Running Redis 24/7? You're Leaving 40% on the Table Without Reserved Nodes 🔥

# monitoring/ri-coverage.tf

resource "aws_lambda_function" "ri_monitor" {
filename = data.archive_file.ri_monitor.output_path
function_name = "elasticache-ri-monitor"
role = aws_iam_role.ri_monitor.arn
handler = "index.handler"
runtime = "python3.12"
timeout = 30
source_code_hash = data.archive_file.ri_monitor.output_base64sha256

environment {
variables = {
SNS_TOPIC_ARN = aws_sns_topic.cost_alerts.arn
}
}
}

data "archive_file" "ri_monitor" {
type = "zip"
output_path = "${path.module}/ri_monitor.zip"

source {
content = <<-PYTHON
import boto3
import os
from datetime import datetime, timedelta

def handler(event, context):
ec = boto3.client('elasticache')
sns = boto3.client('sns')

# Get all running nodes
clusters = ec.describe_cache_clusters()['CacheClusters']
running_nodes = {}
for c in clusters:
key = f"{c['CacheNodeType']}|{c['Engine']}"
running_nodes[key] = running_nodes.get(key, 0) + c['NumCacheNodes']

# Get active reservations
reservations = ec.describe_reserved_cache_nodes()['ReservedCacheNodes']
reserved = {}
expiring_soon = []

for r in reservations:
if r['State'] == 'active':
key = f"{r['CacheNodeType']}|{r['ProductDescription']}"
reserved[key] = reserved.get(key, 0) + r['CacheNodeCount']

# Check if expiring within 30 days
end_time = r['StartTime'] + timedelta(seconds=r['Duration'])
if end_time - datetime.now(end_time.tzinfo) < timedelta(days=30):
expiring_soon.append({
'id': r['ReservedCacheNodeId'],
'type': r['CacheNodeType'],
'expires': end_time.strftime('%Y-%m-%d')
})

# Find unreserved nodes
unreserved = []
for key, count in running_nodes.items():
reserved_count = reserved.get(key, 0)
if count > reserved_count:
node_type, engine = key.split('|')
unreserved.append(
f" {node_type} ({engine}): "
f"{count - reserved_count} unreserved of {count} total"
)

# Build alert
alerts = []
if unreserved:
alerts.append("UNRESERVED NODES (wasting money!):\n"
+ "\n".join(unreserved))
if expiring_soon:
alerts.append("EXPIRING WITHIN 30 DAYS:\n" + "\n".join(
f" {e['id']} ({e['type']}) expires {e['expires']}"
for e in expiring_soon
))

if alerts:
sns.publish(
TopicArn=os.environ['SNS_TOPIC_ARN'],
Subject='ElastiCache RI Coverage Alert',
Message="\n\n".join(alerts)
)

return {'unreserved': len(unreserved), 'expiring': len(expiring_soon)}
PYTHON
filename = "index.py"
}
}

# Run weekly
resource "aws_cloudwatch_event_rule" "weekly_ri_check" {
name = "elasticache-ri-check"
schedule_expression = "rate(7 days)"
}

resource "aws_cloudwatch_event_target" "ri_monitor" {
rule = aws_cloudwatch_event_rule.weekly_ri_check.name
arn = aws_lambda_function.ri_monitor.arn
}

resource "aws_lambda_permission" "allow_eventbridge" {
action = "lambda:InvokeFunction"
function_name = aws_lambda_function.ri_monitor.function_name
principal = "events.amazonaws.com"
source_arn = aws_cloudwatch_event_rule.weekly_ri_check.arn
}

resource "aws_sns_topic" "cost_alerts" {
name = "elasticache-cost-alerts"
}