MON-77 Some documentation & lower thresold levels

cloud/azure/eventhub/README.md

@@ -0,0 +1,53 @@
+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}"
+}
+```
+
+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 |
+| message | Message sent when an alert is triggered | string | - | yes |
+| use_filter_tags | Filter the data with service tags if true | string | `true` | no |
+
+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

@@ -1,31 +1,35 @@
 variable "environment" {}
 
-variable "down_message" {}
+variable "message" {
-
+  description = "Message sent when an alert is triggered"
-variable "failed_requests_message" {}
+}
-
-variable "errors_message" {}
 
 variable "delay" {
+  description = "Delay in seconds for the metric evaluation"
   default = 600
 }
 
 variable "failed_requests_rate_thresold_critical" {
-  default = 5
+  description = "Failed requests ratio (percentage) to trigger the critical alert"
+  default = 3
 }
 
 variable "failed_requests_rate_thresold_warning" {
-  default = 3
+  description = "Failed requests ratio (percentage) to trigger a warning alert"
+  default = 1
 }
 
 variable "errors_rate_thresold_critical" {
-  default = 5
+  description = "Errors ratio (percentage) to trigger the critical alert"
-}
-
-variable "errors_rate_thresold_warning" {
   default = 3
 }
 
+variable "errors_rate_thresold_warning" {
+  description = "Errors ratio (percentage) to trigger a warning alert"
+  default = 1
+}
+
 variable "use_filter_tags" {
+  description = "Filter the data with service tags if true"
   default = "true"
 }

cloud/azure/eventhub/monitors-eventhub.tf

@@ -9,7 +9,7 @@ data "template_file" "filter" {
 
 resource "datadog_monitor" "eventhub_status" {
   name    = "[${var.environment}] Event Hub status"
-  message = "${var.down_message}"
+  message = "${var.message}"
 
   query = <<EOF
       avg(last_5m): avg:azure.eventhub_namespaces.status{${data.template_file.filter.rendered}} by {name,resource_group,region} != 1
@@ -18,7 +18,7 @@ resource "datadog_monitor" "eventhub_status" {
 
   notify_no_data      = true
   evaluation_delay    = "${var.delay}"
-  renotify_interval   = 60
+  renotify_interval   = 0
   notify_audit        = false
   timeout_h           = 0
   include_tags        = true
@@ -30,7 +30,7 @@ resource "datadog_monitor" "eventhub_status" {
 
 resource "datadog_monitor" "eventhub_failed_requests" {
   name    = "[${var.environment}] Event Hub failed requests"
-  message = "${var.failed_requests_message}"
+  message = "${var.message}"
 
   query = <<EOF
         avg(last_5m): (
@@ -49,7 +49,7 @@ resource "datadog_monitor" "eventhub_failed_requests" {
 
   notify_no_data      = false
   evaluation_delay    = "${var.delay}"
-  renotify_interval   = 60
+  renotify_interval   = 0
   notify_audit        = false
   timeout_h           = 0
   include_tags        = true
@@ -61,7 +61,7 @@ resource "datadog_monitor" "eventhub_failed_requests" {
 
 resource "datadog_monitor" "eventhub_errors" {
   name    = "[${var.environment}] Event Hub errors"
-  message = "${var.errors_message}"
+  message = "${var.message}"
 
   query = <<EOF
         avg(last_5m): (
@@ -84,7 +84,7 @@ resource "datadog_monitor" "eventhub_errors" {
 
   notify_no_data      = false
   evaluation_delay    = "${var.delay}"
-  renotify_interval   = 60
+  renotify_interval   = 0
   notify_audit        = false
   timeout_h           = 0
   include_tags        = true