MON-451: Do not notify no data alerts for Azure app services memory usage and add app services status monitor

cloud/azure/app-services/README.md

@@ -19,6 +19,7 @@ Creates DataDog monitors with the following checks:
 - App Services HTTP 4xx errors too high
 - App Services HTTP 5xx errors too high
 - App Services HTTP successful responses too low
+- App Services is down
 - App Services memory usage
 - App Services response time too high
 
@@ -74,6 +75,12 @@ Creates DataDog monitors with the following checks:
 | response\_time\_threshold\_warning | Warning threshold for response time in seconds | string | `"5"` | no |
 | response\_time\_time\_aggregator | Monitor aggregator for App Services response time [available values: min, max or avg] | string | `"min"` | no |
 | response\_time\_timeframe | Monitor timeframe for App Services response time [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `"last_5m"` | no |
+| status\_enabled | Flag to enable App Services status monitor | string | `"true"` | no |
+| status\_extra\_tags | Extra tags for App Services status monitor | list | `[]` | no |
+| status\_message | Custom message for App Services status monitor | string | `""` | no |
+| status\_silenced | Groups to mute for App Services status monitor | map | `{}` | no |
+| status\_time\_aggregator | Monitor aggregator for App Services status [available values: min, max or avg] | string | `"max"` | no |
+| status\_timeframe | Monitor timeframe for App Services 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
 
@@ -84,6 +91,7 @@ Creates DataDog monitors with the following checks:
 | appservices\_http\_success\_status\_rate\_id | id for monitor appservices_http_success_status_rate |
 | appservices\_memory\_usage\_count\_id | id for monitor appservices_memory_usage_count |
 | appservices\_response\_time\_id | id for monitor appservices_response_time |
+| appservices\_status\_id | id for monitor appservices_status |
 
 ## Related documentation
 

cloud/azure/app-services/inputs.tf

@@ -267,3 +267,39 @@ variable "http_successful_requests_threshold_warning" {
   default     = 30
   description = "Warning regarding acceptable percent of 2xx & 3xx requests"
 }
+
+variable "status_enabled" {
+  description = "Flag to enable App Services status monitor"
+  type        = "string"
+  default     = "true"
+}
+
+variable "status_message" {
+  description = "Custom message for App Services status monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "status_silenced" {
+  description = "Groups to mute for App Services status monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "status_extra_tags" {
+  description = "Extra tags for App Services status monitor"
+  type        = "list"
+  default     = []
+}
+
+variable "status_time_aggregator" {
+  description = "Monitor aggregator for App Services status [available values: min, max or avg]"
+  type        = "string"
+  default     = "max"
+}
+
+variable "status_timeframe" {
+  description = "Monitor timeframe for App Services 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"
+}

cloud/azure/app-services/monitors-app_services.tf

@@ -21,7 +21,7 @@ resource "datadog_monitor" "appservices_response_time" {
 
   silenced = "${var.response_time_silenced}"
 
-  notify_no_data      = true  # Will notify when no data is received
+  notify_no_data      = false # Will NOT notify when no data is received
   renotify_interval   = 0
   require_full_window = false
   timeout_h           = 0
@@ -53,7 +53,7 @@ resource "datadog_monitor" "appservices_memory_usage_count" {
 
   silenced = "${var.memory_usage_silenced}"
 
-  notify_no_data      = true  # Will notify when no data is received
+  notify_no_data      = false # Will NOT notify when no data is received
   renotify_interval   = 0
   require_full_window = false
   timeout_h           = 0
@@ -162,3 +162,30 @@ resource "datadog_monitor" "appservices_http_success_status_rate" {
 
   tags = ["env:${var.environment}", "type:cloud", "provider:azure", "resource:app-services", "team:claranet", "created-by:terraform", "${var.http_successful_requests_extra_tags}"]
 }
+
+# Monitoring App Services status
+resource "datadog_monitor" "appservices_status" {
+  count   = "${var.status_enabled == "true" ? 1 : 0}"
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] App Services is down"
+  type    = "metric alert"
+  message = "${coalesce(var.status_message, var.message)}"
+
+  query = <<EOQ
+      ${var.status_time_aggregator}(${var.status_timeframe}):avg:azure.app_services.status${module.filter-tags.query_alert} by {resource_group,region,name} < 1
+  EOQ
+
+  evaluation_delay = "${var.evaluation_delay}"
+  new_host_delay   = "${var.new_host_delay}"
+
+  thresholds {
+    critical = 1
+  }
+
+  silenced            = "${var.status_silenced}"
+  notify_no_data      = true                                                                                                                                                     # Will notify when no data is received
+  renotify_interval   = 0
+  require_full_window = false
+  timeout_h           = 0
+  include_tags        = true
+  tags                = ["env:${var.environment}", "type:cloud", "provider:azure", "resource:app-services", "team:claranet", "created-by:terraform", "${var.status_extra_tags}"]
+}

cloud/azure/app-services/outputs.tf

@@ -22,3 +22,8 @@ output "appservices_http_success_status_rate_id" {
   description = "id for monitor appservices_http_success_status_rate"
   value       = "${datadog_monitor.appservices_http_success_status_rate.*.id}"
 }
+
+output "appservices_status_id" {
+  description = "id for monitor appservices_status"
+  value       = "${datadog_monitor.appservices_status.*.id}"
+}