Remove infra for collecting metrics

This includes the alert on queue sizes because
there are no more queues

Author: Harriethw

infrastructure/modules/container-apps/alerts.tf

@@ -36,55 +36,3 @@ resource "azurerm_monitor_scheduled_query_rules_alert_v2" "failure_event" {
     }
   }
 }
-
-# IMPORTANT:
-# Enable metrics store with all dimensions: https://docs.azure.cn/en-us/azure-monitor/app/metrics-overview?tabs=standard#custom-metrics-dimensions-and-preaggregation
-# currently this feature is in preview.
-resource "azurerm_monitor_scheduled_query_rules_alert_v2" "queue_length_high" {
-  for_each = var.enable_alerting ? toset([
-    "notifications-message-batch-retries"
-  ]) : []
-
-  name                = "${var.app_short_name}-${each.key}-${var.environment}-queue-length-high-alert"
-  location            = var.region
-  resource_group_name = azurerm_resource_group.main.name
-
-  auto_mitigation_enabled = true
-  description             = "Alert when queue length exceeds ${var.queue_length_alert_threshold}"
-  display_name            = "${var.app_short_name} Notifications Queue Length High Alert"
-  enabled                 = true
-  severity                = 2
-  evaluation_frequency    = "PT10M"
-  window_duration         = "PT10M"
-  scopes                  = [var.app_insights_id]
-
-  criteria {
-    query = <<-KQL
-      customMetrics
-      | where name == "${each.key}"
-      | extend environment = tostring(customDimensions.environment)
-      | where environment == "${var.environment}"
-      | extend value = toreal(value)
-      | summarize avg_value = avg(value) by bin(timestamp, 5m)
-      | where avg_value > ${var.queue_length_alert_threshold}
-    KQL
-
-    metric_measure_column   = "avg_value"
-    time_aggregation_method = "Average"
-    operator  = "GreaterThan"
-    threshold = 0
-
-    failing_periods {
-      minimum_failing_periods_to_trigger_alert = 1
-      number_of_evaluation_periods             = 1
-    }
-  }
-
-  action {
-    action_groups = [var.action_group_id]
-  }
-
-  tags = {
-    environment = var.environment
-  }
-}

infrastructure/modules/container-apps/jobs.tf

@@ -33,14 +33,6 @@ locals {
       job_short_name     = "smk"
       job_container_args = "create_reports --smoke-test"
     }
-    collect_metrics = {
-      cron_expression = "*/5 * * * *"
-      environment_variables = {
-        ENVIRONMENT               = var.environment
-      }
-      job_short_name     = "clm"
-      job_container_args = "collect_metrics"
-    }
   }
 }
 

infrastructure/modules/container-apps/variables.tf

@@ -199,10 +199,6 @@ variable "app_insights_id" {
   type        = string
 }
 
-variable "queue_length_alert_threshold" {
-  description = "If alerting is enabled, alert if storage account queues are greater than this threshold."
-  type        = number
-}
 
 variable "enable_notifications_jobs_schedule" {
   description = "Whether we apply the cron schedules for the notifications container app jobs"

infrastructure/terraform/main.tf

@@ -79,6 +79,5 @@ module "container-apps" {
   target_url                            = var.deploy_container_apps ? "${module.container-apps[0].external_url}healthcheck" : null
   resource_group_name_infra             = local.resource_group_name
   enable_notifications_jobs_schedule    = var.enable_notifications_jobs_schedule
-  queue_length_alert_threshold          = var.queue_length_alert_threshold
   min_replicas                          = var.min_replicas
 }

infrastructure/terraform/variables.tf

@@ -185,12 +185,6 @@ variable "run_notifications_smoke_test" {
   type        = bool
 }
 
-variable "queue_length_alert_threshold" {
-  description = "If alerting is enabled, alert if storage account queues are greater than this threshold."
-  type        = number
-  default     = 5
-}
-
 locals {
   region = "uksouth"