pytorch/.github/workflows/pytorch-linux-bionic-py3.8-gcc9-coverage.yml
zhouzhuojie 59ca89dca8 Fix scribe logs again (#61768)
Summary:
revert the revert of 3624d75 with additional fix in https://github.com/pytorch/pytorch/pull/61764

Got the corrent logs sent to lambda

```
...
,"21721":"OK","21722":"OK","21723":"OK","21724":"OK","21725":"OK","21726":"OK","21727":"OK","21728":"OK","21729":"OK","21730":"OK","21731":"OK","21732":"OK","21733":"OK","21734":"OK","21735":"OK","21736":"OK","21737":"OK","21738":"OK","21739":"OK","21740":"OK","21741":"OK","21742":"OK","21743":"OK","21744":"OK","21745":"OK","21746":"OK","21747":"OK","21748":"OK","21749":"OK","21750":"OK","21751":"OK","21752":"OK","21753":"OK","21754":"OK","21755":"OK","21756":"OK","21757":"OK","21758":"OK","21759":"OK","21760":"OK","21761":"OK","21762":"OK","21763":"OK","21764":"OK","21765":"OK","21766":"OK","21767":"OK","21768":"OK","21769":"OK","21770":"OK","21771":"OK","21772":"OK","21773":"OK","21774":"OK","21775":"OK","21776":"OK","21777":"OK","21778":"OK","21779":"OK","21780":"OK","21781":"OK","21782":"OK","21783":"OK","21784":"OK","21785":"OK","21786":"OK","21787":"OK","21788":"OK","21789":"OK","21790":"OK","21791":"OK","21792":"OK","21793":"OK","21794":"OK","21795":"OK","21796":"OK","21797":"OK","21798":"OK","21799":"OK","21800":"OK","21801":"OK","21802":"OK","21803":"OK","21804":"OK","21805":"OK","21806":"OK","21807":"OK","21808":"OK","21809":"OK","21810":"OK","21811":"OK","21812":"OK","21813":"OK","21814":"OK","21815":"OK","21816":"OK","21817":"OK","21818":"OK","21819":"OK","21820":"OK","21821":"OK","21822":"OK","21823":"OK","21824":"OK","21825":"OK","21826":"OK"}}

class StartProcessesTest:
    tests: 14 failed: 0 skipped: 0 errored: 0
    run_time: 4.86 seconds
    avg_time: 0.35 seconds
    median_time: 0.01 seconds
    3 longest tests:
        test_function_large_ret_val time: 1.55 seconds
        test_pcontext_wait time: 1.11 seconds
        test_void_function time: 1.03 seconds

...
```

Pull Request resolved: https://github.com/pytorch/pytorch/pull/61768

Reviewed By: janeyx99

Differential Revision: D29735781

Pulled By: zhouzhuojie

fbshipit-source-id: 6882e334f5108d20773ad66d5300cd37eb509ded
2021-07-16 17:56:16 -07:00

416 lines
16 KiB
YAML

# @generated DO NOT EDIT MANUALLY
# Template is at: .github/templates/linux_ci_workflow.yml.j2
# Generation script: .github/scripts/generate_ci_workflows.py
name: Linux CI (pytorch-linux-bionic-py3.8-gcc9-coverage)
on:
# TODO: Enable pull_request builds when we can verify capacity can be met by auto-scalers
pull_request:
push:
branches:
- master
- release/*
workflow_dispatch:
env:
BUILD_ENVIRONMENT: pytorch-linux-bionic-py3.8-gcc9-coverage
DOCKER_IMAGE_BASE: 308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/pytorch-linux-bionic-py3.8-gcc9
SCCACHE_BUCKET: ossci-compiler-cache-circleci-v2
TORCH_CUDA_ARCH_LIST: 5.2
IN_CI: 1
# Used for custom_opertor, jit_hooks, custom_backend, see .jenkins/pytorch/build.sh
CUSTOM_TEST_ARTIFACT_BUILD_DIR: build/custom_test_artifacts
ALPINE_IMAGE: "308535385114.dkr.ecr.us-east-1.amazonaws.com/tool/alpine"
concurrency:
group: pytorch-linux-bionic-py3.8-gcc9-coverage-${{ github.event.pull_request.number || github.sha }}
cancel-in-progress: true
jobs:
calculate-docker-image:
runs-on: linux.2xlarge
env:
DOCKER_BUILDKIT: 1
timeout-minutes: 90
outputs:
docker_image: ${{ steps.calculate-tag.outputs.docker_image }}
steps:
- name: Log in to ECR
run: |
aws ecr get-login --no-include-email --region us-east-1 > /tmp/ecr-login.sh
bash /tmp/ecr-login.sh
rm /tmp/ecr-login.sh
- name: Chown workspace
run: |
# Ensure the working directory gets chowned back to the current user
docker run --rm -v "$(pwd)":/v -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .
- name: Clean workspace
run: |
rm -rf "${GITHUB_WORKSPACE:?}/*"
- name: Checkout PyTorch
uses: actions/checkout@v2
with:
# deep clone, to allow use of git merge-base
fetch-depth: 0
- name: Calculate docker image tag
id: calculate-tag
run: |
DOCKER_TAG=$(git rev-parse HEAD:.circleci/docker)
echo "::set-output name=docker_tag::${DOCKER_TAG}"
echo "::set-output name=docker_image::${DOCKER_IMAGE_BASE}:${DOCKER_TAG}"
- name: Check if image should be built
id: check
env:
DOCKER_TAG: ${{ steps.calculate-tag.outputs.docker_tag }}
BASE_REVISION: ${{ github.event.pull_request.base.sha || github.sha }}
run: |
set -x
# Check if image already exists, if it does then skip building it
if docker manifest inspect "${DOCKER_IMAGE_BASE}:${DOCKER_TAG}"; then
exit 0
fi
if [[ "$BASE_REVISION" = "$(git rev-parse HEAD)" ]]; then
# if we're on the base branch then use the parent commit
MERGE_BASE=$(git rev-parse HEAD~)
else
# otherwise we're on a PR, so use the most recent base commit
MERGE_BASE=$(git merge-base HEAD "$BASE_REVISION")
fi
# Covers the case where a previous tag doesn't exist for the tree
# this is only really applicable on trees that don't have `.circleci/docker` at its merge base, i.e. nightly
if ! git rev-parse "$MERGE_BASE:.circleci/docker"; then
echo "Directory '.circleci/docker' not found in commit $MERGE_BASE, you should probably rebase onto a more recent commit"
exit 1
fi
PREVIOUS_DOCKER_TAG=$(git rev-parse "$MERGE_BASE:.circleci/docker")
# If no image exists but the hash is the same as the previous hash then we should error out here
if [[ "${PREVIOUS_DOCKER_TAG}" = "${DOCKER_TAG}" ]]; then
echo "ERROR: Something has gone wrong and the previous image isn't available for the merge-base of your branch"
echo " contact the PyTorch team to restore the original images"
exit 1
fi
echo ::set-output name=rebuild::yes
- name: Build and push docker image
if: steps.check.outputs.rebuild
env:
DOCKER_TAG: ${{ steps.calculate-tag.outputs.docker_tag }}
DOCKER_SKIP_S3_UPLOAD: 1
run: |
export IMAGE_NAME=${DOCKER_IMAGE_BASE#308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/}
cd .circleci/docker && ./build_docker.sh
build:
runs-on: linux.2xlarge
needs: calculate-docker-image
env:
DOCKER_IMAGE: ${{ needs.calculate-docker-image.outputs.docker_image }}
JOB_BASE_NAME: pytorch-linux-bionic-py3.8-gcc9-coverage-build
steps:
- name: Log in to ECR
run: |
aws ecr get-login --no-include-email --region us-east-1 > /tmp/ecr-login.sh
bash /tmp/ecr-login.sh
rm /tmp/ecr-login.sh
- name: Chown workspace
run: |
# Ensure the working directory gets chowned back to the current user
docker run --rm -v "$(pwd)":/v -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .
- name: Clean workspace
run: |
rm -rf "${GITHUB_WORKSPACE:?}/*"
- name: Checkout PyTorch
uses: actions/checkout@v2
with:
fetch-depth: 0 # deep clone, to allow sharding to use git rev-list
submodules: recursive
- name: Pull docker image
run: |
docker pull "${DOCKER_IMAGE}"
- name: Preserve github env variables for use in docker
run: |
env | grep '^GITHUB' > "/tmp/github_env_${GITHUB_RUN_ID}"
- name: Build PyTorch
run: |
docker run \
-e BUILD_ENVIRONMENT \
-e JOB_BASE_NAME \
-e MAX_JOBS="$(nproc --ignore=2)" \
-e SCCACHE_BUCKET \
-e CUSTOM_TEST_ARTIFACT_BUILD_DIR \
-e SKIP_SCCACHE_INITIALIZATION=1 \
-e TORCH_CUDA_ARCH_LIST \
--env-file="/tmp/github_env_${GITHUB_RUN_ID}" \
--security-opt seccomp=unconfined \
--cap-add=SYS_PTRACE \
--tty \
--user jenkins \
-v "${GITHUB_WORKSPACE}:/var/lib/jenkins/workspace" \
-w /var/lib/jenkins/workspace \
"${DOCKER_IMAGE}" \
sh -c 'sudo chown -R jenkins . && .jenkins/pytorch/build.sh'
- name: Display and upload binary build size statistics (Click Me)
# temporary hack: set CIRCLE_* vars, until we update
# tools/stats/print_test_stats.py to natively support GitHub Actions
env:
AWS_DEFAULT_REGION: us-east-1
SCRIBE_GRAPHQL_ACCESS_TOKEN: ${{ secrets.SCRIBE_GRAPHQL_ACCESS_TOKEN }}
CIRCLE_BRANCH: ${{ steps.parse-ref.outputs.branch }}
CIRCLE_PR_NUMBER: ${{ github.event.pull_request.number }}
CIRCLE_SHA1: ${{ github.event.pull_request.head.sha || github.sha }}
CIRCLE_TAG: ${{ steps.parse-ref.outputs.tag }}
CIRCLE_WORKFLOW_ID: '${{ github.run_id }}_${{ github.run_number }}'
run: |
COMMIT_TIME=$(git log --max-count=1 --format=%ct || echo 0)
export COMMIT_TIME
pip3 install requests
python3 -m tools.stats.upload_binary_size_to_scuba || exit 0
- name: Chown workspace
run: |
# Ensure the working directory gets chowned back to the current user
docker run --rm -v "$(pwd)":/v -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .
- name: Archive artifacts into zip
run: |
zip -r artifacts.zip dist/ build/ .pytorch-test-times.json
# Upload to github so that people can click and download artifacts
- uses: actions/upload-artifact@v2
# Don't fail on upload to GH since it's only for user convenience
continue-on-error: true
name: Store PyTorch Build Artifacts on Github
with:
name: ${{ env.BUILD_ENVIRONMENT }}
retention-days: 14
if-no-files-found: error
path:
artifacts.zip
- uses: seemethere/upload-artifact-s3@9d7ceb0ab39c2c88d93ef7792b27425b27d59162
name: Store PyTorch Build Artifacts on S3
with:
name: ${{ env.BUILD_ENVIRONMENT }}
retention-days: 14
if-no-files-found: error
path:
artifacts.zip
- name: Clean up docker images
if: always()
run: |
# Prune all of the docker images
docker system prune -af
generate-test-matrix:
if: ${{ github.repository_owner == 'pytorch' }}
runs-on: ubuntu-18.04
env:
TEST_RUNNER_TYPE: linux.2xlarge
ENABLE_JIT_LEGACY_TEST: ''
ENABLE_MULTIGPU_TEST: ''
ENABLE_NOGPU_NO_AVX_TEST: ''
ENABLE_NOGPU_NO_AVX2_TEST: ''
ENABLE_SLOW_TEST: ''
NUM_TEST_SHARDS: 2
MULTIGPU_RUNNER_TYPE: linux.16xlarge.nvidia.gpu
NOGPU_RUNNER_TYPE: linux.2xlarge
outputs:
matrix: ${{ steps.set-matrix.outputs.matrix }}
render-matrix: ${{ steps.set-matrix.outputs.render-matrix }}
container:
image: python:3.9
steps:
- name: Install dependencies
run: pip install typing-extensions
- name: Clone pytorch/pytorch
uses: actions/checkout@v2
- name: Generating test matrix
id: set-matrix
run: .github/scripts/generate_pytorch_test_matrix.py
test:
if: True
needs:
- calculate-docker-image
- build
- generate-test-matrix
strategy:
matrix: ${{ fromJson(needs.generate-test-matrix.outputs.matrix) }}
fail-fast: false
runs-on: ${{ matrix.runner }}
env:
DOCKER_IMAGE: ${{ needs.calculate-docker-image.outputs.docker_image }}
JOB_BASE_NAME: pytorch-linux-bionic-py3.8-gcc9-coverage-test
TEST_CONFIG: ${{ matrix.config }}
SHARD_NUMBER: ${{ matrix.shard }}
NUM_TEST_SHARDS: ${{ matrix.num_shards }}
steps:
- name: Log in to ECR
run: |
aws ecr get-login --no-include-email --region us-east-1 > /tmp/ecr-login.sh
bash /tmp/ecr-login.sh
rm /tmp/ecr-login.sh
- name: Chown workspace
run: |
# Ensure the working directory gets chowned back to the current user
docker run --rm -v "$(pwd)/../":/v -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .
- name: Clean workspace
run: |
rm -rf "${GITHUB_WORKSPACE:?}/*"
- name: Checkout PyTorch
uses: actions/checkout@v2
with:
submodules: recursive
- name: Pull docker image
run: |
docker pull "${DOCKER_IMAGE}"
- name: Install nvidia driver, nvidia-docker runtime, set GPU_FLAG
if: ${{ contains(env.BUILD_ENVIRONMENT, 'cuda') && !contains(matrix.config, 'nogpu') }}
run: |
bash .github/scripts/install_nvidia_utils_linux.sh
echo "GPU_FLAG=--gpus all" >> "${GITHUB_ENV}"
- name: Determine shm-size
run: |
shm_size="1g"
case "${BUILD_ENVIRONMENT}" in
*cuda*)
shm_size="2g"
;;
*rocm*)
shm_size="8g"
;;
esac
echo "SHM_SIZE=${shm_size}" >> "${GITHUB_ENV}"
- uses: seemethere/download-artifact-s3@0504774707cbc8603d7dca922e8026eb8bf3b47b
name: Download PyTorch Build Artifacts
with:
name: ${{ env.BUILD_ENVIRONMENT }}
- name: Unzip artifacts
run: |
unzip -o artifacts.zip
- name: Output disk space left
run: |
sudo df -H
- name: Preserve github env variables for use in docker
run: |
env | grep '^GITHUB' > "/tmp/github_env_${GITHUB_RUN_ID}"
- name: Test PyTorch
run: |
if [[ $TEST_CONFIG == 'multigpu' ]]; then
TEST_COMMAND=.jenkins/pytorch/multigpu-test.sh
else
TEST_COMMAND=.jenkins/pytorch/test.sh
fi
if [[ $NUM_TEST_SHARDS -ne 2 ]]; then
export SHARD_NUMBER=0
fi
# TODO: Stop building test binaries as part of the build phase
# Used for GPU_FLAG since that doesn't play nice
# shellcheck disable=SC2086
docker run \
${GPU_FLAG:-} \
-e BUILD_ENVIRONMENT \
-e CUSTOM_TEST_ARTIFACT_BUILD_DIR \
-e GITHUB_ACTIONS \
-e IN_CI \
-e SHARD_NUMBER \
-e JOB_BASE_NAME \
-e TEST_CONFIG \
-e NUM_TEST_SHARDS \
-e MAX_JOBS="$(nproc --ignore=2)" \
-e SCCACHE_BUCKET \
--env-file="/tmp/github_env_${GITHUB_RUN_ID}" \
--security-opt seccomp=unconfined \
--cap-add=SYS_PTRACE \
--shm-size="${SHM_SIZE}" \
--tty \
--user jenkins \
-v "${GITHUB_WORKSPACE}:/var/lib/jenkins/workspace" \
-w /var/lib/jenkins/workspace \
"${DOCKER_IMAGE}" \
sh -c 'sudo chown -R jenkins . && pip install dist/*.whl && '$TEST_COMMAND
- name: Chown workspace
if: always()
run: |
# Ensure the working directory gets chowned back to the current user
docker run --rm -v "$(pwd)":/v -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .
- name: Zip test reports for upload
if: always()
run: |
# Remove any previous test reports if they exist
rm -f test-reports-*.zip
zip -r "test-reports-${TEST_CONFIG}.zip" test -i '*.xml'
- uses: actions/upload-artifact@v2
name: Store PyTorch Test Reports
if: always()
with:
name: test-reports-${{ matrix.config }}
retention-days: 14
if-no-files-found: error
path:
test-reports-*.zip
- uses: seemethere/upload-artifact-s3@9d7ceb0ab39c2c88d93ef7792b27425b27d59162
name: Store PyTorch Test Reports on S3
if: always()
with:
name: test-reports-${{ matrix.config }}
retention-days: 14
if-no-files-found: error
path:
test-reports-*.zip
- name: Clean up docker images
if: always()
run: |
# Ensure the working directory gets chowned back to the current user
docker run --rm -v "$(pwd)":/v -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .
# Prune all of the docker images
docker system prune -af
# this is a separate step from test because the log files from test are too
# long: basically, GitHub tries to render all of the log files when you click
# through an action causing extreme slowdown on actions that contain too many
# logs (like test); we can always move it back to the other one, but it
# doesn't create the best experience
render_test_results:
if: always()
needs:
- generate-test-matrix
- test
runs-on: linux.2xlarge
strategy:
matrix: ${{ fromJson(needs.generate-test-matrix.outputs.render-matrix) }}
fail-fast: false
steps:
- name: Checkout PyTorch
uses: actions/checkout@v2
with:
# deep clone, to allow tools/stats/print_test_stats.py to use Git commands
fetch-depth: 0
- uses: actions/download-artifact@v2
name: Download PyTorch Test Reports
with:
name: test-reports-${{ matrix.config }}
path: .
- name: Unzip test reports
run: |
# Should preserve paths so reports should still be in test/test-reports
unzip -o 'test-reports-*.zip'
- name: Install dependencies
# boto3 version copied from .circleci/docker/common/install_conda.sh
run: |
pip3 install -r requirements.txt
pip3 install boto3==1.16.34 junitparser rich
- name: Output Test Results (Click Me)
run: |
python3 tools/render_junit.py test
- name: Parse ref
id: parse-ref
run: .github/scripts/parse_ref.py
- name: Display and upload test statistics (Click Me)
# temporary hack: set CIRCLE_* vars, until we update
# tools/stats/print_test_stats.py to natively support GitHub Actions
env:
AWS_DEFAULT_REGION: us-east-1
CIRCLE_BRANCH: ${{ steps.parse-ref.outputs.branch }}
JOB_BASE_NAME: pytorch-linux-bionic-py3.8-gcc9-coverage-test
CIRCLE_PR_NUMBER: ${{ github.event.pull_request.number }}
CIRCLE_SHA1: ${{ github.event.pull_request.head.sha || github.sha }}
CIRCLE_TAG: ${{ steps.parse-ref.outputs.tag }}
CIRCLE_WORKFLOW_ID: '${{ github.run_id }}_${{ github.run_number }}'
run: |
python3 -m tools.stats.print_test_stats --upload-to-s3 --compare-with-s3 test