)C6Dv diff --git a/common/alerting-message/output.tf b/common/alerting-message/output.tf index 5166314..7865779 100644 --- a/common/alerting-message/output.tf +++ b/common/alerting-message/output.tf @@ -1,3 +1,4 @@ output "alerting-message" { + description = "The generated message string" value = "${data.template_file.alerting-message.rendered}" } diff --git a/databases/mongodb/README.md b/databases/mongodb/README.md index cbb2a64..b665243 100644 --- a/databases/mongodb/README.md +++ b/databases/mongodb/README.md @@ -79,7 +79,8 @@ Inputs | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | | message | Message sent when an alert is triggered | string | - | yes | -| mongodb_replicaset_time_aggregator | Monitor aggregator for Mongodb replicaset [available values: min, max or avg] | string | `avg` | no | | mongodb_replicaset_message | Custom message for Mongodb replicaset monitor | string | `` | no | | mongodb_replicaset_silenced | Groups to mute for Mongodb replicaset monitor | map | `` | no | +| mongodb_replicaset_time_aggregator | Monitor aggregator for Mongodb replicaset [available values: min, max or avg] | string | `max` | no | | mongodb_replicaset_timeframe | Monitor timeframe for Mongodb replicaset [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | + diff --git a/databases/mongodb/inputs.tf b/databases/mongodb/inputs.tf index a3d8f59..0df8a02 100644 --- a/databases/mongodb/inputs.tf +++ b/databases/mongodb/inputs.tf @@ -39,7 +39,7 @@ variable "mongodb_replicaset_message" { variable "mongodb_replicaset_time_aggregator" { description = "Monitor aggregator for Mongodb replicaset [available values: min, max or avg]" type = "string" - default = "avg" + default = "max" } variable "mongodb_replicaset_timeframe" { diff --git a/middleware/apache/README.md b/middleware/apache/README.md index 100631e..f450f8f 100644 --- a/middleware/apache/README.md +++ b/middleware/apache/README.md @@ -19,15 +19,16 @@ Creates a DataDog monitors with the following checks : * Apache connect -Inputs ------- - -| Name | Description | Type | Default | Required | -|------|-------------|:----:|:-----:|:-----:| -| apache_connect_message | Custom message for Apache process monitor | string | `` | no | -| apache_connect_silenced | Groups to mute for Apache process monitor | map | `` | no | -| delay | Delay in seconds for the metric evaluation | string | `15` | no | -| environment | Architecture Environment | string | - | yes | -| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | -| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | -| message | Message sent when an alert is triggered | string | - | yes | +Inputs +------ + +| Name | Description | Type | Default | Required | +|------|-------------|:----:|:-----:|:-----:| +| apache_connect_message | Custom message for Apache process monitor | string | `` | no | +| apache_connect_silenced | Groups to mute for Apache process monitor | map | `` | no | +| delay | Delay in seconds for the metric evaluation | string | `15` | no | +| environment | Architecture Environment | string | - | yes | +| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | +| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | +| message | Message sent when an alert is triggered | string | - | yes | + diff --git a/middleware/nginx/README.md b/middleware/nginx/README.md index 90935cd..09b0386 100644 --- a/middleware/nginx/README.md +++ b/middleware/nginx/README.md @@ -19,15 +19,16 @@ Creates a DataDog monitors with the following checks : * Nginx connect -Inputs ------- - -| Name | Description | Type | Default | Required | -|------|-------------|:----:|:-----:|:-----:| -| environment | Architecture Environment | string | - | yes | -| delay | Delay in seconds for the metric evaluation | string | `15` | no | -| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | -| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | -| message | Message sent when an alert is triggered | string | - | yes | -| nginx_connect_message | Custom message for Nginx process monitor | string | `` | no | -| nginx_connect_silenced | Groups to mute for Nginx process monitor | map | `` | no | +Inputs +------ + +| Name | Description | Type | Default | Required | +|------|-------------|:----:|:-----:|:-----:| +| delay | Delay in seconds for the metric evaluation | string | `15` | no | +| environment | Architecture Environment | string | - | yes | +| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | +| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | +| message | Message sent when an alert is triggered | string | - | yes | +| nginx_connect_message | Custom message for Nginx process monitor | string | `` | no | +| nginx_connect_silenced | Groups to mute for Nginx process monitor | map | `` | no | + diff --git a/middleware/php-fpm/README.md b/middleware/php-fpm/README.md index 9920e2a..7da65aa 100644 --- a/middleware/php-fpm/README.md +++ b/middleware/php-fpm/README.md @@ -20,21 +20,22 @@ Creates a DataDog monitors with the following checks : * PHP FPM connect * PHP FPM load -Inputs ------- - -| Name | Description | Type | Default | Required | -|------|-------------|:----:|:-----:|:-----:| -| delay | Delay in seconds for the metric evaluation | string | `15` | no | -| environment | Architecture Environment | string | - | yes | -| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | -| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | -| message | Message sent when an alert is triggered | string | - | yes | -| php_fpm_busy_time_aggregator | Monitor aggregator for PHP FPM busy worker [available values: min, max or avg] | string | `avg` | no | -| php_fpm_busy_message | Custom message for PHP FPM busy worker monitor | string | `` | no | -| php_fpm_busy_silenced | Groups to mute for PHP FPM busy worker monitor | map | `` | no | -| php_fpm_busy_threshold_critical | php fpm busy critical threshold | string | `0.9` | no | -| php_fpm_busy_threshold_warning | php fpm busy warning threshold | string | `0.8` | no | -| php_fpm_busy_timeframe | Monitor timeframe for PHP FPM busy worker [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_10m` | no | -| php_fpm_connect_message | Custom message for PHP FPM process monitor | string | `` | no | -| php_fpm_connect_silenced | Groups to mute for PHP FPM process monitor | map | `` | no | +Inputs +------ + +| Name | Description | Type | Default | Required | +|------|-------------|:----:|:-----:|:-----:| +| delay | Delay in seconds for the metric evaluation | string | `15` | no | +| environment | Architecture Environment | string | - | yes | +| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | +| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | +| message | Message sent when an alert is triggered | string | - | yes | +| php_fpm_busy_message | Custom message for PHP FPM busy worker monitor | string | `` | no | +| php_fpm_busy_silenced | Groups to mute for PHP FPM busy worker monitor | map | `` | no | +| php_fpm_busy_threshold_critical | php fpm busy critical threshold | string | `0.9` | no | +| php_fpm_busy_threshold_warning | php fpm busy warning threshold | string | `0.8` | no | +| php_fpm_busy_time_aggregator | Monitor aggregator for PHP FPM busy worker [available values: min, max or avg] | string | `avg` | no | +| php_fpm_busy_timeframe | Monitor timeframe for PHP FPM busy worker [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_10m` | no | +| php_fpm_connect_message | Custom message for PHP FPM process monitor | string | `` | no | +| php_fpm_connect_silenced | Groups to mute for PHP FPM process monitor | map | `` | no | + diff --git a/system/generic/README.md b/system/generic/README.md index 05b4268..550a1d3 100644 --- a/system/generic/README.md +++ b/system/generic/README.md @@ -23,43 +23,44 @@ Creates a DataDog monitors with the following checks : * Free disk inodes * Free disk space -Inputs ------- - -| Name | Description | Type | Default | Required | -|------|-------------|:----:|:-----:|:-----:| -| cpu_high_time_aggregator | Monitor aggregator for CPU high [available values: min, max or avg] | string | `min` | no | -| cpu_high_message | Custom message for CPU high monitor | string | `` | no | -| cpu_high_silenced | Groups to mute for CPU high monitor | map | `` | no | -| cpu_high_threshold_critical | CPU high critical threshold | string | `95` | no | -| cpu_high_threshold_warning | CPU high warning threshold | string | `80` | no | -| cpu_high_timeframe | Monitor timeframe for CPU high [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| cpu_load_time_aggregator | Monitor aggregator for CPU load ratio [available values: min, max or avg] | string | `min` | no | -| cpu_load_message | Custom message for CPU load ratio monitor | string | `` | no | -| cpu_load_silenced | Groups to mute for CPU load ratio monitor | map | `` | no | -| cpu_load_threshold_critical | CPU load ratio critical threshold | string | `4` | no | -| cpu_load_threshold_warning | CPU load ratio warning threshold | string | `3` | no | -| cpu_load_timeframe | Monitor timeframe for CPU load ratio [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| delay | Delay in seconds for the metric evaluation | string | `15` | no | -| environment | Architecture Environment | string | - | yes | -| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | -| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | -| free_disk_inodes_time_aggregator | Monitor aggregator for Free disk inodes [available values: min, max or avg] | string | `min` | no | -| free_disk_inodes_message | Custom message for Free disk inodes monitor | string | `` | no | -| free_disk_inodes_silenced | Groups to mute for Free disk inodes monitor | map | `` | no | -| free_disk_inodes_threshold_critical | Free disk space critical threshold | string | `5` | no | -| free_disk_inodes_threshold_warning | Free disk space warning threshold | string | `10` | no | -| free_disk_inodes_timeframe | Monitor timeframe for Free disk inodes [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| free_disk_space_time_aggregator | Monitor aggregator for Free diskspace [available values: min, max or avg] | string | `min` | no | -| free_disk_space_message | Custom message for Free diskspace monitor | string | `` | no | -| free_disk_space_silenced | Groups to mute for Free diskspace monitor | map | `` | no | -| free_disk_space_threshold_critical | Free disk space critical threshold | string | `5` | no | -| free_disk_space_threshold_warning | Free disk space warning threshold | string | `10` | no | -| free_disk_space_timeframe | Monitor timeframe for Free diskspace [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | -| free_memory_time_aggregator | Monitor aggregator for Free memory [available values: min, max or avg] | string | `min` | no | -| free_memory_message | Custom message for Free memory monitor | string | - | yes | -| free_memory_silenced | Groups to mute for Free memory monitor | map | `` | no | -| free_memory_threshold_critical | Free disk space critical threshold | string | `5` | no | -| free_memory_threshold_warning | Free disk space warning threshold | string | `10` | no | -| free_memory_timeframe | Monitor timeframe for Free memory [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_1m` | no | -| message | Message sent when an alert is triggered | string | - | yes | +Inputs +------ + +| Name | Description | Type | Default | Required | +|------|-------------|:----:|:-----:|:-----:| +| cpu_high_message | Custom message for CPU high monitor | string | `` | no | +| cpu_high_silenced | Groups to mute for CPU high monitor | map | `` | no | +| cpu_high_threshold_critical | CPU high critical threshold | string | `90` | no | +| cpu_high_threshold_warning | CPU high warning threshold | string | `85` | no | +| cpu_high_time_aggregator | Monitor aggregator for CPU high [available values: min, max or avg] | string | `min` | no | +| cpu_high_timeframe | Monitor timeframe for CPU high [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_10m` | no | +| cpu_load_message | Custom message for CPU load ratio monitor | string | `` | no | +| cpu_load_silenced | Groups to mute for CPU load ratio monitor | map | `` | no | +| cpu_load_threshold_critical | CPU load ratio critical threshold | string | `2.5` | no | +| cpu_load_threshold_warning | CPU load ratio warning threshold | string | `2` | no | +| cpu_load_time_aggregator | Monitor aggregator for CPU load ratio [available values: min, max or avg] | string | `min` | no | +| cpu_load_timeframe | Monitor timeframe for CPU load ratio [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no | +| delay | Delay in seconds for the metric evaluation | string | `15` | no | +| environment | Architecture Environment | string | - | yes | +| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no | +| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | +| free_disk_inodes_message | Custom message for Free disk inodes monitor | string | `` | no | +| free_disk_inodes_silenced | Groups to mute for Free disk inodes monitor | map | `` | no | +| free_disk_inodes_threshold_critical | Free disk space critical threshold | string | `5` | no | +| free_disk_inodes_threshold_warning | Free disk space warning threshold | string | `10` | no | +| free_disk_inodes_time_aggregator | Monitor aggregator for Free disk inodes [available values: min, max or avg] | string | `min` | no | +| free_disk_inodes_timeframe | Monitor timeframe for Free disk inodes [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| free_disk_space_message | Custom message for Free diskspace monitor | string | `` | no | +| free_disk_space_silenced | Groups to mute for Free diskspace monitor | map | `` | no | +| free_disk_space_threshold_critical | Free disk space critical threshold | string | `10` | no | +| free_disk_space_threshold_warning | Free disk space warning threshold | string | `20` | no | +| free_disk_space_time_aggregator | Monitor aggregator for Free diskspace [available values: min, max or avg] | string | `min` | no | +| free_disk_space_timeframe | Monitor timeframe for Free diskspace [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| free_memory_message | Custom message for Free memory monitor | string | - | yes | +| free_memory_silenced | Groups to mute for Free memory monitor | map | `` | no | +| free_memory_threshold_critical | Free disk space critical threshold | string | `5` | no | +| free_memory_threshold_warning | Free disk space warning threshold | string | `10` | no | +| free_memory_time_aggregator | Monitor aggregator for Free memory [available values: min, max or avg] | string | `max` | no | +| free_memory_timeframe | Monitor timeframe for Free memory [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | +| message | Message sent when an alert is triggered | string | - | yes | + diff --git a/system/generic/inputs.tf b/system/generic/inputs.tf index f55e02c..2d522ee 100644 --- a/system/generic/inputs.tf +++ b/system/generic/inputs.tf @@ -52,12 +52,12 @@ variable "cpu_high_timeframe" { variable "cpu_high_threshold_warning" { description = "CPU high warning threshold" - default = 80 + default = 85 } variable "cpu_high_threshold_critical" { description = "CPU high critical threshold" - default = 95 + default = 90 } variable "cpu_load_silenced" { @@ -81,17 +81,17 @@ variable "cpu_load_time_aggregator" { variable "cpu_load_timeframe" { description = "Monitor timeframe for CPU load ratio [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" - default = "last_5m" + default = "last_15m" } variable "cpu_load_threshold_warning" { description = "CPU load ratio warning threshold" - default = 3 + default = 2 } variable "cpu_load_threshold_critical" { description = "CPU load ratio critical threshold" - default = 4 + default = 2.5 } variable "free_disk_space_silenced" { @@ -120,12 +120,12 @@ variable "free_disk_space_timeframe" { variable "free_disk_space_threshold_warning" { description = "Free disk space warning threshold" - default = 10 + default = 20 } variable "free_disk_space_threshold_critical" { description = "Free disk space critical threshold" - default = 5 + default = 10 } variable "free_disk_inodes_silenced" { @@ -176,13 +176,13 @@ variable "free_memory_message" { variable "free_memory_time_aggregator" { description = "Monitor aggregator for Free memory [available values: min, max or avg]" type = "string" - default = "min" + default = "max" } variable "free_memory_timeframe" { description = "Monitor timeframe for Free memory [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" - default = "last_15m" + default = "last_5m" } variable "free_memory_threshold_warning" { From e9be701e490e09da3b475159324dd7dcbcc7efb4 Mon Sep 17 00:00:00 2001 From: Quentin Manfroi Date: Wed, 27 Jun 2018 18:29:41 +0200 Subject: [PATCH 16/21] MON-191 terraform fmt --- common/alerting-message/output.tf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/common/alerting-message/output.tf b/common/alerting-message/output.tf index 7865779..8a9d93e 100644 --- a/common/alerting-message/output.tf +++ b/common/alerting-message/output.tf @@ -1,4 +1,4 @@ output "alerting-message" { description = "The generated message string" - value = "${data.template_file.alerting-message.rendered}" + value = "${data.template_file.alerting-message.rendered}" } From ebd7e724290b7ee16a16550db488936f774e68d4 Mon Sep 17 00:00:00 2001 From: Quentin Manfroi Date: Mon, 7 May 2018 22:44:08 +0200 Subject: [PATCH 17/21] MON-197 use usable memory instead of free to ignore cache and buffer --- system/generic/monitors-system.tf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/system/generic/monitors-system.tf b/system/generic/monitors-system.tf index f62a56a..e6c2428 100644 --- a/system/generic/monitors-system.tf +++ b/system/generic/monitors-system.tf @@ -139,7 +139,7 @@ resource "datadog_monitor" "datadog_free_memory" { query = < Date: Fri, 22 Jun 2018 14:39:06 +0200 Subject: [PATCH 18/21] MON-185 Fix status aggregator input --- cloud/azure/monitors.tf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/cloud/azure/monitors.tf b/cloud/azure/monitors.tf index b3d6dda..0b64f36 100644 --- a/cloud/azure/monitors.tf +++ b/cloud/azure/monitors.tf @@ -223,7 +223,7 @@ module "servicebus" { status_silenced = "${var.servicebus_status_silenced}" status_message = "${var.servicebus_status_message}" status_timeframe = "${var.servicebus_status_timeframe}" - status_timeframe_time_aggregator = "${var.servicebus_status_time_aggregator}" + status_time_aggregator = "${var.servicebus_status_time_aggregator}" } module "sqldatabase" { From a010d0a4ccf4071f47688874c615c77dd282dccf Mon Sep 17 00:00:00 2001 From: Quentin Manfroi Date: Wed, 27 Jun 2018 18:57:50 +0200 Subject: [PATCH 19/21] MON-185 terraform fmt --- cloud/azure/monitors.tf | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/cloud/azure/monitors.tf b/cloud/azure/monitors.tf index 0b64f36..09be0af 100644 --- a/cloud/azure/monitors.tf +++ b/cloud/azure/monitors.tf @@ -220,9 +220,9 @@ module "servicebus" { filter_tags_use_defaults = "${var.filter_tags_use_defaults}" filter_tags_custom = "${var.filter_tags_custom}" - status_silenced = "${var.servicebus_status_silenced}" - status_message = "${var.servicebus_status_message}" - status_timeframe = "${var.servicebus_status_timeframe}" + status_silenced = "${var.servicebus_status_silenced}" + status_message = "${var.servicebus_status_message}" + status_timeframe = "${var.servicebus_status_timeframe}" status_time_aggregator = "${var.servicebus_status_time_aggregator}" } From 60b51adaea4943eac6eab68d1fc973007de404eb Mon Sep 17 00:00:00 2001 From: Quentin Manfroi Date: Thu, 28 Jun 2018 10:09:11 +0200 Subject: [PATCH 20/21] MON-191 make the elasticsearch status aggregator hardcoded --- cloud/aws/elasticsearch/README.md | Bin 3484 -> 3346 bytes cloud/aws/elasticsearch/inputs.tf | 6 ------ .../elasticsearch/monitors-elasticsearch.tf | 2 +- 3 files changed, 1 insertion(+), 7 deletions(-) diff --git a/cloud/aws/elasticsearch/README.md b/cloud/aws/elasticsearch/README.md index e0582596616d0e414e71e97635bf1a365e09e210..44fb59687d48a0e8b393a10dc8b1f39c2e0c7486 100644 GIT binary patch delta 14 VcmbOuJxOXqJm=#xd18E1mXYy delta 31 ncmbOvHAi|wJm+LFc7w?WIM^rma|%z6W|3n`tk`VFd6^jiplS)X diff --git a/cloud/aws/elasticsearch/inputs.tf b/cloud/aws/elasticsearch/inputs.tf index 499b0c6..6f56332 100644 --- a/cloud/aws/elasticsearch/inputs.tf +++ b/cloud/aws/elasticsearch/inputs.tf @@ -38,12 +38,6 @@ variable "es_cluster_status_message" { default = "" } -variable "es_cluster_status_time_aggregator" { - description = "Monitor aggregator for ES cluster status [available values: min, max or avg]" - type = "string" - default = "max" -} - variable "es_cluster_status_timeframe" { description = "Monitor timeframe for ES cluster status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" type = "string" diff --git a/cloud/aws/elasticsearch/monitors-elasticsearch.tf b/cloud/aws/elasticsearch/monitors-elasticsearch.tf index 3f51e75..b46b5e1 100644 --- a/cloud/aws/elasticsearch/monitors-elasticsearch.tf +++ b/cloud/aws/elasticsearch/monitors-elasticsearch.tf @@ -18,7 +18,7 @@ resource "datadog_monitor" "es_cluster_status" { type = "metric alert" query = <= 2 From 318fa6a0cf8b4b95cb2cb57cbc9f50f37a8987c5 Mon Sep 17 00:00:00 2001 From: Quentin Manfroi Date: Thu, 28 Jun 2018 10:36:28 +0200 Subject: [PATCH 21/21] MON-191 typo on alb threshold description --- cloud/aws/alb/inputs.tf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/cloud/aws/alb/inputs.tf b/cloud/aws/alb/inputs.tf index 584c299..07cb8b3 100644 --- a/cloud/aws/alb/inputs.tf +++ b/cloud/aws/alb/inputs.tf @@ -160,7 +160,7 @@ variable "httpcode_alb_5xx_timeframe" { variable "httpcode_alb_5xx_threshold_critical" { default = 80 - description = "loadbalancer 5xxcritical threshold in percentage" + description = "loadbalancer 5xx critical threshold in percentage" } variable "httpcode_alb_5xx_threshold_warning" {