MON-32 - Elasticache CPU monitors added

cloud/aws/elasticache/README.md

@@ -0,0 +1,45 @@
+AWS ElasticCache Service DataDog monitors
+=========================================
+
+How to use this module
+----------------------
+
+```
+module "datadog-monitors-aws-elasticcache" {
+  source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//cloud/aws/elasticcache?ref={revision}"
+
+  message = "${module.datadog-message-alerting.alerting-message}"
+  environment = "${var.environment}"
+}
+
+```
+
+Purpose
+-------
+Creates DataDog monitors with the following checks :
+
+* CPU High
+
+Inputs
+------
+
+| Name | Description | Type | Default | Required |
+|------|-------------|:----:|:-----:|:-----:|
+| cpu_aggregator | Monitor aggregator for Elasticache CPU high [available values: min, max, sum or avg] | string | `min` | no |
+| cpu_message | Custom message for Elasticache CPU high monitor | string | `` | no |
+| cpu_silenced | Groups to mute for Elasticache CPU high monitor | map | `<map>` | no |
+| cpu_threshold_critical | Elasticache CPU high critical threshold in percentage | string | `95` | no |
+| cpu_threshold_warning | Elasticache CPU high warning threshold in percentage | string | `80` | no |
+| cpu_timeframe | Monitor timeframe for Elasticache CPU high [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
+| delay | Delay in seconds for the metric evaluation | string | `900` | no |
+| 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 |
+
+Related documentation
+---------------------
+
+DataDog documentation: [https://docs.datadoghq.com/integrations/amazon_elasticache/](https://docs.datadoghq.com/integrations/amazon_elasticache/)
+
+AWS ElasticSearch Service Instance metrics documentation: [https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/elasticache-metricscollected.html](https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/elasticache-metricscollected.html)

cloud/aws/elasticache/inputs.tf

@@ -0,0 +1,59 @@
+# Global Terraform
+variable "environment" {
+  description = "Architecture Environment"
+  type        = "string"
+}
+
+# Global DataDog
+variable "delay" {
+  description = "Delay in seconds for the metric evaluation"
+  default     = 900
+}
+
+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     = "*"
+}
+
+# Elasticache specific
+variable "cpu_silenced" {
+  description = "Groups to mute for Elasticache CPU high monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "cpu_message" {
+  description = "Custom message for Elasticache CPU high monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "cpu_aggregator" {
+  description = "Monitor aggregator for Elasticache CPU high [available values: min, max, sum or avg]"
+  type        = "string"
+  default     = "min"
+}
+
+variable "cpu_timeframe" {
+  description = "Monitor timeframe for Elasticache CPU high [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
+  default     = "last_15m"
+}
+
+variable "cpu_threshold_warning" {
+  description = "Elasticache CPU high warning threshold in percentage"
+  default     = 80
+}
+
+variable "cpu_threshold_critical" {
+  description = "Elasticache CPU high critical threshold in percentage"
+  default     = 95
+}

cloud/aws/elasticache/monitors-elasticache.tf

@@ -0,0 +1,39 @@
+data "template_file" "filter" {
+  template = "$${filter}"
+
+  vars {
+    filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_es:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
+  }
+}
+
+resource "datadog_monitor" "elasticache_cpu_high" {
+  name    = "[${var.environment}] Elasticache CPU high {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
+  message = "${coalesce(var.cpu_message, var.message)}"
+
+  type = "metric alert"
+
+  query = <<EOF
+    ${var.cpu_aggregator}(${var.cpu_timeframe}): (
+      ${var.cpu_aggregator}:aws.elasticache.cpuutilization{${data.template_file.filter.rendered}} by {region,name}
+    ) > ${var.cpu_threshold_critical}
+  EOF
+
+  thresholds {
+    warning  = "${var.cpu_threshold_warning}"
+    critical = "${var.cpu_threshold_critical}"
+  }
+
+  notify_no_data      = true
+  evaluation_delay    = "${var.delay}"
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = false
+  new_host_delay      = "${var.delay}"
+
+  silenced = "${var.cpu_silenced}"
+
+  tags = ["env:${var.environment}", "resource:elasticache", "team:aws", "provider:aws"]
+}