argus/deployment_new/templates/server_arm/scripts/install.sh

#!/usr/bin/env bash
set -euo pipefail

ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
PKG_ROOT="$ROOT_DIR"
ENV_FILE="$PKG_ROOT/compose/.env"
COMPOSE_FILE="$PKG_ROOT/compose/docker-compose.yml"

info(){ echo -e "\033[34m[INSTALL]\033[0m $*"; }
err(){ echo -e "\033[31m[ERROR]\033[0m $*" >&2; }

require(){ local ok=1; for c in "$@"; do command -v "$c" >/dev/null 2>&1 || { err "缺少依赖: $c"; ok=0; }; done; [[ $ok -eq 1 ]]; }

require_compose(){
  if docker compose version >/dev/null 2>&1; then return 0; fi
  if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
  err "未检测到 Docker Compose，请安装 docker compose v2 或 docker-compose v1"; exit 1
}

require docker curl jq awk sed tar gzip
require_compose

[[ -f "$ENV_FILE" ]] || { err "缺少 compose/.env，请先运行 scripts/config.sh"; exit 1; }
info "使用环境文件: $ENV_FILE"
set -a; source "$ENV_FILE"; set +a

# 兼容：若 .env 未包含 SWARM_MANAGER_ADDR，则从已存在的 cluster-info.env 读取以避免写空
SMADDR="${SWARM_MANAGER_ADDR:-}"
CI_FILE="$PKG_ROOT/cluster-info.env"
if [[ -z "$SMADDR" && -f "$CI_FILE" ]]; then
  SMADDR=$(sed -n 's/^SWARM_MANAGER_ADDR=\(.*\)$/\1/p' "$CI_FILE" | head -n1)
fi
SWARM_MANAGER_ADDR="$SMADDR"

NET_NAME="${ARGUS_OVERLAY_NET:-argus-sys-net}"
SWARM_AVAILABLE=true

# Swarm init & overlay（ARM 版优先按生产方式启用 Swarm，但在无法启用时退回本地 bridge）
if ! docker info 2>/dev/null | grep -q "Swarm: active"; then
  if [[ -n "${SWARM_MANAGER_ADDR:-}" ]]; then
    info "Swarm 未激活，尝试初始化 Swarm (--advertise-addr $SWARM_MANAGER_ADDR)"
    if ! docker swarm init --advertise-addr "$SWARM_MANAGER_ADDR" >/dev/null 2>&1; then
      err "Swarm 初始化失败，本次部署将退回本地 bridge 网络: $NET_NAME（仅支持单机测试，不支持 swarm client）"
      SWARM_AVAILABLE=false
    else
      info "Swarm 初始化成功"
    fi
  else
    info "SWARM_MANAGER_ADDR 未设置且 Swarm 未激活，将使用本地 bridge 网络: $NET_NAME（仅支持单机测试）"
    SWARM_AVAILABLE=false
  fi
else
  info "Swarm 已激活"
fi

if [[ "$SWARM_AVAILABLE" == true ]]; then
  if ! docker network inspect "$NET_NAME" >/dev/null 2>&1; then
    info "创建 overlay 网络: $NET_NAME"
    docker network create -d overlay --attachable "$NET_NAME" >/dev/null
  else
    info "overlay 网络已存在: $NET_NAME"
  fi

  # 将 Swarm join token 写入 cluster-info.env，供 ARM client 使用
  TOKEN_WORKER=$(docker swarm join-token -q worker 2>/dev/null || echo "")
  TOKEN_MANAGER=$(docker swarm join-token -q manager 2>/dev/null || echo "")
  CI_OUT="$PKG_ROOT/cluster-info.env"
  info "写入 cluster-info.env (manager/token)"
  {
    echo "SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR:-}"
    echo "SWARM_JOIN_TOKEN_WORKER=${TOKEN_WORKER:-}"
    echo "SWARM_JOIN_TOKEN_MANAGER=${TOKEN_MANAGER:-}"
  } > "$CI_OUT"
else
  # 本机无法启用 Swarm，只维护 SWARM_MANAGER_ADDR，join token 留空
  CI_OUT="$PKG_ROOT/cluster-info.env"
  info "写入 cluster-info.env（Swarm 未启用，仅保存 SWARM_MANAGER_ADDR）"
  {
    echo "SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR:-}"
    echo "SWARM_JOIN_TOKEN_WORKER="
    echo "SWARM_JOIN_TOKEN_MANAGER="
  } > "$CI_OUT"

  if ! docker network inspect "$NET_NAME" >/dev/null 2>&1; then
    info "创建本地 bridge 网络: $NET_NAME"
    docker network create "$NET_NAME" >/dev/null
  else
    info "本地网络已存在: $NET_NAME"
  fi
fi

# 导入镜像
IMAGES_DIR="$PKG_ROOT/images"
shopt -s nullglob
tars=("$IMAGES_DIR"/*.tar.gz)
if [[ ${#tars[@]} -eq 0 ]]; then err "images 目录为空，缺少镜像 tar.gz"; exit 1; fi
total=${#tars[@]}; idx=0
for tgz in "${tars[@]}"; do
  idx=$((idx+1))
  info "导入镜像 ($idx/$total): $(basename "$tgz")"
  tmp=$(mktemp); gunzip -c "$tgz" > "$tmp"; docker load -i "$tmp" >/dev/null; rm -f "$tmp"
done
shopt -u nullglob

# 启动服务
PROJECT="${COMPOSE_PROJECT_NAME:-argus-server-arm}"
info "启动服务栈 (docker compose -p $PROJECT up -d)"
docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f "$COMPOSE_FILE" up -d
docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f "$COMPOSE_FILE" ps

# 简单就绪检查（best-effort，不阻塞安装）
code(){ curl -4 -s -o /dev/null -w "%{http_code}" "$1" || echo 000; }
gf_ok(){ local body; body=$(curl -s "http://127.0.0.1:${GRAFANA_PORT:-3000}/api/health" || true); echo "$body" | grep -q '"database"\s*:\s*"ok"'; }

RETRIES=${RETRIES:-60}; SLEEP=${SLEEP:-5}; ok=0
info "等待基础服务就绪 (<= $((RETRIES*SLEEP))s)"
for i in $(seq 1 "$RETRIES"); do
  e1=$(code "http://127.0.0.1:${MASTER_PORT:-32300}/readyz")
  e2=$(code "http://127.0.0.1:${PROMETHEUS_PORT:-9090}/-/ready")
  e3=$(code "http://127.0.0.1:${ALERTMANAGER_PORT:-9093}/api/v2/status")
  e4=000; gf_ok && e4=200
  info "[ready] t=$((i*SLEEP))s master=$e1 prom=$e2 graf=$e4 alert=$e3"
  [[ "$e1" == 200 ]] && ok=$((ok+1))
  [[ "$e2" == 200 ]] && ok=$((ok+1))
  [[ "$e3" == 200 ]] && ok=$((ok+1))
  [[ "$e4" == 200 ]] && ok=$((ok+1))
  if [[ $ok -ge 4 ]]; then break; fi; ok=0; sleep "$SLEEP"
done
[[ $ok -ge 4 ]] || err "部分服务未就绪（可稍后执行 scripts/selfcheck.sh 进行复查）"

# 安装报告（ARM 精简版）
ts=$(date +%Y%m%d-%H%M%S)
RPT="$PKG_ROOT/安装报告_ARM_${ts}.md"
{
  echo "# Argus ARM Server 安装报告 (${ts})"
  echo
  echo "## 端口映射"
  echo "- MASTER_PORT=${MASTER_PORT}"
  echo "- PROMETHEUS_PORT=${PROMETHEUS_PORT}"
  echo "- GRAFANA_PORT=${GRAFANA_PORT}"
  echo "- ALERTMANAGER_PORT=${ALERTMANAGER_PORT}"
  echo "- WEB_PROXY_PORT_8080=${WEB_PROXY_PORT_8080} ... 8085=${WEB_PROXY_PORT_8085}"
  echo
  echo "## 网络"
  echo "- NET=${NET_NAME}"
  echo "- ARGUS_OVERLAY_NET=${ARGUS_OVERLAY_NET:-argus-sys-net}"
  echo
  echo "## 健康检查（简要）"
  echo "- master/readyz=$(code http://127.0.0.1:${MASTER_PORT:-32300}/readyz)"
  echo "- prometheus/ready=$(code http://127.0.0.1:${PROMETHEUS_PORT:-9090}/-/ready)"
  echo "- grafana/api/health=$(code http://127.0.0.1:${GRAFANA_PORT:-3000}/api/health)"
  echo "- alertmanager/api/v2/status=$(code http://127.0.0.1:${ALERTMANAGER_PORT:-9093}/api/v2/status)"
} > "$RPT"
info "已生成报告: $RPT"

# 刷新 web-proxy 上的 nginx 配置（best-effort）
docker exec argus-web-proxy nginx -t >/dev/null 2>&1 && docker exec argus-web-proxy nginx -s reload >/dev/null 2>&1 || true

info "安装完成。可通过 scripts/status.sh 查看当前服务状态。"