wbyc/terraform-datadog-old-monitors
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merged in MON-191-make-the-aggregator-customizable (pull request #87)

Browse Source 
MON-191 make the aggregator customizable

Approved-by: Alexandre Gaillet <alexandre.gaillet@fr.clara.net>
Approved-by: Boris Rousseau <boris.rousseau@morea.fr>
Approved-by: Quentin Manfroi <quentin.manfroi@yahoo.fr>
Approved-by: Laurent Piroelle <laurent.piroelle@fr.clara.net>
This commit is contained in:
Alexandre Gaillet 2018-06-28 08:37:52 +00:00 committed by Quentin Manfroi
commit 12fcaba6cc
63 changed files with 1224 additions and 327 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
cloud/aws/alb/README.md
View File

Binary file not shown.

36
cloud/aws/alb/inputs.tf
View File

@ -38,10 +38,16 @@ variable "alb_no_healthy_instances_message" {
default = ""
}
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"
}
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" {
@ -56,6 +62,12 @@ variable "latency_message" {
default = ""
}
variable "latency_time_aggregator" {
description = "Monitor aggregator for ALB latency [available values: min, max 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"
@ -72,30 +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_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"
}
@ -128,30 +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_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"
description = "loadbalancer 5xx critical threshold in percentage"
}
variable "httpcode_elb_5xx_threshold_warning" {
variable "httpcode_alb_5xx_threshold_warning" {
default = 60
description = "loadbalancer 5xx warning threshold in percentage"
}

56
cloud/aws/alb/monitors-alb.tf
View File

@ -14,9 +14,9 @@ resource "datadog_monitor" "ALB_no_healthy_instances" {
message = "${coalesce(var.alb_no_healthy_instances_message, var.message)}"
query = <<EOF
min(${var.alb_no_healthy_instances_timeframe}): (
${var.alb_no_healthy_instances_time_aggregator}(${var.alb_no_healthy_instances_timeframe}): (
min:aws.applicationelb.healthy_host_count{${data.template_file.filter.rendered}} by {region,loadbalancer}
) <= 0
) < 1
EOF
evaluation_delay = "${var.delay}"
@ -43,8 +43,8 @@ resource "datadog_monitor" "ALB_latency" {
message = "${coalesce(var.latency_message, var.message)}"
query = <<EOF
min(${var.latency_timeframe}): (
min:aws.applicationelb.target_response_time.average{${data.template_file.filter.rendered}} by {region,loadbalancer}
${var.latency_time_aggregator}(${var.latency_timeframe}): (
avg:aws.applicationelb.target_response_time.average{${data.template_file.filter.rendered}} by {region,loadbalancer}
) > ${var.latency_threshold_critical}
EOF
@ -67,26 +67,26 @@ resource "datadog_monitor" "ALB_latency" {
tags = ["env:${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 = "${coalesce(var.httpcode_alb_5xx_message, var.message)}"
query = <<EOF
min(${var.httpcode_elb_5xx_timeframe}): (
sum(${var.httpcode_alb_5xx_timeframe}): (
default(
min:aws.applicationelb.httpcode_elb_5xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
(min:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() + ${var.artificial_requests_count}),
avg:aws.applicationelb.httpcode_alb_5xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
(avg:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() + ${var.artificial_requests_count}),
0) * 100
) > ${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 = "${coalesce(var.httpcode_alb_4xx_message, var.message)}"
query = <<EOF
min(${var.httpcode_elb_4xx_timeframe}): (
sum(${var.httpcode_alb_4xx_timeframe}): (
default(
min:aws.applicationelb.httpcode_elb_4xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
(min:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() + ${var.artificial_requests_count}),
avg:aws.applicationelb.httpcode_alb_4xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
(avg:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() + ${var.artificial_requests_count}),
0) * 100
) > ${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 = "${coalesce(var.httpcode_target_5xx_message, var.message)}"
query = <<EOF
min(${var.httpcode_target_5xx_timeframe}): (
sum(${var.httpcode_target_5xx_timeframe}): (
default(
min:aws.applicationelb.httpcode_target_5xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
(min:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() + ${var.artificial_requests_count}),
avg:aws.applicationelb.httpcode_target_5xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
(avg:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() + ${var.artificial_requests_count}),
0) * 100
) > ${var.httpcode_target_5xx_threshold_critical}
EOF
@ -172,10 +172,10 @@ resource "datadog_monitor" "ALB_httpcode_target_4xx" {
message = "${coalesce(var.httpcode_target_4xx_message, var.message)}"
query = <<EOF
min(${var.httpcode_target_4xx_timeframe}): (
sum(${var.httpcode_target_4xx_timeframe}): (
default(
min:aws.applicationelb.httpcode_target_4xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
(min:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() + ${var.artificial_requests_count}),
avg:aws.applicationelb.httpcode_target_4xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
(avg:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() + ${var.artificial_requests_count}),
0) * 100
) > ${var.httpcode_target_4xx_threshold_critical}
EOF

BIN
cloud/aws/apigateway/README.md
View File

Binary file not shown.

6
cloud/aws/apigateway/inputs.tf
View File

@ -33,6 +33,12 @@ variable "latency_message" {
default = ""
}
variable "latency_time_aggregator" {
description = "Monitor aggregator for API Gateway latency [available values: min, max 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"

16
cloud/aws/apigateway/monitors-api.tf
View File

@ -5,8 +5,8 @@ resource "datadog_monitor" "API_Gateway_latency" {
message = "${coalesce(var.latency_message, var.message)}"
query = <<EOF
min(${var.latency_timeframe}): (
min:aws.apigateway.latency{${var.filter_tags}} by {region,apiname}
${var.latency_time_aggregator}(${var.latency_timeframe}): (
avg:aws.apigateway.latency{${var.filter_tags}} by {region,apiname}
) > ${var.latency_threshold_critical}
EOF
@ -36,10 +36,10 @@ resource "datadog_monitor" "API_http_5xx_errors_count" {
message = "${coalesce(var.http_5xx_requests_message, var.message)}"
query = <<EOF
min(${var.http_5xx_requests_timeframe}): (
sum(${var.http_5xx_requests_timeframe}): (
default(
min:aws.apigateway.5xxerror{${var.filter_tags}} by {region,apiname}.as_count() /
(min:aws.apigateway.count{${var.filter_tags}} by {region,apiname}.as_count() + ${var.artificial_requests_count}),
avg:aws.apigateway.5xxerror{${var.filter_tags}} by {region,apiname}.as_count() /
(avg:aws.apigateway.count{${var.filter_tags}} by {region,apiname}.as_count() + ${var.artificial_requests_count}),
0) * 100
) > ${var.http_5xx_requests_threshold_critical}
EOF
@ -70,10 +70,10 @@ resource "datadog_monitor" "API_http_4xx_errors_count" {
message = "${coalesce(var.http_4xx_requests_message, var.message)}"
query = <<EOF
min(${var.http_4xx_requests_timeframe}): (
sum(${var.http_4xx_requests_timeframe}): (
default(
min:aws.apigateway.4xxerror{${var.filter_tags}} by {region,apiname}.as_count() /
(min:aws.apigateway.count{${var.filter_tags}} by {region,apiname}.as_count() + ${var.artificial_requests_count}),
avg:aws.apigateway.4xxerror{${var.filter_tags}} by {region,apiname}.as_count() /
(avg:aws.apigateway.count{${var.filter_tags}} by {region,apiname}.as_count() + ${var.artificial_requests_count}),
0) * 100
) > ${var.http_4xx_requests_threshold_critical}
EOF

BIN
cloud/aws/elasticsearch/README.md
View File

Binary file not shown.

12
cloud/aws/elasticsearch/inputs.tf
View File

@ -60,6 +60,12 @@ variable "diskspace_message" {
default = ""
}
variable "diskspace_time_aggregator" {
description = "Monitor aggregator for ES cluster diskspace [available values: min, max or avg]"
type = "string"
default = "max"
}
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 +94,12 @@ variable "cpu_message" {
default = ""
}
variable "cpu_time_aggregator" {
description = "Monitor aggregator for ES cluster cpu [available values: min, max or avg]"
type = "string"
default = "min"
}
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"

4
cloud/aws/elasticsearch/monitors-elasticsearch.tf
View File

@ -52,7 +52,7 @@ resource "datadog_monitor" "es_free_space_low" {
type = "metric alert"
query = <<EOF
avg(${var.diskspace_timeframe}): (
${var.diskspace_time_aggregator}(${var.diskspace_timeframe}): (
avg:aws.es.free_storage_space{${data.template_file.filter.rendered}} by {region,name} /
(${var.es_cluster_volume_size}*1000) * 100
) < ${var.diskspace_threshold_critical}
@ -86,7 +86,7 @@ resource "datadog_monitor" "es_cpu_90_15min" {
type = "metric alert"
query = <<EOF
avg(${var.cpu_timeframe}): (
${var.cpu_time_aggregator}(${var.cpu_timeframe}): (
avg:aws.es.cpuutilization{${data.template_file.filter.rendered}} by {region,name}
) > ${var.cpu_threshold_critical}
EOF

81
cloud/aws/elb/README.md
View File

@ -25,42 +25,45 @@ Creates DataDog monitors with the following checks :
* ELB backend http code 4xx percent to high
* ELB backend http code 5xx percent to high
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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 |

12
cloud/aws/elb/inputs.tf
View File

@ -37,6 +37,12 @@ variable "elb_no_healthy_instance_message" {
default = ""
}
variable "elb_no_healthy_instance_time_aggregator" {
description = "Monitor aggregator for ELB no healty instance [available values: min or max]"
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"
@ -167,6 +173,12 @@ variable "elb_backend_latency_message" {
default = ""
}
variable "elb_backend_latency_time_aggregator" {
description = "Monitor aggregator for ELB backend latency [available values: min, max 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"

30
cloud/aws/elb/monitors-elb.tf
View File

@ -11,7 +11,7 @@ resource "datadog_monitor" "ELB_no_healthy_instances" {
message = "${coalesce(var.elb_no_healthy_instance_message, var.message)}"
query = <<EOF
min(${var.elb_no_healthy_instance_timeframe}): (
${var.elb_no_healthy_instance_time_aggregator}(${var.elb_no_healthy_instance_timeframe}): (
min:aws.elb.healthy_host_count{${data.template_file.filter.rendered}} by {region,loadbalancername}
) < 1
EOF
@ -38,10 +38,10 @@ resource "datadog_monitor" "ELB_too_much_4xx" {
message = "${coalesce(var.elb_4xx_message, var.message)}"
query = <<EOF
min(${var.elb_4xx_timeframe}): (
sum(${var.elb_4xx_timeframe}): (
default(
min:aws.elb.httpcode_elb_4xx{${data.template_file.filter.rendered}} by {region,loadbalancername}.as_count() /
(min:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername}.as_count() + ${var.artificial_requests_count}),
avg:aws.elb.httpcode_elb_4xx{${data.template_file.filter.rendered}} by {region,loadbalancername}.as_count() /
(avg:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername}.as_count() + ${var.artificial_requests_count}),
0) * 100
) > ${var.elb_4xx_threshold_critical}
EOF
@ -73,10 +73,10 @@ resource "datadog_monitor" "ELB_too_much_5xx" {
message = "${coalesce(var.elb_5xx_message, var.message)}"
query = <<EOF
min(${var.elb_5xx_timeframe}): (
sum(${var.elb_5xx_timeframe}): (
default(
min:aws.elb.httpcode_elb_5xx{${data.template_file.filter.rendered}} by {region,loadbalancername} /
(min:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername} + ${var.artificial_requests_count}),
avg:aws.elb.httpcode_elb_5xx{${data.template_file.filter.rendered}} by {region,loadbalancername} /
(avg:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername} + ${var.artificial_requests_count}),
0) * 100
) > ${var.elb_5xx_threshold_critical}
EOF
@ -108,10 +108,10 @@ resource "datadog_monitor" "ELB_too_much_4xx_backend" {
message = "${coalesce(var.elb_backend_4xx_message, var.message)}"
query = <<EOF
min(${var.elb_backend_4xx_timeframe}): (
sum(${var.elb_backend_4xx_timeframe}): (
default(
min:aws.elb.httpcode_backend_4xx{${data.template_file.filter.rendered}} by {region,loadbalancername} /
(min:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername} + ${var.artificial_requests_count}),
avg:aws.elb.httpcode_backend_4xx{${data.template_file.filter.rendered}} by {region,loadbalancername} /
(avg:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername} + ${var.artificial_requests_count}),
0) * 100
) > ${var.elb_backend_4xx_threshold_critical}
EOF
@ -143,10 +143,10 @@ resource "datadog_monitor" "ELB_too_much_5xx_backend" {
message = "${coalesce(var.elb_backend_5xx_message, var.message)}"
query = <<EOF
min(${var.elb_backend_5xx_timeframe}): (
sum(${var.elb_backend_5xx_timeframe}): (
default(
min:aws.elb.httpcode_backend_5xx{${data.template_file.filter.rendered}} by {region,loadbalancername} /
(min:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername} + ${var.artificial_requests_count}),
avg:aws.elb.httpcode_backend_5xx{${data.template_file.filter.rendered}} by {region,loadbalancername} /
(avg:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername} + ${var.artificial_requests_count}),
0) * 100
) > ${var.elb_backend_5xx_threshold_critical}
EOF
@ -178,8 +178,8 @@ resource "datadog_monitor" "ELB_backend_latency" {
message = "${coalesce(var.elb_backend_latency_message, var.message)}"
query = <<EOF
min(${var.elb_backend_latency_warning}): (
min:aws.elb.latency{${data.template_file.filter.rendered}} by {region,loadbalancername}
${var.elb_backend_latency_time_aggregator}(${var.elb_backend_latency_timeframe}): (
avg:aws.elb.latency{${data.template_file.filter.rendered}} by {region,loadbalancername}
) > ${var.elb_backend_latency_critical}
EOF

BIN
cloud/aws/kinesis-firehose/README.md
View File

Binary file not shown.

8
cloud/aws/kinesis-firehose/monitors-kinesis-firehose.tf
View File

@ -14,10 +14,10 @@ resource "datadog_monitor" "firehose_incoming_records" {
type = "metric alert"
query = <<EOF
sum(${var.incoming_records_timeframe}): (
avg:aws.firehose.incoming_records{${data.template_file.filter.rendered}} by {region,deliverystreamname}
) <= 0
EOF
sum(${var.incoming_records_timeframe}): (
avg:aws.firehose.incoming_records{${data.template_file.filter.rendered}} by {region,deliverystreamname}
) <= 0
EOF
thresholds {
critical = 0

BIN
cloud/aws/rds/README.md
View File

Binary file not shown.

12
cloud/aws/rds/inputs.tf
View File

@ -38,6 +38,12 @@ variable "cpu_message" {
default = ""
}
variable "cpu_time_aggregator" {
description = "Monitor aggregator for RDS CPU usage [available values: min, max or avg]"
type = "string"
default = "min"
}
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_time_aggregator" {
description = "Monitor aggregator for RDS free diskspace [available values: min, max or avg]"
type = "string"
default = "min"
}
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"

4
cloud/aws/rds/monitors-rds.tf
View File

@ -14,7 +14,7 @@ resource "datadog_monitor" "rds_cpu_90_15min" {
type = "metric alert"
query = <<EOF
avg(${var.cpu_timeframe}): (
${var.cpu_time_aggregator}(${var.cpu_timeframe}): (
avg:aws.rds.cpuutilization{${data.template_file.filter.rendered}} by {region,name}
) > ${var.cpu_threshold_critical}
EOF
@ -46,7 +46,7 @@ resource "datadog_monitor" "rds_free_space_low" {
type = "metric alert"
query = <<EOF
avg(${var.diskspace_timeframe}): (
${var.diskspace_time_aggregator}(${var.diskspace_timeframe}): (
avg:aws.rds.free_storage_space{${data.template_file.filter.rendered}} by {region,name} /
avg:aws.rds.total_storage_space{${data.template_file.filter.rendered}} by {region,name} * 100
) < ${var.diskspace_threshold_critical}

BIN
cloud/aws/vpn/README.md
View File

Binary file not shown.

6
cloud/aws/vpn/inputs.tf
View File

@ -36,6 +36,12 @@ variable "vpn_status_message" {
default = ""
}
variable "vpn_status_time_aggregator" {
description = "Monitor aggregator for VPN status [available values: min, max or avg]"
type = "string"
default = "max"
}
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"

2
cloud/aws/vpn/monitors-vpn.tf
View File

@ -11,7 +11,7 @@ resource "datadog_monitor" "VPN_status" {
message = "${coalesce(var.vpn_status_message, var.message)}"
query = <<EOF
avg(${var.vpn_status_timeframe}): (
${var.vpn_status_time_aggregator}(${var.vpn_status_timeframe}): (
avg:aws.vpn.tunnel_state{${data.template_file.filter.rendered}} by {region,name}
) < 1
EOF

78
cloud/azure/README.md
View File

@ -36,193 +36,268 @@ Inputs
| apimanagement_failed_requests_silenced | Groups to mute for API Management failed requests monitor | map | `<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_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 | `<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_message | Custom message for API Management status monitor | string | `` | no |
| apimanagement_status_silenced | Groups to mute for API Management status monitor | map | `<map>` | 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 | `<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_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 | `<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_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 | `<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_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 | `<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_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 | `<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_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 | `<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 | `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 | `<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_message | Custom message for Event Hub errors monitor | string | `` | no |
| eventhub_errors_rate_silenced | Groups to mute for Event Hub errors monitor | map | `<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_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 | `<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_message | Custom message for Event Hub status monitor | string | `` | no |
| eventhub_status_silenced | Groups to mute for Event Hub status monitor | map | `<map>` | 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 |
| 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 | `<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_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 | `<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_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 | `<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_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 | `<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_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 | `<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_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 | `<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_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 | `<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_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 | `<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_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 | `<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_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 | `<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_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 | `<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_message | Custom message for IoT Hub status monitor | string | `` | no |
| iothub_status_silenced | Groups to mute for IoT Hub status monitor | map | `<map>` | 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 | `<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 | `<map>` | 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 |
| 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 | `<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_message | Custom message for Redis processor monitor | string | `` | no |
| redis_percent_processor_time_silenced | Groups to mute for Redis processor monitor | map | `<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 | `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 | `<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 | `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 | `<map>` | 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 | `<map>` | 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 |
| servicebus_status_aggregator | Monitor timeframe aggregator for Service Bus status [available values: min, max, sum or avg] | string | `min` | no |
| sqldatabase_cpu_message | Custom message for SQL CPU monitor | string | `` | no |
| sqldatabase_cpu_silenced | Groups to mute for SQL CPU monitor | map | `<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 | `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 | `<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_message | Custom message for SQL disk space monitor | string | `` | no |
| sqldatabase_diskspace_silenced | Groups to mute for SQL disk space monitor | map | `<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 | `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 | `<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_message | Custom message for Storage authorization errors monitor | string | `` | no |
| storage_authorization_error_requests_silenced | Groups to mute for Storage authorization errors monitor | map | `<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 | `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 | `<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 | `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 | `<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 | `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 | `<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_message | Custom message for Storage network errors monitor | string | `` | no |
| storage_network_error_requests_silenced | Groups to mute for Storage network errors monitor | map | `<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 | `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 | `<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 | `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 | `<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 | `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 | `<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 | `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 | `<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 | `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 | `<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 | `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 | `<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_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 | `<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 | `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 | `<map>` | 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 | `<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 | `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
---------------------
@ -230,3 +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)

BIN
cloud/azure/apimanagement/README.md
View File

Binary file not shown.

6
cloud/azure/apimanagement/inputs.tf
View File

@ -37,6 +37,12 @@ variable "status_message" {
default = ""
}
variable "status_time_aggregator" {
description = "Monitor aggregator for API Management status [available values: min, max or avg]"
type = "string"
default = "max"
}
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"

12
cloud/azure/apimanagement/monitors-azure-apimanagement.tf
View File

@ -13,8 +13,8 @@ resource "datadog_monitor" "apimgt_status" {
message = "${coalesce(var.status_message, var.message)}"
query = <<EOF
avg(${var.status_timeframe}):avg:azure.apimanagement_service.status{${data.template_file.filter.rendered}} by {resource_group,region,name} < 1
EOF
${var.status_time_aggregator}(${var.status_timeframe}):avg:azure.apimanagement_service.status{${data.template_file.filter.rendered}} by {resource_group,region,name} < 1
EOF
type = "metric alert"
@ -46,7 +46,7 @@ resource "datadog_monitor" "apimgt_failed_requests" {
avg:azure.apimanagement_service.failed_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
avg:azure.apimanagement_service.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() * 100
) > ${var.failed_requests_threshold_critical}
EOF
EOF
thresholds {
critical = "${var.failed_requests_threshold_critical}"
@ -78,7 +78,7 @@ resource "datadog_monitor" "apimgt_other_requests" {
avg:azure.apimanagement_service.other_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
avg:azure.apimanagement_service.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() * 100
) > ${var.other_requests_threshold_critical}
EOF
EOF
thresholds {
critical = "${var.other_requests_threshold_critical}"
@ -110,7 +110,7 @@ resource "datadog_monitor" "apimgt_unauthorized_requests" {
avg:azure.apimanagement_service.unauthorized_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
avg:azure.apimanagement_service.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() * 100
) > ${var.unauthorized_requests_threshold_critical}
EOF
EOF
thresholds {
critical = "${var.unauthorized_requests_threshold_critical}"
@ -142,7 +142,7 @@ resource "datadog_monitor" "apimgt_successful_requests" {
avg:azure.apimanagement_service.successful_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
avg:azure.apimanagement_service.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() * 100
) < ${var.successful_requests_threshold_critical}
EOF
EOF
thresholds {
critical = "${var.successful_requests_threshold_critical}"

BIN
cloud/azure/app-services/README.md
View File

Binary file not shown.

12
cloud/azure/app-services/inputs.tf
View File

@ -35,6 +35,12 @@ variable "response_time_message" {
default = ""
}
variable "response_time_time_aggregator" {
description = "Monitor aggregator for App Services response time [available values: min, max 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_time_aggregator" {
description = "Monitor aggregator for App Services memory usage [available values: min, max or avg]"
type = "string"
default = "min"
}
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"

4
cloud/azure/app-services/monitors-app_services.tf
View File

@ -13,7 +13,7 @@ resource "datadog_monitor" "appservices_response_time" {
message = "${coalesce(var.response_time_message, var.message)}"
query = <<EOF
min(last_5m): (
${var.response_time_time_aggregator}(${var.response_time_timeframe}): (
avg:azure.app_services.average_response_time{${data.template_file.filter.rendered}} by {resource_group,region,name}
) > ${var.response_time_threshold_critical}
EOF
@ -44,7 +44,7 @@ resource "datadog_monitor" "appservices_memory_usage_count" {
message = "${coalesce(var.memory_usage_message, var.message)}"
query = <<EOF
avg(${var.memory_usage_timeframe}): (
${var.memory_usage_time_aggregator}(${var.memory_usage_timeframe}): (
avg:azure.app_services.memory_working_set{${data.template_file.filter.rendered}} by {resource_group,region,name}
) > ${var.memory_usage_threshold_critical}
EOF

BIN
cloud/azure/eventhub/README.md
View File

Binary file not shown.

6
cloud/azure/eventhub/inputs.tf
View File

@ -37,6 +37,12 @@ variable "status_message" {
default = ""
}
variable "status_time_aggregator" {
description = "Monitor aggregator for Event Hub status [available values: min, max or avg]"
type = "string"
default = "max"
}
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"

10
cloud/azure/eventhub/monitors-eventhub.tf
View File

@ -11,8 +11,10 @@ resource "datadog_monitor" "eventhub_status" {
message = "${coalesce(var.status_message, var.message)}"
query = <<EOF
avg(${var.status_timeframe}): avg:azure.eventhub_namespaces.status{${data.template_file.filter.rendered}} by {resource_group,region,name} != 1
EOF
${var.status_time_aggregator}(${var.status_timeframe}): (
avg:azure.eventhub_namespaces.status{${data.template_file.filter.rendered}} by {resource_group,region,name}
) != 1
EOF
type = "metric alert"
@ -42,7 +44,7 @@ resource "datadog_monitor" "eventhub_failed_requests" {
avg:azure.eventhub_namespaces.incoming_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count(),
0) * 100
) > ${var.failed_requests_rate_thresold_critical}
EOF
EOF
type = "metric alert"
@ -82,7 +84,7 @@ resource "datadog_monitor" "eventhub_errors" {
),
0) * 100
) > ${var.errors_rate_thresold_critical}
EOF
EOF
type = "metric alert"

456
cloud/azure/inputs.tf
View File

@ -41,6 +41,18 @@ variable "apimanagement_status_message" {
default = ""
}
variable "apimanagement_status_time_aggregator" {
description = "Monitor aggregator for API Management status [available values: min, max or avg]"
type = "string"
default = "max"
}
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 +65,12 @@ variable "apimanagement_failed_requests_message" {
default = ""
}
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 +93,12 @@ variable "apimanagement_other_requests_message" {
default = ""
}
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 +121,12 @@ variable "apimanagement_unauthorized_requests_message" {
default = ""
}
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 +149,12 @@ variable "apimanagement_successful_requests_message" {
default = ""
}
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 +178,18 @@ variable "appservices_response_time_message" {
default = ""
}
variable "appservices_response_time_time_aggregator" {
description = "Monitor aggregator for App Services response time [available values: min, max 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 +212,18 @@ variable "appservices_memory_usage_message" {
default = ""
}
variable "appservices_memory_usage_time_aggregator" {
description = "Monitor aggregator for App Services memory usage [available values: min, max or avg]"
type = "string"
default = "min"
}
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 +246,12 @@ variable "appservices_http_4xx_requests_message" {
default = ""
}
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 +274,12 @@ variable "appservices_http_5xx_requests_message" {
default = ""
}
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 +302,12 @@ variable "appservices_http_successful_requests_message" {
default = ""
}
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 +331,18 @@ variable "eventhub_status_message" {
default = ""
}
variable "eventhub_status_time_aggregator" {
description = "Monitor aggregator for Event Hub status [available values: min, max or avg]"
type = "string"
default = "max"
}
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 +355,12 @@ variable "eventhub_failed_requests_rate_message" {
default = ""
}
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 +383,12 @@ variable "eventhub_errors_rate_message" {
default = ""
}
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 +412,18 @@ variable "iothub_status_message" {
default = ""
}
variable "iothub_status_time_aggregator" {
description = "Monitor aggregator for IoT Hub status [available values: min, max or avg]"
type = "string"
default = "max"
}
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 +436,18 @@ variable "iothub_total_devices_message" {
default = ""
}
variable "iothub_total_devices_time_aggregator" {
description = "Monitor aggregator for IoT Hub total devices [available values: min, max or avg]"
type = "string"
default = "min"
}
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 +460,12 @@ variable "iothub_too_many_d2c_telemetry_ingress_nosent_message" {
default = ""
}
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 +478,12 @@ variable "iothub_failed_jobs_rate_message" {
default = ""
}
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 +506,12 @@ variable "iothub_failed_listjobs_rate_message" {
default = ""
}
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 +534,12 @@ variable "iothub_failed_queryjobs_rate_message" {
default = ""
}
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 +562,12 @@ variable "iothub_failed_c2d_methods_rate_message" {
default = ""
}
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 +590,12 @@ variable "iothub_failed_c2d_twin_read_rate_message" {
default = ""
}
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 +618,12 @@ variable "iothub_failed_c2d_twin_update_rate_message" {
default = ""
}
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 +646,12 @@ variable "iothub_failed_d2c_twin_read_rate_message" {
default = ""
}
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 +674,12 @@ variable "iothub_failed_d2c_twin_update_rate_message" {
default = ""
}
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 +702,12 @@ variable "iothub_dropped_d2c_telemetry_egress_message" {
default = ""
}
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 +730,12 @@ variable "iothub_orphaned_d2c_telemetry_egress_message" {
default = ""
}
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 +758,12 @@ variable "iothub_invalid_d2c_telemetry_egress_message" {
default = ""
}
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 +787,18 @@ variable "redis_status_message" {
default = ""
}
variable "redis_status_time_aggregator" {
description = "Monitor aggregator for Redis status [available values: min, max or avg]"
type = "string"
default = "max"
}
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 +811,18 @@ variable "redis_evictedkeys_limit_message" {
default = ""
}
variable "redis_evictedkeys_limit_time_aggregator" {
description = "Monitor aggregator for Redis evicted keys [available values: min, max 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 +845,18 @@ variable "redis_percent_processor_time_message" {
default = ""
}
variable "redis_percent_processor_time_time_aggregator" {
description = "Monitor aggregator for Redis processor [available values: min, max or avg]"
type = "string"
default = "min"
}
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 +879,18 @@ variable "redis_server_load_rate_message" {
default = ""
}
variable "redis_server_load_rate_time_aggregator" {
description = "Monitor aggregator for Redis server load [available values: min, max or avg]"
type = "string"
default = "min"
}
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
@ -668,10 +914,10 @@ 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"
default = "max"
}
variable "servicebus_status_timeframe" {
@ -692,6 +938,18 @@ variable "sqldatabase_cpu_message" {
default = ""
}
variable "sqldatabase_cpu_time_aggregator" {
description = "Monitor aggregator for SQL CPU [available values: min, max or avg]"
type = "string"
default = "min"
}
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 +972,18 @@ variable "sqldatabase_diskspace_message" {
default = ""
}
variable "sqldatabase_diskspace_time_aggregator" {
description = "Monitor aggregator for SQL disk space [available values: min, max or avg]"
type = "string"
default = "max"
}
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 +1006,18 @@ variable "sqldatabase_dtu_message" {
default = ""
}
variable "sqldatabase_dtu_time_aggregator" {
description = "Monitor aggregator for SQL DTU [available values: min, max 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 +1040,12 @@ variable "sqldatabase_deadlock_message" {
default = ""
}
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 +1064,18 @@ variable "storage_availability_message" {
default = ""
}
variable "storage_availability_time_aggregator" {
description = "Monitor aggregator for Storage availability [available values: min, max or avg]"
type = "string"
default = "max"
}
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 +1098,18 @@ variable "storage_successful_requests_message" {
default = ""
}
variable "storage_successful_requests_time_aggregator" {
description = "Monitor aggregator for Storage sucessful requests [available values: min, max or avg]"
type = "string"
default = "max"
}
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 +1132,18 @@ variable "storage_latency_message" {
default = ""
}
variable "storage_latency_time_aggregator" {
description = "Monitor aggregator for Storage latency [available values: min, max 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 +1166,18 @@ variable "storage_timeout_error_requests_message" {
default = ""
}
variable "storage_timeout_error_requests_time_aggregator" {
description = "Monitor aggregator for Storage timeout [available values: min, max or avg]"
type = "string"
default = "min"
}
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 +1200,18 @@ variable "storage_network_error_requests_message" {
default = ""
}
variable "storage_network_error_requests_time_aggregator" {
description = "Monitor aggregator for Storage network errors [available values: min, max or avg]"
type = "string"
default = "min"
}
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 +1234,18 @@ variable "storage_throttling_error_requests_message" {
default = ""
}
variable "storage_throttling_error_requests_time_aggregator" {
description = "Monitor aggregator for Storage throttling errors [available values: min, max or avg]"
type = "string"
default = "min"
}
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 +1268,18 @@ variable "storage_server_other_error_requests_message" {
default = ""
}
variable "storage_server_other_error_requests_time_aggregator" {
description = "Monitor aggregator for Storage other errors [available values: min, max or avg]"
type = "string"
default = "min"
}
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 +1302,18 @@ variable "storage_client_other_error_requests_message" {
default = ""
}
variable "storage_client_other_error_requests_time_aggregator" {
description = "Monitor aggregator for Storage other errors [available values: min, max or avg]"
type = "string"
default = "min"
}
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 +1336,18 @@ variable "storage_authorization_error_requests_message" {
default = ""
}
variable "storage_authorization_error_requests_time_aggregator" {
description = "Monitor aggregator for Storage authorization errors [available values: min, max or avg]"
type = "string"
default = "min"
}
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 +1371,18 @@ variable "streamanalytics_status_message" {
default = ""
}
variable "streamanalytics_status_time_aggregator" {
description = "Monitor aggregator for Stream Analytics status [available values: min, max or avg]"
type = "string"
default = "max"
}
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 +1395,18 @@ variable "streamanalytics_su_utilization_message" {
default = ""
}
variable "streamanalytics_su_utilization_time_aggregator" {
description = "Monitor aggregator for Stream Analytics utilization [available values: min, max or avg]"
type = "string"
default = "min"
}
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 +1429,12 @@ variable "streamanalytics_failed_function_requests_message" {
default = ""
}
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 +1457,18 @@ variable "streamanalytics_conversion_errors_message" {
default = ""
}
variable "streamanalytics_conversion_errors_time_aggregator" {
description = "Monitor aggregator for Stream Analytics conversion errors [available values: min, max or avg]"
type = "string"
default = "min"
}
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 +1491,18 @@ variable "streamanalytics_runtime_errors_message" {
default = ""
}
variable "streamanalytics_runtime_errors_time_aggregator" {
description = "Monitor aggregator for Stream Analytics runtime errors [available values: min, max or avg]"
type = "string"
default = "min"
}
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

151
cloud/azure/iothubs/README.md
View File

@ -33,83 +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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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_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 | `<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 | `<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 |
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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 | `<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)

12
cloud/azure/iothubs/inputs.tf
View File

@ -32,6 +32,12 @@ variable "status_message" {
default = ""
}
variable "status_time_aggregator" {
description = "Monitor aggregator for IoT Hub status [available values: min, max, sum or avg]"
type = "string"
default = "max"
}
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_time_aggregator" {
description = "Monitor aggregator for IoT Hub total devices [available values: min, max, sum or avg]"
type = "string"
default = "min"
}
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"

8
cloud/azure/iothubs/monitors-iothubs.tf
View File

@ -105,7 +105,9 @@ resource "datadog_monitor" "status" {
message = "${coalesce(var.status_message, var.message)}"
query = <<EOF
avg(${var.status_timeframe}):avg:azure.devices_iothubs.status{${var.filter_tags}} by {resource_group,region,name} < 1
${var.status_time_aggregator}(${var.status_timeframe}): (
avg:azure.devices_iothubs.status{${var.filter_tags}} by {resource_group,region,name}
) < 1
EOF
type = "metric alert"
@ -130,7 +132,9 @@ resource "datadog_monitor" "total_devices" {
message = "${coalesce(var.total_devices_message, var.message)}"
query = <<EOF
avg(${var.total_devices_timeframe}):avg:azure.devices_iothubs.devices.total_devices{${var.filter_tags}} by {resource_group,region,name} == 0
${var.total_devices_time_aggregator}(${var.total_devices_timeframe}): (
avg:azure.devices_iothubs.devices.total_devices{${var.filter_tags}} by {resource_group,region,name}
) == 0
EOF
type = "metric alert"

82
cloud/azure/monitors.tf
View File

@ -10,20 +10,26 @@ module "apimanagement" {
status_silenced = "${var.apimanagement_status_silenced}"
status_message = "${var.apimanagement_status_message}"
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_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 = "${var.apimanagement_other_requests_message}"
other_requests_timeframe = "${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_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 = "${var.apimanagement_unauthorized_requests_message}"
unauthorized_requests_timeframe = "${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 +46,29 @@ 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_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 = "${var.appservices_http_5xx_requests_message}"
http_5xx_requests_timeframe = "${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_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 = "${var.appservices_memory_usage_message}"
memory_usage_time_aggregator = "${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 = "${var.appservices_response_time_message}"
response_time_time_aggregator = "${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 = "${var.appservices_response_time_threshold_warning}"
}
@ -72,12 +85,16 @@ module "eventhub" {
status_silenced = "${var.eventhub_status_silenced}"
status_message = "${var.eventhub_status_message}"
status_time_aggregator = "${var.eventhub_status_time_aggregator}"
status_timeframe = "${var.eventhub_status_timeframe}"
errors_rate_silenced = "${var.eventhub_errors_rate_silenced}"
errors_rate_message = "${var.eventhub_errors_rate_message}"
errors_rate_timeframe = "${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_timeframe = "${var.eventhub_failed_requests_rate_timeframe}"
failed_requests_rate_thresold_critical = "${var.eventhub_failed_requests_rate_thresold_critical}"
failed_requests_rate_thresold_warning = "${var.eventhub_failed_requests_rate_thresold_warning}"
}
@ -93,51 +110,68 @@ module "iothub" {
status_silenced = "${var.iothub_status_silenced}"
status_message = "${var.iothub_status_message}"
status_time_aggregator = "${var.iothub_status_time_aggregator}"
status_timeframe = "${var.iothub_status_timeframe}"
total_devices_silenced = "${var.iothub_total_devices_silenced}"
total_devices_message = "${var.iothub_total_devices_message}"
total_devices_time_aggregator = "${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 = "${var.iothub_too_many_d2c_telemetry_ingress_nosent_message}"
too_many_d2c_telemetry_ingress_nosent_timeframe = "${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_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 = "${var.iothub_failed_c2d_methods_rate_message}"
failed_c2d_methods_rate_timeframe = "${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_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 = "${var.iothub_failed_c2d_twin_update_rate_message}"
failed_c2d_twin_update_rate_timeframe = "${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_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 = "${var.iothub_failed_d2c_twin_update_rate_message}"
failed_d2c_twin_update_rate_timeframe = "${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_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 = "${var.iothub_failed_listjobs_rate_message}"
failed_listjobs_rate_timeframe = "${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_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 = "${var.iothub_invalid_d2c_telemetry_egress_message}"
invalid_d2c_telemetry_egress_timeframe = "${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_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 = "${var.iothub_orphaned_d2c_telemetry_egress_rate_threshold_warning}"
}
@ -154,16 +188,24 @@ module "redis" {
status_silenced = "${var.redis_status_silenced}"
status_message = "${var.redis_status_message}"
status_time_aggregator = "${var.redis_status_time_aggregator}"
status_timeframe = "${var.redis_status_timeframe}"
evictedkeys_limit_silenced = "${var.redis_evictedkeys_limit_silenced}"
evictedkeys_limit_message = "${var.redis_evictedkeys_limit_message}"
evictedkeys_limit_time_aggregator = "${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 = "${var.redis_percent_processor_time_message}"
percent_processor_time_time_aggregator = "${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 = "${var.redis_server_load_rate_message}"
server_load_rate_time_aggregator = "${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 = "${var.redis_server_load_rate_threshold_warning}"
}
@ -178,10 +220,10 @@ module "servicebus" {
filter_tags_use_defaults = "${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_time_aggregator = "${var.servicebus_status_time_aggregator}"
}
module "sqldatabase" {
@ -196,17 +238,24 @@ module "sqldatabase" {
cpu_silenced = "${var.sqldatabase_cpu_silenced}"
cpu_message = "${var.sqldatabase_cpu_message}"
cpu_time_aggregator = "${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 = "${var.sqldatabase_deadlock_message}"
deadlock_timeframe = "${var.sqldatabase_deadlock_timeframe}"
deadlock_threshold_critical = "${var.sqldatabase_deadlock_threshold_critical}"
diskspace_silenced = "${var.sqldatabase_diskspace_silenced}"
diskspace_message = "${var.sqldatabase_diskspace_message}"
diskspace_time_aggregator = "${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 = "${var.sqldatabase_dtu_message}"
dtu_time_aggregator = "${var.sqldatabase_dtu_time_aggregator}"
dtu_timeframe = "${var.sqldatabase_dtu_timeframe}"
dtu_threshold_critical = "${var.sqldatabase_dtu_threshold_critical}"
dtu_threshold_warning = "${var.sqldatabase_dtu_threshold_warning}"
}
@ -223,38 +272,56 @@ module "storage" {
authorization_error_requests_silenced = "${var.storage_authorization_error_requests_silenced}"
authorization_error_requests_message = "${var.storage_authorization_error_requests_message}"
authorization_error_requests_time_aggregator = "${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 = "${var.storage_availability_message}"
availability_time_aggregator = "${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 = "${var.storage_client_other_error_requests_message}"
client_other_error_requests_time_aggregator = "${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 = "${var.storage_latency_message}"
latency_time_aggregator = "${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 = "${var.storage_network_error_requests_message}"
network_error_requests_time_aggregator = "${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 = "${var.storage_server_other_error_requests_message}"
server_other_error_requests_time_aggregator = "${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 = "${var.storage_successful_requests_message}"
successful_requests_time_aggregator = "${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 = "${var.storage_throttling_error_requests_message}"
throttling_error_requests_time_aggregator = "${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 = "${var.storage_timeout_error_requests_message}"
timeout_error_requests_time_aggregator = "${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 = "${var.storage_timeout_error_requests_threshold_warning}"
}
@ -271,18 +338,25 @@ module "streamanalytics" {
conversion_errors_silenced = "${var.streamanalytics_conversion_errors_silenced}"
conversion_errors_message = "${var.streamanalytics_conversion_errors_message}"
conversion_errors_time_aggregator = "${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 = "${var.streamanalytics_failed_function_requests_message}"
failed_function_requests_timeframe = "${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_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_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}"
}

BIN
cloud/azure/redis/README.md
View File

Binary file not shown.

24
cloud/azure/redis/inputs.tf
View File

@ -37,6 +37,12 @@ variable "status_message" {
default = ""
}
variable "status_time_aggregator" {
description = "Monitor aggregator for Redis status [available values: min, max or avg]"
type = "string"
default = "max"
}
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_time_aggregator" {
description = "Monitor aggregator for Redis evicted keys [available values: min, max 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_time_aggregator" {
description = "Monitor aggregator for Redis processor [available values: min, max or avg]"
type = "string"
default = "min"
}
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_time_aggregator" {
description = "Monitor aggregator for Redis server load [available values: min, max or avg]"
type = "string"
default = "min"
}
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"

12
cloud/azure/redis/monitors-azure-redis.tf
View File

@ -11,8 +11,10 @@ resource "datadog_monitor" "status" {
message = "${coalesce(var.status_message, var.message)}"
query = <<EOF
avg(${var.status_timeframe}):avg:azure.cache_redis.status{${data.template_file.filter.rendered}} by {resource_group,region,name} != 1
EOF
${var.status_time_aggregator}(${var.status_timeframe}): (
avg:azure.cache_redis.status{${data.template_file.filter.rendered}} by {resource_group,region,name}
) != 1
EOF
type = "metric alert"
@ -36,7 +38,7 @@ resource "datadog_monitor" "evictedkeys" {
message = "${coalesce(var.evictedkeys_limit_message, var.message)}"
query = <<EOF
avg(${var.evictedkeys_limit_timeframe}): (
${var.evictedkeys_limit_time_aggregator}(${var.evictedkeys_limit_timeframe}): (
avg:azure.cache_redis.evictedkeys{${data.template_file.filter.rendered}} by {resource_group,region,name}
) > ${var.evictedkeys_limit_threshold_critical}
EOF
@ -68,7 +70,7 @@ resource "datadog_monitor" "percent_processor_time" {
message = "${coalesce(var.percent_processor_time_message, var.message)}"
query = <<EOF
avg(${var.percent_processor_time_timeframe}): (
${var.percent_processor_time_time_aggregator}(${var.percent_processor_time_timeframe}): (
avg:azure.cache_redis.percent_processor_time{${data.template_file.filter.rendered}} by {resource_group,region,name}
) > ${var.percent_processor_time_threshold_critical}
EOF
@ -100,7 +102,7 @@ resource "datadog_monitor" "server_load" {
message = "${coalesce(var.server_load_rate_message, var.message)}"
query = <<EOF
avg(${var.server_load_rate_timeframe}): (
${var.server_load_rate_time_aggregator}(${var.server_load_rate_timeframe}): (
avg:azure.cache_redis.server_load{${data.template_file.filter.rendered}} by {resource_group,region,name}
) > ${var.server_load_rate_threshold_critical}
EOF

BIN
cloud/azure/servicebus/README.md
View File

Binary file not shown.

6
cloud/azure/servicebus/inputs.tf
View File

@ -37,10 +37,10 @@ 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"
default = "max"
}
variable "status_timeframe" {

4
cloud/azure/servicebus/monitors-service-bus.tf
View File

@ -11,8 +11,8 @@ resource "datadog_monitor" "servicebus_status" {
message = "${coalesce(var.status_message, var.message)}"
query = <<EOF
${var.status_aggregator}(${var.status_timeframe}): (
${var.status_aggregator}:azure.servicebus_namespaces.status{${data.template_file.filter.rendered}} by {resource_group,region,name}
${var.status_time_aggregator}(${var.status_timeframe}): (
avg:azure.servicebus_namespaces.status{${data.template_file.filter.rendered}} by {resource_group,region,name}
) != 1
EOF

BIN
cloud/azure/sql-database/README.md
View File

Binary file not shown.

18
cloud/azure/sql-database/inputs.tf
View File

@ -37,6 +37,12 @@ variable "cpu_message" {
default = ""
}
variable "cpu_time_aggregator" {
description = "Monitor aggregator for SQL CPU [available values: min, max or avg]"
type = "string"
default = "min"
}
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_time_aggregator" {
description = "Monitor aggregator for SQL disk space [available values: min, max or avg]"
type = "string"
default = "max"
}
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_time_aggregator" {
description = "Monitor aggregator for SQL DTU [available values: min, max 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"

6
cloud/azure/sql-database/monitors-sql-database-basics.tf
View File

@ -11,7 +11,7 @@ resource "datadog_monitor" "sql-database_cpu_90_15min" {
message = "${coalesce(var.cpu_message, var.message)}"
query = <<EOF
avg(${var.cpu_timeframe}): (
${var.cpu_time_aggregator}(${var.cpu_timeframe}): (
avg:azure.sql_servers_databases.cpu_percent{${data.template_file.filter.rendered}} by {resource_group,region,name}
) > ${var.cpu_threshold_critical}
EOF
@ -44,7 +44,7 @@ resource "datadog_monitor" "sql-database_free_space_low" {
type = "metric alert"
query = <<EOF
avg(${var.diskspace_timeframe}): (
${var.diskspace_time_aggregator}(${var.diskspace_timeframe}): (
avg:azure.sql_servers_databases.storage_percent{${data.template_file.filter.rendered}} by {resource_group,region,name}
) > ${var.diskspace_threshold_critical}
EOF
@ -76,7 +76,7 @@ resource "datadog_monitor" "sql-database_dtu_consumption_high" {
type = "metric alert"
query = <<EOF
avg(${var.dtu_timeframe}): (
${var.dtu_time_aggregator}(${var.dtu_timeframe}): (
azure.sql_servers_databases.dtu_consumption_percent{${data.template_file.filter.rendered}} by {resource_group,region,name}
) > ${var.dtu_threshold_critical}
EOF

10
cloud/azure/storage/README.md
View File

@ -36,16 +36,19 @@ Inputs
| authorization_error_requests_silenced | Groups to mute for Storage authorization errors monitor | map | `<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_message | Custom message for Storage availability monitor | string | `` | no |
| availability_silenced | Groups to mute for Storage availability monitor | map | `<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_message | Custom message for Storage other errors monitor | string | `` | no |
| client_other_error_requests_silenced | Groups to mute for Storage other errors monitor | map | `<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 |
@ -55,32 +58,38 @@ Inputs
| latency_silenced | Groups to mute for Storage latency monitor | map | `<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_message | Custom message for Storage network errors monitor | string | `` | no |
| network_error_requests_silenced | Groups to mute for Storage network errors monitor | map | `<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_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 | `<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_message | Custom message for Storage sucessful requests monitor | string | `` | no |
| successful_requests_silenced | Groups to mute for Storage sucessful requests monitor | map | `<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_message | Custom message for Storage throttling error monitor | string | `` | no |
| throttling_error_requests_silenced | Groups to mute for Storage throttling error monitor | map | `<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_message | Custom message for Storage timeout monitor | string | `` | no |
| timeout_error_requests_silenced | Groups to mute for Storage timeout monitor | map | `<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
@ -93,3 +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)

54
cloud/azure/storage/inputs.tf
View File

@ -37,6 +37,12 @@ variable "availability_message" {
default = ""
}
variable "availability_time_aggregator" {
description = "Monitor aggregator for Storage availability [available values: min, max or avg]"
type = "string"
default = "max"
}
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_time_aggregator" {
description = "Monitor aggregator for Storage sucessful requests [available values: min, max or avg]"
type = "string"
default = "max"
}
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_time_aggregator" {
description = "Monitor aggregator for Storage latency [available values: min, max 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_time_aggregator" {
description = "Monitor aggregator for Storage timeout [available values: min, max or avg]"
type = "string"
default = "min"
}
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_time_aggregator" {
description = "Monitor aggregator for Storage network errors [available values: min, max or avg]"
type = "string"
default = "min"
}
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_time_aggregator" {
description = "Monitor aggregator for Storage throttling errors [available values: min, max or avg]"
type = "string"
default = "min"
}
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_time_aggregator" {
description = "Monitor aggregator for Storage other errors [available values: min, max or avg]"
type = "string"
default = "min"
}
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_time_aggregator" {
description = "Monitor aggregator for Storage other errors [available values: min, max or avg]"
type = "string"
default = "min"
}
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_time_aggregator" {
description = "Monitor aggregator for Storage authorization errors [available values: min, max or avg]"
type = "string"
default = "min"
}
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"

18
cloud/azure/storage/monitors-azure-storage.tf
View File

@ -11,7 +11,7 @@ resource "datadog_monitor" "availability" {
message = "${coalesce(var.availability_message, var.message)}"
query = <<EOF
avg(${var.availability_timeframe}): (default(
${var.availability_time_aggregator}(${var.availability_timeframe}): (default(
avg:azure.storage.availability{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
100)) < ${var.availability_threshold_critical}
EOF
@ -42,7 +42,7 @@ resource "datadog_monitor" "successful_requests" {
message = "${coalesce(var.successful_requests_message, var.message)}"
query = <<EOF
avg(${var.successful_requests_timeframe}): (default(
${var.successful_requests_time_aggregator}(${var.successful_requests_timeframe}): (default(
avg:azure.storage.percent_success{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
100)) < ${var.successful_requests_threshold_critical}
EOF
@ -73,7 +73,7 @@ resource "datadog_monitor" "latency" {
message = "${coalesce(var.latency_message, var.message)}"
query = <<EOF
min(${var.latency_timeframe}): (default(
${var.latency_time_aggregator}(${var.latency_timeframe}): (default(
avg:azure.storage.average_e2_e_latency{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
0)) > ${var.latency_threshold_critical}
EOF
@ -104,7 +104,7 @@ resource "datadog_monitor" "timeout_error_requests" {
message = "${coalesce(var.timeout_error_requests_message, var.message)}"
query = <<EOF
avg(${var.timeout_error_requests_timeframe}): (default(
${var.timeout_error_requests_time_aggregator}(${var.timeout_error_requests_timeframe}): (default(
avg:azure.storage.percent_timeout_error{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
0)) > ${var.timeout_error_requests_threshold_critical}
EOF
@ -135,7 +135,7 @@ resource "datadog_monitor" "network_error_requests" {
message = "${coalesce(var.network_error_requests_message, var.message)}"
query = <<EOF
avg(${var.network_error_requests_timeframe}): (default(
${var.network_error_requests_time_aggregator}(${var.network_error_requests_timeframe}): (default(
avg:azure.storage.percent_network_error{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
0)) > ${var.network_error_requests_threshold_critical}
EOF
@ -166,7 +166,7 @@ resource "datadog_monitor" "throttling_error_requests" {
message = "${coalesce(var.throttling_error_requests_message, var.message)}"
query = <<EOF
avg(${var.throttling_error_requests_timeframe}): (default(
${var.throttling_error_requests_time_aggregator}(${var.throttling_error_requests_timeframe}): (default(
avg:azure.storage.percent_throttling_error{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
0)) > ${var.throttling_error_requests_threshold_critical}
EOF
@ -197,7 +197,7 @@ resource "datadog_monitor" "server_other_error_requests" {
message = "${coalesce(var.server_other_error_requests_message, var.message)}"
query = <<EOF
avg(${var.server_other_error_requests_timeframe}): (default(
${var.server_other_error_requests_time_aggregator}(${var.server_other_error_requests_timeframe}): (default(
avg:azure.storage.percent_server_other_error{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
0)) > ${var.server_other_error_requests_threshold_critical}
EOF
@ -228,7 +228,7 @@ resource "datadog_monitor" "client_other_error_requests" {
message = "${coalesce(var.client_other_error_requests_message, var.message)}"
query = <<EOF
avg(${var.client_other_error_requests_timeframe}): (default(
${var.client_other_error_requests_time_aggregator}(${var.client_other_error_requests_timeframe}): (default(
avg:azure.storage.percent_client_other_error{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
0)) > ${var.client_other_error_requests_threshold_critical}
EOF
@ -259,7 +259,7 @@ resource "datadog_monitor" "authorization_error_requests" {
message = "${coalesce(var.authorization_error_requests_message, var.message)}"
query = <<EOF
avg(${var.authorization_error_requests_timeframe}): (default(
${var.authorization_error_requests_time_aggregator}(${var.authorization_error_requests_timeframe}): (default(
avg:azure.storage.percent_authorization_error{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
0)) > ${var.authorization_error_requests_threshold_critical}
EOF

BIN
cloud/azure/stream-analytics/README.md
View File

Binary file not shown.

24
cloud/azure/stream-analytics/inputs.tf
View File

@ -37,6 +37,12 @@ variable "status_message" {
default = ""
}
variable "status_time_aggregator" {
description = "Monitor aggregator for Stream Analytics status [available values: min, max or avg]"
type = "string"
default = "max"
}
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_time_aggregator" {
description = "Monitor aggregator for Stream Analytics utilization [available values: min, max or avg]"
type = "string"
default = "min"
}
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"
@ -111,6 +123,12 @@ variable "conversion_errors_message" {
default = ""
}
variable "conversion_errors_time_aggregator" {
description = "Monitor aggregator for Stream Analytics conversion errors [available values: min, max or avg]"
type = "string"
default = "min"
}
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 +157,12 @@ variable "runtime_errors_message" {
default = ""
}
variable "runtime_errors_time_aggregator" {
description = "Monitor aggregator for Stream Analytics runtime errors [available values: min, max or avg]"
type = "string"
default = "min"
}
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"

10
cloud/azure/stream-analytics/monitors-stream-analytics.tf
View File

@ -11,7 +11,9 @@ resource "datadog_monitor" "status" {
message = "${coalesce(var.status_message, var.message)}"
query = <<EOF
avg(${var.status_timeframe}):avg:azure.streamanalytics_streamingjobs.status{${data.template_file.filter.rendered}} by {resource_group,region,name} < 1
${var.status_time_aggregator}(${var.status_timeframe}): (
avg:azure.streamanalytics_streamingjobs.status{${data.template_file.filter.rendered}} by {resource_group,region,name}
) < 1
EOF
type = "metric alert"
@ -36,7 +38,7 @@ resource "datadog_monitor" "su_utilization" {
message = "${coalesce(var.su_utilization_message, var.message)}"
query = <<EOF
avg(${var.su_utilization_timeframe}): (
${var.su_utilization_time_aggregator}(${var.su_utilization_timeframe}): (
avg:azure.streamanalytics_streamingjobs.resource_utilization{${data.template_file.filter.rendered}} by {resource_group,region,name}
) > ${var.su_utilization_threshold_critical}
EOF
@ -101,7 +103,7 @@ resource "datadog_monitor" "conversion_errors" {
message = "${coalesce(var.conversion_errors_message, var.message)}"
query = <<EOF
avg(${var.conversion_errors_timeframe}): (
${var.conversion_errors_time_aggregator}(${var.conversion_errors_timeframe}): (
avg:azure.streamanalytics_streamingjobs.conversion_errors{${data.template_file.filter.rendered}} by {resource_group,region,name}
) > ${var.conversion_errors_threshold_critical}
EOF
@ -133,7 +135,7 @@ resource "datadog_monitor" "runtime_errors" {
message = "${coalesce(var.runtime_errors_message, var.message)}"
query = <<EOF
avg(${var.runtime_errors_timeframe}): (
${var.runtime_errors_time_aggregator}(${var.runtime_errors_timeframe}): (
avg:azure.streamanalytics_streamingjobs.errors{${data.template_file.filter.rendered}} by {resource_group,region,name}
) > ${var.runtime_errors_threshold_critical}
EOF

BIN
common/alerting-message/README.md
View File

Binary file not shown.

3
common/alerting-message/output.tf
View File

@ -1,3 +1,4 @@
output "alerting-message" {
value = "${data.template_file.alerting-message.rendered}"
description = "The generated message string"
value = "${data.template_file.alerting-message.rendered}"
}

2
databases/mongodb/README.md
View File

@ -81,4 +81,6 @@ Inputs
| message | Message sent when an alert is triggered | string | - | yes |
| mongodb_replicaset_message | Custom message for Mongodb replicaset monitor | string | `` | no |
| mongodb_replicaset_silenced | Groups to mute for Mongodb replicaset monitor | map | `<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 |

6
databases/mongodb/inputs.tf
View File

@ -36,6 +36,12 @@ variable "mongodb_replicaset_message" {
default = ""
}
variable "mongodb_replicaset_time_aggregator" {
description = "Monitor aggregator for Mongodb replicaset [available values: min, max or avg]"
type = "string"
default = "max"
}
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"

2
databases/mongodb/monitors-mongo.tf
View File

@ -11,7 +11,7 @@ resource "datadog_monitor" "mongodb_replicaset_state" {
message = "${coalesce(var.mongodb_replicaset_message, var.message)}"
query = <<EOF
avg(${var.mongodb_replicaset_timeframe}): (
${var.mongodb_replicaset_time_aggregator}(${var.mongodb_replicaset_timeframe}): (
avg:mongodb.replset.health{${data.template_file.filter.rendered}} by {region,replset_name}
) < 1
EOF

25
middleware/apache/README.md
View File

@ -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 | `<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 | `<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 |

25
middleware/nginx/README.md
View File

@ -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 | `<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 | `<map>` | no |

36
middleware/php-fpm/README.md
View File

@ -20,20 +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_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 | `<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 | `<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 | `<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 | `<map>` | no |

6
middleware/php-fpm/inputs.tf
View File

@ -38,6 +38,12 @@ variable "php_fpm_busy_message" {
default = ""
}
variable "php_fpm_busy_time_aggregator" {
description = "Monitor aggregator for PHP FPM busy worker [available values: min, max 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"

2
middleware/php-fpm/monitors-fpm.tf
View File

@ -13,7 +13,7 @@ resource "datadog_monitor" "datadog_php_fpm_connect_idle" {
type = "metric alert"
query = <<EOF
avg(${var.php_fpm_busy_timeframe}): (
${var.php_fpm_busy_time_aggregator}(${var.php_fpm_busy_timeframe}): (
avg:php_fpm.processes.active{${data.template_file.filter.rendered}} by {region, host} /
( avg:php_fpm.processes.idle{${data.template_file.filter.rendered}} by {region, host} +
avg:php_fpm.processes.active{${data.template_file.filter.rendered}} by {region, host} )

76
system/generic/README.md
View File

@ -23,38 +23,44 @@ Creates a DataDog monitors with the following checks :
* Free disk inodes
* Free disk space
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 | `<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_message | Custom message for CPU load ratio monitor | string | `` | no |
| cpu_load_silenced | Groups to mute for CPU load ratio monitor | map | `<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_message | Custom message for Free disk inodes monitor | string | `` | no |
| free_disk_inodes_silenced | Groups to mute for Free disk inodes monitor | map | `<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_message | Custom message for Free diskspace monitor | string | `` | no |
| free_disk_space_silenced | Groups to mute for Free diskspace monitor | map | `<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_message | Custom message for Free memory monitor | string | - | yes |
| free_memory_silenced | Groups to mute for Free memory monitor | map | `<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 | `<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 | `<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 | `<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 | `<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 | `<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 |

48
system/generic/inputs.tf
View File

@ -38,20 +38,26 @@ variable "cpu_high_message" {
default = ""
}
variable "cpu_high_time_aggregator" {
description = "Monitor aggregator for CPU high [available values: min, max 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"
default = "last_5m"
default = "last_10m"
}
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" {
@ -66,20 +72,26 @@ variable "cpu_load_message" {
default = ""
}
variable "cpu_load_time_aggregator" {
description = "Monitor aggregator for CPU load ratio [available values: min, max 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"
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" {
@ -94,6 +106,12 @@ variable "free_disk_space_message" {
default = ""
}
variable "free_disk_space_time_aggregator" {
description = "Monitor aggregator for Free diskspace [available values: min, max 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"
@ -102,12 +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" {
@ -122,6 +140,12 @@ variable "free_disk_inodes_message" {
default = ""
}
variable "free_disk_inodes_time_aggregator" {
description = "Monitor aggregator for Free disk inodes [available values: min, max 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"
@ -149,10 +173,16 @@ variable "free_memory_message" {
type = "string"
}
variable "free_memory_time_aggregator" {
description = "Monitor aggregator for Free memory [available values: min, max or avg]"
type = "string"
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_1m"
default = "last_5m"
}
variable "free_memory_threshold_warning" {

12
system/generic/monitors-system.tf
View File

@ -11,7 +11,7 @@ resource "datadog_monitor" "datadog_cpu_too_high" {
message = "${coalesce(var.cpu_high_message, var.message)}"
query = <<EOF
min(${var.cpu_high_timeframe}): (
${var.cpu_high_time_aggregator}(${var.cpu_high_timeframe}): (
100 - avg:system.cpu.idle{${data.template_file.filter.rendered}} by {region,host}
) > ${var.cpu_high_threshold_critical}
EOF
@ -42,7 +42,7 @@ resource "datadog_monitor" "datadog_load_too_high" {
message = "${coalesce(var.cpu_load_message, var.message)}"
query = <<EOF
min(${var.cpu_load_timeframe}): (
${var.cpu_load_time_aggregator}(${var.cpu_load_timeframe}): (
avg:system.load.5{${data.template_file.filter.rendered}} by {region,host} /
avg:system.core.count{${data.template_file.filter.rendered}} by {region,host}
) > ${var.cpu_load_threshold_critical}
@ -74,7 +74,7 @@ resource "datadog_monitor" "datadog_free_disk_space_too_low" {
message = "${coalesce(var.free_disk_space_message, var.message)}"
query = <<EOF
min(${var.free_disk_space_timeframe}): (
${var.free_disk_space_time_aggregator}(${var.free_disk_space_timeframe}): (
avg:system.disk.free{${data.template_file.filter.rendered},dd_disk:enabled} by {region,host,device} /
avg:system.disk.total{${data.template_file.filter.rendered},dd_disk:enabled} by {region,host,device} * 100
) < ${var.free_disk_space_threshold_critical}
@ -106,7 +106,7 @@ resource "datadog_monitor" "datadog_free_disk_space_inodes_too_low" {
message = "${coalesce(var.free_disk_inodes_message, var.message)}"
query = <<EOF
min(${var.free_disk_inodes_timeframe}): (
${var.free_disk_inodes_time_aggregator}(${var.free_disk_inodes_timeframe}): (
avg:system.fs.inodes.free{${data.template_file.filter.rendered},dd_disk:enabled} by {region,host,device} /
avg:system.fs.inodes.total{${data.template_file.filter.rendered},dd_disk:enabled} by {region,host,device} * 100
) < ${var.free_disk_inodes_threshold_critical}
@ -138,8 +138,8 @@ resource "datadog_monitor" "datadog_free_memory" {
message = "${var.free_memory_message}"
query = <<EOF
min(${var.free_memory_timeframe}): (
avg:system.mem.free{${data.template_file.filter.rendered}} by {region,host} /
${var.free_memory_time_aggregator}(${var.free_memory_timeframe}): (
avg:system.mem.usable{${data.template_file.filter.rendered}} by {region,host} /
avg:system.mem.total{${data.template_file.filter.rendered}} by {region,host} * 100
) < ${var.free_memory_threshold_critical}
EOF