Merged in MON-77-azure-hub-event-monitors (pull request #7)

MON-77 Azure Event Hub monitors

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

cloud/azure/eventhub/README.md

@@ -0,0 +1,54 @@
+Event Hub Datadog monitor
+=========================
+
+How to use this module
+----------------------
+
+```
+module "datadog-monitors-azure-eventhub" {
+  source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//cloud/azure/eventhub?ref={revision}"
+
+  message = "${module.datadog-message-alerting.alerting-message}"
+  environment = "${var.environment}"
+  subscription_id = "${var.subscription_id}"
+}
+```
+
+Purpose
+-------
+Creates a Datadog monitor with the following checks :
+
+* Service status check
+* Failed request ratio
+* Erroneous requests ratio
+
+Inputs
+------
+
+| Name | Description | Type | Default | Required |
+|------|-------------|:----:|:-----:|:-----:|
+| delay | Delay in seconds for the metric evaluation | string | `600` | no |
+| environment | Architecture environment | string | - | yes |
+| errors_rate_thresold_critical | Errors ratio (percentage) to trigger the critical alert | string | `3` | no |
+| errors_rate_thresold_warning | Errors ratio (percentage) to trigger a warning alert | string | `1` | no |
+| failed_requests_rate_thresold_critical | Failed requests ratio (percentage) to trigger the critical alert | string | `3` | no |
+| failed_requests_rate_thresold_warning | Failed requests ratio (percentage) to trigger a warning alert | string | `1` | 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 |
+
+Outputs
+-------
+
+| Name | Description |
+|------|-------------|
+| errors_monitor_id | Id of the `errors` monitor |
+| failed_requests_monitor_id | Id of the `failed requests` monitor |
+| status_monitor_id | Id of the `status` monitor |
+
+Related documentation
+---------------------
+
+Datadog documentation : [https://docs.datadoghq.com/integrations/azure_event_hub/](https://docs.datadoghq.com/integrations/azure_event_hub/)
+
+Azure metrics documentation : [https://docs.microsoft.com/en-us/azure/event-hubs/event-hubs-metrics-azure-monitor](https://docs.microsoft.com/en-us/azure/event-hubs/event-hubs-metrics-azure-monitor)

cloud/azure/eventhub/inputs.tf

@@ -0,0 +1,45 @@
+# Global Terraform
+variable "environment" {
+  description = "Architecture environment"
+  type = "string"
+}
+
+# Global DataDog
+variable "message" {
+  description = "Message sent when an alert 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     = "*"
+}
+
+variable "failed_requests_rate_thresold_critical" {
+  description = "Failed requests ratio (percentage) to trigger the critical alert"
+  default = 3
+}
+
+variable "failed_requests_rate_thresold_warning" {
+  description = "Failed requests ratio (percentage) to trigger a warning alert"
+  default = 1
+}
+
+variable "errors_rate_thresold_critical" {
+  description = "Errors ratio (percentage) to trigger the critical alert"
+  default = 3
+}
+
+variable "errors_rate_thresold_warning" {
+  description = "Errors ratio (percentage) to trigger a warning alert"
+  default = 1
+}

cloud/azure/eventhub/monitors-eventhub.tf

@@ -0,0 +1,100 @@
+data "template_file" "filter" {
+  template = "$${filter}"
+
+  vars {
+    filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_azure_eventhub:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
+  }
+}
+
+resource "datadog_monitor" "eventhub_status" {
+  name    = "[${var.environment}] Event Hub status is not ok on {{name}}"
+  message = "${var.message}"
+
+  query = <<EOF
+      avg(last_5m): avg:azure.eventhub_namespaces.status{${data.template_file.filter.rendered}} by {name,resource_group,region} != 1
+      EOF
+  type  = "metric alert"
+
+  notify_no_data      = true
+  evaluation_delay    = "${var.delay}"
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+  new_host_delay      = "${var.delay}"
+  no_data_timeframe   = 20
+
+  tags = ["env:${var.environment}", "resource:eventhub", "team:azure", "provider:azure"]
+}
+
+resource "datadog_monitor" "eventhub_failed_requests" {
+  name    = "[${var.environment}] Event Hub too much failed requests on {{name}}"
+  message = "${var.message}"
+
+  query = <<EOF
+        avg(last_5m): (
+          avg:azure.eventhub_namespaces.failed_requests{${data.template_file.filter.rendered}} by {name,resource_group,region}
+        ) * 100 / (
+          avg:azure.eventhub_namespaces.successful_requests{${data.template_file.filter.rendered}} by {name,resource_group,region} +
+          avg:azure.eventhub_namespaces.failed_requests{${data.template_file.filter.rendered}} by {name,resource_group,region}
+        ) > ${var.failed_requests_rate_thresold_critical}
+        EOF
+  type  = "metric alert"
+
+  thresholds {
+    critical = "${var.failed_requests_rate_thresold_critical}"
+    warning  = "${var.failed_requests_rate_thresold_warning}"
+  }
+
+  notify_no_data      = false
+  evaluation_delay    = "${var.delay}"
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+  new_host_delay      = "${var.delay}"
+  no_data_timeframe   = 20
+
+  tags = ["env:${var.environment}", "resource:eventhub", "team:azure", "provider:azure"]
+}
+
+resource "datadog_monitor" "eventhub_errors" {
+  name    = "[${var.environment}] Event Hub too much errors on {{name}}"
+  message = "${var.message}"
+
+  query = <<EOF
+        avg(last_5m): (
+          avg:azure.eventhub_namespaces.internal_server_errors{${data.template_file.filter.rendered}} by {name,resource_group,region} +
+          avg:azure.eventhub_namespaces.server_busy_errors{${data.template_file.filter.rendered}} by {name,resource_group,region} +
+          avg:azure.eventhub_namespaces.other_errors{${data.template_file.filter.rendered}} by {name,resource_group,region}
+        ) * 100 / (
+          avg:azure.eventhub_namespaces.successful_requests{${data.template_file.filter.rendered}} by {name,resource_group,region} +
+          avg:azure.eventhub_namespaces.internal_server_errors{${data.template_file.filter.rendered}} by {name,resource_group,region} +
+          avg:azure.eventhub_namespaces.server_busy_errors{${data.template_file.filter.rendered}} by {name,resource_group,region} +
+          avg:azure.eventhub_namespaces.other_errors{${data.template_file.filter.rendered}} by {name,resource_group,region}
+        ) > ${var.errors_rate_thresold_critical}
+        EOF
+  type  = "metric alert"
+
+  thresholds {
+    critical = "${var.errors_rate_thresold_critical}"
+    warning  = "${var.errors_rate_thresold_warning}"
+  }
+
+  notify_no_data      = false
+  evaluation_delay    = "${var.delay}"
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+  new_host_delay      = "${var.delay}"
+  no_data_timeframe   = 20
+
+  tags = ["env:${var.environment}", "resource:eventhub", "team:azure", "provider:azure"]
+}

cloud/azure/eventhub/outputs.tf

@@ -0,0 +1,11 @@
+output "status_monitor_id" {
+  value = "${datadog_monitor.eventhub_failed_requests.id}"
+}
+
+output "failed_requests_monitor_id" {
+  value = "${datadog_monitor.eventhub_status.id}"
+}
+
+output "errors_monitor_id" {
+  value = "${datadog_monitor.eventhub_errors.id}"
+}