[#43] 区分server&client 不同compose project;修改require compose监测

This commit is contained in:
2025-11-17 12:17:11 +08:00
parent 69e7a3e2b8
commit 5b617f62a8
10 changed files with 83 additions and 15 deletions

View File

@@ -9,7 +9,14 @@ ENV_OUT="$PKG_ROOT/compose/.env"
info(){ echo -e "\033[34m[CONFIG-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 ]]; }
require docker curl jq awk sed tar gzip nvidia-smi
# 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
# 磁盘空间检查(MB)
check_disk(){ local p="$1"; local need=10240; local free

View File

@@ -9,7 +9,14 @@ 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; [[ $ok -eq 1 ]]; }
require docker docker compose nvidia-smi
# Compose 检测:优先 docker compose(v2),回退 docker-compose(v1)
require_compose(){
if docker compose version >/dev/null 2>&1; then return 0; fi
if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
err "未检测到 Docker Compose,请安装 docker compose v2 或 docker-compose v1"; exit 1
}
require docker nvidia-smi
require_compose
[[ -f "$ENV_FILE" ]] || { err "缺少 compose/.env,请先运行 scripts/config.sh"; exit 1; }
info "使用环境文件: $ENV_FILE"
@@ -52,9 +59,10 @@ info "日志目录已准备并赋权 1777: logs/infer logs/train"
stat -c '%a %U:%G %n' "$PKG_ROOT/logs/infer" "$PKG_ROOT/logs/train" 2>/dev/null || true
# 启动 compose 并跟踪日志
info "启动 GPU 节点 (docker compose up -d)"
docker compose --env-file "$ENV_FILE" -f "$COMPOSE_FILE" up -d
docker compose --env-file "$ENV_FILE" -f "$COMPOSE_FILE" ps
PROJECT="${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

View File

@@ -6,11 +6,23 @@ PKG_ROOT="$ROOT_DIR"
ENV_FILE="$PKG_ROOT/compose/.env"
COMPOSE_FILE="$PKG_ROOT/compose/docker-compose.yml"
# load COMPOSE_PROJECT_NAME if provided in compose/.env
if [[ -f "$ENV_FILE" ]]; then set -a; source "$ENV_FILE"; set +a; fi
PROJECT="${COMPOSE_PROJECT_NAME:-argus-client}"
info(){ echo -e "\033[34m[UNINSTALL-GPU]\033[0m $*"; }
err(){ echo -e "\033[31m[ERROR]\033[0m $*" >&2; }
# Compose 检测:优先 docker compose(v2),回退 docker-compose(v1)
require_compose(){
if docker compose version >/dev/null 2>&1; then return 0; fi
if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
err "未检测到 Docker Compose,请安装 docker compose v2 或 docker-compose v1"; exit 1
}
require_compose
if [[ -f "$ENV_FILE" ]]; then
info "stopping compose project"
docker compose --env-file "$ENV_FILE" -f "$COMPOSE_FILE" down --remove-orphans || true
info "stopping compose project (project=$PROJECT)"
docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f "$COMPOSE_FILE" down --remove-orphans || true
else
info "compose/.env not found; attempting to remove container by name"
fi
@@ -22,4 +34,3 @@ docker rm -f argus-net-warmup >/dev/null 2>&1 || true
docker rm -f argus-metric-gpu-node-swarm >/dev/null 2>&1 || true
info "uninstall completed"