58 lines
3.0 KiB
Bash
58 lines
3.0 KiB
Bash
#!/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; [[ $ok -eq 1 ]]; }
|
||
require docker docker compose nvidia-smi
|
||
|
||
[[ -f "$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
|
||
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" ${BINDIP:+--dns "$BINDIP"} 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
|
||
|
||
# 容器内连通性检查:BINDIP 与 FTPIP 可达
|
||
ping_ok(){ docker exec argus-net-warmup sh -lc "ping -c 1 -W 2 $1 >/dev/null 2>&1"; }
|
||
if [[ -n "${BINDIP:-}" ]]; then
|
||
if ping_ok "$BINDIP"; then info "warmup 内可达 BINDIP=$BINDIP"; else err "容器内无法 ping 通 BINDIP=$BINDIP"; exit 1; fi
|
||
fi
|
||
if [[ -n "${FTPIP:-}" ]]; then
|
||
if ping_ok "$FTPIP"; then info "warmup 内可达 FTPIP=$FTPIP"; else err "容器内无法 ping 通 FTPIP=$FTPIP"; exit 1; fi
|
||
fi
|
||
|
||
# 导入 GPU bundle 镜像
|
||
IMG_TGZ=$(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 "$tmp"
|
||
|
||
# 确保日志目录存在(宿主侧,用于映射 /logs/infer 与 /logs/train)
|
||
mkdir -p "$PKG_ROOT/logs/infer" "$PKG_ROOT/logs/train"
|
||
info "日志目录已准备: logs/infer logs/train"
|
||
|
||
# 启动 compose 并跟踪日志
|
||
info "启动 GPU 节点 (docker compose up -d)"
|
||
docker compose --env-file "$ENV_FILE" -f "$COMPOSE_FILE" up -d
|
||
docker compose --env-file "$ENV_FILE" -f "$COMPOSE_FILE" ps
|
||
info "跟踪节点容器日志(按 Ctrl+C 退出)"
|
||
docker logs -f argus-metric-gpu-node-swarm || true
|