141 lines
6.0 KiB
Bash
141 lines
6.0 KiB
Bash
#!/usr/bin/env bash
|
||
set -euo pipefail
|
||
|
||
# ARM Client-CPU 配置脚本：
|
||
# - 读取 server 侧生成的 cluster-info.env（包含 SWARM_MANAGER_ADDR / SWARM_JOIN_TOKEN_WORKER）
|
||
# - 加入 Swarm（worker）
|
||
# - 预热 overlay 网络，确保能通过 master.argus.com 访问 server
|
||
# - 生成/更新 compose/.env（填充 Swarm 相关字段，保留人工填写的 AGENT_*、CPU_NODE_HOSTNAME 等）
|
||
|
||
ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||
PKG_ROOT="$ROOT_DIR"
|
||
ENV_EX="$PKG_ROOT/compose/.env.example"
|
||
ENV_OUT="$PKG_ROOT/compose/.env"
|
||
|
||
info(){ echo -e "\033[34m[CONFIG-ARM-CLIENT]\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; [[ $ok -eq 1 ]]; }
|
||
|
||
# Compose 检测：优先 docker compose（v2），回退 docker-compose（v1）
|
||
require_compose(){
|
||
if docker compose version >/dev/null 2>&1; then return 0; fi
|
||
if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
|
||
err "未检测到 Docker Compose，请安装 docker compose v2 或 docker-compose v1"; exit 1
|
||
}
|
||
|
||
require docker curl jq awk sed tar gzip
|
||
require_compose
|
||
|
||
[[ -f "$ENV_EX" ]] || { err "缺少模板文件: $ENV_EX"; exit 1; }
|
||
|
||
# 磁盘空间检查（MB）
|
||
check_disk(){ local p="$1"; local need=5120; local free
|
||
free=$(df -Pm "$p" | awk 'NR==2{print $4+0}')
|
||
if [[ -z "$free" || "$free" -lt "$need" ]]; then err "磁盘空间不足: $p 剩余 ${free:-0}MB (<${need}MB)"; fi
|
||
}
|
||
check_disk "$PKG_ROOT" || true
|
||
check_disk "/var/lib/docker" || true
|
||
|
||
# 导入 cluster-info.env（默认取当前包根，也可用 CLUSTER_INFO 指定路径）
|
||
CI_IN="${CLUSTER_INFO:-$PKG_ROOT/cluster-info.env}"
|
||
NET_NAME="${ARGUS_OVERLAY_NET:-argus-sys-net}"
|
||
|
||
SWARM_AVAILABLE=true
|
||
|
||
if [[ -f "$CI_IN" ]]; then
|
||
info "读取 cluster-info.env: $CI_IN"
|
||
set -a; source "$CI_IN"; set +a
|
||
|
||
# 尝试加入 Swarm（幂等），允许 join-token 为空
|
||
if [[ -n "${SWARM_MANAGER_ADDR:-}" && -n "${SWARM_JOIN_TOKEN_WORKER:-}" ]]; then
|
||
info "尝试加入 Swarm（幂等）：$SWARM_MANAGER_ADDR"
|
||
docker swarm join --token "$SWARM_JOIN_TOKEN_WORKER" "$SWARM_MANAGER_ADDR":2377 >/dev/null 2>&1 || true
|
||
fi
|
||
|
||
# 检查当前节点 Swarm 状态
|
||
if ! docker info 2>/dev/null | grep -q "Swarm: active"; then
|
||
info "检测到当前节点 Swarm 未启用，client_arm 将退回本地 network 模式"
|
||
SWARM_AVAILABLE=false
|
||
fi
|
||
else
|
||
info "未找到 cluster-info.env（$CI_IN），client_arm 将以本地 network 模式运行"
|
||
SWARM_AVAILABLE=false
|
||
fi
|
||
|
||
# 生成/更新 .env（保留人工填写项，不覆盖已有键）
|
||
if [[ ! -f "$ENV_OUT" ]]; then
|
||
cp "$ENV_EX" "$ENV_OUT"
|
||
fi
|
||
|
||
set_kv(){ local k="$1" v="$2"; if grep -q "^${k}=" "$ENV_OUT"; then sed -i -E "s#^${k}=.*#${k}=${v}#" "$ENV_OUT"; else echo "${k}=${v}" >> "$ENV_OUT"; fi }
|
||
|
||
if [[ "$SWARM_AVAILABLE" == true ]]; then
|
||
# ===== Swarm 模式：强依赖 overlay 网络和 DNS alias =====
|
||
# 导入 busybox 并做 overlay 预热与连通性
|
||
if ! docker image inspect busybox:latest >/dev/null 2>&1; then
|
||
if [[ -f "$PKG_ROOT/images/busybox.tar" ]]; then
|
||
info "加载 busybox.tar 以预热 overlay"
|
||
docker load -i "$PKG_ROOT/images/busybox.tar" >/dev/null
|
||
else
|
||
err "缺少 busybox 镜像（包内 images/busybox.tar 或本地 busybox:latest），无法预热 overlay $NET_NAME"; exit 1
|
||
fi
|
||
fi
|
||
|
||
docker rm -f argus-net-warmup >/dev/null 2>&1 || true
|
||
info "启动 warmup 容器加入 overlay: $NET_NAME"
|
||
docker run -d --rm --name argus-net-warmup --network "$NET_NAME" busybox:latest sleep 600 >/dev/null 2>&1 || true
|
||
for i in {1..60}; do docker network inspect "$NET_NAME" >/dev/null 2>&1 && { info "overlay 可见 (t=${i}s)"; break; }; sleep 1; done
|
||
docker network inspect "$NET_NAME" >/dev/null 2>&1 || { err "预热后仍未看到 overlay: $NET_NAME；请确认 server 侧 overlay 已创建且可达"; exit 1; }
|
||
|
||
if ! docker exec argus-net-warmup sh -lc "ping -c 1 -W 2 master.argus.com >/dev/null 2>&1"; then
|
||
err "warmup 容器内无法通过别名访问 master.argus.com；请确认 server compose 已启动并加入 overlay $NET_NAME"
|
||
exit 1
|
||
fi
|
||
info "warmup 容器内可达 master.argus.com（Docker DNS + alias 正常）"
|
||
|
||
# 写入与 Swarm 相关的字段，便于后续诊断
|
||
set_kv SWARM_MANAGER_ADDR "${SWARM_MANAGER_ADDR:-}"
|
||
set_kv SWARM_JOIN_TOKEN_WORKER "${SWARM_JOIN_TOKEN_WORKER:-}"
|
||
set_kv SWARM_JOIN_TOKEN_MANAGER "${SWARM_JOIN_TOKEN_MANAGER:-}"
|
||
|
||
# 若未显式设置 MASTER_ENDPOINT，则默认走 overlay 别名
|
||
if ! grep -q '^MASTER_ENDPOINT=' "$ENV_OUT"; then
|
||
echo "MASTER_ENDPOINT=http://master.argus.com:3000" >> "$ENV_OUT"
|
||
fi
|
||
else
|
||
# ===== 本地 network 退化模式：不依赖 Swarm 和 overlay =====
|
||
if ! docker network inspect "$NET_NAME" >/dev/null 2>&1; then
|
||
info "创建本地 bridge 网络: $NET_NAME（client_arm 退化模式）"
|
||
docker network create "$NET_NAME" >/dev/null
|
||
else
|
||
info "本地网络已存在: $NET_NAME"
|
||
fi
|
||
|
||
# 若未显式设置 MASTER_ENDPOINT，则提示用户后续手动配置
|
||
if ! grep -q '^MASTER_ENDPOINT=' "$ENV_OUT"; then
|
||
echo "MASTER_ENDPOINT=" >> "$ENV_OUT"
|
||
fi
|
||
|
||
ME=$(grep -E '^MASTER_ENDPOINT=' "$ENV_OUT" | head -1 | cut -d= -f2-)
|
||
if [[ -z "$ME" ]]; then
|
||
err "本地 network 模式下必须配置 MASTER_ENDPOINT（示例：http://<Server-IP>:<Port>），请编辑 compose/.env 后重试"
|
||
else
|
||
info "当前为本地 network 模式，metric-cpu-node 将通过 MASTER_ENDPOINT=${ME} 访问 master"
|
||
fi
|
||
fi
|
||
|
||
# 检查用户必须填写的字段
|
||
REQ_VARS=(AGENT_ENV AGENT_USER AGENT_INSTANCE CPU_NODE_HOSTNAME)
|
||
missing=()
|
||
for v in "${REQ_VARS[@]}"; do
|
||
val=$(grep -E "^$v=" "$ENV_OUT" | head -1 | cut -d= -f2-)
|
||
if [[ -z "$val" ]]; then missing+=("$v"); fi
|
||
done
|
||
if [[ ${#missing[@]} -gt 0 ]]; then
|
||
err "以下变量必须在 compose/.env 中填写：${missing[*]}（已保留你现有的内容，不会被覆盖）"
|
||
exit 1
|
||
fi
|
||
|
||
info "已生成 compose/.env；可执行 scripts/install.sh 启动 ARM Client-CPU"
|