[#40] log目录供宿主机其他程序可写

This commit is contained in:
2025-11-12 15:06:37 +08:00
parent df1f519355
commit 06131a268a
4 changed files with 39 additions and 6 deletions

View File

@@ -79,3 +79,9 @@ 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"
# 准备并赋权宿主日志目录(幂等,便于安装前人工检查/预创建)
mkdir -p "$PKG_ROOT/logs/train" "$PKG_ROOT/logs/infer"
chmod 1777 "$PKG_ROOT/logs/train" "$PKG_ROOT/logs/infer" || true
info "日志目录权限(期待 1777,含粘滞位):"
stat -c '%a %U:%G %n' "$PKG_ROOT/logs/train" "$PKG_ROOT/logs/infer" 2>/dev/null || true

View File

@@ -45,13 +45,20 @@ IMG_TGZ=$(ls -1 "$PKG_ROOT"/images/argus-sys-metric-test-node-bundle-gpu-*.tar.g
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 "$tmp"
# 确保日志目录存在(宿主侧,用于映射 /logs/infer 与 /logs/train)
# 确保日志目录存在(宿主侧,用于映射 /logs/infer 与 /logs/train),并赋权 1777(粘滞位)
mkdir -p "$PKG_ROOT/logs/infer" "$PKG_ROOT/logs/train"
info "日志目录已准备: logs/infer logs/train"
chmod 1777 "$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" "$PKG_ROOT/logs/train" 2>/dev/null || true
# 启动 compose 并跟踪日志
info "启动 GPU 节点 (docker compose up -d)"
docker compose --env-file "$ENV_FILE" -f "$COMPOSE_FILE" up -d
docker compose --env-file "$ENV_FILE" -f "$COMPOSE_FILE" ps
# 再次校准宿主日志目录权限,避免容器内脚本对 bind mount 权限回退
chmod 1777 "$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