[#47] 增加cpu bundle镜像构建

This commit is contained in:
2025-11-14 16:43:34 +08:00
parent b402fdf960
commit 69e7a3e2b8
8 changed files with 434 additions and 9 deletions

1
src/bundle/cpu-node-bundle/.gitignore vendored Normal file
View File

@@ -0,0 +1 @@
.build*/

View File

@@ -0,0 +1,33 @@
FROM ubuntu:22.04
ARG ARGUS_BUILD_UID=2133
ARG ARGUS_BUILD_GID=2015
ENV DEBIAN_FRONTEND=noninteractive \
TZ=Asia/Shanghai \
ARGUS_LOGS_WORLD_WRITABLE=1
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 supervisor vim less tar gzip python3; \
rm -rf /var/lib/apt/lists/*; \
ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
WORKDIR /
# Offline fluent-bit assets and bundle tarball are staged by the build script
COPY node-bootstrap.sh /usr/local/bin/node-bootstrap.sh
COPY private/start-fluent-bit.sh /private/start-fluent-bit.sh
COPY private/etc /private/etc
COPY private/packages /private/packages
COPY bundle/ /bundle/
RUN chmod +x /usr/local/bin/node-bootstrap.sh /private/start-fluent-bit.sh || true; \
mkdir -p /logs/train /logs/infer /buffers /opt/argus-metric; \
if [ "${ARGUS_LOGS_WORLD_WRITABLE}" = "1" ]; then chmod 1777 /logs/train /logs/infer || true; else chmod 755 /logs/train /logs/infer || true; fi; \
chmod 770 /buffers || true
ENTRYPOINT ["/usr/local/bin/node-bootstrap.sh"]

View File

@@ -0,0 +1,124 @@
#!/usr/bin/env bash
set -euo pipefail
echo "[BOOT] CPU 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="0" # N/A on CPU
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 and state
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
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

View File

@@ -1,5 +0,0 @@
{
"commit": "5b85c4c2fcf5d32d4f68aaef345c53096359b2f1",
"database": "ok",
"version": "11.1.0"
}

View File

@@ -1 +1 @@
{"status":"success","data":{"activeTargets":[{"discoveredLabels":{"__address__":"10.0.1.13:9400","__meta_filepath":"/private/argus/metric/prometheus/targets/dcgm_exporter.json","__metrics_path__":"/metrics","__scheme__":"http","__scrape_interval__":"15s","__scrape_timeout__":"10s","hostname":"swarm-metric-node-001","instance":"dcgm-exporter-A1","ip":"10.0.1.13","job":"dcgm","node_id":"A1","user_id":"yuyr"},"labels":{"hostname":"swarm-metric-node-001","instance":"dcgm-exporter-A1","ip":"10.0.1.13","job":"dcgm","node_id":"A1","user_id":"yuyr"},"scrapePool":"dcgm","scrapeUrl":"http://10.0.1.13:9400/metrics","globalUrl":"http://10.0.1.13:9400/metrics","lastError":"","lastScrape":"2025-11-06T17:13:58.44079249+08:00","lastScrapeDuration":0.001229132,"health":"up","scrapeInterval":"15s","scrapeTimeout":"10s"},{"discoveredLabels":{"__address__":"10.0.1.13:9100","__meta_filepath":"/private/argus/metric/prometheus/targets/node_exporter.json","__metrics_path__":"/metrics","__scheme__":"http","__scrape_interval__":"15s","__scrape_timeout__":"10s","hostname":"swarm-metric-node-001","instance":"node-exporter-A1","ip":"10.0.1.13","job":"node","node_id":"A1","user_id":"yuyr"},"labels":{"hostname":"swarm-metric-node-001","instance":"node-exporter-A1","ip":"10.0.1.13","job":"node","node_id":"A1","user_id":"yuyr"},"scrapePool":"node","scrapeUrl":"http://10.0.1.13:9100/metrics","globalUrl":"http://10.0.1.13:9100/metrics","lastError":"","lastScrape":"2025-11-06T17:13:54.277705211+08:00","lastScrapeDuration":0.024348657,"health":"up","scrapeInterval":"15s","scrapeTimeout":"10s"}],"droppedTargets":[],"droppedTargetCounts":{"dcgm":0,"node":0}}}
{"status":"success","data":{"activeTargets":[{"discoveredLabels":{"__address__":"10.0.1.13:9400","__meta_filepath":"/private/argus/metric/prometheus/targets/dcgm_exporter.json","__metrics_path__":"/metrics","__scheme__":"http","__scrape_interval__":"15s","__scrape_timeout__":"10s","hostname":"swarm-metric-node-001","instance":"dcgm-exporter-A1","ip":"10.0.1.13","job":"dcgm","node_id":"A1","user_id":"yuyr"},"labels":{"hostname":"swarm-metric-node-001","instance":"dcgm-exporter-A1","ip":"10.0.1.13","job":"dcgm","node_id":"A1","user_id":"yuyr"},"scrapePool":"dcgm","scrapeUrl":"http://10.0.1.13:9400/metrics","globalUrl":"http://10.0.1.13:9400/metrics","lastError":"","lastScrape":"2025-11-14T16:20:36.702023128+08:00","lastScrapeDuration":0.001054193,"health":"up","scrapeInterval":"15s","scrapeTimeout":"10s"},{"discoveredLabels":{"__address__":"10.0.1.13:9100","__meta_filepath":"/private/argus/metric/prometheus/targets/node_exporter.json","__metrics_path__":"/metrics","__scheme__":"http","__scrape_interval__":"15s","__scrape_timeout__":"10s","hostname":"swarm-metric-node-001","instance":"node-exporter-A1","ip":"10.0.1.13","job":"node","node_id":"A1","user_id":"yuyr"},"labels":{"hostname":"swarm-metric-node-001","instance":"node-exporter-A1","ip":"10.0.1.13","job":"node","node_id":"A1","user_id":"yuyr"},"scrapePool":"node","scrapeUrl":"http://10.0.1.13:9100/metrics","globalUrl":"http://10.0.1.13:9100/metrics","lastError":"","lastScrape":"2025-11-14T16:20:34.338081675+08:00","lastScrapeDuration":0.019183536,"health":"up","scrapeInterval":"15s","scrapeTimeout":"10s"}],"droppedTargets":[],"droppedTargetCounts":{"dcgm":0,"node":0}}}

View File

@@ -1 +0,0 @@
{"status":"success","data":{"activeTargets":[{"discoveredLabels":{"__address__":"10.0.1.15:9400","__meta_filepath":"/private/argus/metric/prometheus/targets/dcgm_exporter.json","__metrics_path__":"/metrics","__scheme__":"http","__scrape_interval__":"15s","__scrape_timeout__":"10s","hostname":"swarm-metric-node-001","instance":"dcgm-exporter-A1","ip":"10.0.1.15","job":"dcgm","node_id":"A1","user_id":"yuyr"},"labels":{"hostname":"swarm-metric-node-001","instance":"dcgm-exporter-A1","ip":"10.0.1.15","job":"dcgm","node_id":"A1","user_id":"yuyr"},"scrapePool":"dcgm","scrapeUrl":"http://10.0.1.15:9400/metrics","globalUrl":"http://10.0.1.15:9400/metrics","lastError":"","lastScrape":"2025-11-06T15:47:37.200098366+08:00","lastScrapeDuration":0.001361528,"health":"up","scrapeInterval":"15s","scrapeTimeout":"10s"},{"discoveredLabels":{"__address__":"10.0.1.15:9100","__meta_filepath":"/private/argus/metric/prometheus/targets/node_exporter.json","__metrics_path__":"/metrics","__scheme__":"http","__scrape_interval__":"15s","__scrape_timeout__":"10s","hostname":"swarm-metric-node-001","instance":"node-exporter-A1","ip":"10.0.1.15","job":"node","node_id":"A1","user_id":"yuyr"},"labels":{"hostname":"swarm-metric-node-001","instance":"node-exporter-A1","ip":"10.0.1.15","job":"node","node_id":"A1","user_id":"yuyr"},"scrapePool":"node","scrapeUrl":"http://10.0.1.15:9100/metrics","globalUrl":"http://10.0.1.15:9100/metrics","lastError":"","lastScrape":"2025-11-06T15:47:40.184367879+08:00","lastScrapeDuration":0.02923333,"health":"up","scrapeInterval":"15s","scrapeTimeout":"10s"}],"droppedTargets":[],"droppedTargetCounts":{"dcgm":0,"node":0}}}