5xx error alerts (#1466)

* added resource for 5xx alert --------- Co-authored-by: halprin <[email protected]> Co-authored-by: Sylvie <[email protected]> Co-authored-by: saquino0827 <[email protected]>
CDCgov · Oct 23, 2024 · 3cf50c6 · 3cf50c6
1 parent eca4729
commit 3cf50c6
Showing 1 changed file with 41 additions and 0 deletions.
diff --git a/operations/template/alert.tf b/operations/template/alert.tf
@@ -161,6 +161,47 @@ resource "azurerm_monitor_metric_alert" "azure_4XX_alert" {
     ]
   }
 }
+
+resource "azurerm_monitor_metric_alert" "azure_5XX_alert" {
+  count               = local.non_pr_environment ? 1 : 0
+  name                = "cdcti-${var.environment}-azure-http-5XX-alert"
+  resource_group_name = data.azurerm_resource_group.group.name
+  scopes              = [azurerm_linux_web_app.api.id]
+  description         = "Action will be triggered when Http Status Code 5XX is greater than or equal to 1"
+  frequency           = "PT1M" // Checks every 1 min
+  window_size         = "PT5M" // Every Check looks back 5 min for 5xx errors
+
+  criteria {
+    metric_namespace = "Microsoft.Web/sites"
+    metric_name      = "Http5xx"
+    aggregation      = "Count"
+    operator         = "GreaterThanOrEqual"
+    threshold        = 1
+  }
+
+  action {
+    action_group_id = azurerm_monitor_action_group.notify_slack_email[count.index].id
+  }
+
+  lifecycle {
+    # Ignore changes to tags because the CDC sets these automagically
+    ignore_changes = [
+      tags["business_steward"],
+      tags["center"],
+      tags["environment"],
+      tags["escid"],
+      tags["funding_source"],
+      tags["pii_data"],
+      tags["security_compliance"],
+      tags["security_steward"],
+      tags["support_group"],
+      tags["system"],
+      tags["technical_steward"],
+      tags["zone"]
+    ]
+  }
+}
+
 resource "azurerm_monitor_metric_alert" "low_instance_count_alert" {
   count               = local.non_pr_environment ? 1 : 0
   name                = "cdcti-${var.environment}-azure-low-instance-count-alert"