服务器监控告警系统

服务器综合监控告警脚本

一键检查服务器核心指标：CPU、内存、磁盘、网络、关键进程状态，适合作为定时巡检脚本。

#!/bin/bash
# server_health_check.sh

HOSTNAME=$(hostname)
ALERT=0
ALERT_MSG=""

echo "=========================================="
echo " 服务器健康检查: $HOSTNAME"
echo " $(date)"
echo "=========================================="
echo ""

# CPU检查
echo "--- CPU ---"
CPU_IDLE=$(top -bn1 | grep "Cpu(s)" | awk '{print $8}' | cut -d. -f1)
CPU_USAGE=$((100 - CPU_IDLE))
LOAD=$(uptime | awk -F'load average:' '{print $2}')
echo "CPU使用率: ${CPU_USAGE}%"
echo "负载: $LOAD"
if [ "$CPU_USAGE" -gt 90 ]; then
    echo "  WARNING: CPU使用率超过90%"
    ALERT=1
fi
echo ""

# 内存检查
echo "--- 内存 ---"
MEM_INFO=$(free -m | grep Mem)
MEM_TOTAL=$(echo "$MEM_INFO" | awk '{print $2}')
MEM_USED=$(echo "$MEM_INFO" | awk '{print $3}')
MEM_PERCENT=$((MEM_USED * 100 / MEM_TOTAL))
echo "内存: ${MEM_USED}MB / ${MEM_TOTAL}MB (${MEM_PERCENT}%)"
if [ "$MEM_PERCENT" -gt 85 ]; then
    echo "  WARNING: 内存使用率超过85%"
    ALERT=1
fi
echo ""

# Swap检查
SWAP_INFO=$(free -m | grep Swap)
SWAP_USED=$(echo "$SWAP_INFO" | awk '{print $3}')
if [ "$SWAP_USED" -gt 100 ]; then
    echo "  WARNING: Swap使用了 ${SWAP_USED}MB"
    ALERT=1
fi

# 磁盘检查
echo "--- 磁盘 ---"
df -h | grep '^/dev/' | while read line; do
    MOUNT=$(echo "$line" | awk '{print $6}')
    USAGE=$(echo "$line" | awk '{print $5}' | tr -d '%')
    echo "$MOUNT: ${USAGE}%"
    if [ "$USAGE" -gt 85 ]; then
        echo "  WARNING: $MOUNT 使用率 ${USAGE}%"
    fi
done
echo ""

# 关键进程检查
echo "--- 关键进程 ---"
for svc in nginx httpd php-fpm mysqld redis; do
    if systemctl is-active "$svc" &>/dev/null; then
        echo "  $svc: running"
    else
        echo "  $svc: STOPPED"
        ALERT=1
    fi
done
echo ""

# 网络连接数
echo "--- 网络 ---"
CONN_COUNT=$(ss -s | grep estab | awk '{print $2}')
echo "已建立连接数: $CONN_COUNT"
TIME_WAIT=$(ss -ant | grep TIME-WAIT | wc -l)
echo "TIME_WAIT连接: $TIME_WAIT"
echo ""

# 最近登录
echo "--- 最近登录 ---"
last -5 -w
echo ""

if [ "$ALERT" -eq 0 ]; then
    echo "结果: 全部正常"
else
    echo "结果: 存在异常，请检查上述WARNING项"
fi