[#41] 优化gpu bundle构建优化
This commit is contained in:
1
src/bundle/gpu-node-bundle/.gitignore
vendored
Normal file
1
src/bundle/gpu-node-bundle/.gitignore
vendored
Normal file
@@ -0,0 +1 @@
|
||||
.build*/
|
||||
43
src/bundle/gpu-node-bundle/Dockerfile
Normal file
43
src/bundle/gpu-node-bundle/Dockerfile
Normal file
@@ -0,0 +1,43 @@
|
||||
ARG CUDA_VER=12.2.2
|
||||
FROM nvidia/cuda:${CUDA_VER}-runtime-ubuntu22.04
|
||||
|
||||
ARG CLIENT_VER=0.0.0
|
||||
ARG BUNDLE_DATE=00000000
|
||||
|
||||
LABEL org.opencontainers.image.title="argus-sys-metric-test-node-bundle-gpu" \
|
||||
org.opencontainers.image.description="GPU node bundle with embedded Argus client artifact" \
|
||||
org.opencontainers.image.version="${CLIENT_VER}" \
|
||||
org.opencontainers.image.revision_date="${BUNDLE_DATE}" \
|
||||
maintainer="Argus"
|
||||
|
||||
ENV DEBIAN_FRONTEND=noninteractive \
|
||||
TZ=Asia/Shanghai \
|
||||
ARGUS_LOGS_WORLD_WRITABLE=1 \
|
||||
ES_HOST=es.log.argus.com \
|
||||
ES_PORT=9200 \
|
||||
CLUSTER=local \
|
||||
RACK=dev
|
||||
|
||||
RUN set -eux; \
|
||||
apt-get update; \
|
||||
apt-get install -y --no-install-recommends \
|
||||
ca-certificates curl wget iproute2 iputils-ping net-tools jq tzdata cron procps vim less \
|
||||
tar gzip; \
|
||||
rm -rf /var/lib/apt/lists/*; \
|
||||
ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
|
||||
|
||||
WORKDIR /
|
||||
|
||||
# Expect staged build context to provide these directories/files
|
||||
COPY bundle/ /bundle/
|
||||
COPY node-bootstrap.sh /usr/local/bin/node-bootstrap.sh
|
||||
COPY private/start-fluent-bit.sh /private/start-fluent-bit.sh
|
||||
COPY private/etc /private/etc
|
||||
COPY private/packages /private/packages
|
||||
|
||||
RUN chmod +x /usr/local/bin/node-bootstrap.sh /private/start-fluent-bit.sh || true; \
|
||||
mkdir -p /logs/train /logs/infer /buffers /opt/argus-metric; \
|
||||
chmod 1777 /logs/train /logs/infer || true; \
|
||||
chmod 770 /buffers || true
|
||||
|
||||
ENTRYPOINT ["/usr/local/bin/node-bootstrap.sh"]
|
||||
127
src/bundle/gpu-node-bundle/node-bootstrap.sh
Normal file
127
src/bundle/gpu-node-bundle/node-bootstrap.sh
Normal file
@@ -0,0 +1,127 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
echo "[BOOT] GPU node bundle starting"
|
||||
|
||||
INSTALL_ROOT="/opt/argus-metric"
|
||||
BUNDLE_DIR="/bundle"
|
||||
STATE_DIR_BASE="/private/argus/agent"
|
||||
|
||||
mkdir -p "$INSTALL_ROOT" "$STATE_DIR_BASE" /logs/train /logs/infer /buffers || true
|
||||
|
||||
# Ensure world-writable logs dir with sticky bit (align with deployment_new policy)
|
||||
if [[ "${ARGUS_LOGS_WORLD_WRITABLE:-1}" == "1" ]]; then
|
||||
chmod 1777 /logs/train /logs/infer || true
|
||||
else
|
||||
chmod 755 /logs/train /logs/infer || true
|
||||
fi
|
||||
chmod 770 /buffers || true
|
||||
|
||||
installed_ok=0
|
||||
|
||||
# 1) already installed?
|
||||
if [[ -L "$INSTALL_ROOT/current" && -d "$INSTALL_ROOT/current" ]]; then
|
||||
echo "[BOOT] client already installed at $INSTALL_ROOT/current"
|
||||
else
|
||||
# 2) try local bundle first (argus-metric_*.tar.gz)
|
||||
tarball=$(ls -1 "$BUNDLE_DIR"/argus-metric_*.tar.gz 2>/dev/null | head -1 || true)
|
||||
if [[ -n "${tarball:-}" ]]; then
|
||||
echo "[BOOT] installing from local bundle: $(basename "$tarball")"
|
||||
tmp=$(mktemp -d)
|
||||
tar -xzf "$tarball" -C "$tmp"
|
||||
# locate root containing version.json
|
||||
root="$tmp"
|
||||
if [[ ! -f "$root/version.json" ]]; then
|
||||
sub=$(find "$tmp" -mindepth 1 -maxdepth 1 -type d | head -n1 || true)
|
||||
[[ -n "$sub" && -f "$sub/version.json" ]] && root="$sub"
|
||||
fi
|
||||
if [[ ! -f "$root/version.json" ]]; then
|
||||
echo "[BOOT][WARN] version.json not found in bundle; fallback to FTP"
|
||||
else
|
||||
ver=$(sed -n 's/.*"version"\s*:\s*"\([^"]\+\)".*/\1/p' "$root/version.json" | head -n1)
|
||||
if [[ -z "$ver" ]]; then
|
||||
echo "[BOOT][WARN] failed to parse version from version.json; fallback to FTP"
|
||||
else
|
||||
target_root="$INSTALL_ROOT"
|
||||
version_dir="$target_root/versions/$ver"
|
||||
mkdir -p "$version_dir"
|
||||
shopt -s dotglob
|
||||
mv "$root"/* "$version_dir/" 2>/dev/null || true
|
||||
shopt -u dotglob
|
||||
if [[ -f "$version_dir/install.sh" ]]; then
|
||||
chmod +x "$version_dir/install.sh" 2>/dev/null || true
|
||||
(
|
||||
export AUTO_START_DCGM="${AUTO_START_DCGM:-1}"
|
||||
export DCGM_EXPORTER_DISABLE_PROFILING="${DCGM_EXPORTER_DISABLE_PROFILING:-1}"
|
||||
export DCGM_EXPORTER_LISTEN="${DCGM_EXPORTER_LISTEN:-:9400}"
|
||||
cd "$version_dir" && ./install.sh "$version_dir"
|
||||
)
|
||||
echo "$ver" > "$target_root/LATEST_VERSION" 2>/dev/null || true
|
||||
ln -sfn "$version_dir" "$target_root/current" 2>/dev/null || true
|
||||
if [[ -L "$target_root/current" && -d "$target_root/current" ]]; then
|
||||
installed_ok=1
|
||||
echo "[BOOT] local bundle install OK: version=$ver"
|
||||
else
|
||||
echo "[BOOT][WARN] current symlink not present after install; will rely on healthcheck to confirm"
|
||||
fi
|
||||
else
|
||||
echo "[BOOT][WARN] install.sh missing under $version_dir; fallback to FTP"
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
|
||||
# 3) fallback: use FTP setup if not installed
|
||||
if [[ ! -L "$INSTALL_ROOT/current" && "$installed_ok" -eq 0 ]]; then
|
||||
echo "[BOOT] fallback to FTP setup"
|
||||
if [[ -z "${FTPIP:-}" || -z "${FTP_USER:-}" || -z "${FTP_PASSWORD:-}" ]]; then
|
||||
echo "[BOOT][ERROR] FTP variables not set (FTPIP/FTP_USER/FTP_PASSWORD)" >&2
|
||||
exit 1
|
||||
fi
|
||||
curl -u "$FTP_USER:$FTP_PASSWORD" -fsSL "ftp://$FTPIP:21/setup.sh" -o /tmp/setup.sh
|
||||
chmod +x /tmp/setup.sh
|
||||
/tmp/setup.sh --server "$FTPIP" --user "$FTP_USER" --password "$FTP_PASSWORD" --port 21
|
||||
fi
|
||||
fi
|
||||
|
||||
# 4) ensure argus-agent is running (best-effort)
|
||||
if ! pgrep -x argus-agent >/dev/null 2>&1; then
|
||||
echo "[BOOT] starting argus-agent (not detected)"
|
||||
setsid /usr/local/bin/argus-agent >/var/log/argus-agent.log 2>&1 < /dev/null &
|
||||
fi
|
||||
|
||||
# 5) post-install selfcheck (run once) and state
|
||||
# prefer current version dir; fallback to first version under /opt/argus-metric/versions
|
||||
ver_dir=""
|
||||
if [[ -L "$INSTALL_ROOT/current" ]]; then
|
||||
ver_dir="$(readlink -f "$INSTALL_ROOT/current" 2>/dev/null || true)"
|
||||
fi
|
||||
if [[ -z "$ver_dir" ]]; then
|
||||
# pick the latest by name (semver-like); best-effort
|
||||
ver_dir="$(ls -d "$INSTALL_ROOT"/versions/* 2>/dev/null | sort -V | tail -n1 || true)"
|
||||
fi
|
||||
|
||||
if [[ -n "$ver_dir" && -x "$ver_dir/check_health.sh" ]]; then
|
||||
echo "[BOOT] running initial health check: $ver_dir/check_health.sh"
|
||||
if "$ver_dir/check_health.sh" >> "$ver_dir/.health_check.init.log" 2>&1; then
|
||||
echo "[BOOT] initial health check completed (see $ver_dir/.health_check.init.log)"
|
||||
else
|
||||
echo "[BOOT][WARN] initial health check reported issues (see $ver_dir/.health_check.init.log)"
|
||||
fi
|
||||
else
|
||||
echo "[BOOT][WARN] initial health check skipped (script missing: $ver_dir/check_health.sh)"
|
||||
fi
|
||||
|
||||
host="$(hostname)"
|
||||
state_dir="$STATE_DIR_BASE/${host}"
|
||||
mkdir -p "$state_dir" 2>/dev/null || true
|
||||
for i in {1..60}; do
|
||||
if [[ -s "$state_dir/node.json" ]]; then
|
||||
echo "[BOOT] node state present: $state_dir/node.json"
|
||||
break
|
||||
fi
|
||||
sleep 2
|
||||
done
|
||||
|
||||
echo "[BOOT] ready; entering sleep"
|
||||
exec sleep infinity
|
||||
Reference in New Issue
Block a user