add azure timeout (#5907)

* add azure timeout

* rework

azure-pipelines.yml

@@ -12,68 +12,79 @@ pr:
   - master
   - release/*
 
-pool: dsvm-spot-pool
+jobs:
+  - job: pytest
+    # how long to run the job before automatically cancelling
+    timeoutInMinutes: 45
+    # how much time to give 'run always even if cancelled tasks' before stopping them
+    cancelTimeoutInMinutes: 2
 
-strategy:
-  matrix:
-    PT16:
-      torch.version: '1.6'
-      python.version: '3.7'
+    pool: dsvm-spot-pool
 
-# ToDo: this need to have installed docker in the base image...
-#container: pytorchlightning/pytorch_lightning:base-cuda-py3.7-torch1.6
-#container: "pytorchlightning/pytorch_lightning:base-cuda-py$[ variables['python.version'] ]-torch1.6"
-container:
-    # base ML image: mcr.microsoft.com/azureml/openmpi3.1.2-cuda10.2-cudnn8-ubuntu18.04
-    image: "pytorchlightning/pytorch_lightning:base-cuda-py3.7-torch1.6"
-    #endpoint: azureContainerRegistryConnection
-    options: "--runtime=nvidia -e NVIDIA_VISIBLE_DEVICES=all"
+    #strategy:
+    #  matrix:
+    #    PT16:
+    #      torch.version: '1.6'
+    #      python.version: '3.7'
 
-steps:
-- bash: |
-    lspci | egrep 'VGA|3D'
-    whereis nvidia
-    nvidia-smi
-    python --version
-    pip --version
-    pip list
-  displayName: 'Image info & NVIDIA'
+    # ToDo: this need to have installed docker in the base image...
+    #container: pytorchlightning/pytorch_lightning:base-cuda-py3.7-torch1.6
+    #container: "pytorchlightning/pytorch_lightning:base-cuda-py$[ variables['python.version'] ]-torch1.6"
+    container:
+      # base ML image: mcr.microsoft.com/azureml/openmpi3.1.2-cuda10.2-cudnn8-ubuntu18.04
+      image: "pytorchlightning/pytorch_lightning:base-cuda-py3.7-torch1.6"
+      #endpoint: azureContainerRegistryConnection
+      options: "--runtime=nvidia -e NVIDIA_VISIBLE_DEVICES=all"
 
-- bash: |
-    #sudo apt-get install -y cmake
-    # python -m pip install "pip==20.1"
-    pip install --requirement requirements.txt --find-links https://download.pytorch.org/whl/cpu/torch_stable.html
-    python -c "fname = 'requirements/extra.txt' ; lines = [line for line in open(fname).readlines() if 'fairscale' not in line] ; open(fname, 'w').writelines(lines)"
-    python -c "fname = 'requirements/extra.txt' ; lines = [line for line in open(fname).readlines() if 'horovod' not in line] ; open(fname, 'w').writelines(lines)"
-    pip install --requirement ./requirements/devel.txt --upgrade-strategy only-if-needed
-    pip install git+https://$(AUTH_TOKEN)@github.com/PyTorchLightning/lightning-dtrun.git@v0.0.2 --no-cache-dir
-    pip list
-  displayName: 'Install dependencies'
+    workspace:
+      clean: all
 
-- script: |
-    python tests/collect_env_details.py
-  displayName: 'Env details'
+    steps:
 
-- bash: |
-    wget https://pl-public-data.s3.amazonaws.com/legacy/checkpoints.zip -P legacy/
-    unzip -o legacy/checkpoints.zip -d legacy/
-    ls -l legacy/checkpoints/
-  displayName: 'Get legacy checkpoints'
+    - bash: |
+        lspci | egrep 'VGA|3D'
+        whereis nvidia
+        nvidia-smi
+        python --version
+        pip --version
+        pip list
+      displayName: 'Image info & NVIDIA'
 
-- script: |
-    python -m coverage run --source pytorch_lightning -m pytest pytorch_lightning tests -v --durations=50
-  displayName: 'Testing: standard'
+    - bash: |
+        #sudo apt-get install -y cmake
+        # python -m pip install "pip==20.1"
+        pip install --requirement requirements.txt --find-links https://download.pytorch.org/whl/cpu/torch_stable.html
+        python -c "fname = 'requirements/extra.txt' ; lines = [line for line in open(fname).readlines() if 'fairscale' not in line] ; open(fname, 'w').writelines(lines)"
+        python -c "fname = 'requirements/extra.txt' ; lines = [line for line in open(fname).readlines() if 'horovod' not in line] ; open(fname, 'w').writelines(lines)"
+        pip install --requirement ./requirements/devel.txt --upgrade-strategy only-if-needed
+        pip install git+https://$(AUTH_TOKEN)@github.com/PyTorchLightning/lightning-dtrun.git@v0.0.2 --no-cache-dir
+        pip list
+      displayName: 'Install dependencies'
 
-- script: |
-    sh tests/special_tests.sh
-  displayName: 'Testing: special'
+    - script: |
+        python tests/collect_env_details.py
+      displayName: 'Env details'
 
-- bash: |
-    python -m coverage report
-    python -m coverage xml
-    codecov --token $(CODECOV_TOKEN) --flags=gpu,pytest --name="GPU-coverage" --env=linux,azure
-  displayName: 'Statistics'
+    - bash: |
+        wget https://pl-public-data.s3.amazonaws.com/legacy/checkpoints.zip -P legacy/
+        unzip -o legacy/checkpoints.zip -d legacy/
+        ls -l legacy/checkpoints/
+      displayName: 'Get legacy checkpoints'
 
-- script: |
-    python -m pytest benchmarks pl_examples -v --maxfail=2 --durations=0
-  displayName: 'Testing: extended'
+    - script: |
+        python -m coverage run --source pytorch_lightning -m pytest pytorch_lightning tests -v --durations=50
+      displayName: 'Testing: standard'
+
+    - script: |
+        sh tests/special_tests.sh
+      displayName: 'Testing: special'
+
+    - bash: |
+        python -m coverage report
+        python -m coverage xml
+        codecov --token $(CODECOV_TOKEN) --flags=gpu,pytest --name="GPU-coverage" --env=linux,azure
+      displayName: 'Statistics'
+
+    - script: |
+        python -m pytest benchmarks pl_examples -v --maxfail=2 --durations=0
+      displayName: 'Testing: extended'