build more dockers & slack fails (#12675)

* build dockers
* add slack
* Apply suggestions from code review

Co-authored-by: Akihiro Nitta <nitta@akihironitta.com>

.github/workflows/ci_dockers.yml

@@ -28,8 +28,8 @@ jobs:
       fail-fast: false
       matrix:
         # the config used in '.azure-pipelines/gpu-tests.yml' since the Dockerfile uses the cuda image
-        python_version: ["3.7"]
-        pytorch_version: ["1.8"]
+        python_version: ["3.9"]
+        pytorch_version: ["1.10", "1.11"]
     steps:
       - name: Checkout
         uses: actions/checkout@v2
@@ -73,9 +73,10 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
+        python_version: ["3.7", "3.9"]
+        pytorch_version: ["1.8", "1.11"]
         include:
           # the config used in '.azure-pipelines/gpu-tests.yml'
-          - {python_version: "3.7", pytorch_version: "1.8"}
           - {python_version: "3.9", pytorch_version: "1.10"}
     steps:
       - name: Checkout

.github/workflows/events-nightly.yml

@@ -48,6 +48,18 @@ jobs:
           repository_url: https://test.pypi.org/legacy/
           verbose: true
 
+      # report failure to Slack
+      - name: Slack notification
+        if: failure() && github.event_name == 'schedule'
+        uses: ravsamhq/notify-slack-action@v1
+        with:
+          status: ${{ job.status }}
+          token: ${{ secrets.GITHUB_TOKEN }}
+          notification_title: 'Publish nightly package to test.pypi.org'
+          message_format: '{emoji} *{workflow}* {status_message}, see <{run_url}|detail>, cc: <@UR9FXE6QG>'  #Borda
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
+
   docker-XLA:
     if: ${{ github.repository_owner == 'PyTorchLightning' }}
     runs-on: ubuntu-20.04
@@ -83,6 +95,18 @@ jobs:
           tags: pytorchlightning/pytorch_lightning:base-xla-py${{ matrix.python_version }}-torch${{ matrix.xla_version }}
         timeout-minutes: 55
 
+      # report failure to Slack
+      - name: Slack notification
+        if: failure() && github.event_name == 'schedule'
+        uses: ravsamhq/notify-slack-action@v1
+        with:
+          status: ${{ job.status }}
+          token: ${{ secrets.GITHUB_TOKEN }}
+          notification_title: ${{ format('XLA; {0} py{1} for *{2}*', runner.os, matrix.python_version, matrix.xla_version) }}
+          message_format: '{emoji} *{workflow}* {status_message}, see <{run_url}|detail>, cc: <@U01GD29QCAV>'  #kaushikb11
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
+
   docker-CUDA:
     if: ${{ github.repository_owner == 'PyTorchLightning' }}
     runs-on: ubuntu-20.04
@@ -92,7 +116,10 @@ jobs:
         include:
           # the config used in '.azure-pipelines/gpu-tests.yml'
           - {python_version: "3.7", pytorch_version: "1.8"}
-          # latest (not used)
+          - {python_version: "3.7", pytorch_version: "1.10"}
+          # latest (used in Tutorials)
+          - {python_version: "3.8", pytorch_version: "1.8"}
+          - {python_version: "3.9", pytorch_version: "1.10"}
           - {python_version: "3.9", pytorch_version: "1.11"}
 
     steps:
@@ -118,6 +145,18 @@ jobs:
           tags: pytorchlightning/pytorch_lightning:base-cuda-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }}
         timeout-minutes: 85
 
+      # report failure to Slack
+      - name: Slack notification
+        if: failure() && github.event_name == 'schedule'
+        uses: ravsamhq/notify-slack-action@v1
+        with:
+          status: ${{ job.status }}
+          token: ${{ secrets.GITHUB_TOKEN }}
+          notification_title: ${{ format('CUDA; {0} py{1} for *{2}*', runner.os, matrix.python_version, matrix.pytorch_version) }}
+          message_format: '{emoji} *{workflow}* {status_message}, see <{run_url}|detail>, cc: <@U01A5T7EY9M>'  #akihironitta
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
+
   docker-Conda:
     if: ${{ github.repository_owner == 'PyTorchLightning' }}
     runs-on: ubuntu-20.04
@@ -157,6 +196,18 @@ jobs:
           tags: pytorchlightning/pytorch_lightning:base-conda-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }}
         timeout-minutes: 85
 
+      # report failure to Slack
+      - name: Slack notification
+        if: failure() && github.event_name == 'schedule'
+        uses: ravsamhq/notify-slack-action@v1
+        with:
+          status: ${{ job.status }}
+          token: ${{ secrets.GITHUB_TOKEN }}
+          notification_title: ${{ format('Conda; {0} py{1} for *{2}*', runner.os, matrix.python_version, matrix.pytorch_version) }}
+          message_format: '{emoji} *{workflow}* {status_message}, see <{run_url}|detail>, cc: <@U01A5T7EY9M>'  #akihironitta
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
+
   docker-IPU:
     if: ${{ github.repository_owner == 'PyTorchLightning' }}
     runs-on: ubuntu-20.04
@@ -203,3 +254,15 @@ jobs:
           push: ${{ env.PUSH_TO_HUB }}
           tags: pytorchlightning/pytorch_lightning:ipu-ci-runner-py${{ matrix.python_version }}
         timeout-minutes: 55
+
+      # report failure to Slack
+      - name: Slack notification
+        if: failure() && github.event_name == 'schedule'
+        uses: ravsamhq/notify-slack-action@v1
+        with:
+          status: ${{ job.status }}
+          token: ${{ secrets.GITHUB_TOKEN }}
+          notification_title: ${{ format('IPU; {0} py{1} for *{2}*', runner.os, matrix.python_version, matrix.pytorch_version) }}
+          message_format: '{emoji} *{workflow}* {status_message}, see <{run_url}|detail>, cc: <@U01BULUS2BG>'  #SeanNaren
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}

dockers/README.md

@@ -64,7 +64,7 @@ sudo systemctl restart docker
 and later run the docker image with `--gpus all` so for example
 
 ```
-docker run --rm -it --gpus all pytorchlightning/pytorch_lightning:base-cuda-py3.7-torch1.6
+docker run --rm -it --gpus all pytorchlightning/pytorch_lightning:base-cuda-py3.9-torch1.10
 ```
 
 ## Run Jupyter server