Merge branch 'MON-493-AzureVM_monitor_requests_failed' into 'master'

MON-493: Add Azure VM monitor - Requests failed

Closes MON-493

See merge request claranet/pt-monitoring/projects/datadog/terraform/monitors!92

cloud/azure/virtual-machine/README.md

@@ -21,6 +21,7 @@ Creates DataDog monitors with the following checks:
 - Virtual Machine disk space
 - Virtual Machine is unreachable
 - Virtual Machine RAM reserved
+- Virtual Machine requests failed
 
 ## Inputs
 
@@ -62,6 +63,13 @@ Creates DataDog monitors with the following checks:
 | ram\_reserved\_threshold\_warning | Virtual Machine RAM reserved limit (warning threshold) | string | `"90"` | no |
 | ram\_reserved\_time\_aggregator | Monitor aggregator for Virtual Machine RAM reserved [available values: min, max, sum or avg] | string | `"min"` | no |
 | ram\_reserved\_timeframe | Monitor timeframe for Virtual Machine RAM reserved [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `"last_15m"` | no |
+| requests\_failed\_enabled | Flag to enable Virtual Machine requests failed monitor | string | `"true"` | no |
+| requests\_failed\_extra\_tags | Extra tags for Virtual Machine requests failed monitor | list(string) | `[]` | no |
+| requests\_failed\_message | Custom message for Virtual Machine requests failed monitor | string | `""` | no |
+| requests\_failed\_threshold\_critical | Virtual Machine requests failed limit (critical threshold) | string | `"95"` | no |
+| requests\_failed\_threshold\_warning | Virtual Machine requests failed limit (warning threshold) | string | `"90"` | no |
+| requests\_failed\_time\_aggregator | Monitor aggregator for Virtual Machine requests failed [available values: min, max, sum or avg] | string | `"min"` | no |
+| requests\_failed\_timeframe | Monitor timeframe for Virtual Machine requests failed [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `"last_10m"` | no |
 | status\_enabled | Flag to enable Virtual Machine status monitor | string | `"true"` | no |
 | status\_extra\_tags | Extra tags for Virtual Machine status monitor | list(string) | `[]` | no |
 | status\_message | Custom message for Virtual Machine status monitor | string | `""` | no |
@@ -76,6 +84,7 @@ Creates DataDog monitors with the following checks:
 | virtualmachine\_credit\_cpu\_remaining\_too\_low\_id | id for monitor virtualmachine_credit_cpu_remaining_too_low |
 | virtualmachine\_disk\_space\_id | id for monitor virtualmachine_disk_space |
 | virtualmachine\_ram\_reserved\_id | id for monitor virtualmachine_ram_reserved |
+| virtualmachine\_requests\_failed\_id | id for monitor virtualmachine_requests_failed |
 | virtualmachine\_status\_id | id for monitor virtualmachine_status |
 
 ## Related documentation

cloud/azure/virtual-machine/inputs.tf

@@ -230,3 +230,43 @@ variable "disk_space_message" {
   type        = string
   default     = ""
 }
+
+variable "requests_failed_enabled" {
+  description = "Flag to enable Virtual Machine requests failed monitor"
+  type        = string
+  default     = "true"
+}
+
+variable "requests_failed_message" {
+  description = "Custom message for Virtual Machine requests failed monitor"
+  type        = string
+  default     = ""
+}
+
+variable "requests_failed_extra_tags" {
+  description = "Extra tags for Virtual Machine requests failed monitor"
+  type        = list(string)
+  default     = []
+}
+
+variable "requests_failed_time_aggregator" {
+  description = "Monitor aggregator for Virtual Machine requests failed [available values: min, max, sum or avg]"
+  type        = string
+  default     = "min"
+}
+
+variable "requests_failed_timeframe" {
+  description = "Monitor timeframe for Virtual Machine requests failed [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 "requests_failed_threshold_warning" {
+  description = "Virtual Machine requests failed limit (warning threshold)"
+  default     = 90
+}
+
+variable "requests_failed_threshold_critical" {
+  description = "Virtual Machine requests failed limit (critical threshold)"
+  default     = 95
+}

cloud/azure/virtual-machine/monitors-virtual-machine.tf

@@ -167,3 +167,40 @@ EOQ
     ignore_changes = ["silenced"]
   }
 }
+
+resource "datadog_monitor" "virtualmachine_requests_failed" {
+  count   = var.requests_failed_enabled == "true" ? 1 : 0
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Virtual Machine requests failed {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
+  message = coalesce(var.requests_failed_message, var.message)
+  type    = "query alert"
+
+  query = <<EOQ
+    ${var.requests_failed_time_aggregator}(${var.requests_failed_timeframe}):
+      default( 
+        default(avg:azure.vm.asp.net_applications_total_requests_failed${module.filter-tags.query_alert} by {resource_group,region,name}, 0) /
+        default(avg:azure.vm.asp.net_applications_total_requests_total${module.filter-tags.query_alert} by {resource_group,region,name}, 1)
+      , 0) * 100
+      > ${var.requests_failed_threshold_critical}
+EOQ
+
+  thresholds = {
+    critical = var.requests_failed_threshold_critical
+    warning  = var.requests_failed_threshold_warning
+  }
+
+  evaluation_delay    = var.evaluation_delay
+  new_host_delay      = var.new_host_delay
+  notify_no_data      = false
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = false
+
+  tags = concat(["env:${var.environment}", "type:cloud", "provider:azure", "resource:virtualmachine", "team:claranet", "created-by:terraform"], var.requests_failed_extra_tags)
+
+  lifecycle {
+    ignore_changes = ["silenced"]
+  }
+}

cloud/azure/virtual-machine/outputs.tf

@@ -23,3 +23,8 @@ output "virtualmachine_disk_space_id" {
   value       = datadog_monitor.virtualmachine_disk_space.*.id
 }
 
+output "virtualmachine_requests_failed_id" {
+  description = "id for monitor virtualmachine_requests_failed"
+  value       = datadog_monitor.virtualmachine_requests_failed.*.id
+}
+