Shell脚本如何配置容器监控面板

wen 实用脚本 2026-07-16 1

本文目录导读：

Shell脚本如何配置容器监控面板

基础监控脚本
实时监控面板
高级监控配置
带Web前端的监控面板
完整监控配置脚本
使用说明

我来详细介绍Shell脚本配置容器监控面板的方法：

基础监控脚本

CPU和内存监控

#!/bin/bash
# 容器资源监控脚本
CONTAINERS=$(docker ps --format "{{.Names}}")
echo "容器资源使用情况："
echo "------------------------"
for container in $CONTAINERS; do
    echo "容器: $container"
    # CPU使用率
    cpu_usage=$(docker stats $container --no-stream --format "{{.CPUPerc}}")
    echo "  CPU: $cpu_usage"
    # 内存使用
    mem_usage=$(docker stats $container --no-stream --format "{{.MemUsage}}")
    echo "  内存: $mem_usage"
    # 网络流量
    network=$(docker stats $container --no-stream --format "{{.NetIO}}")
    echo "  网络: $network"
    # 磁盘IO
    block_io=$(docker stats $container --no-stream --format "{{.BlockIO}}")
    echo "  磁盘: $block_io"
    echo ""
done

实时监控面板

#!/bin/bash
# 实时容器监控面板
show_container_panel() {
    clear
    echo "╔══════════════════════════════════════╗"
    echo "║      Docker容器监控面板              ║"
    echo "╠══════════════════════════════════════╣"
    # 获取运行中的容器列表
    docker ps --format "table {{.Names}}\t{{.Status}}\t{{.Ports}}" | head -1
    docker ps --format "table {{.Names}}\t{{.Status}}\t{{.Ports}}" | tail -n +2
    echo "╠══════════════════════════════════════╣"
    # 显示资源使用
    docker stats --no-stream --format "table {{.Container}}\t{{.CPUPerc}}\t{{.MemUsage}}\t{{.NetIO}}"
    echo "╚══════════════════════════════════════╝"
}
# 持续监控
while true; do
    show_container_panel
    echo "按 Ctrl+C 退出监控"
    sleep 5
done

高级监控配置

#!/bin/bash
# 配置监控参数
MONITOR_INTERVAL=10
ALERT_CPU_THRESHOLD=80
ALERT_MEM_THRESHOLD=90
LOG_FILE="/var/log/container_monitor.log"
WEBHOOK_URL="https://your-webhook/alert"
# 初始化监控
init_monitoring() {
    mkdir -p /var/log/container_monitor
    touch $LOG_FILE
}
# 监控单个容器
monitor_container() {
    local container=$1
    # 获取容器状态
    local status=$(docker inspect --format='{{.State.Status}}' $container 2>/dev/null)
    if [ "$status" != "running" ]; then
        log_event "WARNING" "容器 $container 状态异常: $status"
        return
    fi
    # 获取资源使用
    local cpu=$(docker stats $container --no-stream --format "{{.CPUPerc}}" | sed 's/%//')
    local mem_percent=$(docker stats $container --no-stream --format "{{.MemPerc}}" | sed 's/%//')
    # 检查阈值
    if (( $(echo "$cpu > $ALERT_CPU_THRESHOLD" | bc -l) )); then
        send_alert "CPU告警: $container CPU使用率: $cpu%"
    fi
    if (( $(echo "$mem_percent > $ALERT_MEM_THRESHOLD" | bc -l) )); then
        send_alert "内存告警: $container 内存使用率: $mem_percent%"
    fi
    # 记录日志
    log_event "INFO" "$container CPU: ${cpu}% 内存: ${mem_percent}%"
}
# 日志记录
log_event() {
    local level=$1
    local message=$2
    echo "[$(date '+%Y-%m-%d %H:%M:%S')] [$level] $message" >> $LOG_FILE
}
# 发送告警
send_alert() {
    local message=$1
    # Webhook通知
    if [ -n "$WEBHOOK_URL" ]; then
        curl -X POST -H "Content-Type: application/json" \
            -d "{\"text\":\"$message\"}" \
            $WEBHOOK_URL 2>/dev/null
    fi
    # 本地通知
    echo "ALERT: $message" | wall 2>/dev/null
}
# 主循环
main_loop() {
    init_monitoring
    while true; do
        local containers=$(docker ps -q)
        for container in $containers; do
            monitor_container $container &
        done
        wait
        sleep $MONITOR_INTERVAL
    done
}
# 执行监控
main_loop

带Web前端的监控面板

#!/bin/bash
# 生成HTML监控面板
generate_html() {
    local timestamp=$(date '+%Y-%m-%d %H:%M:%S')
    local container_count=$(docker ps -q | wc -l)
    cat > /tmp/dashboard.html <<EOF
<!DOCTYPE html>
<html>
<head>
    <meta charset="UTF-8">
    <meta http-equiv="refresh" content="5">Container Monitor</title>
    <style>
        body { font-family: Arial, sans-serif; background: #1a1a2e; color: #fff; }
        .container { max-width: 1200px; margin: 0 auto; padding: 20px; }
        .header { text-align: center; margin-bottom: 30px; }
        .stats { display: grid; grid-template-columns: repeat(auto-fit, minmax(250px, 1fr)); gap: 20px; }
        .card { background: #16213e; padding: 20px; border-radius: 10px; }
        .running { color: #4ecca3; }
        .stopped { color: #ff6b6b; }
        table { width: 100%; border-collapse: collapse; }
        th, td { padding: 10px; text-align: left; border-bottom: 1px solid #333; }
    </style>
</head>
<body>
    <div class="container">
        <div class="header">
            <h1>容器监控面板</h1>
            <p>更新时间: $timestamp</p>
            <p>运行容器数: $container_count</p>
        </div>
        <div class="stats" id="containerStats">
EOF
    # 为每个容器生成状态卡片
    docker ps --format "{{.Names}} {{.Status}} {{.Ports}}" | while read line; do
        name=$(echo $line | awk '{print $1}')
        status=$(echo $line | awk '{print $2}')
        ports=$(echo $line | awk '{print $3}')
        cat >> /tmp/dashboard.html <<EOF
            <div class="card">
                <h3>$name</h3>
                <p>状态: <span class="$( [ "$status" = "Up" ] && echo "running" || echo "stopped" )">$status</span></p>
                <p>端口: $ports</p>
                <p>CPU: $(docker stats $name --no-stream --format "{{.CPUPerc}}")</p>
                <p>内存: $(docker stats $name --no-stream --format "{{.MemPerc}}")</p>
            </div>
EOF
    done
    cat >> /tmp/dashboard.html <<EOF
        </div>
    </div>
</body>
</html>
EOF
}
# 启动Web服务器
start_web_server() {
    # 使用Python内置HTTP服务器
    cd /tmp
    python3 -m http.server 8080 &
    echo "监控面板: http://localhost:8080/dashboard.html"
}
# 执行
generate_html
start_web_server
# 持续更新
while true; do
    sleep 5
    generate_html
done

完整监控配置脚本

#!/bin/bash
# 容器监控面板完整配置脚本
# 配置参数
CONFIG_DIR="$HOME/.container_monitor"
ALERT_EMAIL="admin@example.com"
SLACK_WEBHOOK="https://hooks.slack.com/services/xxx"
# 初始化配置
init_config() {
    mkdir -p $CONFIG_DIR/{logs,configs}
    # 创建默认配置文件
    cat > $CONFIG_DIR/configs/monitor.conf <<EOF
# 监控配置
MONITOR_INTERVAL=30
CPU_THRESHOLD=80
MEM_THRESHOLD=85
DISK_THRESHOLD=90
RESTART_FAILED_CONTAINERS=true
LOG_RETENTION_DAYS=7
EOF
    echo "配置文件已创建: $CONFIG_DIR/configs/monitor.conf"
}
# 加载配置
load_config() {
    if [ -f "$CONFIG_DIR/configs/monitor.conf" ]; then
        source "$CONFIG_DIR/configs/monitor.conf"
    fi
}
# 显示监控面板
show_dashboard() {
    clear
    echo "======================================"
    echo "      Docker容器监控面板"
    echo "======================================"
    echo ""
    # 系统概览
    echo "系统信息:"
    echo "  主机名: $(hostname)"
    echo "  时间: $(date '+%Y-%m-%d %H:%M:%S')"
    echo "  运行时间: $(uptime -p)"
    echo ""
    # Docker信息
    echo "Docker信息:"
    echo "  总容器数: $(docker ps -aq | wc -l)"
    echo "  运行中: $(docker ps -q | wc -l)"
    echo "  停止: $(docker ps -aq | wc -l) - $(docker ps -q | wc -l) | bc)"
    echo ""
    # 详细容器状态
    echo "容器详情:"
    printf "%-20s %-10s %-10s %-10s %-10s\n" "名称" "状态" "CPU%" "内存%" "重启次数"
    printf "%-20s %-10s %-10s %-10s %-10s\n" "--------------------" "----------" "----------" "----------" "----------"
    for container in $(docker ps -aq); do
        name=$(docker inspect --format='{{.Name}}' $container | sed 's/^\/\(.*\)/\1/')
        status=$(docker inspect --format='{{.State.Status}}' $container)
        cpu=$(docker stats $container --no-stream --format "{{.CPUPerc}}" 2>/dev/null || echo "N/A")
        mem=$(docker stats $container --no-stream --format "{{.MemPerc}}" 2>/dev/null || echo "N/A")
        restart=$(docker inspect --format='{{.RestartCount}}' $container)
        printf "%-20s %-10s %-10s %-10s %-10s\n" "$name" "$status" "$cpu" "$mem" "$restart"
    done
}
# 自动修复功能
auto_heal() {
    load_config
    if [ "$RESTART_FAILED_CONTAINERS" = "true" ]; then
        for container in $(docker ps -aq --filter status=exited --filter status=dead); do
            echo "尝试重启容器: $container"
            docker restart $container
            log_event "INFO" "自动重启容器: $container"
        done
    fi
}
# 日志清理
cleanup_logs() {
    load_config
    find $CONFIG_DIR/logs -name "*.log" -mtime +$LOG_RETENTION_DAYS -delete
    echo "日志清理完成"
}
# 主函数
main() {
    case "$1" in
        start)
            init_config
            echo "启动监控面板..."
            while true; do
                show_dashboard
                auto_heal
                sleep $MONITOR_INTERVAL
            done
            ;;
        stop)
            echo "停止监控面板"
            pkill -f "container_monitor.sh"
            ;;
        status)
            show_dashboard
            ;;
        config)
            echo "当前配置:"
            cat $CONFIG_DIR/configs/monitor.conf
            ;;
        clean)
            cleanup_logs
            ;;
        *)
            echo "用法: $0 {start|stop|status|config|clean}"
            ;;
    esac
}
# 执行
main "$@"

使用说明

安装和运行

# 赋予执行权限
chmod +x container_monitor.sh
# 启动监控
./container_monitor.sh start
# 查看状态
./container_monitor.sh status
# 修改配置
./container_monitor.sh config

配置告警

# 配置告警阈值
cat > /etc/docker/daemon.json <<EOF
{
  "live-restore": true,
  "log-driver": "json-file",
  "log-opts": {
    "max-size": "10m",
    "max-file": "3"
  }
}
EOF
# 重启Docker服务
systemctl restart docker

这个监控面板提供了完整的容器监控解决方案,包括实时监控、告警通知、自动恢复等功能。