阿里云ECS资源监控脚本

#!/bin/bash # 阿里云ECS资源监控与成本优化脚本 # 需要安装阿里云CLI并配置AccessKey # 安装: pip install aliyun-cli 或 下载官方CLI REGION="cn-hangzhou" ACCESS_KEY_ID="your_access_key_id" ACCESS_KEY_SECRET="your_access_key_secret" CPU_THRESHOLD=20 # CPU低于此值视为闲置 DISK_THRESHOLD=30 # 磁盘使用率低于此值视为浪费 LOG_FILE="/var/log/aliyun_ecs_monitor.log" REPORT_FILE="/tmp/aliyun_ecs_report_$(date +%Y%m%d).txt" log_msg() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] $1" | tee -a "$LOG_FILE" "$REPORT_FILE" } log_msg "===== 阿里云ECS资源监控 =====" log_msg "区域: $REGION" log_msg "时间: $(date '+%Y-%m-%d %H:%M:%S')" # 检查阿里云CLI if ! command -v aliyun >/dev/null 2>&1; then log_msg "❌ 阿里云CLI未安装" log_msg "安装方法: https://help.aliyun.com/document_detail/139508.html" exit 1 fi # 配置凭证 export ALIBABA_CLOUD_ACCESS_KEY_ID=$ACCESS_KEY_ID export ALIBABA_CLOUD_ACCESS_KEY_SECRET=$ACCESS_KEY_SECRET # 1. 获取ECS实例列表 log_msg "" log_msg "【1. ECS实例列表】" INSTANCES=$(aliyun ecs DescribeInstances --RegionId $REGION --output cols=InstanceId,InstanceName,Status,InstanceType,PublicIpAddress 2>/dev/null) if [ -z "$INSTANCES" ]; then log_msg " 无ECS实例或查询失败" exit 0 fi echo "$INSTANCES" | while read line; do log_msg " $line" done INSTANCE_COUNT=$(echo "$INSTANCES" | wc -l) log_msg " 实例总数: $INSTANCE_COUNT" # 2. 获取监控数据（最近1小时平均CPU） log_msg "" log_msg "【2. 资源使用率分析（最近1小时）】" log_msg " 正在获取云监控数据..." # 获取实例ID列表 INSTANCE_IDS=$(aliyun ecs DescribeInstances --RegionId $REGION --output cols=InstanceId 2>/dev/null | tail -n +2) IDLE_COUNT=0 TOTAL_COST=0 for instance_id in $INSTANCE_IDS; do # 获取CPU平均使用率 CPU_AVG=$(aliyun cms DescribeMetricLast --Namespace acs_ecs_dashboard --MetricName cpu_total --Period 3600 --Dimensions "[{"instanceId":"$instance_id"}]" --output cols=Average 2>/dev/null | tail -1) # 获取实例名称 INSTANCE_NAME=$(aliyun ecs DescribeInstanceAttribute --InstanceId $instance_id --output cols=InstanceName 2>/dev/null | tail -1) # 获取实例规格和价格估算 INSTANCE_TYPE=$(aliyun ecs DescribeInstanceAttribute --InstanceId $instance_id --output cols=InstanceType 2>/dev/null | tail -1) CPU_VAL=$(echo "$CPU_AVG" | grep -oE '[0-9.]+' | head -1) CPU_VAL=${CPU_VAL:-0} if (( $(echo "$CPU_VAL < $CPU_THRESHOLD" | bc -l) )); then log_msg " ⚠️ 闲置实例: $INSTANCE_NAME ($instance_id)" log_msg " CPU: ${CPU_VAL}% (低于阈值${CPU_THRESHOLD}%)" log_msg " 规格: $INSTANCE_TYPE" IDLE_COUNT=$((IDLE_COUNT + 1)) else log_msg " ✓ $INSTANCE_NAME: CPU ${CPU_VAL}%" fi done # 3. 磁盘使用分析 log_msg "" log_msg "【3. 磁盘使用分析】" DISKS=$(aliyun ecs DescribeDisks --RegionId $REGION --output cols=DiskId,Size,Category,Status 2>/dev/null) echo "$DISKS" | while read line; do log_msg " $line" done # 4. 成本优化建议 log_msg "" log_msg "【4. 成本优化建议】" if [ "$IDLE_COUNT" -gt 0 ]; then log_msg " 🔴 发现 $IDLE_COUNT 台闲置实例，建议：" log_msg " 1. 降配：降低实例规格，节省费用" log_msg " 2. 释放：确认无用后释放实例" log_msg " 3. 转包年包月：长期使用的实例转预付费更便宜" else log_msg " ✅ 无明显闲置实例" fi log_msg "" log_msg " 其他优化建议：" log_msg " - 检查是否有未挂载的磁盘（浪费费用）" log_msg " - 检查弹性公网IP是否有闲置" log_msg " - 考虑使用抢占式实例降低成本" log_msg " - 设置自动伸缩，按需扩缩容" # 5. 安全组检查 log_msg "" log_msg "【5. 安全组风险检查】" SECURITY_GROUPS=$(aliyun ecs DescribeSecurityGroups --RegionId $REGION --output cols=SecurityGroupId,SecurityGroupName 2>/dev/null) echo "$SECURITY_GROUPS" | while read line; do sg_id=$(echo "$line" | awk '{print $1}') if [ -n "$sg_id" ]; then # 检查是否有0.0.0.0/0开放高危端口 RISK=$(aliyun ecs DescribeSecurityGroupAttribute --SecurityGroupId $sg_id --output cols=SourceCidrIp,IpProtocol,PortRange 2>/dev/null | grep -E "0.0.0.0/0.*(22|3306|6379|27017|1433)") if [ -n "$RISK" ]; then log_msg " ⚠️ 安全组 $sg_id 存在高危端口对外开放:" echo "$RISK" | while read r; do log_msg " $r" done fi fi done log_msg "" log_msg "===== 监控完成 =====" log_msg "报告已保存到: $REPORT_FILE"

[{"name": "REGION", "label": "\u963f\u91cc\u4e91\u533a\u57df", "default": "cn-hangzhou"}, {"name": "ACCESS_KEY_ID", "label": "AccessKey ID", "default": "your_access_key_id"}, {"name": "ACCESS_KEY_SECRET", "label": "AccessKey Secret", "default": "your_access_key_secret"}, {"name": "CPU_THRESHOLD", "label": "\u95f2\u7f6eCPU\u9608\u503c(%)", "default": "20"}]