Merged in MON-316-monitors-for-server-farms (pull request #166)

MON-316 monitors for server farms

Approved-by: jeremy.nancel@fr.clara.net <jeremy.nancel@fr.clara.net>
Approved-by: Quentin Manfroi <quentin.manfroi@yahoo.fr>

README.md

@@ -103,6 +103,7 @@ The `//` is very important, it's a terraform specific syntax used to separate gi
 		- [keyvault](https://bitbucket.org/morea/terraform.feature.datadog/src/master/cloud/azure/keyvault/)
 		- [postgresql](https://bitbucket.org/morea/terraform.feature.datadog/src/master/cloud/azure/postgresql/)
 		- [redis](https://bitbucket.org/morea/terraform.feature.datadog/src/master/cloud/azure/redis/)
+		- [serverfarms](https://bitbucket.org/morea/terraform.feature.datadog/src/master/cloud/azure/serverfarms/)
 		- [servicebus](https://bitbucket.org/morea/terraform.feature.datadog/src/master/cloud/azure/servicebus/)
 		- [sql-database](https://bitbucket.org/morea/terraform.feature.datadog/src/master/cloud/azure/sql-database/)
 		- [storage](https://bitbucket.org/morea/terraform.feature.datadog/src/master/cloud/azure/storage/)

cloud/azure/serverfarms/README.md

@@ -0,0 +1,65 @@
+# CLOUD AZURE SERVERFARMS DataDog monitors
+
+## How to use this module
+
+```
+module "datadog-monitors-cloud-azure-serverfarms" {
+  source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//cloud/azure/serverfarms?ref={revision}"
+
+  environment = "${var.environment}"
+  message     = "${module.datadog-message-alerting.alerting-message}"
+}
+
+```
+
+## Purpose
+
+Creates DataDog monitors with the following checks:
+
+- Serverfarm CPU percentage is too high
+- Serverfarm is down
+- Serverfarm memory percentage is too high
+
+## Inputs
+
+| Name | Description | Type | Default | Required |
+|------|-------------|:----:|:-----:|:-----:|
+| cpu_percentage_enabled | Flag to enable the serverfarms cpu_percentage monitor | string | `true` | no |
+| cpu_percentage_extra_tags | Extra tags for serverfarms cpu_percentage monitor | list | `[]` | no |
+| cpu_percentage_message | Custom message for serverfarm cpu_percentage monitor | string | `` | no |
+| cpu_percentage_silenced | Groups to mute for serverfarm cpu_percentage monitor | map | `{}` | no |
+| cpu_percentage_threshold_critical | CPU percentage (critical threshold) | string | `95` | no |
+| cpu_percentage_threshold_warning | CPU percentage (warning threshold) | string | `90` | no |
+| cpu_percentage_time_aggregator | Monitor aggregator for serverfarms cpu_percentage [available values: min, max or avg] | string | `min` | no |
+| cpu_percentage_timeframe | Monitor timeframe for serverfarms cpu_percentage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_10m` | 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 |
+| memory_percentage_enabled | Flag to enable the serverfarms memory_percentage monitor | string | `true` | no |
+| memory_percentage_extra_tags | Extra tags for serverfarms memory_percentage monitor | list | `[]` | no |
+| memory_percentage_message | Custom message for serverfarm memory_percentage monitor | string | `` | no |
+| memory_percentage_silenced | Groups to mute for serverfarm memory_percentage monitor | map | `{}` | no |
+| memory_percentage_threshold_critical | Memory percentage (critical threshold) | string | `95` | no |
+| memory_percentage_threshold_warning | Memory percentage (warning threshold) | string | `90` | no |
+| memory_percentage_time_aggregator | Monitor aggregator for serverfarms memory_percentage [available values: min, max or avg] | string | `min` | no |
+| memory_percentage_timeframe | Monitor timeframe for serverfarms memory_percentage [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 serverfarms monitor is triggered | string | - | yes |
+| new_host_delay | Delay in seconds before monitor new resource | string | `300` | no |
+| status_enabled | Flag to enable the serverfarms status monitor | string | `true` | no |
+| status_extra_tags | Extra tags for serverfarms status monitor | list | `[]` | no |
+| status_message | Custom message for serverfarm status monitor | string | `` | no |
+| status_silenced | Groups to mute for serverfarm status monitor | map | `{}` | no |
+| status_time_aggregator | Monitor aggregator for serverfarms status [available values: min, max or avg] | string | `min` | no |
+| status_timeframe | Monitor timeframe for serverfarms status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
+
+## Outputs
+
+| Name | Description |
+|------|-------------|
+| cpu_percentage_id | id for monitor cpu_percentage |
+| memory_percentage_id | id for monitor memory_percentage |
+| status_id | id for monitor status |
+
+## Related documentation
+

cloud/azure/serverfarms/inputs.tf

@@ -0,0 +1,163 @@
+# Global Terraform
+variable "environment" {
+  description = "Architecture environment"
+  type        = "string"
+}
+
+# Global DataDog
+variable "message" {
+  description = "Message sent when a serverfarms monitor is triggered"
+}
+
+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 "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     = "*"
+}
+
+# Azure serverfarms specific variables
+
+# Status
+variable "status_enabled" {
+  description = "Flag to enable the serverfarms status monitor"
+  type        = "string"
+  default     = "true"
+}
+
+variable "status_message" {
+  description = "Custom message for serverfarm status monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "status_silenced" {
+  type        = "map"
+  description = "Groups to mute for serverfarm status monitor"
+  default     = {}
+}
+
+variable "status_extra_tags" {
+  description = "Extra tags for serverfarms status monitor"
+  type        = "list"
+  default     = []
+}
+
+variable "status_time_aggregator" {
+  description = "Monitor aggregator for serverfarms status [available values: min, max or avg]"
+  type        = "string"
+  default     = "min"
+}
+
+variable "status_timeframe" {
+  description = "Monitor timeframe for serverfarms 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"
+}
+
+# CPU percentage
+variable "cpu_percentage_enabled" {
+  description = "Flag to enable the serverfarms cpu_percentage monitor"
+  type        = "string"
+  default     = "true"
+}
+
+variable "cpu_percentage_message" {
+  description = "Custom message for serverfarm cpu_percentage monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "cpu_percentage_silenced" {
+  type        = "map"
+  description = "Groups to mute for serverfarm cpu_percentage monitor"
+  default     = {}
+}
+
+variable "cpu_percentage_extra_tags" {
+  description = "Extra tags for serverfarms cpu_percentage monitor"
+  type        = "list"
+  default     = []
+}
+
+variable "cpu_percentage_time_aggregator" {
+  description = "Monitor aggregator for serverfarms cpu_percentage [available values: min, max or avg]"
+  type        = "string"
+  default     = "min"
+}
+
+variable "cpu_percentage_timeframe" {
+  description = "Monitor timeframe for serverfarms cpu_percentage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
+  type        = "string"
+  default     = "last_10m"
+}
+
+variable "cpu_percentage_threshold_critical" {
+  description = "CPU percentage (critical threshold)"
+  default     = 95
+}
+
+variable "cpu_percentage_threshold_warning" {
+  description = "CPU percentage (warning threshold)"
+  default     = 90
+}
+
+# Memory percentage
+variable "memory_percentage_enabled" {
+  description = "Flag to enable the serverfarms memory_percentage monitor"
+  type        = "string"
+  default     = "true"
+}
+
+variable "memory_percentage_message" {
+  description = "Custom message for serverfarm memory_percentage monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "memory_percentage_silenced" {
+  type        = "map"
+  description = "Groups to mute for serverfarm memory_percentage monitor"
+  default     = {}
+}
+
+variable "memory_percentage_extra_tags" {
+  description = "Extra tags for serverfarms memory_percentage monitor"
+  type        = "list"
+  default     = []
+}
+
+variable "memory_percentage_time_aggregator" {
+  description = "Monitor aggregator for serverfarms memory_percentage [available values: min, max or avg]"
+  type        = "string"
+  default     = "min"
+}
+
+variable "memory_percentage_timeframe" {
+  description = "Monitor timeframe for serverfarms memory_percentage [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 "memory_percentage_threshold_critical" {
+  description = "Memory percentage (critical threshold)"
+  default     = 95
+}
+
+variable "memory_percentage_threshold_warning" {
+  description = "Memory percentage (warning threshold)"
+  default     = 90
+}

cloud/azure/serverfarms/modules.tf

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

cloud/azure/serverfarms/monitors-azure-serverfarms.tf

@@ -0,0 +1,93 @@
+resource "datadog_monitor" "status" {
+  count   = "${var.status_enabled ? 1 : 0}"
+  name    = "[${var.environment}] Serverfarm is down"
+  message = "${coalesce(var.status_message, var.message)}"
+
+  query = <<EOF
+    ${var.status_time_aggregator}(${var.status_timeframe}): (
+      avg:azure.web_serverfarms.status${module.filter-tags.query_alert} by {resource_group,region,name}
+    ) != 1
+  EOF
+
+  type = "metric alert"
+
+  silenced = "${var.status_silenced}"
+
+  notify_no_data      = true
+  evaluation_delay    = "${var.evaluation_delay}"
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = false
+  new_host_delay      = "${var.new_host_delay}"
+
+  tags = ["env:${var.environment}", "type:cloud", "provider:azure", "resource:serverfarms", "team:claranet", "created-by:terraform", "${var.status_extra_tags}"]
+}
+
+resource "datadog_monitor" "cpu_percentage" {
+  count   = "${var.cpu_percentage_enabled ? 1 : 0}"
+  name    = "[${var.environment}] Serverfarm CPU percentage is too high {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
+  message = "${coalesce(var.cpu_percentage_message, var.message)}"
+
+  query = <<EOF
+    ${var.cpu_percentage_time_aggregator}(${var.cpu_percentage_timeframe}): (
+      avg:azure.web_serverfarms.cpu_percentage${module.filter-tags.query_alert} by {resource_group,region,name}
+    ) > ${var.cpu_percentage_threshold_critical}
+  EOF
+
+  type = "metric alert"
+
+  thresholds {
+    warning  = "${var.cpu_percentage_threshold_warning}"
+    critical = "${var.cpu_percentage_threshold_critical}"
+  }
+
+  silenced = "${var.cpu_percentage_silenced}"
+
+  notify_no_data      = false
+  evaluation_delay    = "${var.evaluation_delay}"
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = false
+  new_host_delay      = "${var.new_host_delay}"
+
+  tags = ["env:${var.environment}", "type:cloud", "provider:azure", "resource:serverfarms", "team:claranet", "created-by:terraform", "${var.cpu_percentage_extra_tags}"]
+}
+
+resource "datadog_monitor" "memory_percentage" {
+  count   = "${var.memory_percentage_enabled ? 1 : 0}"
+  name    = "[${var.environment}] Serverfarm memory percentage is too high {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
+  message = "${coalesce(var.memory_percentage_message, var.message)}"
+
+  query = <<EOF
+    ${var.memory_percentage_time_aggregator}(${var.memory_percentage_timeframe}): (
+      avg:azure.web_serverfarms.memory_percentage${module.filter-tags.query_alert} by {resource_group,region,name}
+    ) > ${var.memory_percentage_threshold_critical}
+  EOF
+
+  type = "metric alert"
+
+  thresholds {
+    warning  = "${var.memory_percentage_threshold_warning}"
+    critical = "${var.memory_percentage_threshold_critical}"
+  }
+
+  silenced = "${var.memory_percentage_silenced}"
+
+  notify_no_data      = false
+  evaluation_delay    = "${var.evaluation_delay}"
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = false
+  new_host_delay      = "${var.new_host_delay}"
+
+  tags = ["env:${var.environment}", "type:cloud", "provider:azure", "resource:serverfarms", "team:claranet", "created-by:terraform", "${var.memory_percentage_extra_tags}"]
+}

cloud/azure/serverfarms/outputs.tf

@@ -0,0 +1,14 @@
+output "status_id" {
+  description = "id for monitor status"
+  value       = "${datadog_monitor.status.*.id}"
+}
+
+output "cpu_percentage_id" {
+  description = "id for monitor cpu_percentage"
+  value       = "${datadog_monitor.cpu_percentage.*.id}"
+}
+
+output "memory_percentage_id" {
+  description = "id for monitor memory_percentage"
+  value       = "${datadog_monitor.memory_percentage.*.id}"
+}