Add CACHEBUSTER to always get the latest pip packages

.github/workflows/docker-presubmit.yml

@@ -29,6 +29,11 @@ jobs:
           registry: gcr.io
           username: _json_key
           password: ${{ secrets.GCP_CREDS }}
+      -
+        name: Grab the date to do cache busting (assumes same day OK to keep)
+        run: |
+          echo "::set-output name=DATE::$(date +'%Y-%m-%d')"
+        id: date
       -
         name: Build containers, and push to GCR only if the 'build and push to gcr.io for staging' label is applied
         id: docker_build
@@ -39,6 +44,7 @@ jobs:
           target: devel
           build-args: |
             PYTHON_VERSION=${{ matrix.python-version }}
+            CACHEBUSTER=${{ steps.date.outputs.DATE }}
           tags: |
             gcr.io/tensorflow-sigs/build:${{ github.event.number }}-${{ matrix.python-version }}
           cache-from: |

.github/workflows/docker.yml

@@ -50,6 +50,9 @@ jobs:
           major_version=$(grep "^#define TF_MAJOR_VERSION" ./tensorflow/tensorflow/core/public/version.h | grep -o "[[:digit:]]\+")
           minor_version=$(grep "^#define TF_MINOR_VERSION" ./tensorflow/tensorflow/core/public/version.h | grep -o "[[:digit:]]\+")
           echo ::set-output name=TF_VERSION::${major_version}.${minor_version}
+          # Also get the current date to do cache busting. Assumes one day
+          # is an ok range for rebuilds
+          echo "::set-output name=DATE::$(date +'%Y-%m-%d')"
         id: tf-version
       -
         name: Build and push
@@ -61,6 +64,7 @@ jobs:
           target: devel
           build-args: |
             PYTHON_VERSION=${{ matrix.python-version }}
+            CACHEBUSTER=${{ steps.tf-version.outputs.DATE }}
           tags: |
             tensorflow/build:latest-${{ matrix.python-version }}
             tensorflow/build:${{ steps.tf-version.outputs.TF_VERSION }}-${{ matrix.python-version }}

tf_sig_build_dockerfiles/Dockerfile

@@ -41,6 +41,12 @@ RUN curl -sSL https://sdk.cloud.google.com > /tmp/gcl && bash /tmp/gcl --install
 # RUN wget https://github.com/llvm/llvm-project/releases/download/llvmorg-13.0.0/clang+llvm-13.0.0-x86_64-linux-gnu-ubuntu-20.04.tar.xz -O /clang.tar.xz && tar xf /clang.tar.xz clang+llvm-13.0.0-x86_64-linux-gnu-ubuntu-20.04/bin/clang-format && mv ./clang+llvm-13.0.0-x86_64-linux-gnu-ubuntu-20.04/bin/clang-format /usr/local/bin/clang-format && rm -rf ./clang+llvm-13.0.0-x86_64-linux-gnu-ubuntu.tar.xz ./clang+llvm-13.0.0-x86_64-linux-gnu-ubuntu
 
 
+# All lines past this point are reset when $CACHEBUSTER is set. We need this
+# for Python specifically because we install some nightly packages which are
+# likely to change daily.
+ARG CACHEBUSTER=0
+RUN echo $CACHEBUSTER
+
 # Setup Python environment. PYTHON_VERSION is e.g. "python3.8"
 ARG PYTHON_VERSION
 COPY setup.python.sh /setup.python.sh

tf_sig_build_dockerfiles/devel.requirements.txt

@@ -27,7 +27,8 @@ gast == 0.4.0
 # Note that here we want the latest version that matches TF major.minor version
 # Note that we must use nightly here as these are used in nightly jobs
 # For release jobs, we will pin these on the release branch
-# TODO(angerson) We need to somehow invalidate the cache on these regularly
+# Note that the CACHEBUSTER variable, set in the CI builds, will force these to
+# be the latest version.
 keras-nightly ~= 2.9.0.dev
 tb-nightly ~= 2.9.0.a
 tf-estimator-nightly ~= 2.9.0.dev