弹性与高可用架构场景

场景 1：多可用区 Web 应用程序

# Create RDS with Multi-AZ enabled
aws rds create-db-instance \
  --db-instance-identifier prod-mysql \
  --db-instance-class db.t3.large \
  --engine mysql \
  --multi-az \
  --master-username admin \
  --master-user-password Pass123! \
  --allocated-storage 100

# Create ASG across 3 AZs
aws autoscaling create-auto-scaling-group \
  --auto-scaling-group-name web-asg \
  --min-size 2 --max-size 10 --desired-capacity 3 \
  --availability-zones us-east-1a us-east-1b us-east-1c \
  --target-group-arns arn:aws:elasticloadbalancing:us-east-1:123:targetgroup/web-tg/abc

场景 2：负载下的 RDS 读扩展

# Create a Read Replica from the primary RDS instance
aws rds create-db-instance-read-replica \
  --db-instance-identifier prod-mysql-replica \
  --source-db-instance-identifier prod-mysql \
  --db-instance-class db.t3.large \
  --availability-zone us-east-1b

# Application code: use replica endpoint for reads
# Primary endpoint: prod-mysql.cluster.us-east-1.rds.amazonaws.com (writes)
# Replica endpoint: prod-mysql-replica.xyz.us-east-1.rds.amazonaws.com (reads)

场景 3：CPU 峰值时的自动扩缩

# Target tracking policy: scale to keep CPU at 60%
aws autoscaling put-scaling-policy \
  --auto-scaling-group-name api-asg \
  --policy-name cpu-tracking \
  --policy-type TargetTrackingScaling \
  --target-tracking-configuration '{
    "PredefinedMetricSpecification": {"PredefinedMetricType": "ASGAverageCPUUtilization"},
    "TargetValue": 60.0,
    "DisableScaleIn": false
  }'

# Scheduled action: pre-warm to 5 instances at 8 AM weekdays
aws autoscaling put-scheduled-update-group-action \
  --auto-scaling-group-name api-asg \
  --scheduled-action-name morning-scale-out \
  --recurrence '0 8 * * MON-FRI' \
  --min-size 5

场景 4：Route 53 故障转移到灾难恢复站点

# Create Route 53 health check for primary ALB
aws route53 create-health-check \
  --caller-reference $(date +%s) \
  --health-check-config '{
    "Type": "HTTPS",
    "FullyQualifiedDomainName": "app.example.com",
    "Port": 443,
    "RequestInterval": 30,
    "FailureThreshold": 3
  }'

# Primary failover record (associated with health check)
# Secondary failover record -> S3 static website endpoint
# Route 53 automatically switches if health check fails

场景 5：使用 SQS 实现解耦和弹性

# SQS-based order decoupling pattern
# 1. Frontend: PUT order to SQS (returns 200 immediately to customer)
aws sqs send-message \
  --queue-url https://sqs.us-east-1.amazonaws.com/123/orders \
  --message-body '{"orderId": "ORD-123", "items": [...]}'

# 2. Backend worker: polls SQS when DB is available
aws sqs receive-message \
  --queue-url https://sqs.us-east-1.amazonaws.com/123/orders \
  --max-number-of-messages 10

# 3. On success: delete message from queue
# 4. On failure: visibility timeout expires -> message reappears for retry
# 5. After max retries: message goes to Dead Letter Queue (DLQ)

场景 6：Pilot Light 灾难恢复

# Pilot Light: replicate database to DR Region
aws rds create-db-instance-read-replica \
  --db-instance-identifier prod-mysql-dr \
  --source-db-instance-identifier prod-mysql \
  --db-instance-class db.t3.large \
  --source-region us-east-1 \
  --destination-region us-west-2

# During disaster: promote replica in us-west-2 to standalone
aws rds promote-read-replica \
  --db-instance-identifier prod-mysql-dr \
  --region us-west-2
# Then launch app servers from AMIs using CloudFormation in us-west-2

场景 7：使用 SQS Dead-Letter Queue 处理失败消息

# Set redrive policy to move failed messages to DLQ after 3 attempts
aws sqs set-queue-attributes \
  --queue-url https://sqs.us-east-1.amazonaws.com/123/orders \
  --attributes '{
    "RedrivePolicy": "{\"deadLetterTargetArn\": \"arn:aws:sqs:us-east-1:123:orders-dlq\", \"maxReceiveCount\": \"3\"}"
  }'

# CloudWatch alarm on DLQ depth
aws cloudwatch put-metric-alarm \
  --alarm-name orders-dlq-depth \
  --metric-name ApproximateNumberOfMessagesVisible \
  --namespace AWS/SQS \
  --dimensions Name=QueueName,Value=orders-dlq \
  --threshold 1 --comparison-operator GreaterThanOrEqualToThreshold \
  --evaluation-periods 1 --period 60 --statistic Sum

场景 8：Aurora Global Database

# Add a secondary region to an Aurora Global Database
aws rds create-global-cluster \
  --global-cluster-identifier prod-global \
  --source-db-cluster-identifier arn:aws:rds:us-east-1:123:cluster:prod-aurora

# Add secondary Region cluster
aws rds create-db-cluster \
  --db-cluster-identifier prod-aurora-eu \
  --engine aurora-postgresql \
  --global-cluster-identifier prod-global \
  --region eu-west-1

场景 9：带 ALB 和自动扩缩的 ECS 服务

# Create ECS Fargate service with ALB and multi-AZ placement
aws ecs create-service \
  --cluster prod-cluster \
  --service-name api-service \
  --task-definition api-task:5 \
  --desired-count 3 \
  --launch-type FARGATE \
  --network-configuration '{
    "awsvpcConfiguration": {
      "subnets": ["subnet-1a", "subnet-1b", "subnet-1c"],
      "securityGroups": ["sg-app"],
      "assignPublicIp": "DISABLED"
    }
  }' \
  --load-balancers '[{
    "targetGroupArn": "arn:...:targetgroup/api-tg/abc",
    "containerName": "api",
    "containerPort": 8080
  }]'

场景 10：使用 Route 53 运行状况检查进行故障转移

# Route 53 weighted record with health check association
aws route53 change-resource-record-sets \
  --hosted-zone-id Z1234567890 \
  --change-batch '{
    "Changes": [{
      "Action": "UPSERT",
      "ResourceRecordSet": {
        "Name": "app.example.com",
        "Type": "A",
        "SetIdentifier": "instance-1a",
        "Weight": 50,
        "HealthCheckId": "hc-abc123",
        "TTL": 30,
        "ResourceRecords": [{"Value": "10.0.1.10"}]
      }
    }]
  }'

场景 11：使用 DynamoDB Global Tables 实现多区域 HA

# Convert a DynamoDB table to a Global Table
# (table must exist in all target Regions first)
aws dynamodb create-global-table \
  --global-table-name PlayerData \
  --replication-group '[{"RegionName": "us-east-1"}, {"RegionName": "ap-southeast-1"}]'

# Add another Region to an existing Global Table
aws dynamodb update-global-table \
  --global-table-name PlayerData \
  --replica-updates '[{"Create": {"RegionName": "eu-west-1"}}]'

快速检查

课程回顾