yuyr
34cb239bf4
当前部署情况 - h1: 部署server & client - h2: 部署client - 部署2025-11-25 - 部署目录： /home2/argus/server , /home2/argus/client - 部署使用账号：argus 网络拓扑： - h1 作为docker swarm manager - h2 作为worker加入docker swarm - docker swarm 上创建overlay network 访问方式： - 通过ssh到h1服务器，端口转发 20006-20011 端口到笔记本本地； - 门户网址：http://localhost:20006/dashboard 部署截图：    注意事项： - server各容器使用域名作为overlay network上alias别名，实现域名访问，当前版本禁用bind作为域名解析，原因是容器重启后IP变化场景bind机制复杂且不稳定。 - client 构建是内置安装包，容器启动时执行安装流程，后续重启容器跳过安装步骤。 - UID/GID：部署使用 argus账号 uid=2133, gid=2015。 Reviewed-on: #51 Reviewed-by: sundapeng <sundp@mail.zgclab.edu.cn> Reviewed-by: xuxt <xuxt@zgclab.edu.cn> Reviewed-by: huhy <husteryezi@163.com>
138 lines
5.9 KiB
Bash
138 lines
5.9 KiB
Bash
#!/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; [[ $ok -eq 1 ]]; }
|
||
# Compose 检测：优先 docker compose（v2），回退 docker-compose（v1）
|
||
require_compose(){
|
||
if docker compose version >/dev/null 2>&1; then return 0; fi
|
||
if command -v docker-compose >/devnull 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
|
||
err "未检测到 Docker Compose，请安装 docker compose v2 或 docker-compose v1"; exit 1
|
||
}
|
||
require docker curl jq awk sed tar gzip
|
||
require_compose
|
||
|
||
[[ -f "$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="$SMADDR"
|
||
|
||
# Swarm init & overlay
|
||
if ! docker info 2>/dev/null | grep -q "Swarm: active"; then
|
||
[[ -n "${SWARM_MANAGER_ADDR:-}" ]] || { err "SWARM_MANAGER_ADDR 未设置，请在 scripts/config.sh 中配置"; exit 1; }
|
||
info "初始化 Swarm (--advertise-addr $SWARM_MANAGER_ADDR)"
|
||
docker swarm init --advertise-addr "$SWARM_MANAGER_ADDR" >/dev/null 2>&1 || true
|
||
else
|
||
info "Swarm 已激活"
|
||
fi
|
||
NET_NAME="${ARGUS_OVERLAY_NET:-argus-sys-net}"
|
||
if ! docker network inspect "$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: $NET_NAME"
|
||
fi
|
||
|
||
# Load images
|
||
IMAGES_DIR="$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 "$tmp"
|
||
done
|
||
shopt -u nullglob
|
||
|
||
# Compose up
|
||
PROJECT="${COMPOSE_PROJECT_NAME:-argus-server}"
|
||
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
|
||
|
||
# Wait readiness (best-effort)
|
||
code(){ curl -4 -s -o /dev/null -w "%{http_code}" "$1" || echo 000; }
|
||
prom_ok(){ (exec 3<>/dev/tcp/127.0.0.1/${PROMETHEUS_PORT:-9090}) >/dev/null 2>&1 && return 0 || return 1; }
|
||
kb_ok(){ local body; body=$(curl -s "http://127.0.0.1:${KIBANA_PORT:-5601}/api/status" || true); echo "$body" | grep -q '"level"\s*:\s*"available"'; }
|
||
RETRIES=${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=$(code "http://127.0.0.1:${ES_HTTP_PORT:-9200}/_cluster/health")
|
||
e3=000; prom_ok && e3=200
|
||
e4=$(code "http://127.0.0.1:${GRAFANA_PORT:-3000}/api/health")
|
||
e5=$(code "http://127.0.0.1:${ALERTMANAGER_PORT:-9093}/api/v2/status")
|
||
e6=$(kb_ok && echo 200 || echo 000)
|
||
info "[ready] t=$((i*SLEEP))s master=$e1 es=$e2 prom=$e3 graf=$e4 alert=$e5 kibana=$e6"
|
||
[[ "$e1" == 200 ]] && ok=$((ok+1))
|
||
[[ "$e2" == 200 ]] && ok=$((ok+1))
|
||
[[ "$e3" == 200 ]] && ok=$((ok+1))
|
||
[[ "$e4" == 200 ]] && ok=$((ok+1))
|
||
[[ "$e5" == 200 ]] && ok=$((ok+1))
|
||
[[ "$e6" == 200 ]] && ok=$((ok+1))
|
||
if [[ $ok -ge 6 ]]; then break; fi; ok=0; sleep "$SLEEP"
|
||
done
|
||
[[ $ok -ge 6 ]] || err "部分服务未就绪（可稍后重试 selfcheck）"
|
||
|
||
# Swarm join tokens
|
||
TOKEN_WORKER=$(docker swarm join-token -q worker 2>/dev/null || echo "")
|
||
TOKEN_MANAGER=$(docker swarm join-token -q manager 2>/dev/null || echo "")
|
||
|
||
# cluster-info.env（compose 场景下不再依赖 BINDIP/FTPIP）
|
||
CI="$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"
|
||
info "已输出 $CI"
|
||
|
||
# 安装报告
|
||
ts=$(date +%Y%m%d-%H%M%S)
|
||
RPT="$PKG_ROOT/安装报告_${ts}.md"
|
||
{
|
||
echo "# Argus Server 安装报告 (${ts})"
|
||
echo
|
||
echo "## 端口映射"
|
||
echo "- MASTER_PORT=${MASTER_PORT}"
|
||
echo "- ES_HTTP_PORT=${ES_HTTP_PORT}"
|
||
echo "- KIBANA_PORT=${KIBANA_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=${WEB_PROXY_PORT_8085}"
|
||
echo
|
||
echo "## Swarm/Overlay"
|
||
echo "- SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR:-}"
|
||
echo "- NET=${NET_NAME}"
|
||
echo "- JOIN_TOKEN_WORKER=${TOKEN_WORKER:-}"
|
||
echo "- JOIN_TOKEN_MANAGER=${TOKEN_MANAGER:-}"
|
||
echo
|
||
echo "## 健康检查（简要）"
|
||
echo "- master/readyz=$(code http://127.0.0.1:${MASTER_PORT:-32300}/readyz)"
|
||
echo "- es/_cluster/health=$(code http://127.0.0.1:${ES_HTTP_PORT:-9200}/_cluster/health)"
|
||
echo "- grafana/api/health=$(code http://127.0.0.1:${GRAFANA_PORT:-3000}/api/health)"
|
||
echo "- prometheus/tcp=$([[ $(prom_ok; echo $?) == 0 ]] && echo 200 || echo 000)"
|
||
echo "- alertmanager/api/v2/status=$(code http://127.0.0.1:${ALERTMANAGER_PORT:-9093}/api/v2/status)"
|
||
echo "- kibana/api/status=$([[ $(kb_ok; echo $?) == 0 ]] && echo available || echo not-ready)"
|
||
} > "$RPT"
|
||
info "已生成报告: $RPT"
|
||
|
||
info "安装完成。可将 cluster-info.env 分发给 Client-GPU 安装方。"
|
||
docker exec argus-web-proxy nginx -t >/dev/null 2>&1 && docker exec argus-web-proxy nginx -s reload >/dev/null 2>&1 || true
|