fix(deploy): keep BuildKit cache and use Huawei mirrors for API images
Independent Staging Quality Gate / validate (push) Successful in 10m36s
Independent Staging Quality Gate / publish (push) Successful in 7m7s

Gitea run 2828 validated, then publish hit the 60-minute deadline while
Aliyun apt/pip crawled at about 22 kB/s after a 72h cache prune on a
runner with 677 GiB free. Skip BuildKit prune when disk is above the
minimum, split API apt/pip layers, and point apt/pypi at Huawei Cloud.
This commit is contained in:
jesse-ux
2026-09-21 10:56:38 +08:00
parent 27a6c39b94
commit 0c3c9d6b42
5 changed files with 63 additions and 21 deletions
+7 -4
View File
@@ -2,15 +2,18 @@ FROM swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/library/python:3.12-slim
ENV PYTHONUNBUFFERED=1 \
PIP_NO_CACHE_DIR=1 \
PIP_INDEX_URL=https://mirrors.aliyun.com/pypi/simple/ \
PIP_INDEX_URL=https://mirrors.huaweicloud.com/repository/pypi/simple/ \
PIP_DEFAULT_TIMEOUT=60
WORKDIR /app
COPY requirements.txt deploy/patch_vedastro_update_check.py ./
RUN sed -i 's|http://deb.debian.org|https://mirrors.aliyun.com|g' /etc/apt/sources.list.d/debian.sources \
# Apt packages are their own layer so a later pip timeout can reuse them.
# Huawei mirrors share the SWR path already used for the base image; Aliyun
# debian/pypi at ~22 kB/s cannot finish this RUN inside the 60-minute publish job.
RUN sed -i 's|http://deb.debian.org|https://mirrors.huaweicloud.com|g' /etc/apt/sources.list.d/debian.sources \
&& apt-get -o Acquire::Retries=3 -o Acquire::http::Timeout=30 -o Acquire::https::Timeout=30 update \
&& apt-get install -y --no-install-recommends build-essential nodejs \
&& python -m pip install -r requirements.txt \
&& apt-get install -y --no-install-recommends build-essential nodejs
RUN python -m pip install -r requirements.txt \
&& python patch_vedastro_update_check.py \
&& apt-get purge -y --auto-remove build-essential \
&& rm -rf /var/lib/apt/lists/*
+20 -14
View File
@@ -66,20 +66,26 @@ if [ -n "$STALE_IMAGES" ]; then
printf '%s\n' "$STALE_IMAGES" | xargs -r docker image rm || true
fi
# BuildKit layer cache is what lets the publish job reuse the Dockerfile
# `npm ci` layer instead of rebuilding it from scratch behind the mirror (a
# 7-minute image build versus 47). `docker image prune --force` above removes
# only dangling images; BuildKit cache records live in the builder store, not
# in dangling images, so nothing before this point touches them. Reclaim them
# in tiers: drop entries nobody has used for 72 hours, re-measure, and escalate
# to `--all` only when the runner is still below the threshold.
docker builder prune --force --filter until=72h
TIERED_GIB="$(free_gib)"
echo "docker root $DOCKER_ROOT has ${TIERED_GIB} GiB free after aged build-cache reclaim"
if [ "$TIERED_GIB" -lt "$MINIMUM_FREE_GIB" ]; then
echo "still below ${MINIMUM_FREE_GIB} GiB; escalating to a full BuildKit cache prune"
docker builder prune --force --all
# BuildKit layer cache is what lets the publish job reuse apt/pip/`npm ci`
# layers instead of rebuilding behind a slow mirror (7-minute image builds
# versus 4760). `docker image prune --force` above removes only dangling
# images; BuildKit cache lives in the builder store. Do not touch it while
# the runner still has at least MINIMUM_FREE_GIB. Aged and full prunes are
# reachable only after re-measuring and finding the disk actually short.
CACHE_GIB="$(free_gib)"
echo "docker root $DOCKER_ROOT has ${CACHE_GIB} GiB free before BuildKit reclaim"
if [ "$CACHE_GIB" -lt "$MINIMUM_FREE_GIB" ]; then
echo "below ${MINIMUM_FREE_GIB} GiB; pruning BuildKit cache unused for 72h"
docker builder prune --force --filter until=72h
TIERED_GIB="$(free_gib)"
echo "docker root $DOCKER_ROOT has ${TIERED_GIB} GiB free after aged build-cache reclaim"
if [ "$TIERED_GIB" -lt "$MINIMUM_FREE_GIB" ]; then
echo "still below ${MINIMUM_FREE_GIB} GiB; escalating to a full BuildKit cache prune"
docker builder prune --force --all
fi
else
echo "keeping BuildKit layer cache; ${CACHE_GIB} GiB free"
TIERED_GIB="$CACHE_GIB"
fi
AFTER_GIB="$(free_gib)"