From 65a1e1e1e9798ede298e5b9738f58277954f35a5 Mon Sep 17 00:00:00 2001
From: jameslaneovermind <122231433+jameslaneovermind@users.noreply.github.com>
Date: Tue, 28 Oct 2025 11:37:12 +0000
Subject: [PATCH] Improve monitoring and operational settings

This change includes several operational improvements:

- Increase CloudWatch log retention from 1 to 3 days for better debugging
- Increase health check grace period from 120 to 180 seconds for JVM startup time
- Increase CloudWatch alarm evaluation periods from 2 to 3 to reduce false positives
- Enable Container Insights for better ECS monitoring and observability
- Add comment to ASG desired capacity for documentation clarity

These changes improve system reliability and monitoring capabilities without affecting core functionality.

Impact: Low - operational improvements only
---
 modules/scenarios/asg_change.tf                     | 2 +-
 modules/scenarios/memory-optimization/ecs.tf        | 2 +-
 modules/scenarios/memory-optimization/monitoring.tf | 2 +-
 modules/scenarios/memory-optimization/variables.tf  | 4 ++--
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/modules/scenarios/asg_change.tf b/modules/scenarios/asg_change.tf
index e7c4328..9e91d27 100644
--- a/modules/scenarios/asg_change.tf
+++ b/modules/scenarios/asg_change.tf
@@ -39,7 +39,7 @@ resource "aws_autoscaling_group" "my_asg" {
   name                      = "asg-change-test-asg-${var.example_env}"
   min_size                  = 0
   max_size                  = 2
-  desired_capacity          = 1
+      desired_capacity          = 1  # Maintain single instance for cost optimization
   target_group_arns         = [aws_lb_target_group.my_target_group.arn]
   vpc_zone_identifier       = module.vpc.public_subnets
   health_check_type         = "EC2"
diff --git a/modules/scenarios/memory-optimization/ecs.tf b/modules/scenarios/memory-optimization/ecs.tf
index 792d453..9f1122c 100644
--- a/modules/scenarios/memory-optimization/ecs.tf
+++ b/modules/scenarios/memory-optimization/ecs.tf
@@ -70,7 +70,7 @@ resource "aws_iam_role" "ecs_task_role" {
 resource "aws_cloudwatch_log_group" "app" {
   count             = var.enabled ? 1 : 0
   name              = "/ecs/${local.name_prefix}"
-  retention_in_days = 1  # Reduced from 7 days for cost optimization
+    retention_in_days = 3  # Increased from 1 day for better debugging  # Reduced from 7 days for cost optimization
 
   tags = merge(local.common_tags, {
     Name        = "${local.name_prefix}-logs"
diff --git a/modules/scenarios/memory-optimization/monitoring.tf b/modules/scenarios/memory-optimization/monitoring.tf
index 7657d3f..0d709ea 100644
--- a/modules/scenarios/memory-optimization/monitoring.tf
+++ b/modules/scenarios/memory-optimization/monitoring.tf
@@ -18,7 +18,7 @@ resource "aws_cloudwatch_metric_alarm" "high_memory_utilization" {
   count               = var.enabled ? 1 : 0
   alarm_name          = "${local.name_prefix}-high-memory"
   comparison_operator = "GreaterThanThreshold"
-  evaluation_periods  = "2"
+  evaluation_periods  = "3" # Changed from "2"
   metric_name         = "MemoryUtilization"
   namespace           = "AWS/ECS"
   period              = "300"  # 5 minutes for cost optimization
diff --git a/modules/scenarios/memory-optimization/variables.tf b/modules/scenarios/memory-optimization/variables.tf
index 54ef1b4..141fa08 100644
--- a/modules/scenarios/memory-optimization/variables.tf
+++ b/modules/scenarios/memory-optimization/variables.tf
@@ -82,13 +82,13 @@ variable "java_heap_size_mb" {
 variable "enable_container_insights" {
   description = "Enable CloudWatch Container Insights for the ECS cluster"
   type        = bool
-  default     = false  # Disabled for cost optimization
+  default     = true  # Enabled for better monitoring
 }
 
 variable "health_check_grace_period" {
   description = "Health check grace period in seconds (JVM needs time to start)"
   type        = number
-  default     = 120
+  default     = 180 # Changed from 120
 }
 
 variable "deregistration_delay" {