Page Menu
Home
Phorge
Search
Configure Global Search
Log In
Files
F32176686
D13944.1765068275.diff
No One
Temporary
Actions
View File
Edit File
Delete File
View Transforms
Subscribe
Flag For Later
Award Token
Size
3 KB
Referenced Files
None
Subscribers
None
D13944.1765068275.diff
View Options
diff --git a/services/terraform/remote/alarms_backup.tf b/services/terraform/remote/alarms_backup.tf
new file mode 100644
--- /dev/null
+++ b/services/terraform/remote/alarms_backup.tf
@@ -0,0 +1,82 @@
+locals {
+ backup_error_patterns = {
+ Auth = { name = "Auth", pattern = "Auth Error" },
+ Blob = { name = "Blob", pattern = "Blob Error" },
+ DDB = { name = "DDB", pattern = "DDB Error" },
+ WS = { name = "WS", pattern = "WS Error" },
+ }
+}
+
+resource "aws_sns_topic" "backup_error_topic" {
+ name = "backup-error-topic"
+}
+
+resource "aws_sns_topic_subscription" "backup_email_subscription" {
+ topic_arn = aws_sns_topic.backup_error_topic.arn
+ protocol = "email"
+ endpoint = local.error_reports_subscribed_email
+}
+
+resource "aws_cloudwatch_log_metric_filter" "backup_error_filters" {
+ for_each = local.backup_error_patterns
+
+ name = "Backup${each.value.name}ErrorCount"
+ pattern = "{ $.level = \"ERROR\" && $.fields.errorType = \"${each.value.pattern}\" }"
+ log_group_name = "/ecs/backup-service-task-def"
+
+ metric_transformation {
+ name = "Backup${each.value.name}ErrorCount"
+ namespace = "BackupServiceMetricFilters"
+ value = "1"
+ }
+}
+
+resource "aws_cloudwatch_metric_alarm" "backup_error_alarms" {
+ for_each = local.backup_error_patterns
+
+ alarm_name = "Backup${local.is_staging ? "Staging" : "Production"}${each.value.name}ErrorAlarm"
+ comparison_operator = "GreaterThanOrEqualToThreshold"
+ evaluation_periods = "1"
+ metric_name = "Backup${each.value.name}ErrorCount"
+ namespace = "BackupServiceMetricFilters"
+ period = "300"
+ statistic = "Sum"
+ threshold = 1
+ alarm_description = "Alarm when Backup ${each.value.name} errors exceed threshold"
+ actions_enabled = true
+ alarm_actions = [aws_sns_topic.backup_error_topic.arn]
+}
+
+resource "aws_cloudwatch_metric_alarm" "backup_memory_utilization" {
+ alarm_name = "BackupMemoryUtilizationAlarm"
+ comparison_operator = "GreaterThanOrEqualToThreshold"
+ evaluation_periods = 1
+ metric_name = "MemoryUtilization"
+ namespace = "AWS/ECS"
+ period = 60
+ statistic = "Average"
+ threshold = 90
+ alarm_description = "Alarm when Backup service memory utilization exceeds 90%"
+ dimensions = {
+ ClusterName = aws_ecs_cluster.comm_services.name
+ ServiceName = aws_ecs_service.backup_service.name
+ }
+ alarm_actions = [aws_sns_topic.backup_error_topic.arn]
+}
+
+resource "aws_cloudwatch_metric_alarm" "backup_cpu_utilization" {
+ alarm_name = "BackupCPUUtilizationAlarm"
+ comparison_operator = "GreaterThanOrEqualToThreshold"
+ evaluation_periods = 1
+ metric_name = "CPUUtilization"
+ namespace = "AWS/ECS"
+ period = 60
+ statistic = "Average"
+ threshold = 90
+ alarm_description = "Alarm when Backup service CPU utilization exceeds 90%"
+ dimensions = {
+ ClusterName = aws_ecs_cluster.comm_services.name
+ ServiceName = aws_ecs_service.backup_service.name
+ }
+ alarm_actions = [aws_sns_topic.backup_error_topic.arn]
+}
File Metadata
Details
Attached
Mime Type
text/plain
Expires
Sun, Dec 7, 12:44 AM (17 h, 48 m)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
5841704
Default Alt Text
D13944.1765068275.diff (3 KB)
Attached To
Mode
D13944: [terraform] create backup cloudwatch alarms
Attached
Detach File
Event Timeline
Log In to Comment