Merged in MON-122-add-aurora-monitors (pull request #96)

MON-122 Add Aurora replica lag monitor

Approved-by: David Drugeon-Hamon <david.drugeon.hamon@fr.clara.net>
Approved-by: Quentin Manfroi <quentin.manfroi@yahoo.fr>
Approved-by: Rafael Romero Carmona <rafael.romero.carmona@fr.clara.net>
Approved-by: Guillaume Kérivel <guillaume.kerivel@fr.clara.net>

README.md

@@ -84,6 +84,10 @@ The `//` is very important, it's a terraform specific syntax used to separate gi
 		- [elb](https://bitbucket.org/morea/terraform.feature.datadog/src/master/cloud/aws/elb/)
 		- [kinesis-firehose](https://bitbucket.org/morea/terraform.feature.datadog/src/master/cloud/aws/kinesis-firehose/)
 		- [rds](https://bitbucket.org/morea/terraform.feature.datadog/src/master/cloud/aws/rds/)
+			- [aurora](https://bitbucket.org/morea/terraform.feature.datadog/src/master/cloud/aws/rds/aurora/)
+				- [mysql](https://bitbucket.org/morea/terraform.feature.datadog/src/master/cloud/aws/rds/aurora/mysql/)
+				- [postgresql](https://bitbucket.org/morea/terraform.feature.datadog/src/master/cloud/aws/rds/aurora/postgresql/)
+			- [common](https://bitbucket.org/morea/terraform.feature.datadog/src/master/cloud/aws/rds/common/)
 		- [vpn](https://bitbucket.org/morea/terraform.feature.datadog/src/master/cloud/aws/vpn/)
 	- [azure](https://bitbucket.org/morea/terraform.feature.datadog/src/master/cloud/azure/)
 		- [apimanagement](https://bitbucket.org/morea/terraform.feature.datadog/src/master/cloud/azure/apimanagement/)

cloud/aws/alb/modules.tf

@@ -2,7 +2,7 @@ module "filter-tags" {
   source = "../../../common/filter-tags"
 
   environment              = "${var.environment}"
-  resource                 = "alb"
+  resource                 = "aws_alb"
   filter_tags_use_defaults = "${var.filter_tags_use_defaults}"
   filter_tags_custom       = "${var.filter_tags_custom}"
 }

cloud/aws/elasticsearch/modules.tf

@@ -2,7 +2,7 @@ module "filter-tags" {
   source = "../../../common/filter-tags"
 
   environment              = "${var.environment}"
-  resource                 = "elasticsearch"
+  resource                 = "aws_elasticsearch"
   filter_tags_use_defaults = "${var.filter_tags_use_defaults}"
   filter_tags_custom       = "${var.filter_tags_custom}"
 }

cloud/aws/elb/modules.tf

@@ -2,7 +2,7 @@ module "filter-tags" {
   source = "../../../common/filter-tags"
 
   environment              = "${var.environment}"
-  resource                 = "elb"
+  resource                 = "aws_elb"
   filter_tags_use_defaults = "${var.filter_tags_use_defaults}"
   filter_tags_custom       = "${var.filter_tags_custom}"
 }

cloud/aws/kinesis-firehose/modules.tf

@@ -2,7 +2,7 @@ module "filter-tags" {
   source = "../../../common/filter-tags"
 
   environment              = "${var.environment}"
-  resource                 = "kinesis-firehose"
+  resource                 = "aws_kinesis-firehose"
   filter_tags_use_defaults = "${var.filter_tags_use_defaults}"
   filter_tags_custom       = "${var.filter_tags_custom}"
 }

cloud/aws/rds/aurora/mysql/README.md

@@ -0,0 +1,46 @@
+# CLOUD AWS RDS AURORA MYSQL DataDog monitors
+
+## How to use this module
+
+```
+module "datadog-monitors-cloud-aws-rds-aurora-mysql" {
+  source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//cloud/aws/rds/aurora/mysql?ref={revision}"
+
+  environment = "${var.environment}"
+  message     = "${module.datadog-message-alerting.alerting-message}"
+}
+
+```
+
+## Purpose
+
+Creates DataDog monitors with the following checks:
+
+- RDS Aurora Mysql replica lag
+
+## Inputs
+
+| Name | Description | Type | Default | Required |
+|------|-------------|:----:|:-----:|:-----:|
+| aurora_replicalag_enabled | Flag to enable RDS Aurora replica lag monitor | string | `true` | no |
+| aurora_replicalag_extra_tags | Extra tags for RDS Aurora replica lag monitor | list | `<list>` | no |
+| aurora_replicalag_message | Custom message for RDS Aurora replica lag monitor | string | `` | no |
+| aurora_replicalag_silenced | Groups to mute for RDS Aurora replica lag monitor | map | `<map>` | no |
+| aurora_replicalag_threshold_critical | Aurora replica lag in milliseconds (critical threshold) | string | `200` | no |
+| aurora_replicalag_threshold_warning | Aurora replica lag in milliseconds (warning threshold) | string | `100` | no |
+| aurora_replicalag_timeframe | Monitor timeframe for RDS Aurora replica lag monitor [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 |
+| evaluation_delay | Delay in seconds for the metric evaluation | string | `900` | no |
+| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
+| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
+| message | Message sent when an alert is triggered | string | - | yes |
+| new_host_delay | Delay in seconds before monitor new resource | string | `300` | no |
+
+## Outputs
+
+| Name | Description |
+|------|-------------|
+| rds_aurora_mysql_replica_lag_id | id for monitor rds_aurora_mysql_replica_lag |
+
+## Related documentation
+

cloud/aws/rds/aurora/mysql/inputs.tf

@@ -0,0 +1,72 @@
+# Global Terraform
+variable "environment" {
+  description = "Architecture Environment"
+  type        = "string"
+}
+
+# Global DataDog
+variable "evaluation_delay" {
+  description = "Delay in seconds for the metric evaluation"
+  default     = 900
+}
+
+variable "new_host_delay" {
+  description = "Delay in seconds before monitor new resource"
+  default     = 300
+}
+
+variable "message" {
+  description = "Message sent when an alert is triggered"
+}
+
+variable "filter_tags_use_defaults" {
+  description = "Use default filter tags convention"
+  default     = "true"
+}
+
+variable "filter_tags_custom" {
+  description = "Tags used for custom filtering when filter_tags_use_defaults is false"
+  default     = "*"
+}
+
+# AWS RDS Aurora instance specific
+
+variable "aurora_replicalag_silenced" {
+  description = "Groups to mute for RDS Aurora replica lag monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "aurora_replicalag_enabled" {
+  description = "Flag to enable RDS Aurora replica lag monitor"
+  type        = "string"
+  default     = "true"
+}
+
+variable "aurora_replicalag_extra_tags" {
+  description = "Extra tags for RDS Aurora replica lag monitor"
+  type        = "list"
+  default     = []
+}
+
+variable "aurora_replicalag_message" {
+  description = "Custom message for RDS Aurora replica lag monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "aurora_replicalag_timeframe" {
+  description = "Monitor timeframe for RDS Aurora replica lag monitor [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 "aurora_replicalag_threshold_warning" {
+  description = "Aurora replica lag in milliseconds (warning threshold)"
+  default     = "100"
+}
+
+variable "aurora_replicalag_threshold_critical" {
+  description = "Aurora replica lag in milliseconds (critical threshold)"
+  default     = "200"
+}

cloud/aws/rds/aurora/mysql/modules.tf

@@ -0,0 +1,8 @@
+module "filter-tags" {
+  source = "../../../../../common/filter-tags"
+
+  environment              = "${var.environment}"
+  resource                 = "aws_rds"
+  filter_tags_use_defaults = "${var.filter_tags_use_defaults}"
+  filter_tags_custom       = "${var.filter_tags_custom}"
+}

cloud/aws/rds/aurora/mysql/monitors-rds-aurora-mysql.tf

@@ -0,0 +1,32 @@
+### RDS Aurora Mysql Replica Lag monitor ###
+resource "datadog_monitor" "rds_aurora_mysql_replica_lag" {
+  count   = "${var.aurora_replicalag_enabled ? 1 : 0}"
+  name    = "[${var.environment}] RDS Aurora Mysql replica lag {{#is_alert}}{{{comparator}}} {{threshold}} ms ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}} ms ({{value}}%){{/is_warning}}"
+  message = "${coalesce(var.aurora_replicalag_message, var.message)}"
+
+  type = "metric alert"
+
+  query = <<EOF
+  avg(${var.aurora_replicalag_timeframe}): (
+    avg:aws.rds.aurora_replica_lag${module.filter-tags.query_alert} by {region,name}
+  ) > ${var.aurora_replicalag_threshold_critical}
+EOF
+
+  thresholds {
+    warning  = "${var.aurora_replicalag_threshold_warning}"
+    critical = "${var.aurora_replicalag_threshold_critical}"
+  }
+
+  notify_no_data      = true
+  evaluation_delay    = "${var.evaluation_delay}"
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = false
+  new_host_delay      = "${var.new_host_delay}"
+
+  silenced = "${var.aurora_replicalag_silenced}"
+
+  tags = ["env:${var.environment}", "type:cloud", "provider:aws", "resource:rds-aurora-mysql", "team:claranet", "created-by:terraform", "${var.aurora_replicalag_extra_tags}"]
+}

cloud/aws/rds/aurora/mysql/outputs.tf

@@ -0,0 +1,4 @@
+output "rds_aurora_mysql_replica_lag_id" {
+  description = "id for monitor rds_aurora_mysql_replica_lag"
+  value       = "${datadog_monitor.rds_aurora_mysql_replica_lag.*.id}"
+}

cloud/aws/rds/aurora/postgresql/README.md

@@ -0,0 +1,46 @@
+# CLOUD AWS RDS AURORA POSTGRESQL DataDog monitors
+
+## How to use this module
+
+```
+module "datadog-monitors-cloud-aws-rds-aurora-postgresql" {
+  source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//cloud/aws/rds/aurora/postgresql?ref={revision}"
+
+  environment = "${var.environment}"
+  message     = "${module.datadog-message-alerting.alerting-message}"
+}
+
+```
+
+## Purpose
+
+Creates DataDog monitors with the following checks:
+
+- RDS Aurora PostgreSQL replica lag
+
+## Inputs
+
+| Name | Description | Type | Default | Required |
+|------|-------------|:----:|:-----:|:-----:|
+| aurora_replicalag_enabled | Flag to enable RDS Aurora replica lag monitor | string | `true` | no |
+| aurora_replicalag_extra_tags | Extra tags for RDS Aurora replica lag monitor | list | `<list>` | no |
+| aurora_replicalag_message | Custom message for RDS Aurora replica lag monitor | string | `` | no |
+| aurora_replicalag_silenced | Groups to mute for RDS Aurora replica lag monitor | map | `<map>` | no |
+| aurora_replicalag_threshold_critical | Aurora replica lag in milliseconds (critical threshold) | string | `200` | no |
+| aurora_replicalag_threshold_warning | Aurora replica lag in milliseconds (warning threshold) | string | `100` | no |
+| aurora_replicalag_timeframe | Monitor timeframe for RDS Aurora replica lag monitor [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 |
+| evaluation_delay | Delay in seconds for the metric evaluation | string | `900` | no |
+| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
+| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
+| message | Message sent when an alert is triggered | string | - | yes |
+| new_host_delay | Delay in seconds before monitor new resource | string | `300` | no |
+
+## Outputs
+
+| Name | Description |
+|------|-------------|
+| rds_aurora_postgresql_replica_lag_id | id for monitor rds_aurora_postgresql_replica_lag |
+
+## Related documentation
+

cloud/aws/rds/aurora/postgresql/inputs.tf

@@ -0,0 +1,72 @@
+# Global Terraform
+variable "environment" {
+  description = "Architecture Environment"
+  type        = "string"
+}
+
+# Global DataDog
+variable "evaluation_delay" {
+  description = "Delay in seconds for the metric evaluation"
+  default     = 900
+}
+
+variable "new_host_delay" {
+  description = "Delay in seconds before monitor new resource"
+  default     = 300
+}
+
+variable "message" {
+  description = "Message sent when an alert is triggered"
+}
+
+variable "filter_tags_use_defaults" {
+  description = "Use default filter tags convention"
+  default     = "true"
+}
+
+variable "filter_tags_custom" {
+  description = "Tags used for custom filtering when filter_tags_use_defaults is false"
+  default     = "*"
+}
+
+# AWS RDS Aurora instance specific
+
+variable "aurora_replicalag_silenced" {
+  description = "Groups to mute for RDS Aurora replica lag monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "aurora_replicalag_enabled" {
+  description = "Flag to enable RDS Aurora replica lag monitor"
+  type        = "string"
+  default     = "true"
+}
+
+variable "aurora_replicalag_extra_tags" {
+  description = "Extra tags for RDS Aurora replica lag monitor"
+  type        = "list"
+  default     = []
+}
+
+variable "aurora_replicalag_message" {
+  description = "Custom message for RDS Aurora replica lag monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "aurora_replicalag_timeframe" {
+  description = "Monitor timeframe for RDS Aurora replica lag monitor [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 "aurora_replicalag_threshold_warning" {
+  description = "Aurora replica lag in milliseconds (warning threshold)"
+  default     = "100"
+}
+
+variable "aurora_replicalag_threshold_critical" {
+  description = "Aurora replica lag in milliseconds (critical threshold)"
+  default     = "200"
+}

cloud/aws/rds/aurora/postgresql/modules.tf

@@ -0,0 +1,8 @@
+module "filter-tags" {
+  source = "../../../../../common/filter-tags"
+
+  environment              = "${var.environment}"
+  resource                 = "aws_rds"
+  filter_tags_use_defaults = "${var.filter_tags_use_defaults}"
+  filter_tags_custom       = "${var.filter_tags_custom}"
+}

cloud/aws/rds/aurora/postgresql/monitors-rds-aurora-postgresql.tf

@@ -0,0 +1,32 @@
+### RDS Aurora Postgresql Replica Lag monitor ###
+resource "datadog_monitor" "rds_aurora_postgresql_replica_lag" {
+  count   = "${var.aurora_replicalag_enabled ? 1 : 0}"
+  name    = "[${var.environment}] RDS Aurora PostgreSQL replica lag {{#is_alert}}{{{comparator}}} {{threshold}} ms ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}} ms ({{value}}%){{/is_warning}}"
+  message = "${coalesce(var.aurora_replicalag_message, var.message)}"
+
+  type = "metric alert"
+
+  query = <<EOF
+  avg(${var.aurora_replicalag_timeframe}): (
+    avg:aws.rds.rdsto_aurora_postgre_sqlreplica_lag${module.filter-tags.query_alert} by {region,name}
+  ) > ${var.aurora_replicalag_threshold_critical}
+EOF
+
+  thresholds {
+    warning  = "${var.aurora_replicalag_threshold_warning}"
+    critical = "${var.aurora_replicalag_threshold_critical}"
+  }
+
+  notify_no_data      = true
+  evaluation_delay    = "${var.evaluation_delay}"
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = false
+  new_host_delay      = "${var.new_host_delay}"
+
+  silenced = "${var.aurora_replicalag_silenced}"
+
+  tags = ["env:${var.environment}", "type:cloud", "provider:aws", "resource:rds-aurora-postgresql", "team:claranet", "created-by:terraform", "${var.aurora_replicalag_extra_tags}"]
+}

cloud/aws/rds/aurora/postgresql/outputs.tf

@@ -0,0 +1,4 @@
+output "rds_aurora_postgresql_replica_lag_id" {
+  description = "id for monitor rds_aurora_postgresql_replica_lag"
+  value       = "${datadog_monitor.rds_aurora_postgresql_replica_lag.*.id}"
+}

cloud/aws/rds/common/README.md

@@ -1,10 +1,10 @@
-# CLOUD AWS RDS DataDog monitors
+# CLOUD AWS RDS COMMON DataDog monitors
 
 ## How to use this module
 
 ```
-module "datadog-monitors-cloud-aws-rds" {
-  source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//cloud/aws/rds?ref={revision}"
+module "datadog-monitors-cloud-aws-rds-common" {
+  source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//cloud/aws/rds/common?ref={revision}"
 
   environment = "${var.environment}"
   message     = "${module.datadog-message-alerting.alerting-message}"
@@ -18,6 +18,7 @@ Creates DataDog monitors with the following checks:
 
 - RDS instance CPU high
 - RDS instance free space
+- RDS replica lag
 
 ## Inputs
 
@@ -45,6 +46,13 @@ Creates DataDog monitors with the following checks:
 | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
 | message | Message sent when an alert is triggered | string | - | yes |
 | new_host_delay | Delay in seconds before monitor new resource | string | `300` | no |
+| replicalag_enabled | Flag to enable RDS replica lag monitor | string | `true` | no |
+| replicalag_extra_tags | Extra tags for RDS replica lag monitor | list | `<list>` | no |
+| replicalag_message | Custom message for RDS replica lag monitor | string | `` | no |
+| replicalag_silenced | Groups to mute for RDS replica lag monitor | map | `<map>` | no |
+| replicalag_threshold_critical | replica lag in seconds (critical threshold) | string | `300` | no |
+| replicalag_threshold_warning | replica lag in seconds (warning threshold) | string | `200` | no |
+| replicalag_timeframe | Monitor timeframe for RDS replica lag monitor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
 
 ## Outputs
 
@@ -52,9 +60,11 @@ Creates DataDog monitors with the following checks:
 |------|-------------|
 | rds_cpu_90_15min_id | id for monitor rds_cpu_90_15min |
 | rds_free_space_low_id | id for monitor rds_free_space_low |
+| rds_replica_lag_id | id for monitor rds_replica_lag |
 
 ## Related documentation
 
 DataDog documentation: [https://docs.datadoghq.com/integrations/amazon_rds/](https://docs.datadoghq.com/integrations/amazon_rds/)
 
 AWS RDS Instance metrics documentation: [https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/rds-metricscollected.html](https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/rds-metricscollected.html)
+

cloud/aws/rds/common/inputs.tf

@@ -122,3 +122,43 @@ variable "diskspace_threshold_critical" {
   description = "Disk free space in percent (critical threshold)"
   default     = "10"
 }
+
+variable "replicalag_silenced" {
+  description = "Groups to mute for RDS replica lag monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "replicalag_enabled" {
+  description = "Flag to enable RDS replica lag monitor"
+  type        = "string"
+  default     = "true"
+}
+
+variable "replicalag_extra_tags" {
+  description = "Extra tags for RDS replica lag monitor"
+  type        = "list"
+  default     = []
+}
+
+variable "replicalag_message" {
+  description = "Custom message for RDS replica lag monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "replicalag_timeframe" {
+  description = "Monitor timeframe for RDS replica lag monitor [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 "replicalag_threshold_warning" {
+  description = "replica lag in seconds (warning threshold)"
+  default     = "200"
+}
+
+variable "replicalag_threshold_critical" {
+  description = "replica lag in seconds (critical threshold)"
+  default     = "300"
+}

cloud/aws/rds/common/modules.tf

@@ -1,8 +1,8 @@
 module "filter-tags" {
-  source = "../../../common/filter-tags"
+  source = "../../../../common/filter-tags"
 
   environment              = "${var.environment}"
-  resource                 = "rds"
+  resource                 = "aws_rds"
   filter_tags_use_defaults = "${var.filter_tags_use_defaults}"
   filter_tags_custom       = "${var.filter_tags_custom}"
 }

cloud/aws/rds/common/monitors-rds-common.tf

@@ -64,3 +64,36 @@ EOF
 
   tags = ["env:${var.environment}", "type:cloud", "provider:aws", "resource:rds", "team:claranet", "created-by:terraform", "${var.diskspace_extra_tags}"]
 }
+
+### RDS Replica Lag monitor ###
+resource "datadog_monitor" "rds_replica_lag" {
+  count   = "${var.replicalag_enabled ? 1 : 0}"
+  name    = "[${var.environment}] RDS replica lag {{#is_alert}}{{{comparator}}} {{threshold}} ms ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}} ms ({{value}}%){{/is_warning}}"
+  message = "${coalesce(var.replicalag_message, var.message)}"
+
+  type = "metric alert"
+
+  query = <<EOF
+  avg(${var.replicalag_timeframe}): (
+    avg:aws.rds.replica_lag${module.filter-tags.query_alert} by {region,name}
+  ) > ${var.replicalag_threshold_critical}
+EOF
+
+  thresholds {
+    warning  = "${var.replicalag_threshold_warning}"
+    critical = "${var.replicalag_threshold_critical}"
+  }
+
+  notify_no_data      = true
+  evaluation_delay    = "${var.evaluation_delay}"
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = false
+  new_host_delay      = "${var.new_host_delay}"
+
+  silenced = "${var.replicalag_silenced}"
+
+  tags = ["env:${var.environment}", "type:cloud", "provider:aws", "resource:rds", "team:claranet", "created-by:terraform", "${var.replicalag_extra_tags}"]
+}

cloud/aws/rds/common/outputs.tf

@@ -7,3 +7,8 @@ output "rds_free_space_low_id" {
   description = "id for monitor rds_free_space_low"
   value       = "${datadog_monitor.rds_free_space_low.*.id}"
 }
+
+output "rds_replica_lag_id" {
+  description = "id for monitor rds_replica_lag"
+  value       = "${datadog_monitor.rds_replica_lag.*.id}"
+}