启用自动扩缩组指标收集

启用自动扩缩组指标收集

1. 为 Lambda 创建 IAM 角色。

   LAMBDA_ROLE=$(aws iam create-role \
     --role-name lambda-asg-enable-metrics \
     --assume-role-policy-document '{"Version": "2012-10-17","Statement": [{ "Effect": "Allow", "Principal": {"Service": "lambda.amazonaws.com"}, "Action": "sts:AssumeRole"}]}' \
     --output text \
     --query 'Role.Arn')
   echo $LAMBDA_ROLE
   

2. 创建允许描述 Amazon EKS 节点组和启用自动扩缩组指标收集的策略。

   cat > /tmp/lambda-policy.json <<EOF
   {
       "Version": "2012-10-17",
       "Statement": [
         {
           "Effect": "Allow",
           "Action": [
               "eks:DescribeNodegroup",
               "autoscaling:EnableMetricsCollection"
               ],
           "Resource": [
               "*"
           ]
         }
       ]
   }
   EOF
   LAMBDA_POLICY_ARN=$(aws iam create-policy \
     --policy-name lambda-asg-enable-metrics-policy \
     --policy-document file:///tmp/lambda-policy.json \
     --output text \
     --query 'Policy.Arn')
   echo $LAMBDA_POLICY_ARN
   

3. 向 Lambda 的 IAM 角色附加策略。

   aws iam attach-role-policy \
     --policy-arn $LAMBDA_POLICY_ARN \
     --role-name lambda-asg-enable-metrics
   

4. 添加 AWSLambdaBasicExecutionRole 托管策略，该策略具有函数将日志写入 CloudWatch Logs 所需的权限。

   aws iam attach-role-policy \
     --role-name lambda-asg-enable-metrics \
     --policy-arn arn:aws:iam::aws:policy/service-role/AWSLambdaBasicExecutionRole
   

5. 创建 Lambda 代码。

   cat > /tmp/lambda-handler.py <<EOF
   import json
   import boto3
   import time
   import logging
   
   eks = boto3.client('eks')
   autoscaling = boto3.client('autoscaling')
   
   logger = logging.getLogger()
   logger.setLevel(logging.INFO)
   
   def lambda_handler(event, context):
       ASG_METRICS_COLLLECTION_TAG_NAME = "ASG_METRICS_COLLLECTION_ENABLED"
       initial_retry_delay = 10
       attempts = 0 
       
       #print(event)
       
       if not event["detail"]["eventName"] == "CreateNodegroup":
           print("invalid event.")
           return -1
           
       clusterName = event["detail"]["requestParameters"]["name"]
       nodegroupName = event["detail"]["requestParameters"]["nodegroupName"]
       try:
           metricsCollectionEnabled = event["detail"]["requestParameters"]["tags"][ASG_METRICS_COLLLECTION_TAG_NAME]
       except KeyError:
           print(ASG_METRICS_COLLLECTION_TAG_NAME, "tag not found.")
           return
       
       # Check if metrics collection is enabled in tags
       if metricsCollectionEnabled.lower() != "true":
           print("Metrics collection is not enabled in nodegroup tags.")
           return
       
       # Get the name of the associated autoscaling group
       print("Getting the autoscaling group name for nodegroup=", nodegroupName, ", cluster=", clusterName )
       for i in range(0,10):
           try:
               autoScalingGroup = eks.describe_nodegroup(clusterName=clusterName,nodegroupName=nodegroupName)["nodegroup"]["resources"]["autoScalingGroups"][0]["name"]
           except:
               attempts += 1
               print("Failed to obtain the associated autoscaling group for nodegroup", nodegroupName, "Retrying in", initial_retry_delay*attempts, "seconds.")
               time.sleep(initial_retry_delay*attempts)
           else:
               break
       
       print("Enabling metrics collection on autoscaling group ", autoScalingGroup)
       
       # Enable metrics collection in the autoscaling group
       try:
           enableMetricsCollection = autoscaling.enable_metrics_collection(AutoScalingGroupName=autoScalingGroup,Granularity="1Minute")
       except:
           print("Unable to enable metrics collection on nodegroup=",nodegroup)
       print("Enabled metrics collection on nodegroup", nodegroupName)
   EOF
   

6. 创建部署程序包。

   cd /tmp 
   zip function.zip lambda-handler.py
   

7. 创建一个 Lambda 函数。

   LAMBDA_ARN=$(aws lambda create-function --function-name asg-enable-metrics-collection \
     --zip-file fileb://function.zip --handler lambda-handler.lambda_handler \
     --runtime python3.9 \
     --timeout 600 \
     --role $LAMBDA_ROLE \
     --output text \
     --query 'FunctionArn')
   echo $LAMBDA_ARN
   

8. 创建 EventBridge 规则。

   RULE_ARN=$(aws events put-rule --name CreateNodegroupRuleToLambda \
     --event-pattern "{\"source\":[\"aws.eks\"],\"detail-type\":[\"AWS API Call via CloudTrail\"],\"detail\":{\"eventName\":[\"CreateNodegroup\"],\"eventSource\":[\"eks.amazonaws.com\"]}}" \
     --output text \
     --query 'RuleArn')
   echo $RULE_ARN
   

9. 添加 Lambda 函数作为目标。

   aws events put-targets --rule CreateNodegroupRuleToLambda \
    --targets "Id"="1","Arn"="$LAMBDA_ARN"
   

10. 添加允许 EventBridge 调用 Lambda 函数的策略。

    aws lambda add-permission \
      --function-name asg-enable-metrics-collection \
      --statement-id CreateNodegroupRuleToLambda \
      --action 'lambda:InvokeFunction' \
      --principal events.amazonaws.com \
      --source-arn $RULE_ARN