Merged in MON-79-azure-storage-monitors (pull request #16)

MON-79: Azure Storage monitors

Approved-by: Adrien Broyere <adrien.broyere@fr.clara.net>
Approved-by: Quentin Manfroi <quentin.manfroi@yahoo.fr>
Approved-by: Jérôme Respaut <shr3ps@gmail.com>
Approved-by: Alexandre Gaillet <alexandre.gaillet@fr.clara.net>
Approved-by: Laurent Piroelle <laurent.piroelle@fr.clara.net>

cloud/azure/storage/README.md

@@ -0,0 +1,58 @@
+Azure Storage DataDog monitors
+==============================
+
+How to use this module
+----------------------
+
+```
+module "datadog-monitors-azure-storage" {
+  source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//cloud/azure/storage?ref={revision}"
+
+  message = "${module.datadog-message-alerting.alerting-message}"
+  environment = "${var.environment}"
+}
+```
+
+Purpose
+-------
+Creates a DataDog monitors with the following checks :
+
+* Service availability
+* End to end latency
+* Minimum successful requests
+* Maximum timeout error requests
+* Maximum network error requests
+* Maximum throttling error requests
+* Maximum server other error requests
+* Maximum client other error requests
+* Maximum authorization error requests
+
+Inputs
+------
+
+| Name | Description | Type | Default | Required |
+|------|-------------|:----:|:-----:|:-----:|
+| delay | Delay in seconds for the metric evaluation | string | `600` | no |
+| environment | Architecture environment | string | - | yes |
+| message | Message sent when a monitor is triggered | string | - | yes |
+| filter_tags_use_defaults | Use default tagging convention | string | `true` | no |
+| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
+| availability_threshold_critical | Minimum threshold of availability | string | `90` | no |
+| successful_requests_threshold_critical | Minimum threshold of successful requests | string | `90` | no |
+| latency_threshold_critical | Maximum threshold of latency in ms | string | `1000` | no |
+| timeout_error_requests_threshold_critical | Maximum threshold of timeout error requests in percent | string | `35` | no |
+| network_error_requests_threshold_critical | Maximum threshold of network error requests in percent | string | `35` | no |
+| throttling_error_requests_threshold_critical | Maximum threshold of throttling error requests in percent | string | `50` | no |
+| server_other_error_requests_threshold_critical | Maximum threshold of server other error requests in percent | string | `50` | no |
+| client_other_error_requests_threshold_critical | Maximum threshold of client other error requests in percent | string | `75` | no |
+| authorization_error_requests_threshold_critical | Maximum threshold of authorization error requests in percent | string | `75` | no |
+
+Related documentation
+---------------------
+
+DataDog documentation: [https://docs.datadoghq.com/integrations/azure_storage/](https://docs.datadoghq.com/integrations/azure_storage/)
+
+DataDog blog: [https://www.datadoghq.com/blog/monitor-azure-storage-datadog/](https://www.datadoghq.com/blog/monitor-azure-storage-datadog/)
+
+Azure Redis 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)
+

cloud/azure/storage/inputs.tf

@@ -0,0 +1,72 @@
+# Global Terraform
+variable "environment" {
+  description = "Architecture environment"
+  type = "string"
+}
+
+# Global DataDog
+variable "message" {
+  description = "Message sent when a Redis monitor is triggered"
+}
+
+variable "delay" {
+  description = "Delay in seconds for the metric evaluation"
+  default     = 600
+}
+
+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 Storage specific
+variable "availability_threshold_critical" {
+  description = "Minimum acceptable percent of availability for a storage"
+  default = 90
+}
+
+variable "successful_requests_threshold_critical" {
+  description = "Minimum acceptable percent of successful requests for a storage"
+  default = 90
+}
+
+variable "latency_threshold_critical" {
+  description = "Maximum acceptable end to end latency (ms) for a storage"
+  default = 1000
+}
+
+variable "timeout_error_requests_threshold_critical" {
+  description = "Maximum acceptable percent of timeout error requests for a storage"
+  default = 5
+}
+
+variable "network_error_requests_threshold_critical" {
+  description = "Maximum acceptable percent of network error requests for a storage"
+  default = 5
+}
+
+variable "throttling_error_requests_threshold_critical" {
+  description = "Maximum acceptable percent of throttling error requests for a storage"
+  default = 10
+}
+
+variable "server_other_error_requests_threshold_critical" {
+  description = "Maximum acceptable percent of server other error requests for a storage"
+  default = 10
+}
+
+variable "client_other_error_requests_threshold_critical" {
+  description = "Maximum acceptable percent of client other error requests for a storage"
+  default = 15
+}
+
+variable "authorization_error_requests_threshold_critical" {
+  description = "Maximum acceptable percent of authorization error requests for a storage"
+  default = 15
+}
+

cloud/azure/storage/monitors-azure-storage.tf

@@ -0,0 +1,273 @@
+data "template_file" "filter" {
+  template = "$${filter}"
+
+  vars {
+    filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_azure_storage:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
+  }
+}
+
+resource "datadog_monitor" "availability" {
+  name    = "[${var.environment}] Azure Storage {{name}} unvailability detected"
+  message = "${var.message}"
+
+  query = <<EOF
+    avg(last_5m): (
+      avg:azure.storage.availability{${data.template_file.filter.rendered}} by {resource_group,storage_type,name}
+    ) < ${var.availability_threshold_critical}
+EOF
+
+  thresholds {
+    critical  = "${var.availability_threshold_critical}"
+  }
+
+  type                = "metric alert"
+  notify_no_data      = true
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+  new_host_delay      = "${var.delay}"
+  evaluation_delay    = "${var.delay}"
+  renotify_interval   = 0
+  no_data_timeframe   = 20
+
+  tags = ["env:${var.environment}", "resource:storage", "team:azure", "provider:azure"]
+}
+
+resource "datadog_monitor" "successful_requests" {
+  name    = "[${var.environment}] Azure Storage {{name}} too much failed requests"
+  message = "${var.message}"
+
+  query = <<EOF
+    avg(last_5m): (
+      avg:azure.storage.percent_success{${data.template_file.filter.rendered}} by {resource_group,storage_type,name}
+    ) < ${var.successful_requests_threshold_critical}
+EOF
+
+  thresholds {
+    critical  = "${var.successful_requests_threshold_critical}"
+  }
+
+  type                = "metric alert"
+  notify_no_data      = true
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+  new_host_delay      = "${var.delay}"
+  evaluation_delay    = "${var.delay}"
+  renotify_interval   = 0
+  no_data_timeframe   = 20
+
+  tags = ["env:${var.environment}", "resource:storage", "team:azure", "provider:azure"]
+}
+
+resource "datadog_monitor" "latency" {
+  name    = "[${var.environment}] Azure Storage {{name}} too high end to end latency"
+  message = "${var.message}"
+
+  query = <<EOF
+    max(last_5m): (
+      avg:azure.storage.average_e2_e_latency{${data.template_file.filter.rendered}} by {resource_group,storage_type,name}
+    ) > ${var.latency_threshold_critical}
+EOF
+
+  thresholds {
+    critical  = "${var.latency_threshold_critical}"
+  }
+
+  type                = "metric alert"
+  notify_no_data      = true
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+  new_host_delay      = "${var.delay}"
+  evaluation_delay    = "${var.delay}"
+  renotify_interval   = 0
+  no_data_timeframe   = 20
+
+  tags = ["env:${var.environment}", "resource:storage", "team:azure", "provider:azure"]
+}
+
+resource "datadog_monitor" "timeout_error_requests" {
+  name    = "[${var.environment}] Azure Storage {{value}}% of timeout error requests on {{name}}"
+  message = "${var.message}"
+
+  query = <<EOF
+    avg(last_5m): (
+      avg:azure.storage.percent_timeout_error{${data.template_file.filter.rendered}} by {resource_group,storage_type,name}
+    ) > ${var.timeout_error_requests_threshold_critical}
+EOF
+
+  thresholds {
+    critical  = "${var.timeout_error_requests_threshold_critical}"
+  }
+
+  type                = "metric alert"
+  notify_no_data      = true
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+  new_host_delay      = "${var.delay}"
+  evaluation_delay    = "${var.delay}"
+  renotify_interval   = 0
+  no_data_timeframe   = 20
+
+  tags = ["env:${var.environment}", "resource:storage", "team:azure", "provider:azure"]
+}
+
+
+resource "datadog_monitor" "network_error_requests" {
+  name    = "[${var.environment}] Azure Storage {{value}}% of network error requests on {{name}}"
+  message = "${var.message}"
+
+  query = <<EOF
+    avg(last_5m): (
+      avg:azure.storage.percent_network_error{${data.template_file.filter.rendered}} by {resource_group,storage_type,name}
+    ) > ${var.network_error_requests_threshold_critical}
+EOF
+
+  thresholds {
+    critical  = "${var.network_error_requests_threshold_critical}"
+  }
+
+  type                = "metric alert"
+  notify_no_data      = true
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+  new_host_delay      = "${var.delay}"
+  evaluation_delay    = "${var.delay}"
+  renotify_interval   = 0
+  no_data_timeframe   = 20
+
+  tags = ["env:${var.environment}", "resource:storage", "team:azure", "provider:azure"]
+}
+
+
+resource "datadog_monitor" "throttling_error_requests" {
+  name    = "[${var.environment}] Azure Storage {{value}}% of throttling error requests on {{name}}"
+  message = "${var.message}"
+
+  query = <<EOF
+    avg(last_5m): (
+      avg:azure.storage.percent_throttling_error{${data.template_file.filter.rendered}} by {resource_group,storage_type,name}
+    ) > ${var.throttling_error_requests_threshold_critical}
+EOF
+
+  thresholds {
+    critical  = "${var.throttling_error_requests_threshold_critical}"
+  }
+
+  type                = "metric alert"
+  notify_no_data      = true
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+  new_host_delay      = "${var.delay}"
+  evaluation_delay    = "${var.delay}"
+  renotify_interval   = 0
+  no_data_timeframe   = 20
+
+  tags = ["env:${var.environment}", "resource:storage", "team:azure", "provider:azure"]
+}
+
+
+resource "datadog_monitor" "server_other_error_requests" {
+  name    = "[${var.environment}] Azure Storage {{value}}% of server_other error requests on {{name}}"
+  message = "${var.message}"
+
+  query = <<EOF
+    avg(last_5m): (
+      avg:azure.storage.percent_server_other_error{${data.template_file.filter.rendered}} by {resource_group,storage_type,name}
+    ) > ${var.server_other_error_requests_threshold_critical}
+EOF
+
+  thresholds {
+    critical  = "${var.server_other_error_requests_threshold_critical}"
+  }
+
+  type                = "metric alert"
+  notify_no_data      = true
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+  new_host_delay      = "${var.delay}"
+  evaluation_delay    = "${var.delay}"
+  renotify_interval   = 0
+  no_data_timeframe   = 20
+
+  tags = ["env:${var.environment}", "resource:storage", "team:azure", "provider:azure"]
+}
+
+
+resource "datadog_monitor" "client_other_error_requests" {
+  name    = "[${var.environment}] Azure Storage {{value}}% of client_other error requests on {{name}}"
+  message = "${var.message}"
+
+  query = <<EOF
+    avg(last_5m): (
+      avg:azure.storage.percent_client_other_error{${data.template_file.filter.rendered}} by {resource_group,storage_type,name}
+    ) > ${var.client_other_error_requests_threshold_critical}
+EOF
+
+  thresholds {
+    critical  = "${var.client_other_error_requests_threshold_critical}"
+  }
+
+  type                = "metric alert"
+  notify_no_data      = true
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+  new_host_delay      = "${var.delay}"
+  evaluation_delay    = "${var.delay}"
+  renotify_interval   = 0
+  no_data_timeframe   = 20
+
+  tags = ["env:${var.environment}", "resource:storage", "team:azure", "provider:azure"]
+}
+
+
+resource "datadog_monitor" "authorization_error_requests" {
+  name    = "[${var.environment}] Azure Storage {{value}}% of authorization error requests on {{name}}"
+  message = "${var.message}"
+
+  query = <<EOF
+    avg(last_5m): (
+      avg:azure.storage.percent_authorization_error{${data.template_file.filter.rendered}} by {resource_group,storage_type,name}
+    ) > ${var.authorization_error_requests_threshold_critical}
+EOF
+
+  thresholds {
+    critical  = "${var.authorization_error_requests_threshold_critical}"
+  }
+
+  type                = "metric alert"
+  notify_no_data      = true
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+  new_host_delay      = "${var.delay}"
+  evaluation_delay    = "${var.delay}"
+  renotify_interval   = 0
+  no_data_timeframe   = 20
+
+  tags = ["env:${var.environment}", "resource:storage", "team:azure", "provider:azure"]
+}