diff --git a/cloud/aws/apigateway/README.md b/cloud/aws/apigateway/README.md index d20226b..755cfce 100644 --- a/cloud/aws/apigateway/README.md +++ b/cloud/aws/apigateway/README.md @@ -35,14 +35,17 @@ Inputs | 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_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_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 917c7ed..83acd7c 100644 --- a/cloud/aws/apigateway/inputs.tf +++ b/cloud/aws/apigateway/inputs.tf @@ -33,6 +33,12 @@ variable "latency_message" { default = "" } +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" + default = "last_5m" +} + variable "latency_threshold_critical" { default = 800 description = "Alerting threshold in milliseconds" @@ -59,6 +65,12 @@ variable "http_5xx_requests_message" { default = "" } +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" + default = "last_5m" +} + variable "http_5xx_requests_threshold_critical" { default = 20 description = "Maximum critical acceptable percent of 5xx errors" @@ -85,6 +97,12 @@ variable "http_4xx_requests_message" { default = "" } +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" + default = "last_5m" +} + variable "http_4xx_requests_threshold_critical" { default = 30 description = "Maximum critical acceptable percent of 4xx errors" diff --git a/cloud/aws/apigateway/monitors-api.tf b/cloud/aws/apigateway/monitors-api.tf index 07ed72e..8fd52a7 100644 --- a/cloud/aws/apigateway/monitors-api.tf +++ b/cloud/aws/apigateway/monitors-api.tf @@ -5,7 +5,7 @@ resource "datadog_monitor" "API_Gateway_latency" { message = "${coalesce(var.latency_message, var.message)}" query = < ${var.latency_threshold_critical} EOF @@ -36,7 +36,7 @@ resource "datadog_monitor" "API_http_5xx_errors_count" { message = "${coalesce(var.http_5xx_requests_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 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_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_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 | | 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 | | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no | diff --git a/cloud/aws/elasticsearch/inputs.tf b/cloud/aws/elasticsearch/inputs.tf index 55b26c5..4d3fb2c 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_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" + default = "last_30m" +} + variable "es_cluster_volume_size" { description = "ElasticSearch Domain volume size (in GB)" } @@ -54,6 +60,12 @@ variable "diskspace_message" { default = "" } +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" + default = "last_15m" +} + variable "diskspace_threshold_warning" { description = "Disk free space in percent (warning threshold)" default = "20" @@ -76,6 +88,12 @@ variable "cpu_message" { default = "" } +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" + default = "last_15m" +} + variable "cpu_threshold_warning" { description = "CPU usage in percent (warning threshold)" default = "80" diff --git a/cloud/aws/elasticsearch/monitors-elasticsearch.tf b/cloud/aws/elasticsearch/monitors-elasticsearch.tf index 0db5ae1..47dc1e2 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 @@ -52,7 +52,7 @@ 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 424b8c7..ec188f8 100644 --- a/cloud/aws/elb/README.md +++ b/cloud/aws/elb/README.md @@ -30,32 +30,37 @@ Inputs | Name | Description | Type | Default | Required | |------|-------------|:----:|:-----:|:-----:| -| dd_aws_elb | # ELB | string | `disable` | 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 | | 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_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_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 | -| delay | Delay in seconds for the metric evaluation | string | `900` | 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 | diff --git a/cloud/aws/elb/inputs.tf b/cloud/aws/elb/inputs.tf index 6cd1338..4809da0 100644 --- a/cloud/aws/elb/inputs.tf +++ b/cloud/aws/elb/inputs.tf @@ -25,10 +25,6 @@ variable "filter_tags_custom" { } ## ELB -variable "dd_aws_elb" { - default = "disable" -} - variable "elb_no_healthy_instance_silenced" { description = "Groups to mute for ELB no healty instance monitor" type = "map" @@ -41,6 +37,12 @@ variable "elb_no_healthy_instance_message" { default = "" } +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" + default = "last_5m" +} + variable "elb_4xx_silenced" { description = "Groups to mute for ELB 4xx errors monitor" type = "map" @@ -53,6 +55,12 @@ variable "elb_4xx_message" { default = "" } +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" + default = "last_5m" +} + variable "elb_4xx_threshold_warning" { description = "loadbalancer 4xx warning threshold in percentage" default = 5 @@ -75,6 +83,12 @@ variable "elb_5xx_message" { default = "" } +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" + default = "last_5m" +} + variable "elb_5xx_threshold_warning" { description = "loadbalancer 5xx warning threshold in percentage" default = 5 @@ -97,6 +111,12 @@ variable "elb_backend_4xx_message" { default = "" } +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" + default = "last_5m" +} + variable "elb_backend_4xx_threshold_warning" { description = "loadbalancer backend 4xx warning threshold in percentage" default = 5 @@ -119,6 +139,12 @@ variable "elb_backend_5xx_message" { default = "" } +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" + default = "last_5m" +} + variable "elb_backend_5xx_threshold_warning" { description = "loadbalancer backend 5xx warning threshold in percentage" default = 5 @@ -141,6 +167,12 @@ variable "elb_backend_latency_message" { default = "" } +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" + default = "last_5m" +} + variable "elb_backend_latency_warning" { description = "latency warning threshold in seconds" default = 1 diff --git a/cloud/aws/elb/monitors-elb.tf b/cloud/aws/elb/monitors-elb.tf index 1977a08..a36f403 100644 --- a/cloud/aws/elb/monitors-elb.tf +++ b/cloud/aws/elb/monitors-elb.tf @@ -11,7 +11,7 @@ resource "datadog_monitor" "ELB_no_healthy_instances" { message = "${coalesce(var.elb_no_healthy_instance_message, var.message)}" query = < ${var.elb_backend_latency_critical} EOF diff --git a/cloud/aws/rds/README.md b/cloud/aws/rds/README.md index c3eaa1d..f921ee0 100644 --- a/cloud/aws/rds/README.md +++ b/cloud/aws/rds/README.md @@ -29,12 +29,14 @@ Inputs | cpu_silenced | Groups to mute for RDS CPU usage 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 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_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 | | diskspace_threshold_warning | Disk free space in percent (warning threshold) | string | `20` | no | +| diskspace_timeframe | 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`] | string | `last_15m` | no | | environment | Architecture Environment | string | - | yes | -| delay | Delay in seconds for the metric evaluation | string | `900` | 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 | diff --git a/cloud/aws/rds/inputs.tf b/cloud/aws/rds/inputs.tf index d651b09..37be0e2 100644 --- a/cloud/aws/rds/inputs.tf +++ b/cloud/aws/rds/inputs.tf @@ -38,6 +38,12 @@ variable "cpu_message" { default = "" } +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" + default = "last_15m" +} + variable "cpu_threshold_warning" { description = "CPU usage in percent (warning threshold)" default = "80" @@ -60,6 +66,12 @@ variable "diskspace_message" { default = "" } +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" + default = "last_15m" +} + variable "diskspace_threshold_warning" { description = "Disk free space in percent (warning threshold)" default = "20" diff --git a/cloud/aws/rds/monitors-rds.tf b/cloud/aws/rds/monitors-rds.tf index 79b1670..2717d1d 100644 --- a/cloud/aws/rds/monitors-rds.tf +++ b/cloud/aws/rds/monitors-rds.tf @@ -14,7 +14,7 @@ resource "datadog_monitor" "rds_cpu_90_15min" { type = "metric alert" query = < ${var.cpu_threshold_critical} EOF @@ -46,7 +46,7 @@ resource "datadog_monitor" "rds_free_space_low" { type = "metric alert" query = <` | no | +| vpn_status_timeframe | Monitor timeframe for VPN status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | diff --git a/cloud/aws/vpn/inputs.tf b/cloud/aws/vpn/inputs.tf index 7e9f468..13314b6 100644 --- a/cloud/aws/vpn/inputs.tf +++ b/cloud/aws/vpn/inputs.tf @@ -35,3 +35,9 @@ variable "vpn_status_message" { type = "string" default = "" } + +variable "vpn_status_timeframe" { + description = "Monitor timeframe for VPN status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" + type = "string" + default = "last_5m" +} diff --git a/cloud/aws/vpn/monitors-vpn.tf b/cloud/aws/vpn/monitors-vpn.tf index 8a3cddb..1f94ebf 100644 --- a/cloud/aws/vpn/monitors-vpn.tf +++ b/cloud/aws/vpn/monitors-vpn.tf @@ -11,7 +11,7 @@ resource "datadog_monitor" "VPN_status" { message = "${coalesce(var.vpn_status_message, var.message)}" query = <