feat(build): reduce build time for ingestion image (#5225)

.github/workflows/metadata-ingestion-slow.yml

@@ -1,51 +0,0 @@
-name: metadata ingestion slow integration tests
-on:
-  push:
-    branches:
-      - master
-    paths-ignore:
-      - "docs/**"
-      - "**.md"
-  pull_request:
-    branches:
-      - master
-    paths:
-      - "**/nifi/**"
-      - "**/nifi.py"
-      - "**/hana/**"
-      - "**/hana.py"
-  release:
-    types: [published, edited]
-
-jobs:
-  metadata-ingestion-slow-integration:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version: ["3.9"]
-    steps:
-      - uses: actions/checkout@v2
-      - uses: actions/setup-python@v2
-        with:
-          python-version: ${{ matrix.python-version }}
-      - name: Install dependencies
-        run: ./metadata-ingestion/scripts/install_deps.sh
-      - name: Run metadata-ingestion slow integration tests
-        run: ./gradlew :metadata-ingestion:testSlowIntegration
-      - uses: actions/upload-artifact@v2
-        if: always()
-        with:
-          name: Test Results (metadata ingestion slow integration tests)
-          path: |
-            **/build/reports/tests/test/**
-            **/build/test-results/test/**
-            **/junit.*.xml
-
-  event-file:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Upload
-        uses: actions/upload-artifact@v2
-        with:
-          name: Event File
-          path: ${{ github.event_path }}

docker/datahub-ingestion/Dockerfile

@@ -1,20 +1,11 @@
 # Defining environment
 ARG APP_ENV=prod
 
-FROM python:3.8 as base
+FROM acryldata/datahub-ingestion-base as base
 # ENV DOCKERIZE_VERSION v0.6.1
 # RUN apk --no-cache add curl tar \
 #     && curl https://repo1.maven.org/maven2/org/eclipse/jetty/jetty-runner/9.4.20.v20190813/jetty-runner-9.4.20.v20190813.jar --output jetty-runner.jar \
 #     && curl -L https://github.com/jwilder/dockerize/releases/download/$DOCKERIZE_VERSION/dockerize-linux-amd64-$DOCKERIZE_VERSION.tar.gz | tar -C /usr/local/bin -xzv
-RUN apt-get update && apt-get install -y \
-        jq \
-        librdkafka-dev \
-        python3-ldap \
-        libldap2-dev \
-        libsasl2-dev \
-        libsasl2-modules \
-        ldap-utils \
-    && python -m pip install --upgrade pip wheel setuptools==57.5.0
 
 
 FROM openjdk:8 as prod-build
@@ -29,6 +20,7 @@ RUN cd /datahub-src/metadata-ingestion && \
 
 FROM base as prod-install
 COPY --from=prod-codegen /datahub-src/metadata-ingestion /datahub-ingestion
+COPY --from=prod-codegen /root/.cache/pip /root/.cache/pip
 ARG RELEASE_VERSION
 RUN cd /datahub-ingestion && \
     sed -i.bak "s/__version__ = \"0.0.0.dev0\"/__version__ = \"$RELEASE_VERSION\"/" src/datahub/__init__.py && \