dev_1.0.0_xuxt 完成web和alert模块开发，以及模块e2e测试 (#21)

Co-authored-by: xiuting.xu <xiutingxt.xu@gmail.com> Reviewed-on: #21 Reviewed-by: huhy <husteryezi@163.com> Reviewed-by: sundapeng <sundp@mail.zgclab.edu.cn> Reviewed-by: yuyr <yuyr@zgclab.edu.cn>
2025-10-14 10:20:45 +08:00
parent c098f1d3ce
commit 8fbe107ac9
89 changed files with 7152 additions and 0 deletions
--- a/src/alert/README.md
+++ b/src/alert/README.md
@@ -0,0 +1,13 @@
+# Alertmanager
+
+## 启动示例
+
+```bash
+docker run -d --name alertmanager \
+  -p 9093:9093 \
+  -v /opt/alertmanager/data:/alertmanager \
+  argus-alert:latest
+```
+
+## 动态配置
+修改alertmanager.yml后，调用`/-/reload`接口可以重新加载配置
--- a/src/alert/alertmanager/build/Dockerfile
+++ b/src/alert/alertmanager/build/Dockerfile
@@ -0,0 +1,86 @@
+# 基于 Ubuntu 24.04
+FROM ubuntu:24.04
+
+# 切换到 root 用户
+USER root
+
+# 安装必要依赖
+RUN apt-get update && \
+    apt-get install -y wget supervisor net-tools inetutils-ping vim ca-certificates passwd && \
+    apt-get clean && rm -rf /var/lib/apt/lists/*
+
+# 设置 Alertmanager 版本
+ARG ALERTMANAGER_VERSION=0.28.1
+
+# 下载并解压 Alertmanager 二进制
+RUN wget https://github.com/prometheus/alertmanager/releases/download/v${ALERTMANAGER_VERSION}/alertmanager-${ALERTMANAGER_VERSION}.linux-amd64.tar.gz && \
+    tar xvf alertmanager-${ALERTMANAGER_VERSION}.linux-amd64.tar.gz && \
+    mv alertmanager-${ALERTMANAGER_VERSION}.linux-amd64 /usr/local/alertmanager && \
+    rm alertmanager-${ALERTMANAGER_VERSION}.linux-amd64.tar.gz
+
+ENV ALERTMANAGER_BASE_PATH=/private/argus/alert/alertmanager
+ENV ARGUS_UID=2133
+ENV ARGUS_GID=2015
+
+RUN mkdir -p /usr/share/alertmanager && \
+    mkdir -p ${ALERTMANAGER_BASE_PATH} && \
+    mkdir -p /private/argus/etc && \
+    rm -rf /alertmanager && \
+    ln -s ${ALERTMANAGER_BASE_PATH} /alertmanager
+
+# 创建 alertmanager 用户（可自定义 UID/GID）
+# 创建 alertmanager 用户组
+RUN groupadd -g ${ARGUS_GID} alertmanager
+
+# 创建 alertmanager 用户并指定组
+RUN useradd -M -s /usr/sbin/nologin -u ${ARGUS_UID} -g ${ARGUS_GID} alertmanager
+
+RUN chown -R alertmanager:alertmanager /usr/share/alertmanager && \
+    chown -R alertmanager:alertmanager /alertmanager && \
+    chown -R alertmanager:alertmanager ${ALERTMANAGER_BASE_PATH} && \
+    chown -R alertmanager:alertmanager /private/argus/etc && \
+    chown -R alertmanager:alertmanager /usr/local/bin
+
+# 配置内网 apt 源 (如果指定了内网选项)
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+        echo "Configuring intranet apt sources..." && \
+        cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
+        echo "deb [trusted=yes] http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
+        echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
+        echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
+    fi
+
+
+# 配置部署时使用的 apt 源
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+    echo "deb [trusted=yes] https://10.92.132.52/mirrors/ubuntu2204/ jammy main" > /etc/apt/sources.list; \
+    fi
+
+# 创建 supervisor 日志目录
+RUN mkdir -p /var/log/supervisor
+
+# 复制 supervisor 配置文件
+COPY src/alert/alertmanager/build/supervisord.conf /etc/supervisor/conf.d/supervisord.conf
+
+# 复制启动脚本
+COPY src/alert/alertmanager/build/start-am-supervised.sh /usr/local/bin/start-am-supervised.sh
+RUN chmod +x /usr/local/bin/start-am-supervised.sh
+
+# 复制 Alertmanager 配置文件
+COPY src/alert/alertmanager/build/alertmanager.yml /etc/alertmanager/alertmanager.yml
+RUN chmod +x /etc/alertmanager/alertmanager.yml
+# COPY src/alert/alertmanager/build/alertmanager.yml ${ALERTMANAGER_BASE_PATH}/alertmanager.yml
+
+# 复制 DNS 监控脚本
+COPY src/alert/alertmanager/build/dns-monitor.sh /usr/local/bin/dns-monitor.sh
+RUN chmod +x /usr/local/bin/dns-monitor.sh
+
+# 保持 root 用户，由 supervisor 控制 user 切换
+USER root
+
+# 暴露端口（Alertmanager 默认端口 9093）
+EXPOSE 9093
+
+# 使用 supervisor 作为入口点
+CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]
+
--- a/src/alert/alertmanager/build/alertmanager.yml
+++ b/src/alert/alertmanager/build/alertmanager.yml
@@ -0,0 +1,19 @@
+global:
+  resolve_timeout: 5m
+
+route:
+  group_by: ['alertname', 'instance']   # 分组：相同 alertname + instance 的告警合并
+  group_wait: 30s        # 第一个告警后，等 30s 看是否有同组告警一起发
+  group_interval: 5m     # 同组告警变化后，至少 5 分钟再发一次
+  repeat_interval: 3h    # 相同告警，3 小时重复提醒一次
+  receiver: 'null'
+
+receivers:
+  - name: 'null'
+
+inhibit_rules:
+  - source_match:
+      severity: 'critical'     # critical 告警存在时
+    target_match:
+      severity: 'warning'      # 抑制相同 instance 的 warning 告警
+    equal: ['instance']
--- a/src/alert/alertmanager/build/dns-monitor.sh
+++ b/src/alert/alertmanager/build/dns-monitor.sh
@@ -0,0 +1,68 @@
+#!/bin/bash
+
+# DNS监控脚本 - 每10秒检查dns.conf是否有变化
+# 如果有变化则执行update-dns.sh脚本
+
+DNS_CONF="/private/argus/etc/dns.conf"
+DNS_BACKUP="/tmp/dns.conf.backup"
+UPDATE_SCRIPT="/private/argus/etc/update-dns.sh"
+LOG_FILE="/var/log/supervisor/dns-monitor.log"
+
+# 确保日志文件存在
+touch "$LOG_FILE"
+
+log_message() {
+    echo "$(date '+%Y-%m-%d %H:%M:%S') [DNS-Monitor] $1" >> "$LOG_FILE"
+}
+
+log_message "DNS监控脚本启动"
+
+while true; do
+    if [ -f "$DNS_CONF" ]; then
+        if [ -f "$DNS_BACKUP" ]; then
+            # 比较文件内容
+            if ! cmp -s "$DNS_CONF" "$DNS_BACKUP"; then
+                log_message "检测到DNS配置变化"
+
+                # 更新备份文件
+                cp "$DNS_CONF" "$DNS_BACKUP"
+
+                # 执行更新脚本
+                if [ -x "$UPDATE_SCRIPT" ]; then
+                    log_message "执行DNS更新脚本: $UPDATE_SCRIPT"
+                    "$UPDATE_SCRIPT" >> "$LOG_FILE" 2>&1
+                    if [ $? -eq 0 ]; then
+                        log_message "DNS更新脚本执行成功"
+                    else
+                        log_message "DNS更新脚本执行失败"
+                    fi
+                else
+                    log_message "警告: 更新脚本不存在或不可执行: $UPDATE_SCRIPT"
+                fi
+            fi
+        else
+
+            # 第一次检测到配置文件，执行更新脚本
+            if [ -x "$UPDATE_SCRIPT" ]; then
+                log_message "执行DNS更新脚本: $UPDATE_SCRIPT"
+                "$UPDATE_SCRIPT" >> "$LOG_FILE" 2>&1
+                if [ $? -eq 0 ]; then
+                    log_message "DNS更新脚本执行成功"
+
+		    # 第一次运行，创建备份并执行更新
+		    cp "$DNS_CONF" "$DNS_BACKUP"
+		    log_message "创建DNS配置备份文件"
+
+                else
+                    log_message "DNS更新脚本执行失败"
+                fi
+            else
+                log_message "警告: 更新脚本不存在或不可执行: $UPDATE_SCRIPT"
+            fi
+        fi
+    else
+        log_message "警告: DNS配置文件不存在: $DNS_CONF"
+    fi
+
+    sleep 10
+done
--- a/src/alert/alertmanager/build/start-am-supervised.sh
+++ b/src/alert/alertmanager/build/start-am-supervised.sh
@@ -0,0 +1,26 @@
+#!/bin/bash
+set -euo pipefail
+
+echo "[INFO] Starting Alertmanager under supervisor..."
+
+ALERTMANAGER_BASE_PATH=${ALERTMANAGER_BASE_PATH:-/private/argus/alert/alertmanager}
+
+echo "[INFO] Alertmanager base path: ${ALERTMANAGER_BASE_PATH}"
+
+# 生成配置文件
+echo "[INFO] Generating Alertmanager configuration file..."
+sed "s|\${ALERTMANAGER_BASE_PATH}|${ALERTMANAGER_BASE_PATH}|g" \
+    /etc/alertmanager/alertmanager.yml > ${ALERTMANAGER_BASE_PATH}/alertmanager.yml
+
+
+# 记录容器 IP 地址
+DOMAIN=alertmanager.alert.argus.com
+IP=$(ifconfig | grep -A 1 eth0 | grep inet | awk '{print $2}')
+echo "current IP: ${IP}"
+echo "${IP}" > /private/argus/etc/${DOMAIN}
+
+
+echo "[INFO] Starting Alertmanager process..."
+
+# 启动 Alertmanager 主进程
+exec /usr/local/alertmanager/alertmanager --config.file=/etc/alertmanager/alertmanager.yml --storage.path=/alertmanager --cluster.listen-address=""
--- a/src/alert/alertmanager/build/supervisord.conf
+++ b/src/alert/alertmanager/build/supervisord.conf
@@ -0,0 +1,39 @@
+[supervisord]
+nodaemon=true
+logfile=/var/log/supervisor/supervisord.log
+pidfile=/var/run/supervisord.pid
+user=root
+
+[program:alertmanager]
+command=/usr/local/bin/start-am-supervised.sh
+user=alertmanager
+stdout_logfile=/var/log/supervisor/alertmanager.log
+stderr_logfile=/var/log/supervisor/alertmanager_error.log
+autorestart=true
+startretries=3
+startsecs=10
+stopwaitsecs=20
+killasgroup=true
+stopasgroup=true
+
+[program:dns-monitor]
+command=/usr/local/bin/dns-monitor.sh
+user=root
+stdout_logfile=/var/log/supervisor/dns-monitor.log
+stderr_logfile=/var/log/supervisor/dns-monitor_error.log
+autorestart=true
+startretries=3
+startsecs=5
+stopwaitsecs=10
+killasgroup=true
+stopasgroup=true
+
+[unix_http_server]
+file=/var/run/supervisor.sock
+chmod=0700
+
+[supervisorctl]
+serverurl=unix:///var/run/supervisor.sock
+
+[rpcinterface:supervisor]
+supervisor.rpcinterface_factory = supervisor.rpcinterface:make_main_rpcinterface
--- a/src/alert/alertmanager/config/rule_files/README.md
+++ b/src/alert/alertmanager/config/rule_files/README.md
@@ -0,0 +1,60 @@
+# 告警配置
+
+> 参考：[自定义Prometheus告警规则](https://yunlzheng.gitbook.io/prometheus-book/parti-prometheus-ji-chu/alert/prometheus-alert-rule)
+
+在Prometheus中配置告警的有两个步骤：
+
+1. 写告警规则文件（rules文件）
+2. 在promethues.yml里加载规则，并配置Alertmanager
+
+## 1. 编写告警规则文件
+告警规则如下：
+```yml
+groups:
+  - name: example-rules
+    interval: 30s  # 每30秒评估一次
+    rules:
+      - alert: InstanceDown
+        expr: up == 0
+        for: 1m
+        labels:
+          severity: critical
+        annotations:
+          summary: "实例 {{ $labels.instance }} 已宕机"
+          description: "{{ $labels.instance }} 在 {{ $labels.job }} 中无响应超过 1 分钟。"
+
+      - alert: HighCpuUsage
+        expr: 100 - (avg by (instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "CPU 使用率过高"
+          description: "实例 {{ $labels.instance }} CPU 使用率超过 80% 持续 5 分钟。"
+```
+
+其中：
+
+- `alert`：告警规则的名称。
+- `expr`：基于PromQL表达式告警触发条件，用于计算是否有时间序列满足该条件。
+- `for`：评估等待时间，可选参数。用于表示只有当触发条件持续一段时间后才发送告警。在等待期间新产生告警的状态为pending。
+- `labels`：自定义标签，允许用户指定要附加到告警上的一组附加标签，可以在Alertmanager中做路由和分组。
+- `annotations`：用于指定一组附加信息，比如用于描述告警详细信息的文字等，annotations的内容在告警产生时会一同作为参数发送到Alertmanager。可以提供告警摘要和详细信息。
+
+## 2. promothues.yml里引用
+在prometheus.yml中加上`rule_files`和`alerting`:
+
+```yml
+global:
+  [ evaluation_interval: <duration> | default = 1m ]
+
+rule_files:
+  [ - <filepath_glob> ... ]
+
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets:
+            - "localhost:9093"   # Alertmanager 地址
+
+```
--- a/src/alert/alertmanager/config/rule_files/example_rules.yml
+++ b/src/alert/alertmanager/config/rule_files/example_rules.yml
@@ -0,0 +1,37 @@
+groups:
+  - name: example-rules
+    interval: 30s  # 每30秒评估一次
+    rules:
+      - alert: InstanceDown
+        expr: up == 0
+        for: 1m
+        labels:
+          severity: critical
+        annotations:
+          summary: "实例 {{ $labels.instance }} 已宕机"
+          description: "{{ $labels.instance }} 在 {{ $labels.job }} 中无响应超过 1 分钟。"
+
+      - alert: HighCpuUsage
+        expr: 100 - (avg by (instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "CPU 使用率过高"
+          description: "实例 {{ $labels.instance }} CPU 使用率超过 80% 持续 5 分钟。"
+      - alert: HighMemoryUsage
+        expr: (node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100 > 80
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "内存使用率过高"
+          description: "实例 {{ $labels.instance }} 内存使用率超过 80% 持续 5 分钟。"
+      - alert: DiskSpaceLow
+        expr: (node_filesystem_size_bytes{fstype!~"tmpfs|overlay"} - node_filesystem_free_bytes{fstype!~"tmpfs|overlay"}) / node_filesystem_size_bytes{fstype!~"tmpfs|overlay"} * 100 > 90
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "磁盘空间不足"
+          description: "实例 {{ $labels.instance }} 磁盘空间不足超过 90% 持续 10 分钟。"
--- a/src/alert/tests/data/alertmanager/alertmanager.yml
+++ b/src/alert/tests/data/alertmanager/alertmanager.yml
@@ -0,0 +1,19 @@
+global:
+  resolve_timeout: 5m
+
+route:
+  group_by: ['alertname', 'instance']   # 分组：相同 alertname + instance 的告警合并
+  group_wait: 30s        # 第一个告警后，等 30s 看是否有同组告警一起发
+  group_interval: 5m     # 同组告警变化后，至少 5 分钟再发一次
+  repeat_interval: 3h    # 相同告警，3 小时重复提醒一次
+  receiver: 'null'
+
+receivers:
+  - name: 'null'
+
+inhibit_rules:
+  - source_match:
+      severity: 'critical'     # critical 告警存在时
+    target_match:
+      severity: 'warning'      # 抑制相同 instance 的 warning 告警
+    equal: ['instance']
--- a/src/alert/tests/data/alertmanager/nflog
+++ b/src/alert/tests/data/alertmanager/nflog
--- a/src/alert/tests/data/alertmanager/silences
+++ b/src/alert/tests/data/alertmanager/silences
--- a/src/alert/tests/data/etc/alertmanager.alert.argus.com
+++ b/src/alert/tests/data/etc/alertmanager.alert.argus.com
@@ -0,0 +1 @@
+172.18.0.2
--- a/src/alert/tests/docker-compose.yml
+++ b/src/alert/tests/docker-compose.yml
@@ -0,0 +1,37 @@
+version: '3.8'
+services:
+  alertmanager:
+    build:
+      context: ../../../
+      dockerfile: src/alert/alertmanager/build/Dockerfile
+      args:
+        ARGUS_UID: ${ARGUS_UID:-2133}
+        ARGUS_GID: ${ARGUS_GID:-2015}
+        USE_INTRANET: ${USE_INTRANET:-false}
+    image: argus-alertmanager:latest
+    container_name: argus-alertmanager
+    environment:
+      - ALERTMANAGER_BASE_PATH=/private/argus/alert/alertmanager
+      - ARGUS_UID=${ARGUS_UID:-2133}
+      - ARGUS_GID=${ARGUS_GID:-2015}
+    ports:
+      - "${ARGUS_PORT:-9093}:9093"
+    volumes:
+      - ${DATA_ROOT:-./data}/alertmanager:/private/argus/alert/alertmanager
+      - ${DATA_ROOT:-./data}/etc:/private/argus/etc
+    networks:
+      - argus-network
+    restart: unless-stopped
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
+networks:
+  argus-network:
+    driver: bridge
+    name: argus-network
+
+volumes:
+  alertmanager_data:
+    driver: local
--- a/src/alert/tests/scripts/01_bootstrap.sh
+++ b/src/alert/tests/scripts/01_bootstrap.sh
@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+set -euo pipefail
+root="$(cd "$(dirname "${BASH_SOURCE[0]}")/../" && pwd)"
+project_root="$(cd "$root/../../.." && pwd)"
+
+source "$project_root/scripts/common/build_user.sh"
+load_build_user
+
+# 创建新的private目录结构 (基于argus目录结构)
+echo "[INFO] Creating private directory structure for supervisor-based containers..."
+mkdir -p "$root/private/argus/alert/alertmanager"
+mkdir -p "$root/private/argus/etc/"
+
+# 设置数据目录权限
+echo "[INFO] Setting permissions for data directories..."
+chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$root/private/argus/alert/alertmanager" 2>/dev/null || true
+chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$root/private/argus/etc" 2>/dev/null || true
+
+echo "[INFO] Supervisor-based containers will manage their own scripts and configurations"
--- a/src/alert/tests/scripts/02_up.sh
+++ b/src/alert/tests/scripts/02_up.sh
@@ -0,0 +1,10 @@
+#!/usr/bin/env bash
+set -euo pipefail
+cd "$(dirname "$0")/.."
+compose_cmd="docker compose"
+if ! $compose_cmd version >/dev/null 2>&1; then
+  if command -v docker-compose >/dev/null 2>&1; then compose_cmd="docker-compose"; else
+    echo "需要 Docker Compose，请安装后重试" >&2; exit 1; fi
+fi
+$compose_cmd -p alert-mvp up -d --remove-orphans
+echo "[OK] 服务已启动：Alertmanager http://localhost:9093"
--- a/src/alert/tests/scripts/03_alertmanager_add_alert.sh
+++ b/src/alert/tests/scripts/03_alertmanager_add_alert.sh
@@ -0,0 +1,106 @@
+#!/bin/bash
+set -euo pipefail
+
+# ==========================================================
+# Alertmanager 测试脚本
+# ==========================================================
+
+ALERTMANAGER_URL="http://localhost:9093"
+TEST_ALERT_NAME_CRITICAL="NodeDown"
+TEST_ALERT_NAME_WARNING="HighCPU"
+TMP_LOG="/tmp/test-alertmanager.log"
+
+# 等待参数
+am_wait_attempts=30
+am_wait_interval=2
+
+GREEN="\033[1;32m"
+RED="\033[1;31m"
+YELLOW="\033[1;33m"
+RESET="\033[0m"
+
+# ==========================================================
+# 函数定义
+# ==========================================================
+
+wait_for_alertmanager() {
+  local attempt=1
+  echo "[INFO] 等待 Alertmanager 启动中..."
+  while (( attempt <= am_wait_attempts )); do
+    if curl -fsS "${ALERTMANAGER_URL}/api/v2/status" >/dev/null 2>&1; then
+      echo -e "${GREEN}[OK] Alertmanager 已就绪 (attempt=${attempt}/${am_wait_attempts})${RESET}"
+      return 0
+    fi
+    echo "[..] Alertmanager 尚未就绪 (${attempt}/${am_wait_attempts})"
+    sleep "${am_wait_interval}"
+    (( attempt++ ))
+  done
+  echo -e "${RED}[ERROR] Alertmanager 在 ${am_wait_attempts} 次尝试后仍未就绪${RESET}"
+  return 1
+}
+
+log_step() {
+  echo -e "${YELLOW}==== $1 ====${RESET}"
+}
+
+# ==========================================================
+# 主流程
+# ==========================================================
+
+log_step "测试 Alertmanager 开始"
+echo "[INFO] Alertmanager 地址: $ALERTMANAGER_URL"
+
+# Step 1: 等待 Alertmanager 启动
+wait_for_alertmanager
+
+# Step 2: 触发一个critical测试告警
+echo "[INFO] 发送critical测试告警..."
+curl -fsS -X POST "${ALERTMANAGER_URL}/api/v2/alerts" \
+  -H "Content-Type: application/json" \
+  -d '[
+    {
+      "labels": {
+        "alertname": "'"${TEST_ALERT_NAME_CRITICAL}"'",
+        "instance": "node-1",
+        "severity": "critical"
+      },
+      "annotations": {
+        "summary": "节点 node-1 宕机"
+      }
+    }
+  ]' \
+  -o "$TMP_LOG"
+
+if [ $? -eq 0 ]; then
+  echo -e "${GREEN}[OK] 已成功发送critical测试告警${RESET}"
+else
+  echo -e "${RED}[ERROR] critical告警发送失败！${RESET}"
+  cat "$TMP_LOG"
+  exit 1
+fi
+
+# Step 3: 触发一个warning测试告警
+echo "[INFO] 发送warning测试告警..."
+curl -fsS -X POST "${ALERTMANAGER_URL}/api/v2/alerts" \
+  -H "Content-Type: application/json" \
+  -d '[
+    {
+      "labels": {
+        "alertname": "'"${TEST_ALERT_NAME_WARNING}"'",
+        "instance": "node-1",
+        "severity": "warning"
+      },
+      "annotations": {
+        "summary": "节点 node-1 CPU 使用率过高"
+      }
+    }
+  ]' \
+  -o "$TMP_LOG"
+
+if [ $? -eq 0 ]; then
+  echo -e "${GREEN}[OK] 已成功发送warning测试告警${RESET}"
+else
+  echo -e "${RED}[ERROR] warning告警发送失败！${RESET}"
+  cat "$TMP_LOG"
+  exit 1
+fi
--- a/src/alert/tests/scripts/04_query_alerts.sh
+++ b/src/alert/tests/scripts/04_query_alerts.sh
@@ -0,0 +1,71 @@
+#!/bin/bash
+set -euo pipefail
+
+# ==========================================================
+# Alertmanager 测试脚本（含启动等待）
+# ==========================================================
+
+ALERTMANAGER_URL="http://localhost:9093"
+TEST_ALERT_NAME_CRITICAL="NodeDown"
+TEST_ALERT_NAME_WARNING="HighCPU"
+TMP_LOG="/tmp/test-alertmanager.log"
+
+# 等待参数
+am_wait_attempts=30
+am_wait_interval=2
+
+GREEN="\033[1;32m"
+RED="\033[1;31m"
+YELLOW="\033[1;33m"
+RESET="\033[0m"
+
+# ==========================================================
+# 函数定义
+# ==========================================================
+
+wait_for_alertmanager() {
+  local attempt=1
+  echo "[INFO] 等待 Alertmanager 启动中..."
+  while (( attempt <= am_wait_attempts )); do
+    if curl -fsS "${ALERTMANAGER_URL}/api/v2/status" >/dev/null 2>&1; then
+      echo -e "${GREEN}[OK] Alertmanager 已就绪 (attempt=${attempt}/${am_wait_attempts})${RESET}"
+      return 0
+    fi
+    echo "[..] Alertmanager 尚未就绪 (${attempt}/${am_wait_attempts})"
+    sleep "${am_wait_interval}"
+    (( attempt++ ))
+  done
+  echo -e "${RED}[ERROR] Alertmanager 在 ${am_wait_attempts} 次尝试后仍未就绪${RESET}"
+  return 1
+}
+
+log_step() {
+  echo -e "${YELLOW}==== $1 ====${RESET}"
+}
+
+# ==========================================================
+# 主流程
+# ==========================================================
+
+log_step "查询 Alertmanager 当前告警列表开始"
+echo "[INFO] Alertmanager 地址: $ALERTMANAGER_URL"
+
+# Step 1: 等待 Alertmanager 启动
+wait_for_alertmanager
+
+# Step 2: 查询当前告警列表
+echo "[INFO] 查询当前告警..."
+sleep 1
+curl -fsS "${ALERTMANAGER_URL}/api/v2/alerts" | jq '.' || {
+  echo -e "${RED}[WARN] 无法解析返回 JSON，请检查 jq 是否安装${RESET}"
+  curl -s "${ALERTMANAGER_URL}/api/v2/alerts"
+}
+
+# Step 3: 检查告警是否包含 NodeDown
+if curl -fsS "${ALERTMANAGER_URL}/api/v2/alerts" | grep -q "${TEST_ALERT_NAME_CRITICAL}"; then
+  echo -e "${GREEN}✅ 测试通过：Alertmanager 已成功接收告警 ${TEST_ALERT_NAME_CRITICAL}${RESET}"
+else
+  echo -e "${RED}❌ 测试失败：未检测到告警 ${TEST_ALERT_NAME_CRITICAL}${RESET}"
+fi
+
+log_step "测试结束"
--- a/src/alert/tests/scripts/05_down.sh
+++ b/src/alert/tests/scripts/05_down.sh
@@ -0,0 +1,21 @@
+#!/usr/bin/env bash
+set -euo pipefail
+cd "$(dirname "$0")/.."
+compose_cmd="docker compose"
+if ! $compose_cmd version >/dev/null 2>&1; then
+  if command -v docker-compose >/dev/null 2>&1; then compose_cmd="docker-compose"; else
+    echo "需要 Docker Compose，请安装后重试" >&2; exit 1; fi
+fi
+$compose_cmd -p alert-mvp down
+echo "[OK] 已停止所有容器"
+
+# 清理private目录内容
+echo "[INFO] 清理private目录内容..."
+cd "$(dirname "$0")/.."
+if [ -d "private" ]; then
+    # 删除private目录及其所有内容
+    rm -rf private
+    echo "[OK] 已清理private目录"
+else
+    echo "[INFO] private目录不存在，无需清理"
+fi
--- a/src/alert/tests/scripts/e2e_test.sh
+++ b/src/alert/tests/scripts/e2e_test.sh
@@ -0,0 +1,105 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+echo "======================================="
+echo "ARGUS Alert System End-to-End Test"
+echo "======================================="
+echo ""
+
+# 记录测试开始时间
+test_start_time=$(date +%s)
+
+# 函数：等待服务就绪
+wait_for_services() {
+    echo "[INFO] Waiting for all services to be ready..."
+    local max_attempts=${SERVICE_WAIT_ATTEMPTS:-120}
+    local attempt=1
+
+    while [ $attempt -le $max_attempts ]; do
+        if curl -fs http://localhost:9093/api/v2/status >/dev/null 2>&1; then
+            echo "[OK] All services are ready!"
+            return 0
+        fi
+        echo "    Waiting for services... ($attempt/$max_attempts)"
+        sleep 5
+        ((attempt++))
+    done
+
+    echo "[ERROR] Services not ready after $max_attempts attempts"
+    return 1
+}
+
+# 函数：显示测试步骤
+show_step() {
+    echo ""
+    echo "🔄 Step $1: $2"
+    echo "----------------------------------------"
+}
+
+# 函数：验证步骤结果
+verify_step() {
+    if [ $? -eq 0 ]; then
+        echo "✅ $1 - SUCCESS"
+    else
+        echo "❌ $1 - FAILED"
+        exit 1
+    fi
+}
+
+# 开始端到端测试
+show_step "1" "Bootstrap - Initialize environment"
+./scripts/01_bootstrap.sh
+verify_step "Bootstrap"
+
+show_step "2" "Startup - Start all services"
+./scripts/02_up.sh
+verify_step "Service startup"
+
+# 等待服务完全就绪
+wait_for_services || exit 1
+
+# 发送告警数据
+show_step "3" "Add alerts - Send test alerts to Alertmanager"
+./scripts/03_alertmanager_add_alert.sh
+verify_step "Send test alerts"
+
+# 查询告警数据
+show_step "4" "Verify data - Query Alertmanager"
+./scripts/04_query_alerts.sh
+verify_step "Data verification"
+
+
+# 检查服务健康状态
+show_step "Health" "Check service health"
+echo "[INFO] Checking service health..."
+
+# 检查 Alertmanager 状态
+if curl -fs "http://localhost:9093/api/v2/status" >/dev/null 2>&1; then
+    am_status="available"
+    echo "✅ Alertmanager status: $am_status"
+else
+    am_status="unavailable"
+    echo "⚠️  Alertmanager status: $am_status"
+fi
+verify_step "Service health check"
+
+# 清理环境
+show_step "5" "Cleanup - Stop all services"
+./scripts/05_down.sh
+verify_step "Service cleanup"
+
+# 计算总测试时间
+test_end_time=$(date +%s)
+total_time=$((test_end_time - test_start_time))
+
+echo ""
+echo "======================================="
+echo "🎉 END-TO-END TEST COMPLETED SUCCESSFULLY!"
+echo "======================================="
+echo "📊 Test Summary:"
+echo "   • Total time: ${total_time}s"
+echo "   • Alertmanager status: $am_status"
+echo "   • All services started and stopped successfully"
+echo ""
+echo "✅ The ARGUS Alert system is working correctly!"
+echo ""