feat: better control of GRPC docker cache (#2070)

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

.github/workflows/generate_grpc_cache.yaml

@@ -0,0 +1,90 @@
+name: 'generate and publish GRPC docker caches'
+
+on:
+- workflow_dispatch
+
+concurrency:
+  group: ci-${{ github.head_ref || github.ref }}-${{ github.repository }}
+  cancel-in-progress: true
+
+jobs:
+  generate_caches:
+    strategy:
+      matrix:
+        include:
+          - grpc-base-image: ubuntu:22.04
+            runs-on: 'ubuntu-latest'
+            platforms: 'linux/amd64'
+    runs-on: ${{matrix.runs-on}}
+    steps:
+      - name: Release space from worker
+        if: matrix.runs-on == 'ubuntu-latest'
+        run: |
+          echo "Listing top largest packages"
+          pkgs=$(dpkg-query -Wf '${Installed-Size}\t${Package}\t${Status}\n' | awk '$NF == "installed"{print $1 "\t" $2}' | sort -nr)
+          head -n 30 <<< "${pkgs}"
+          echo
+          df -h
+          echo
+          sudo apt-get remove -y '^llvm-.*|^libllvm.*' || true
+          sudo apt-get remove --auto-remove android-sdk-platform-tools || true
+          sudo apt-get purge --auto-remove android-sdk-platform-tools || true
+          sudo rm -rf /usr/local/lib/android
+          sudo apt-get remove -y '^dotnet-.*|^aspnetcore-.*' || true
+          sudo rm -rf /usr/share/dotnet
+          sudo apt-get remove -y '^mono-.*' || true
+          sudo apt-get remove -y '^ghc-.*' || true
+          sudo apt-get remove -y '.*jdk.*|.*jre.*' || true
+          sudo apt-get remove -y 'php.*' || true
+          sudo apt-get remove -y hhvm powershell firefox monodoc-manual msbuild || true
+          sudo apt-get remove -y '^google-.*' || true
+          sudo apt-get remove -y azure-cli || true
+          sudo apt-get remove -y '^mongo.*-.*|^postgresql-.*|^mysql-.*|^mssql-.*' || true
+          sudo apt-get remove -y '^gfortran-.*' || true
+          sudo apt-get remove -y microsoft-edge-stable || true
+          sudo apt-get remove -y firefox || true
+          sudo apt-get remove -y powershell || true
+          sudo apt-get remove -y r-base-core || true
+          sudo apt-get autoremove -y
+          sudo apt-get clean
+          echo
+          echo "Listing top largest packages"
+          pkgs=$(dpkg-query -Wf '${Installed-Size}\t${Package}\t${Status}\n' | awk '$NF == "installed"{print $1 "\t" $2}' | sort -nr)
+          head -n 30 <<< "${pkgs}"
+          echo
+          sudo rm -rfv build || true
+          sudo rm -rf /usr/share/dotnet || true
+          sudo rm -rf /opt/ghc || true
+          sudo rm -rf "/usr/local/share/boost" || true
+          sudo rm -rf "$AGENT_TOOLSDIRECTORY" || true
+          df -h
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@master
+        with:
+          platforms: all
+
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@master
+
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Cache GRPC
+        uses: docker/build-push-action@v5
+        with:
+          builder: ${{ steps.buildx.outputs.name }}
+          # The build-args MUST be an EXACT match between the image cache and other workflow steps that want to use that cache.
+          # This means that even the MAKEFLAGS have to be an EXACT match.
+          # If the build-args are not an EXACT match, it will result in a cache miss, which will require GRPC to be built from scratch.
+          build-args: |
+            GRPC_BASE_IMAGE=${{ matrix.grpc-base-image }}
+            MAKEFLAGS=--jobs=4 --output-sync=target
+            GRPC_VERSION=v1.58.0
+          context: .
+          file: ./Dockerfile
+          cache-to: type=gha,ignore-error=true
+          target: grpc
+          platforms: ${{ matrix.platforms }}
+          push: false

.github/workflows/image-pr.yml

@@ -22,6 +22,7 @@ jobs:
       platforms: ${{ matrix.platforms }}
       runs-on: ${{ matrix.runs-on }}
       base-image: ${{ matrix.base-image }}
+      grpc-base-image: ${{ matrix.grpc-base-image }}
       makeflags: ${{ matrix.makeflags }}
     secrets:
       dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
@@ -61,12 +62,14 @@ jobs:
             ffmpeg: 'false'
             image-type: 'extras'
             base-image: "rocm/dev-ubuntu-22.04:6.0-complete"
+            grpc-base-image: "ubuntu:22.04"
             runs-on: 'arc-runner-set'
             makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'sycl_f16'
             platforms: 'linux/amd64'
             tag-latest: 'false'
             base-image: "intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04"
+            grpc-base-image: "ubuntu:22.04"
             tag-suffix: 'sycl-f16-ffmpeg'
             ffmpeg: 'true'
             image-type: 'extras'
@@ -85,6 +88,7 @@ jobs:
       platforms: ${{ matrix.platforms }}
       runs-on: ${{ matrix.runs-on }}
       base-image: ${{ matrix.base-image }}
+      grpc-base-image: ${{ matrix.grpc-base-image }}
       makeflags: ${{ matrix.makeflags }}
     secrets:
       dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
@@ -102,11 +106,12 @@ jobs:
             image-type: 'core'
             runs-on: 'ubuntu-latest'
             base-image: "ubuntu:22.04"
-            makeflags: "--jobs=5 --output-sync=target"
+            makeflags: "--jobs=4 --output-sync=target"
           - build-type: 'sycl_f16'
             platforms: 'linux/amd64'
             tag-latest: 'false'
             base-image: "intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04"
+            grpc-base-image: "ubuntu:22.04"
             tag-suffix: 'sycl-f16-ffmpeg-core'
             ffmpeg: 'true'
             image-type: 'core'
@@ -122,4 +127,4 @@ jobs:
             image-type: 'core'
             runs-on: 'ubuntu-latest'
             base-image: "ubuntu:22.04"
-            makeflags: "--jobs=5 --output-sync=target"
+            makeflags: "--jobs=4 --output-sync=target"

.github/workflows/image.yml

@@ -26,6 +26,7 @@ jobs:
       platforms: ${{ matrix.platforms }}
       runs-on: ${{ matrix.runs-on }}
       base-image: ${{ matrix.base-image }}
+      grpc-base-image: ${{ matrix.grpc-base-image }}
       aio: ${{ matrix.aio }}
       makeflags: ${{ matrix.makeflags }}
       latest-image: ${{ matrix.latest-image }}
@@ -129,6 +130,7 @@ jobs:
             image-type: 'extras'
             aio: "-aio-gpu-hipblas"
             base-image: "rocm/dev-ubuntu-22.04:6.0-complete"
+            grpc-base-image: "ubuntu:22.04"
             latest-image: 'latest-gpu-hipblas'
             latest-image-aio: 'latest-aio-gpu-hipblas'
             runs-on: 'arc-runner-set'
@@ -140,12 +142,14 @@ jobs:
             ffmpeg: 'false'
             image-type: 'extras'
             base-image: "rocm/dev-ubuntu-22.04:6.0-complete"
+            grpc-base-image: "ubuntu:22.04"
             runs-on: 'arc-runner-set'
             makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'sycl_f16'
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             base-image: "intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04"
+            grpc-base-image: "ubuntu:22.04"
             tag-suffix: '-sycl-f16-ffmpeg'
             ffmpeg: 'true'
             image-type: 'extras'
@@ -158,6 +162,7 @@ jobs:
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             base-image: "intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04"
+            grpc-base-image: "ubuntu:22.04"
             tag-suffix: '-sycl-f32-ffmpeg'
             ffmpeg: 'true'
             image-type: 'extras'
@@ -171,6 +176,7 @@ jobs:
             platforms: 'linux/amd64'
             tag-latest: 'false'
             base-image: "intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04"
+            grpc-base-image: "ubuntu:22.04"
             tag-suffix: '-sycl-f16-core'
             ffmpeg: 'false'
             image-type: 'core'
@@ -180,6 +186,7 @@ jobs:
             platforms: 'linux/amd64'
             tag-latest: 'false'
             base-image: "intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04"
+            grpc-base-image: "ubuntu:22.04"
             tag-suffix: '-sycl-f32-core'
             ffmpeg: 'false'
             image-type: 'core'
@@ -189,6 +196,7 @@ jobs:
             platforms: 'linux/amd64'
             tag-latest: 'false'
             base-image: "intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04"
+            grpc-base-image: "ubuntu:22.04"
             tag-suffix: '-sycl-f16-ffmpeg-core'
             ffmpeg: 'true'
             image-type: 'core'
@@ -198,6 +206,7 @@ jobs:
             platforms: 'linux/amd64'
             tag-latest: 'false'
             base-image: "intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04"
+            grpc-base-image: "ubuntu:22.04"
             tag-suffix: '-sycl-f32-ffmpeg-core'
             ffmpeg: 'true'
             image-type: 'core'
@@ -210,6 +219,7 @@ jobs:
             ffmpeg: 'true'
             image-type: 'core'
             base-image: "rocm/dev-ubuntu-22.04:6.0-complete"
+            grpc-base-image: "ubuntu:22.04"
             runs-on: 'arc-runner-set'
             makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'hipblas'
@@ -219,6 +229,7 @@ jobs:
             ffmpeg: 'false'
             image-type: 'core'
             base-image: "rocm/dev-ubuntu-22.04:6.0-complete"
+            grpc-base-image: "ubuntu:22.04"
             runs-on: 'arc-runner-set'
             makeflags: "--jobs=3 --output-sync=target"
   
@@ -236,6 +247,7 @@ jobs:
       runs-on: ${{ matrix.runs-on }}
       aio: ${{ matrix.aio }}
       base-image: ${{ matrix.base-image }}
+      grpc-base-image: ${{ matrix.grpc-base-image }}
       makeflags: ${{ matrix.makeflags }}
       latest-image: ${{ matrix.latest-image }}
       latest-image-aio: ${{ matrix.latest-image-aio }}
@@ -258,7 +270,7 @@ jobs:
             aio: "-aio-cpu"
             latest-image: 'latest-cpu'
             latest-image-aio: 'latest-aio-cpu'
-            makeflags: "--jobs=5 --output-sync=target"
+            makeflags: "--jobs=4 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"
@@ -269,7 +281,7 @@ jobs:
             image-type: 'core'
             base-image: "ubuntu:22.04"
             runs-on: 'ubuntu-latest'
-            makeflags: "--jobs=5 --output-sync=target"
+            makeflags: "--jobs=4 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "1"
@@ -280,7 +292,7 @@ jobs:
             image-type: 'core'
             base-image: "ubuntu:22.04"
             runs-on: 'ubuntu-latest'
-            makeflags: "--jobs=5 --output-sync=target"
+            makeflags: "--jobs=4 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"
@@ -291,7 +303,7 @@ jobs:
             image-type: 'core'
             runs-on: 'ubuntu-latest'
             base-image: "ubuntu:22.04"
-            makeflags: "--jobs=5 --output-sync=target"
+            makeflags: "--jobs=4 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "1"
@@ -302,4 +314,4 @@ jobs:
             image-type: 'core'
             runs-on: 'ubuntu-latest'
             base-image: "ubuntu:22.04"
-            makeflags: "--jobs=5 --output-sync=target"
+            makeflags: "--jobs=4 --output-sync=target"

.github/workflows/image_build.yml

@@ -6,6 +6,10 @@ on:
     inputs:
       base-image:
         description: 'Base image'
+        required: true
+        type: string
+      grpc-base-image:
+        description: 'GRPC Base image, must be a compatible image with base-image'
         required: false
         default: ''
         type: string
@@ -57,7 +61,7 @@ on:
       makeflags:
         description: 'Make Flags'
         required: false
-        default: '--jobs=3 --output-sync=target'
+        default: '--jobs=4 --output-sync=target'
         type: string
       aio:
         description: 'AIO Image Name'
@@ -201,15 +205,16 @@ jobs:
         uses: docker/build-push-action@v5
         with:
           builder: ${{ steps.buildx.outputs.name }}
+          # The build-args MUST be an EXACT match between the image cache and other workflow steps that want to use that cache.
+          # This means that even the MAKEFLAGS have to be an EXACT match.
+          # If the build-args are not an EXACT match, it will result in a cache miss, which will require GRPC to be built from scratch.
           build-args: |
-            IMAGE_TYPE=${{ inputs.image-type }}
+            GRPC_BASE_IMAGE=${{ inputs.grpc-base-image || inputs.base-image }}
-            BASE_IMAGE=${{ inputs.base-image }}
+            MAKEFLAGS=--jobs=4 --output-sync=target
-            MAKEFLAGS=${{ inputs.makeflags }}
             GRPC_VERSION=v1.58.0
           context: .
           file: ./Dockerfile
           cache-from: type=gha
-          cache-to: type=gha,ignore-error=true
           target: grpc
           platforms: ${{ inputs.platforms }}
           push: false

Dockerfile

@@ -1,5 +1,6 @@
 ARG IMAGE_TYPE=extras
 ARG BASE_IMAGE=ubuntu:22.04
+ARG GRPC_BASE_IMAGE=${BASE_IMAGE}
 
 # extras or core
 FROM ${BASE_IMAGE} as requirements-core
@@ -104,7 +105,7 @@ RUN if [ ! -e /usr/bin/python ]; then \
 ###################################
 ###################################
 
-FROM ${BASE_IMAGE} as grpc
+FROM ${GRPC_BASE_IMAGE} as grpc
 
 ARG MAKEFLAGS
 ARG GRPC_VERSION=v1.58.0