Linux系统资源监控告警脚本

#!/bin/bash # ========================================== # Linux系统资源监控告警脚本 # 用途：监控系统资源，超过阈值时告警 # 使用方法：bash system_monitor.sh # ========================================== # 告警阈值配置 CPU_THRESHOLD=80 MEM_THRESHOLD=85 DISK_THRESHOLD=90 LOAD_THRESHOLD=$(nproc) SWAP_THRESHOLD=50 # 告警方式配置（可选） ALERT_EMAIL="" ALERT_WEBHOOK="" echo "========== 系统资源监控报告 ==========" echo "监控时间: $(date '+%Y-%m-%d %H:%M:%S')" echo "主机名: $(hostname)" echo "系统: $(uname -a | cut -d' ' -f1-3)" echo "" ALERTS=() add_alert() { ALERTS+=("$1") } # 1. CPU使用率 echo "【1. CPU使用率】" CPU_USAGE=$(top -bn1 | grep "Cpu(s)" | awk '{print 100 - $8}' | cut -d. -f1) CPU_CORES=$(nproc) LOAD_AVG=$(cat /proc/loadavg | awk '{print $1, $2, $3}') LOAD_1MIN=$(echo $LOAD_AVG | awk '{print $1}') echo " CPU使用率: ${CPU_USAGE}%" echo " CPU核心数: $CPU_CORES" echo " 负载均衡: $LOAD_AVG" if [ "$CPU_USAGE" -ge "$CPU_THRESHOLD" ]; then add_alert "🔴 CPU使用率过高: ${CPU_USAGE}% (阈值: ${CPU_THRESHOLD}%)" echo " 🔴 CPU使用率超过阈值!" else echo " ✅ CPU使用率正常" fi if (( $(echo "$LOAD_1MIN > $LOAD_THRESHOLD" | bc -l) )); then add_alert "🔴 系统负载过高: ${LOAD_1MIN} (阈值: ${LOAD_THRESHOLD})" echo " 🔴 系统负载超过阈值!" fi # Top CPU进程 echo " Top 5 CPU进程:" ps aux --sort=-%cpu | head -6 | tail -5 | awk '{printf " %-10s %5s%% %s ", $1, $3, $11}' echo "" # 2. 内存使用率 echo "【2. 内存使用率】" MEM_TOTAL=$(free -m | awk '/^Mem:/ {print $2}') MEM_USED=$(free -m | awk '/^Mem:/ {print $3}') MEM_AVAILABLE=$(free -m | awk '/^Mem:/ {print $7}') MEM_USAGE=$(echo "scale=1; $MEM_USED * 100 / $MEM_TOTAL" | bc | cut -d. -f1) SWAP_TOTAL=$(free -m | awk '/^Swap:/ {print $2}') SWAP_USED=$(free -m | awk '/^Swap:/ {print $3}') if [ "$SWAP_TOTAL" -gt 0 ]; then SWAP_USAGE=$(echo "scale=1; $SWAP_USED * 100 / $SWAP_TOTAL" | bc | cut -d. -f1) else SWAP_USAGE=0 fi echo " 总内存: ${MEM_TOTAL}MB" echo " 已用内存: ${MEM_USED}MB" echo " 可用内存: ${MEM_AVAILABLE}MB" echo " 内存使用率: ${MEM_USAGE}%" echo " Swap使用: ${SWAP_USED}/${SWAP_TOTAL}MB (${SWAP_USAGE}%)" if [ "$MEM_USAGE" -ge "$MEM_THRESHOLD" ]; then add_alert "🔴 内存使用率过高: ${MEM_USAGE}% (阈值: ${MEM_THRESHOLD}%)" echo " 🔴 内存使用率超过阈值!" else echo " ✅ 内存使用率正常" fi if [ "$SWAP_USAGE" -ge "$SWAP_THRESHOLD" ]; then add_alert "⚠️ Swap使用率过高: ${SWAP_USAGE}% (阈值: ${SWAP_THRESHOLD}%)" echo " ⚠️ Swap使用率超过阈值!" fi # Top内存进程 echo " Top 5内存进程:" ps aux --sort=-%mem | head -6 | tail -5 | awk '{printf " %-10s %5s%% %s ", $1, $4, $11}' echo "" # 3. 磁盘使用率 echo "【3. 磁盘使用率】" df -h | grep -E '^/dev/' | while read line; do DEVICE=$(echo $line | awk '{print $1}') SIZE=$(echo $line | awk '{print $2}') USED=$(echo $line | awk '{print $3}') AVAIL=$(echo $line | awk '{print $4}') USAGE=$(echo $line | awk '{print $5}' | tr -d '%') MOUNT=$(echo $line | awk '{print $6}') if [ "$USAGE" -ge "$DISK_THRESHOLD" ]; then echo " 🔴 $MOUNT ($DEVICE): ${USAGE}% (${USED}/${SIZE}) - 超过阈值!" add_alert "🔴 磁盘使用率过高: $MOUNT ${USAGE}% (阈值: ${DISK_THRESHOLD}%)" else echo " ✅ $MOUNT ($DEVICE): ${USAGE}% (${USED}/${SIZE})" fi done # 大文件提示 echo " 提示: 执行 find / -type f -size +100M 可查找大文件" echo "" # 4. 网络状态 echo "【4. 网络状态】" # 网络接口流量 echo " 网络接口流量:" for iface in $(ls /sys/class/net/ | grep -v lo); do RX=$(cat /sys/class/net/$iface/statistics/rx_bytes 2>/dev/null) TX=$(cat /sys/class/net/$iface/statistics/tx_bytes 2>/dev/null) if [ -n "$RX" ]; then RX_MB=$(echo "scale=1; $RX / 1024 / 1024" | bc) TX_MB=$(echo "scale=1; $TX / 1024 / 1024" | bc) echo " $iface: 接收${RX_MB}MB, 发送${TX_MB}MB" fi done # 连接数统计 ESTABLISHED=$(ss -s | grep estab | awk '{print $4}' | tr -d ',') TIME_WAIT=$(ss -tan | grep -c TIME-WAIT) echo " 已建立连接: $ESTABLISHED" echo " TIME_WAIT连接: $TIME_WAIT" if [ "$TIME_WAIT" -gt 1000 ]; then add_alert "⚠️ TIME_WAIT连接过多: $TIME_WAIT，可能存在连接泄漏" echo " ⚠️ TIME_WAIT连接过多!" fi echo "" # 5. 进程状态 echo "【5. 进程状态】" TOTAL_PROCS=$(ps aux | wc -l) ZOMBIE_PROCS=$(ps aux | grep -c 'Z') RUNNING_PROCS=$(ps aux | grep -c 'R') echo " 总进程数: $TOTAL_PROCS" echo " 运行中进程: $RUNNING_PROCS" echo " 僵尸进程: $ZOMBIE_PROCS" if [ "$ZOMBIE_PROCS" -gt 0 ]; then add_alert "⚠️ 存在僵尸进程: $ZOMBIE_PROCS 个" echo " ⚠️ 存在僵尸进程!" echo " 僵尸进程详情:" ps aux | grep 'Z' | grep -v grep | head -5 fi echo "" # 6. 系统服务状态 echo "【6. 关键服务状态】" CRITICAL_SERVICES="sshd nginx mysql redis docker" for service in $CRITICAL_SERVICES; do if systemctl list-units --type=service --all | grep -q "${service}.service"; then if systemctl is-active --quiet $service 2>/dev/null; then echo " ✅ $service: 运行中" else echo " ❌ $service: 未运行" add_alert "❌ 关键服务未运行: $service" fi fi done echo "" # 7. 告警汇总 echo "【7. 告警汇总】" if [ ${#ALERTS[@]} -eq 0 ]; then echo " ✅ 系统运行正常，无告警" else echo " 🔴 发现 ${#ALERTS[@]} 个告警:" for alert in "${ALERTS[@]}"; do echo " $alert" done # 发送告警（如果配置了） if [ -n "$ALERT_EMAIL" ]; then echo " 📧 已发送邮件告警到: $ALERT_EMAIL" fi if [ -n "$ALERT_WEBHOOK" ]; then echo " 🔔 已发送Webhook告警" fi fi echo "" # 8. 系统健康评分 echo "【8. 系统健康评分】" SCORE=100 [ "$CPU_USAGE" -ge "$CPU_THRESHOLD" ] && SCORE=$((SCORE-20)) [ "$MEM_USAGE" -ge "$MEM_THRESHOLD" ] && SCORE=$((SCORE-20)) [ "$SWAP_USAGE" -ge "$SWAP_THRESHOLD" ] && SCORE=$((SCORE-10)) [ "$ZOMBIE_PROCS" -gt 0 ] && SCORE=$((SCORE-10)) [ "$TIME_WAIT" -gt 1000 ] && SCORE=$((SCORE-10)) if [ "$SCORE" -ge 90 ]; then echo " 健康评分: $SCORE/100 🟢 优秀" elif [ "$SCORE" -ge 70 ]; then echo " 健康评分: $SCORE/100 🟡 良好" elif [ "$SCORE" -ge 50 ]; then echo " 健康评分: $SCORE/100 🟠 一般" else echo " 健康评分: $SCORE/100 🔴 较差" fi echo "" echo "========== 监控完成 ==========" echo "提示: 可将此脚本加入crontab定时执行，实现持续监控"

[]