yuyr 7430896fab v1.0.0 发布合并回master (#52)
Co-authored-by: sundapeng <sundp@mail.zgclab.edu.cn>
Co-authored-by: xuxt <xuxt@zgclab.edu.cn>
Reviewed-on: #52
2025-11-25 16:00:50 +08:00

73 lines
3.9 KiB
Bash
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

#!/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-GPU]\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; [[ $ok -eq 1 ]]; }
# Compose 检测:优先 docker composev2回退 docker-composev1
require_compose(){
if docker compose version >/dev/null 2>&1; then return 0; fi
if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
err "未检测到 Docker Compose请安装 docker compose v2 或 docker-compose v1"; exit 1
}
require docker nvidia-smi
require_compose
[[ -f "$ENV_FILE" ]] || { err "缺少 compose/.env请先运行 scripts/config.sh"; exit 1; }
info "使用环境文件: $ENV_FILE"
# 预热 overlay当 config 执行很久之前或容器已被清理时warmup 可能不存在)
set -a; source "$ENV_FILE"; set +a
NET_NAME="${ARGUS_OVERLAY_NET:-argus-sys-net}"
info "检查 overlay 网络可见性: $NET_NAME"
if ! docker network inspect "$NET_NAME" >/dev/null 2>&1; then
# 如 Overlay 不可见,尝试用 busybox 预热(仅为确保 worker 节点已加入 overlay
if ! docker image inspect busybox:latest >/dev/null 2>&1; then
if [[ -f "$PKG_ROOT/images/busybox.tar" ]]; then docker load -i "$PKG_ROOT/images/busybox.tar"; else err "缺少 busybox 镜像images/busybox.tar 或本地 busybox:latest"; exit 1; fi
fi
docker rm -f argus-net-warmup >/dev/null 2>&1 || true
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 && break; sleep 1; done
docker network inspect "$NET_NAME" >/dev/null 2>&1 || { err "预热后仍未看到 overlay: $NET_NAME;请确认 manager 已创建并网络可达"; exit 1; }
info "overlay 已可见warmup=argus-net-warmup"
fi
# 若本函数内重新创建了 warmup 容器,同样测试一次 alias 数据通路
if docker ps --format '{{.Names}}' | grep -q '^argus-net-warmup$'; then
if ! docker exec argus-net-warmup sh -lc "ping -c 1 -W 2 master.argus.com >/dev/null 2>&1"; then
err "GPU install 阶段warmup 容器内无法通过别名访问 master.argus.com请检查 overlay $NET_NAME 与 server 状态"
exit 1
fi
info "GPU install 阶段warmup 容器内可达 master.argus.com"
fi
# 导入 GPU bundle 镜像
IMG_TGZ=$(ls -1 "$PKG_ROOT"/images/argus-sys-metric-test-node-bundle-gpu-*.tar.gz 2>/dev/null | head -1 || true)
[[ -n "$IMG_TGZ" ]] || { err "找不到 GPU bundle 镜像 tar.gz"; exit 1; }
info "导入 GPU bundle 镜像: $(basename "$IMG_TGZ")"
tmp=$(mktemp); gunzip -c "$IMG_TGZ" > "$tmp"; docker load -i "$tmp" >/dev/null; rm -f "$tmp"
# 确保日志目录存在(宿主侧,用于映射 /logs/infer 与 /logs/train并赋权 1777粘滞位
mkdir -p "$PKG_ROOT/logs/infer" "$PKG_ROOT/logs/train"
chmod 1777 "$PKG_ROOT/logs/infer" "$PKG_ROOT/logs/train" || true
info "日志目录已准备并赋权 1777: logs/infer logs/train"
stat -c '%a %U:%G %n' "$PKG_ROOT/logs/infer" "$PKG_ROOT/logs/train" 2>/dev/null || true
# 启动 compose 并跟踪日志
PROJECT="${COMPOSE_PROJECT_NAME:-argus-client}"
info "启动 GPU 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 "$COMPOSE_FILE" ps
# 再次校准宿主日志目录权限,避免容器内脚本对 bind mount 权限回退
chmod 1777 "$PKG_ROOT/logs/infer" "$PKG_ROOT/logs/train" || true
stat -c '%a %U:%G %n' "$PKG_ROOT/logs/infer" "$PKG_ROOT/logs/train" 2>/dev/null || true
info "跟踪节点容器日志(按 Ctrl+C 退出)"
docker logs -f argus-metric-gpu-node-swarm || true