CloudWatch 日志与日志洞察

CloudWatch Logs 概述

日志组和日志流

# Create a log group with 30-day retention
aws logs create-log-group \
  --log-group-name /myapp/production/api

aws logs put-retention-policy \
  --log-group-name /myapp/production/api \
  --retention-in-days 30

# List log streams in a group
aws logs describe-log-streams \
  --log-group-name /myapp/production/api \
  --order-by LastEventTime \
  --descending

从 Lambda 和 EC2 发送日志

# CloudWatch Agent config for tailing an application log file
# /opt/aws/amazon-cloudwatch-agent/etc/amazon-cloudwatch-agent.json
# {
#   "logs": {
#     "logs_collected": {
#       "files": {
#         "collect_list": [{
#           "file_path": "/var/log/myapp/app.log",
#           "log_group_name": "/myapp/production/api",
#           "log_stream_name": "{instance_id}",
#           "timestamp_format": "%Y-%m-%dT%H:%M:%S"
#         }]
#       }
#     }
#   }
# }

CloudWatch Logs Insights

# Find the top 10 slowest Lambda invocations in the last hour
aws logs start-query \
  --log-group-name /aws/lambda/my-function \
  --start-time $(date -d '1 hour ago' +%s) \
  --end-time $(date +%s) \
  --query-string 'filter @type = "REPORT"
| fields @requestId, @duration
| sort @duration desc
| limit 10'

Logs Insights 查询语言

# Count errors by status code in the last 24 hours
fields @timestamp, @message
| filter @message like /ERROR/
| parse @message '* * * [*] "* *" * *' as host, user, datetime, request, method, status, bytes
| stats count(*) as errorCount by status
| sort errorCount desc
| limit 20

指标筛选器：从日志到指标

# Create a metric filter that counts ERROR lines
aws logs put-metric-filter \
  --log-group-name /myapp/production/api \
  --filter-name ErrorCount \
  --filter-pattern 'ERROR' \
  --metric-transformations \
    metricName=ApplicationErrors,metricNamespace=MyApp,metricValue=1,defaultValue=0

# Now create an alarm on the resulting metric
aws cloudwatch put-metric-alarm \
  --alarm-name HighErrorRate \
  --metric-name ApplicationErrors \
  --namespace MyApp \
  --statistic Sum \
  --period 60 \
  --evaluation-periods 1 \
  --threshold 10 \
  --comparison-operator GreaterThanThreshold \
  --alarm-actions arn:aws:sns:us-east-1:111122223333:Ops

日志订阅和流式传输

# Stream all logs containing ERROR to a Kinesis Firehose for S3 archiving
aws logs put-subscription-filter \
  --log-group-name /myapp/production/api \
  --filter-name ErrorsToFirehose \
  --filter-pattern 'ERROR' \
  --destination-arn arn:aws:firehose:us-east-1:111122223333:deliverystream/LogArchive \
  --distribution 'ByLogStreamName'

保留策略和成本管理

# Set retention on all log groups that have no retention policy
aws logs describe-log-groups \
  --query 'logGroups[?!retentionInDays].logGroupName' \
  --output text | tr '\t' '\n' | while read lg; do
    aws logs put-retention-policy \
      --log-group-name "$lg" \
      --retention-in-days 90
    echo "Set 90-day retention on $lg"
done

VPC Flow Logs

# Enable VPC Flow Logs to CloudWatch Logs
aws ec2 create-flow-logs \
  --resource-ids vpc-0abc1234def567890 \
  --resource-type VPC \
  --traffic-type ALL \
  --log-destination-type cloud-watch-logs \
  --log-group-name /aws/vpc/flow-logs \
  --deliver-logs-permission-arn arn:aws:iam::111122223333:role/FlowLogsRole

使用 Insights 查询 VPC Flow Logs

# Find top 10 source IPs by rejected byte volume in the last day
fields srcAddr, dstAddr, dstPort, action, bytes
| filter action = 'REJECT'
| stats sum(bytes) as rejectedBytes by srcAddr
| sort rejectedBytes desc
| limit 10

使用 KMS 加密日志

# Associate a KMS key with a log group
aws logs associate-kms-key \
  --log-group-name /myapp/production/api \
  --kms-key-id arn:aws:kms:us-east-1:111122223333:key/KEY_ID

# Verify encryption is configured
aws logs describe-log-groups \
  --log-group-name-prefix /myapp/production \
  --query 'logGroups[].{Name:logGroupName,KmsKey:kmsKeyId}'

快速检查

课程回顾