Skip to content

build(actions): optimize docker layer caching for bundled-venvs #14945

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 13, 2025
Merged

build(actions): optimize docker layer caching for bundled-venvs #14945

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
82 changes: 41 additions & 41 deletions docker/datahub-actions/Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,10 +126,51 @@ RUN --mount=type=bind,source=./docker/snippets/oracle_instantclient.sh,target=/o
USER datahub
# INLINE-END

# =============================================================================
# PRE-BUILD BUNDLED INGESTION VENVS
# =============================================================================

FROM ingestion-base-slim AS bundled-vEnvs
USER 0

# Set up bundled venv configuration
ARG BUNDLED_VENV_PLUGINS="s3,demo-data"
ARG BUNDLED_CLI_VERSION
ENV DATAHUB_BUNDLED_VENV_PATH=/opt/datahub/venvs
ENV BUNDLED_VENV_PLUGINS=${BUNDLED_VENV_PLUGINS}
ENV BUNDLED_CLI_VERSION=${BUNDLED_CLI_VERSION}

# Create venv directory
RUN mkdir -p $DATAHUB_BUNDLED_VENV_PATH && \
chown -R datahub:datahub $DATAHUB_BUNDLED_VENV_PATH

# Copy the self-contained venv build scripts
COPY --chown=datahub:datahub ./docker/snippets/ingestion/build_bundled_venvs_unified.py /tmp/
COPY --chown=datahub:datahub ./docker/snippets/ingestion/build_bundled_venvs_unified.sh /tmp/

# Make scripts executable
RUN chmod +x /tmp/build_bundled_venvs_unified.sh && \
chmod +x /tmp/build_bundled_venvs_unified.py

USER datahub

# Build bundled venvs using our self-contained script
WORKDIR /tmp
RUN ./build_bundled_venvs_unified.sh

USER datahub

# =============================================================================
# END BUNDLED VENVS SECTION
# =============================================================================

FROM ingestion-base-${APP_ENV} AS final

USER root

ENV DATAHUB_BUNDLED_VENV_PATH=/opt/datahub/venvs
COPY --from=bundled-vEnvs $DATAHUB_BUNDLED_VENV_PATH $DATAHUB_BUNDLED_VENV_PATH

COPY --from=powerman/dockerize:0.24 /usr/local/bin/dockerize /usr/local/bin
COPY --chown=datahub:datahub ./docker/datahub-actions/start.sh /start_datahub_actions.sh
COPY --chown=datahub:datahub ./docker/datahub-actions/readiness-check.sh /readiness-check.sh
Expand Down Expand Up @@ -170,46 +211,5 @@ RUN --mount=type=bind,source=./python-build/version_updater.py,target=/version_u
# really impact image size.
RUN uv pip install -e '/metadata-ingestion/' -e '/datahub-actions/[all]'

# =============================================================================
# PRE-BUILD BUNDLED INGESTION VENVS
# =============================================================================

USER 0

# Set up bundled venv configuration
ARG BUNDLED_VENV_PLUGINS="s3,demo-data"
ARG BUNDLED_CLI_VERSION
ENV DATAHUB_BUNDLED_VENV_PATH=/opt/datahub/venvs
ENV BUNDLED_VENV_PLUGINS=${BUNDLED_VENV_PLUGINS}
ENV BUNDLED_CLI_VERSION=${BUNDLED_CLI_VERSION}

# Create venv directory
RUN mkdir -p $DATAHUB_BUNDLED_VENV_PATH && \
chown -R datahub:datahub $DATAHUB_BUNDLED_VENV_PATH

# Copy the self-contained venv build scripts
COPY --chown=datahub:datahub ./docker/snippets/ingestion/build_bundled_venvs_unified.py /tmp/
COPY --chown=datahub:datahub ./docker/snippets/ingestion/build_bundled_venvs_unified.sh /tmp/

# Make scripts executable
RUN chmod +x /tmp/build_bundled_venvs_unified.sh && \
chmod +x /tmp/build_bundled_venvs_unified.py

USER datahub

# Build bundled venvs using our self-contained script
WORKDIR /tmp
RUN ./build_bundled_venvs_unified.sh

# Remove build scripts to reduce image size
USER 0
RUN rm -rf /tmp/build_bundled_venvs_unified.py /tmp/build_bundled_venvs_unified.sh

USER datahub

# =============================================================================
# END BUNDLED VENVS SECTION
# =============================================================================

ENTRYPOINT [ ]
CMD dockerize -wait ${DATAHUB_GMS_PROTOCOL:-http}://$DATAHUB_GMS_HOST:$DATAHUB_GMS_PORT/health -timeout 240s /start_datahub_actions.sh
Loading