本文目录导读：
我来介绍几种批量巡检云主机状态的方法,主要针对阿里云、腾讯云、AWS等主流云平台。
使用云厂商CLI工具（推荐）
阿里云 CLI 批量巡检
#!/bin/bash
# aliyun_health_check.sh
# 获取所有地域
REGIONS=$(aliyun ecs DescribeRegions --output json | jq -r '.Regions.Region[].RegionId')
for REGION in $REGIONS; do
echo "=== 巡检地域: $REGION ==="
# 获取该地域所有ECS实例
aliyun ecs DescribeInstances \
--RegionId $REGION \
--output json | jq -r '.Instances.Instance[] | [
.InstanceId,
.InstanceName,
.Status,
.PublicIpAddress.IpAddress[],
.InnerIpAddress.IpAddress[]
] | @tsv'
# 检查CPU使用率
aliyun cms DescribeMetricLast \
--Project acs_ecs_dashboard \
--Metric cpu_total \
--Period 300
done
腾讯云 CLI 批量巡检
#!/bin/bash
# tencentcloud_health_check.sh
# 获取所有实例状态
tccli cvm DescribeInstancesStatus \
--Offset 0 \
--Limit 100 | jq -r '.InstanceStatusSet[] | [
.InstanceId,
.InstanceState
] | @tsv'
AWS CLI 批量巡检
#!/bin/bash
# aws_health_check.sh
# 检查所有EC2实例状态
for region in $(aws ec2 describe-regions --query 'Regions[].RegionName' --output text); do
echo "Region: $region"
aws ec2 describe-instances \
--region $region \
--query 'Reservations[].Instances[].[
InstanceId,
State.Name,
InstanceType,
PublicIpAddress
]' \
--output table
done
Python脚本批量巡检
#!/usr/bin/env python3
# cloud_health_check.py
import json
import subprocess
from datetime import datetime
class CloudHealthChecker:
def __init__(self, cloud_provider='aliyun'):
self.cloud_provider = cloud_provider
def check_aliyun_instances(self):
"""巡检阿里云ECS实例"""
regions_cmd = "aliyun ecs DescribeRegions --output json"
regions_output = subprocess.check_output(regions_cmd, shell=True)
regions = json.loads(regions_output)['Regions']['Region']
health_report = []
for region in regions:
region_id = region['RegionId']
# 获取实例列表
cmd = f"aliyun ecs DescribeInstances --RegionId {region_id} --output json"
output = subprocess.check_output(cmd, shell=True)
instances = json.loads(output)['Instances']['Instance']
for instance in instances:
health_info = {
'instance_id': instance['InstanceId'],
'name': instance.get('InstanceName', 'N/A'),
'status': instance['Status'],
'region': region_id,
'check_time': datetime.now().isoformat()
}
# 检查健康状态
if instance['Status'] == 'Running':
# 检查CPU使用率
cpu_cmd = f"""aliyun cms DescribeMetricLast \
--Project acs_ecs_dashboard \
--Metric cpu_total \
--Period 300 \
--Dimensions "[{{\\\"instanceId\\\":\\\"{instance['InstanceId']}\\\"}}]" """
try:
cpu_output = subprocess.check_output(cpu_cmd, shell=True)
cpu_data = json.loads(cpu_output)
if 'Datapoints' in cpu_data:
health_info['cpu_usage'] = cpu_data['Datapoints'][-1]['Average']
except:
health_info['cpu_usage'] = 'N/A'
health_report.append(health_info)
return health_report
def generate_report(self, data):
"""生成巡检报告"""
print(f"\n{'='*60}")
print(f"云主机健康巡检报告 - {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
print(f"{'='*60}")
total = len(data)
running = sum(1 for i in data if i['status'] == 'Running')
stopped = sum(1 for i in data if i['status'] == 'Stopped')
print(f"\n统计信息:")
print(f" 总实例数: {total}")
print(f" 运行中: {running}")
print(f" 已停止: {stopped}")
print(f"\n实例详情:")
print(f"{'InstanceId':<20} {'Name':<20} {'Status':<10} {'Region':<15}")
print("-"*65)
for instance in data:
print(f"{instance['instance_id']:<20} "
f"{instance['name'][:20]:<20} "
f"{instance['status']:<10} "
f"{instance['region']:<15}")
# 保存报告
report_file = f"health_report_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json"
with open(report_file, 'w', encoding='utf-8') as f:
json.dump(data, f, indent=2, ensure_ascii=False)
print(f"\n报告已保存至: {report_file}")
if __name__ == "__main__":
checker = CloudHealthChecker('aliyun')
report = checker.check_aliyun_instances()
checker.generate_report(report)
Ansible自动化巡检
---
# ansible_health_check.yml
- name: 云主机健康巡检
hosts: cloud_instances
gather_facts: yes
vars:
check_time: "{{ ansible_date_time.iso8601 }}"
tasks:
- name: 检查系统资源使用
block:
- name: CPU使用率
shell: |
top -bn1 | grep "Cpu(s)" | \
awk '{print "CPU_Usage: " $2 + $4 "%"}'
register: cpu_usage
- name: 内存使用率
shell: |
free | grep Mem | \
awk '{printf "RAM_Usage: %.2f%%", $3/$2 * 100}'
register: mem_usage
- name: 磁盘使用率
shell: |
df -h / | awk 'NR==2 {print "Disk_Usage: " $5}'
register: disk_usage
- name: 系统运行时间
shell: |
uptime
register: uptime_info
- name: 关键服务检查
shell: |
systemctl is-active --quiet sshd && echo "SSH: Running" || echo "SSH: Stopped"
systemctl is-active --quiet nginx && echo "Nginx: Running" || echo "Nginx: Stopped"
register: service_status
ignore_errors: yes
- name: 生成巡检报告
template:
src: health_report.j2
dest: "/tmp/health_{{ inventory_hostname }}_{{ check_time }}.txt"
delegate_to: localhost
- name: 汇总所有主机报告
hosts: localhost
tasks:
- name: 合并报告
assemble:
src: /tmp/
dest: "/tmp/health_report_{{ ansible_date_time.date }}.txt"
delimiter: "---"
when: false # 需要时启用
完整的巡检脚本示例
#!/bin/bash
# comprehensive_cloud_check.sh
echo "========================================"
echo "云主机综合巡检脚本"
echo "开始时间: $(date)"
echo "========================================"
# 颜色定义
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[1;33m'
NC='\033[0m'
# 配置文件
CONFIG_FILE="cloud_config.ini"
REPORT_DIR="./reports"
mkdir -p $REPORT_DIR
# 加载配置
load_config() {
if [ -f "$CONFIG_FILE" ]; then
source $CONFIG_FILE
else
echo "配置文件不存在，使用默认配置"
CLOUD_PROVIDER="aliyun"
REGIONS="cn-hangzhou,cn-beijing"
CHECK_INTERVAL=300
fi
}
# 巡检单个实例
check_instance() {
local instance_id=$1
local region=$2
echo -e "\n${YELLOW}检查实例: $instance_id${NC}"
# 获取实例状态
STATUS=$(aliyun ecs DescribeInstanceAttribute \
--InstanceId $instance_id \
--RegionId $region \
--output json | jq -r '.Status')
# 检查健康状态
if [ "$STATUS" == "Running" ]; then
echo -e "${GREEN}✓ 实例状态: Running${NC}"
# 获取监控数据
local cpu_output=$(aliyun cms DescribeMetricLast \
--Project acs_ecs_dashboard \
--Metric cpu_total \
--Period 300 \
--Dimensions "[{\"instanceId\":\"$instance_id\"}]" 2>/dev/null)
local mem_output=$(aliyun cms DescribeMetricLast \
--Project acs_ecs_dashboard \
--Metric memory_usedutilization \
--Period 300 \
--Dimensions "[{\"instanceId\":\"$instance_id\"}]" 2>/dev/null)
# 解析CPU使用率
if [ -n "$cpu_output" ]; then
local cpu_usage=$(echo $cpu_output | jq -r '.Datapoints[-1].Average // "N/A"')
echo "CPU使用率: ${cpu_usage}%"
if (( $(echo "$cpu_usage > 80" | bc -l) )); then
echo -e "${RED}⚠ CPU使用率过高${NC}"
fi
fi
# 解析内存使用率
if [ -n "$mem_output" ]; then
local mem_usage=$(echo $mem_output | jq -r '.Datapoints[-1].Average // "N/A"')
echo "内存使用率: ${mem_usage}%"
if (( $(echo "$mem_usage > 80" | bc -l) )); then
echo -e "${RED}⚠ 内存使用率过高${NC}"
fi
fi
else
echo -e "${YELLOW}⚠ 实例状态: $STATUS${NC}"
fi
# 记录结果
echo "$instance_id|$region|$STATUS|$(date +%Y-%m-%d_%H:%M:%S)" >> "$REPORT_DIR/health_$(date +%Y%m%d).log"
}
# 批量巡检
batch_check() {
local regions=$1
IFS=',' read -ra REGION_ARRAY <<< "$regions"
for region in "${REGION_ARRAY[@]}"; do
echo -e "\n${GREEN}巡检地域: $region${NC}"
# 获取该地域所有实例
aliyun ecs DescribeInstances \
--RegionId $region \
--output json | jq -r '.Instances.Instance[].InstanceId' | while read instance_id; do
check_instance $instance_id $region
done
done
}
# 生成HTML报告
generate_html_report() {
local report_date=$(date +%Y%m%d)
local log_file="$REPORT_DIR/health_${report_date}.log"
local html_file="$REPORT_DIR/report_${report_date}.html"
# 统计信息
local total=$(wc -l < $log_file)
local running=$(grep -c "Running" $log_file)
local stopped=$(grep -c "Stopped" $log_file)
cat > $html_file <<EOF
<!DOCTYPE html>
<html>
<head>云主机巡检报告</title>
<style>
body { font-family: Arial, sans-serif; margin: 20px; }
h1 { color: #333; }
.summary { background: #f5f5f5; padding: 15px; border-radius: 5px; }
.running { color: green; }
.stopped { color: red; }
table { border-collapse: collapse; width: 100%; }
th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }
th { background-color: #4CAF50; color: white; }
</style>
</head>
<body>
<h1>云主机健康巡检报告</h1>
<p>生成时间: $(date '+%Y-%m-%d %H:%M:%S')</p>
<div class="summary">
<h2>统计概览</h2>
<p>总实例数: $total</p>
<p>运行中: <span class="running">$running</span></p>
<p>已停止: <span class="stopped">$stopped</span></p>
</div>
<h2>实例详情</h2>
<table>
<tr>
<th>实例ID</th>
<th>地域</th>
<th>状态</th>
<th>检查时间</th>
</tr>
EOF
while IFS='|' read -r id region status time; do
local status_class=""
[ "$status" == "Running" ] && status_class="running" || status_class="stopped"
cat >> $html_file <<EOF
<tr>
<td>$id</td>
<td>$region</td>
<td class="$status_class">$status</td>
<td>$time</td>
</tr>
EOF
done < $log_file
echo "</table></body></html>" >> $html_file
echo -e "${GREEN}HTML报告已生成: $html_file${NC}"
}
# 主程序
main() {
load_config
echo -e "${GREEN}开始批量巡检...${NC}"
batch_check $REGIONS
echo -e "\n${GREEN}生成报告...${NC}"
generate_html_report
echo -e "\n${GREEN}巡检完成!${NC}"
}
main "$@"
使用方法
- 配置云厂商CLI
# 安装CLI工具 pip install aliyun-cli # 或 brew install awscli
配置认证信息
aliyun configure
或
aws configure
2. **运行巡检脚本**
```bash
# 直接运行
bash comprehensive_cloud_check.sh
# Python脚本
python3 cloud_health_check.py
# Ansible
ansible-playbook -i inventory ansible_health_check.yml- 设置定时任务
crontab -e
每天凌晨2点执行巡检
0 2 * /path/to/cloud_check.sh
这些脚本可以根据实际需求进行定制，添加更多检查项如磁盘IO、网络延迟、安全组规则等。
