服务器资源监控告警脚本

#!/bin/bash # ========================================== # 服务器资源监控告警脚本 # 用途：监控CPU、内存、磁盘使用率，超阈值告警 # 使用方法：bash resource_monitor.sh （建议加入crontab每分钟执行） # ========================================== # ========== 配置 ========== CPU_THRESHOLD=80 # CPU使用率告警阈值(%) MEM_THRESHOLD=85 # 内存使用率告警阈值(%) DISK_THRESHOLD=90 # 磁盘使用率告警阈值(%) LOAD_THRESHOLD=0 # 系统负载阈值(0表示不检测，按核心数设置，如4核设为4) CHECK_INTERVAL=60 # 检测间隔(秒)，持续监控模式使用 LOG_FILE="/var/log/resource_monitor.log" ALERT_EMAIL="" # 告警邮箱，留空则不发邮件 WECOM_WEBHOOK="" # 企业微信机器人Webhook，留空则不发 # ========================== mkdir -p "$(dirname "$LOG_FILE")" log_msg() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] $1" | tee -a "$LOG_FILE" } send_alert() { local title="$1" local content="$2" log_msg "【告警】$title: $content" # 邮件告警 if [ -n "$ALERT_EMAIL" ]; then echo -e "$content" | mail -s "【服务器告警】$title" "$ALERT_EMAIL" 2>/dev/null fi # 企业微信告警 if [ -n "$WECOM_WEBHOOK" ]; then curl -s "$WECOM_WEBHOOK" -H "Content-Type: application/json" -d "{ "msgtype": "text", "text": {"content": "【服务器告警】$title\n$content\n主机: $(hostname)\n时间: $(date '+%Y-%m-%d %H:%M:%S')"} }" >/dev/null 2>&1 fi } check_cpu() { CPU_USAGE=$(top -bn1 | grep "Cpu(s)" | awk '{print $2}' | cut -d. -f1) if [ -z "$CPU_USAGE" ]; then CPU_USAGE=$(vmstat 1 2 | tail -1 | awk '{print 100-$15}') fi if [ "$CPU_USAGE" -gt "$CPU_THRESHOLD" ]; then TOP_PROC=$(ps aux --sort=-%cpu | head -4 | tail -3 | awk '{print $11" ("$3"%)"}' | tr '\n' ' ') send_alert "CPU使用率过高" "当前CPU使用率: ${CPU_USAGE}% (阈值: ${CPU_THRESHOLD}%)\nTop进程: $TOP_PROC" else log_msg "CPU使用率: ${CPU_USAGE}% (正常)" fi } check_memory() { MEM_TOTAL=$(free -m | awk 'NR==2{print $2}') MEM_USED=$(free -m | awk 'NR==2{print $3}') MEM_USAGE=$((MEM_USED * 100 / MEM_TOTAL)) if [ "$MEM_USAGE" -gt "$MEM_THRESHOLD" ]; then TOP_PROC=$(ps aux --sort=-%mem | head -4 | tail -3 | awk '{print $11" ("$4"%)"}' | tr '\n' ' ') send_alert "内存使用率过高" "当前内存使用率: ${MEM_USAGE}% (阈值: ${MEM_THRESHOLD}%)\n已用: ${MEM_USED}MB / 总计: ${MEM_TOTAL}MB\nTop进程: $TOP_PROC" else log_msg "内存使用率: ${MEM_USAGE}% (正常)" fi } check_disk() { df -hP | grep -vE "tmpfs|devtmpfs|overlay" | awk 'NR>1{print $6" "$5}' | while read mount usage; do usage_num=${usage%\%} if [ "$usage_num" -gt "$DISK_THRESHOLD" ]; then send_alert "磁盘使用率过高" "分区 $mount 使用率: ${usage} (阈值: ${DISK_THRESHOLD}%)\n$(df -h "$mount" | tail -1)" else log_msg "磁盘 $mount 使用率: $usage (正常)" fi done } check_load() { if [ "$LOAD_THRESHOLD" -gt 0 ]; then LOAD1=$(cat /proc/loadavg | awk '{print $1}') LOAD_STATUS=$(echo "$LOAD1 > $LOAD_THRESHOLD" | bc) if [ "$LOAD_STATUS" = "1" ]; then send_alert "系统负载过高" "1分钟负载: $LOAD1 (阈值: $LOAD_THRESHOLD)\n$(uptime)" else log_msg "系统负载: $LOAD1 (正常)" fi fi } # 单次检测模式（crontab使用） if [ "$1" = "--once" ]; then log_msg "===== 开始单次资源检测 =====" check_cpu check_memory check_disk check_load log_msg "===== 检测完成 =====" exit 0 fi # 持续监控模式 log_msg "===== 资源监控启动，间隔${CHECK_INTERVAL}秒 =====" while true; do check_cpu check_memory check_disk check_load sleep "$CHECK_INTERVAL" done

[{"name": "CPU_THRESHOLD", "label": "CPU\u544a\u8b66\u9608\u503c(%)", "default": "80"}, {"name": "MEM_THRESHOLD", "label": "\u5185\u5b58\u544a\u8b66\u9608\u503c(%)", "default": "85"}, {"name": "DISK_THRESHOLD", "label": "\u78c1\u76d8\u544a\u8b66\u9608\u503c(%)", "default": "90"}, {"name": "ALERT_EMAIL", "label": "\u544a\u8b66\u90ae\u7bb1(\u53ef\u9009)", "default": ""}, {"name": "WECOM_WEBHOOK", "label": "\u4f01\u4e1a\u5fae\u4fe1Webhook(\u53ef\u9009)", "default": ""}]