[#50] x86机器使用qemu模拟方式安装部署arm版本安装包,当前未精简版,只有简单的node exporter功能,删减日志,GPU指标功能,仍使用Swarm组网

This commit is contained in:
2025-12-01 15:27:12 +08:00
parent 4c45166b44
commit a6e1bf7fe7
26 changed files with 1875 additions and 20 deletions

View File

@@ -0,0 +1,105 @@
#!/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}"
info "读取 cluster-info.env: $CI_IN"
[[ -f "$CI_IN" ]] || { err "找不到 cluster-info.env(默认当前包根,或设置环境变量 CLUSTER_INFO 指定绝对路径)"; exit 1; }
set -a; source "$CI_IN"; set +a
[[ -n "${SWARM_MANAGER_ADDR:-}" && -n "${SWARM_JOIN_TOKEN_WORKER:-}" ]] || { err "cluster-info.env 缺少 SWARM 信息(SWARM_MANAGER_ADDR/SWARM_JOIN_TOKEN_WORKER)"; exit 1; }
# 加入 Swarm(幂等)
info "加入 Swarm(幂等):$SWARM_MANAGER_ADDR"
docker swarm join --token "$SWARM_JOIN_TOKEN_WORKER" "$SWARM_MANAGER_ADDR":2377 >/dev/null 2>&1 || true
# 导入 busybox 并做 overlay 预热与连通性
NET_NAME="${ARGUS_OVERLAY_NET:-argus-sys-net}"
if ! docker image inspect busybox:latest >/dev/null 2>&1; then
if [[ -f "$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
# 预热容器(worker 侧加入 overlay 以便本地可见)
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; }
# 通过 warmup 容器测试实际数据通路(alias → master)
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 $NET_NAME"
exit 1
fi
info "warmup 容器内可达 master.argus.com(Docker DNS + alias 正常)"
# 生成/更新 .env(保留人工填写项,不覆盖已有键)
if [[ ! -f "$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 }
# 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" >> "$ENV_OUT"
fi
# 检查用户必须填写的字段
REQ_VARS=(AGENT_ENV AGENT_USER AGENT_INSTANCE CPU_NODE_HOSTNAME)
missing=()
for v in "${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"

View File

@@ -0,0 +1,48 @@
#!/usr/bin/env bash
set -euo pipefail
# ARM Client-CPU 安装脚本:
# - 导入 ARM CPU node 镜像
# - 启动 compose 中的 metric-cpu-node 服务
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-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; [[ $ok -eq 1 ]]; }
require_compose(){
if docker compose version >/dev/null 2>&1; then return 0; fi
if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
err "未检测到 Docker Compose,请安装 docker compose v2 或 docker-compose v1"; exit 1
}
require docker
require_compose
[[ -f "$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
# 导入 ARM CPU node 镜像
IMG_TGZ=$(ls -1 "$PKG_ROOT"/images/argus-sys-metric-test-node-arm64-*.tar.gz 2>/dev/null | head -1 || true)
[[ -n "$IMG_TGZ" ]] || { err "找不到 ARM CPU node 镜像 tar.gz(argus-sys-metric-test-node-arm64-*.tar.gz)"; exit 1; }
info "导入 ARM CPU node 镜像: $(basename "$IMG_TGZ")"
tmp=$(mktemp); gunzip -c "$IMG_TGZ" > "$tmp"; docker load -i "$tmp" >/dev/null; rm -f "$tmp"
# 确保 agent 挂载目录存在
mkdir -p "$PKG_ROOT/private/argus/agent"
# 启动 compose
PROJECT="${COMPOSE_PROJECT_NAME:-argus-client-arm}"
info "启动 ARM CPU 节点 (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
info "ARM Client-CPU 安装完成。可通过 docker logs -f argus-metric-cpu-node 查看节点容器日志。"

View File

@@ -0,0 +1,28 @@
#!/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"
if [[ -f "$ENV_FILE" ]]; then
set -a; source "$ENV_FILE"; set +a
fi
PROJECT="${COMPOSE_PROJECT_NAME:-argus-client-arm}"
err(){ echo -e "\033[31m[ERROR]\033[0m $*" >&2; }
require_compose(){
if docker compose version >/dev/null 2>&1; then return 0; fi
if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
err "未检测到 Docker Compose,请安装 docker compose v2 或 docker-compose v1"; exit 1
}
require_compose
echo "[UNINSTALL-ARM-CLIENT] stopping compose (project=$PROJECT)"
docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f "$COMPOSE_FILE" down --remove-orphans || true
echo "[UNINSTALL-ARM-CLIENT] done"