Delete Underutilized AWS Redshift Clusters

import boto3 creds = _get_creds(cred_label)['creds'] access_key = creds['username'] secret_key = creds['password'] def get_all_redshift_clusters(region=None): all_clusters = {} ec2_client = boto3.client('ec2', aws_access_key_id=access_key, aws_secret_access_key=secret_key, region_name='us-east-1') regions_to_check = [region] if region else [region['RegionName'] for region in ec2_client.describe_regions()['Regions']] for region in regions_to_check: # Initialize the Redshift client for the specified region redshift = boto3.client('redshift', aws_access_key_id=access_key, aws_secret_access_key=secret_key, region_name=region) clusters = [] try: # Using paginator to handle potential pagination of results paginator = redshift.get_paginator('describe_clusters') for page in paginator.paginate(): clusters.extend(page['Clusters']) if clusters: # Check if clusters list is not empty all_clusters[region] = clusters except Exception as e: print(f"Error fetching Redshift clusters in region {region}: {e}") return all_clusters # Set region to None for all regions, or specify a valid AWS region string for a specific region # Example: target_region = 'us-west-1' # Or None for all regions target_region = None # Get all Redshift clusters all_clusters = get_all_redshift_clusters(target_region) if all_clusters: print(f"Total Redshift Clusters: {sum(len(clusters) for clusters in all_clusters.values())}") for region, clusters in all_clusters.items(): print(f"In region {region}:") for cluster in clusters: print(f" - {cluster['ClusterIdentifier']}") else: print("No Redshift clusters found")

import boto3 from datetime import datetime, timedelta creds = _get_creds(cred_label)['creds'] access_key = creds['username'] secret_key = creds['password'] # Constants #LOW_CPU_THRESHOLD = 20 # Example Threshold for CPU utilization #LOOKBACK_PERIOD_HOURS = 24 # Example lookback period in hours LOOKBACK_PERIOD = 3600 * LOOKBACK_PERIOD_HOURS # Convert hours to seconds def get_low_cpu_redshift_clusters(all_clusters): """ Identify and list Redshift clusters with average CPU utilization below a defined threshold over a specific period. Parameters: - all_clusters (dict): Dictionary with region as keys and list of cluster info as values. Returns: - list: List of dictionaries containing Redshift cluster identifiers and their average CPU utilization. """ low_cpu_clusters = [] # List to store the cluster details with low CPU utilization for region, clusters in all_clusters.items(): # Initialize boto3 client for CloudWatch in the specific region cloudwatch = boto3.client('cloudwatch', aws_access_key_id=access_key,aws_secret_access_key=secret_key, region_name=region) for cluster in clusters: cluster_id = cluster['ClusterIdentifier'] try: # Query CloudWatch to fetch the CPU utilization metric for the defined period metrics = cloudwatch.get_metric_data( MetricDataQueries=[ { 'Id': 'cpuUtilization', 'MetricStat': { 'Metric': { 'Namespace': 'AWS/Redshift', 'MetricName': 'CPUUtilization', 'Dimensions': [{'Name': 'ClusterIdentifier', 'Value': cluster_id}] }, 'Period': LOOKBACK_PERIOD, 'Stat': 'Average' # We're interested in the average CPU utilization }, 'ReturnData': True, }, ], StartTime=datetime.utcnow() - timedelta(seconds=LOOKBACK_PERIOD), EndTime=datetime.utcnow() ) # Check if the cluster's CPU utilization falls below the threshold if metrics['MetricDataResults'][0]['Values']: cpu_utilization = metrics['MetricDataResults'][0]['Values'][0] if cpu_utilization < LOW_CPU_THRESHOLD: low_cpu_clusters.append({ 'Region': region, 'ClusterID': cluster_id, 'AverageCPU': cpu_utilization }) except Exception as e: print(f"Error checking CPU utilization for cluster {cluster_id} in region {region}: {e}") return low_cpu_clusters # Example usage (assuming all_clusters is provided from an upstream task) # all_clusters = { # 'us-west-2': [{'ClusterIdentifier': 'cluster1'}, {'ClusterIdentifier': 'cluster2'}], # 'us-east-1': [{'ClusterIdentifier': 'cluster3'}], # } clusters_info = get_low_cpu_redshift_clusters(all_clusters) # Print the results if clusters_info: print("Redshift clusters with low CPU utilization:") for cluster in clusters_info: print(f"Region: {cluster['Region']}, Cluster ID: {cluster['ClusterID']}, Average CPU: {cluster['AverageCPU']:.2f}%") else: print("No Redshift clusters with low CPU utilization found.") context.skip_sub_tasks=True