💡Setup alertmanager and recording rules

Activate Alertmanager at workspace level, recording rules per workload

modules/workloads/java/main.tf

@@ -7,6 +7,7 @@ locals {
 data "aws_partition" "current" {}
 
 
+# deploys collector
 module "helm_addon" {
   source = "github.com/aws-ia/terraform-aws-eks-blueprints/modules/kubernetes-addons/helm-addon"
 
@@ -63,3 +64,30 @@ module "helm_addon" {
 
   addon_context = var.addon_context
 }
+
+
+resource "aws_prometheus_rule_group_namespace" "this" {
+  count = var.enable_recording_rules ? 1 : 0
+
+  name         = "java_rules"
+  workspace_id = var.amp_id
+  data         = <<EOF
+groups:
+  - name: default-metric
+    rules:
+      - record: metric:recording_rule
+        expr: avg(rate(container_cpu_usage_seconds_total[5m]))
+  - name: default-alert
+    rules:
+      - alert: metric:alerting_rule
+        expr: jvm_memory_bytes_used{job="java", area="heap"} / jvm_memory_bytes_max * 100 > 80
+        for: 1m
+        labels:
+            severity: warning
+        annotations:
+            summary: "JVM heap warning"
+            description: "JVM heap of instance `{{$labels.instance}}` from application `{{$labels.application}}` is above 80% for one minute. (current=`{{$value}}%`)"
+EOF
+}
+
+# dashboard

modules/workloads/java/variables.tf

@@ -1,8 +1,7 @@
-variable "java" {
-  default = {
-    a = ""
-    b = ""
-  }
+variable "enable_recording_rules" {
+  description = "Enable AMP recording rules"
+  type        = bool
+  default     = true
 }
 
 variable "amp_endpoint" {