Added CPU Alarm for the l1 and l2 nodes (#18)

Author: pmatsinopoulos

terraform/base_ec2_instance.tf

@@ -14,6 +14,7 @@ module "base_ec2_instance" {
   load_balancer                   = var.load_balancer
 
   node = {
+    alarm_cpu_threshold_percentage       = var.base_node.alarm_cpu_threshold_percentage       # 80
     alarm_memory_threshold_percentage    = var.base_node.alarm_memory_threshold_percentage    # 80
     alarm_disk_used_threshold_percentage = var.base_node.alarm_disk_used_threshold_percentage # 90
     ami_id                               = var.base_node.ami_id                               # "ami-0122205e4fe2524d5" # ubuntu/images/hvm-ssd-gp3/ubuntu-noble-24.04-arm64-server-20250821

terraform/ethereum_ec2_cpu_alarm.tf

@@ -0,0 +1,33 @@
+resource "aws_cloudwatch_metric_alarm" "ethereum_ec2_cpu_high" {
+  alarm_name        = "${var.project}_${var.environment}_ethereum_ec2_cpu_high"
+  alarm_description = "Watches for Ethereum EC2 CPU crossing high limit"
+
+  comparison_operator = "GreaterThanThreshold"
+  evaluation_periods  = "3"
+  datapoints_to_alarm = 3
+
+  metric_name = "CPUUtilization"
+  namespace   = "AWS/EC2"
+  period      = "60"
+  statistic   = "Maximum"
+  threshold   = tostring(var.ethereum_node.alarm_cpu_threshold_percentage)
+
+  alarm_actions = [
+    data.aws_sns_topic.developers_notifications.arn
+  ]
+  ok_actions = [
+    data.aws_sns_topic.developers_notifications.arn
+  ]
+
+  insufficient_data_actions = []
+
+  treat_missing_data = "notBreaching"
+
+  dimensions = {
+    InstanceId = aws_instance.ethereum.id
+  }
+
+  tags = {
+    "Name" = "${var.project}_${var.environment}_ethereum_ec2_cpu_high"
+  }
+}

terraform/modules/l2_op_stack_chains/ec2_cpu_alarm.tf

@@ -0,0 +1,33 @@
+resource "aws_cloudwatch_metric_alarm" "ec2_cpu_high" {
+  alarm_name        = "${var.project}_${var.environment}_${var.node_name}-ec2_cpu_high"
+  alarm_description = "Watches for EC2 CPU crossing high limit"
+
+  comparison_operator = "GreaterThanThreshold"
+  evaluation_periods  = "3"
+  datapoints_to_alarm = 3
+
+  metric_name = "CPUUtilization"
+  namespace   = "AWS/EC2"
+  period      = "60"
+  statistic   = "Maximum"
+  threshold   = tostring(var.node.alarm_cpu_threshold_percentage)
+
+  alarm_actions = [
+    data.aws_sns_topic.developers_notifications.arn
+  ]
+  ok_actions = [
+    data.aws_sns_topic.developers_notifications.arn
+  ]
+
+  insufficient_data_actions = []
+
+  treat_missing_data = "notBreaching"
+
+  dimensions = {
+    InstanceId = aws_instance.ec2_instance.id
+  }
+
+  tags = {
+    "Name" = "${var.project}_${var.environment}_${var.node_name}-ec2_cpu_high"
+  }
+}

terraform/modules/l2_op_stack_chains/variables.tf

@@ -37,6 +37,7 @@ variable "region" {
 
 variable "node" {
   type = object({
+    alarm_cpu_threshold_percentage       = number
     alarm_memory_threshold_percentage    = number
     alarm_disk_used_threshold_percentage = number
     ami_id                               = string

terraform/production/ethereum_ec2_cpu_alarm.tf

@@ -0,0 +1 @@
+../ethereum_ec2_cpu_alarm.tf

terraform/production/terraform.tfvars

@@ -1,4 +1,5 @@
 ethereum_node = {
+  alarm_cpu_threshold_percentage       = 80
   alarm_memory_threshold_percentage    = 90
   alarm_disk_used_threshold_percentage = 90
   ami_id                               = "ami-0122205e4fe2524d5" # ubuntu/images/hvm-ssd-gp3/ubuntu-noble-24.04-arm64-server-20250821
@@ -41,6 +42,7 @@ load_balancer = {
 }
 
 base_node = {
+  alarm_cpu_threshold_percentage       = 80
   alarm_memory_threshold_percentage    = 90
   alarm_disk_used_threshold_percentage = 90
   ami_id                               = "ami-0122205e4fe2524d5" # ubuntu/images/hvm-ssd-gp3/ubuntu-noble-24.04-arm64-server-20250821

terraform/staging/ethereum_ec2_cpu_alarm.tf

@@ -0,0 +1 @@
+../ethereum_ec2_cpu_alarm.tf

terraform/staging/terraform.tfvars

@@ -1,4 +1,5 @@
 ethereum_node = {
+  alarm_cpu_threshold_percentage       = 80
   alarm_memory_threshold_percentage    = 90
   alarm_disk_used_threshold_percentage = 90
   ami_id                               = "ami-0122205e4fe2524d5" # ubuntu/images/hvm-ssd-gp3/ubuntu-noble-24.04-arm64-server-20250821
@@ -8,9 +9,9 @@ ethereum_node = {
   checkpoint_sync_url                  = "https://checkpoint-sync.sepolia.ethpandaops.io"
   ebs_optimized                        = true
   ebs_volume = {
-    size = 3072 # GB, 3TB
-    type = "gp3"
-    iops = 4000
+    size       = 3072 # GB, 3TB
+    type       = "gp3"
+    iops       = 4000
     throughput = 250
   }
   instance_type = "c7g.4xlarge"
@@ -41,6 +42,7 @@ load_balancer = {
 }
 
 base_node = {
+  alarm_cpu_threshold_percentage       = 80
   alarm_memory_threshold_percentage    = 90
   alarm_disk_used_threshold_percentage = 90
   ami_id                               = "ami-0122205e4fe2524d5" # ubuntu/images/hvm-ssd-gp3/ubuntu-noble-24.04-arm64-server-20250821

terraform/variables.tf

@@ -33,6 +33,7 @@ variable "environment" {
 
 variable "ethereum_node" {
   type = object({
+    alarm_cpu_threshold_percentage       = number
     alarm_memory_threshold_percentage    = number
     alarm_disk_used_threshold_percentage = number
     ami_id                               = string
@@ -42,9 +43,9 @@ variable "ethereum_node" {
     checkpoint_sync_url                  = string
     ebs_optimized                        = bool
     ebs_volume = object({
-      size = number
-      type = string
-      iops = number
+      size       = number
+      type       = string
+      iops       = number
       throughput = number
     })
     instance_type = string
@@ -108,6 +109,7 @@ variable "load_balancer" {
 
 variable "base_node" {
   type = object({
+    alarm_cpu_threshold_percentage       = number
     alarm_memory_threshold_percentage    = number
     alarm_disk_used_threshold_percentage = number
     ami_id                               = string