mirror of
https://github.com/zebrajr/pytorch.git
synced 2025-12-06 12:20:52 +01:00
Revert D30620966: [pytorch][PR] Move Parallel[Native|TBB] to GHA
Test Plan: revert-hammer
Differential Revision:
D30620966 (223f886032)
Original commit changeset: 9a23e4b3e168
fbshipit-source-id: b9248d377b9a7b850dfb3f10f3350fbc9855acfe
This commit is contained in:
Nikita Shulga
Facebook GitHub Bot
parent
710a2e933f
commit
9db56531f7
|
|
@ -7,6 +7,8 @@ CONFIG_TREE_DATA = [
|
|||
("5.4", [ # All this subtree rebases to master and then build
|
||||
("3.6", [
|
||||
("important", [X(True)]),
|
||||
("parallel_tbb", [X(True)]),
|
||||
("parallel_native", [X(True)]),
|
||||
("pure_torch", [X(True)]),
|
||||
]),
|
||||
]),
|
||||
|
|
|
|||
90
.circleci/config.yml
generated
90
.circleci/config.yml
generated
|
|
@ -7166,6 +7166,70 @@ workflows:
|
|||
build_environment: "pytorch-linux-pytorch_linux_xenial_py3_6_gcc5_4_distributed-test"
|
||||
docker_image: "308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/pytorch-linux-xenial-py3.6-gcc5.4"
|
||||
resource_class: large
|
||||
- pytorch_linux_build:
|
||||
name: pytorch_paralleltbb_linux_xenial_py3_6_gcc5_4_build
|
||||
requires:
|
||||
- "docker-pytorch-linux-xenial-py3.6-gcc5.4"
|
||||
filters:
|
||||
branches:
|
||||
only:
|
||||
- master
|
||||
- /ci-all\/.*/
|
||||
- /release\/.*/
|
||||
build_environment: "pytorch-paralleltbb-linux-xenial-py3.6-gcc5.4-build"
|
||||
docker_image: "308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/pytorch-linux-xenial-py3.6-gcc5.4"
|
||||
- pytorch_linux_test:
|
||||
name: pytorch_paralleltbb_linux_xenial_py3_6_gcc5_4_test
|
||||
requires:
|
||||
- pytorch_paralleltbb_linux_xenial_py3_6_gcc5_4_build
|
||||
filters:
|
||||
branches:
|
||||
only:
|
||||
- master
|
||||
- /ci-all\/.*/
|
||||
- /release\/.*/
|
||||
build_environment: "pytorch-paralleltbb-linux-xenial-py3.6-gcc5.4-test"
|
||||
docker_image: "308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/pytorch-linux-xenial-py3.6-gcc5.4"
|
||||
resource_class: large
|
||||
- pytorch_linux_test:
|
||||
name: pytorch_linux_pytorch_paralleltbb_linux_xenial_py3_6_gcc5_4_distributed_test
|
||||
requires:
|
||||
- pytorch_paralleltbb_linux_xenial_py3_6_gcc5_4_build
|
||||
build_environment: "pytorch-linux-pytorch_paralleltbb_linux_xenial_py3_6_gcc5_4_distributed-test"
|
||||
docker_image: "308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/pytorch-linux-xenial-py3.6-gcc5.4"
|
||||
resource_class: large
|
||||
- pytorch_linux_build:
|
||||
name: pytorch_parallelnative_linux_xenial_py3_6_gcc5_4_build
|
||||
requires:
|
||||
- "docker-pytorch-linux-xenial-py3.6-gcc5.4"
|
||||
filters:
|
||||
branches:
|
||||
only:
|
||||
- master
|
||||
- /ci-all\/.*/
|
||||
- /release\/.*/
|
||||
build_environment: "pytorch-parallelnative-linux-xenial-py3.6-gcc5.4-build"
|
||||
docker_image: "308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/pytorch-linux-xenial-py3.6-gcc5.4"
|
||||
- pytorch_linux_test:
|
||||
name: pytorch_parallelnative_linux_xenial_py3_6_gcc5_4_test
|
||||
requires:
|
||||
- pytorch_parallelnative_linux_xenial_py3_6_gcc5_4_build
|
||||
filters:
|
||||
branches:
|
||||
only:
|
||||
- master
|
||||
- /ci-all\/.*/
|
||||
- /release\/.*/
|
||||
build_environment: "pytorch-parallelnative-linux-xenial-py3.6-gcc5.4-test"
|
||||
docker_image: "308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/pytorch-linux-xenial-py3.6-gcc5.4"
|
||||
resource_class: large
|
||||
- pytorch_linux_test:
|
||||
name: pytorch_linux_pytorch_parallelnative_linux_xenial_py3_6_gcc5_4_distributed_test
|
||||
requires:
|
||||
- pytorch_parallelnative_linux_xenial_py3_6_gcc5_4_build
|
||||
build_environment: "pytorch-linux-pytorch_parallelnative_linux_xenial_py3_6_gcc5_4_distributed-test"
|
||||
docker_image: "308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/pytorch-linux-xenial-py3.6-gcc5.4"
|
||||
resource_class: large
|
||||
- pytorch_linux_build:
|
||||
name: pytorch_pure_torch_linux_xenial_py3_6_gcc5_4_build
|
||||
requires:
|
||||
|
|
@ -9322,6 +9386,32 @@ workflows:
|
|||
- docker_build_job:
|
||||
name: "docker-pytorch-linux-xenial-py3.6-gcc7"
|
||||
image_name: "pytorch-linux-xenial-py3.6-gcc7"
|
||||
- pytorch_linux_build:
|
||||
name: pytorch_paralleltbb_linux_xenial_py3_6_gcc5_4_build
|
||||
requires:
|
||||
- "docker-pytorch-linux-xenial-py3.6-gcc5.4"
|
||||
build_environment: "pytorch-paralleltbb-linux-xenial-py3.6-gcc5.4-build"
|
||||
docker_image: "308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/pytorch-linux-xenial-py3.6-gcc5.4"
|
||||
- pytorch_linux_test:
|
||||
name: pytorch_paralleltbb_linux_xenial_py3_6_gcc5_4_test
|
||||
requires:
|
||||
- pytorch_paralleltbb_linux_xenial_py3_6_gcc5_4_build
|
||||
build_environment: "pytorch-paralleltbb-linux-xenial-py3.6-gcc5.4-test"
|
||||
docker_image: "308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/pytorch-linux-xenial-py3.6-gcc5.4"
|
||||
resource_class: large
|
||||
- pytorch_linux_build:
|
||||
name: pytorch_parallelnative_linux_xenial_py3_6_gcc5_4_build
|
||||
requires:
|
||||
- "docker-pytorch-linux-xenial-py3.6-gcc5.4"
|
||||
build_environment: "pytorch-parallelnative-linux-xenial-py3.6-gcc5.4-build"
|
||||
docker_image: "308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/pytorch-linux-xenial-py3.6-gcc5.4"
|
||||
- pytorch_linux_test:
|
||||
name: pytorch_parallelnative_linux_xenial_py3_6_gcc5_4_test
|
||||
requires:
|
||||
- pytorch_parallelnative_linux_xenial_py3_6_gcc5_4_build
|
||||
build_environment: "pytorch-parallelnative-linux-xenial-py3.6-gcc5.4-test"
|
||||
docker_image: "308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/pytorch-linux-xenial-py3.6-gcc5.4"
|
||||
resource_class: large
|
||||
- pytorch_linux_build:
|
||||
name: pytorch_pure_torch_linux_xenial_py3_6_gcc5_4_build
|
||||
requires:
|
||||
|
|
|
|||
6
.github/generated-ciflow-ruleset.json
generated
vendored
6
.github/generated-ciflow-ruleset.json
generated
vendored
|
|
@ -10,8 +10,6 @@
|
|||
"linux-xenial-cuda11.3-py3.6-gcc7",
|
||||
"linux-xenial-py3.6-gcc5.4",
|
||||
"linux-xenial-py3.6-gcc7-bazel-test",
|
||||
"parallelnative-linux-xenial-py3.6-gcc5.4",
|
||||
"paralleltbb-linux-xenial-py3.6-gcc5.4",
|
||||
"periodic-libtorch-linux-xenial-cuda11.1-py3.6-gcc7",
|
||||
"periodic-linux-xenial-cuda11.1-py3.6-gcc7",
|
||||
"periodic-win-vs2019-cuda11.1-py3",
|
||||
|
|
@ -29,8 +27,6 @@
|
|||
"linux-bionic-py3.8-gcc9-coverage",
|
||||
"linux-xenial-py3.6-gcc5.4",
|
||||
"linux-xenial-py3.6-gcc7-bazel-test",
|
||||
"parallelnative-linux-xenial-py3.6-gcc5.4",
|
||||
"paralleltbb-linux-xenial-py3.6-gcc5.4",
|
||||
"win-vs2019-cpu-py3"
|
||||
],
|
||||
"ciflow/cuda": [
|
||||
|
|
@ -67,8 +63,6 @@
|
|||
"linux-xenial-cuda11.3-py3.6-gcc7",
|
||||
"linux-xenial-py3.6-gcc5.4",
|
||||
"linux-xenial-py3.6-gcc7-bazel-test",
|
||||
"parallelnative-linux-xenial-py3.6-gcc5.4",
|
||||
"paralleltbb-linux-xenial-py3.6-gcc5.4",
|
||||
"periodic-libtorch-linux-xenial-cuda11.1-py3.6-gcc7",
|
||||
"periodic-linux-xenial-cuda11.1-py3.6-gcc7"
|
||||
],
|
||||
|
|
|
|||
38
.github/scripts/generate_ci_workflows.py
vendored
38
.github/scripts/generate_ci_workflows.py
vendored
|
|
@ -272,32 +272,18 @@ LINUX_WORKFLOWS = [
|
|||
labels={LABEL_CIFLOW_DEFAULT, LABEL_CIFLOW_LINUX, LABEL_CIFLOW_CPU}
|
||||
),
|
||||
),
|
||||
CIWorkflow(
|
||||
arch="linux",
|
||||
build_environment="paralleltbb-linux-xenial-py3.6-gcc5.4",
|
||||
docker_image_base=f"{DOCKER_REGISTRY}/pytorch/pytorch-linux-xenial-py3.6-gcc5.4",
|
||||
test_runner_type=LINUX_CPU_TEST_RUNNER,
|
||||
# This is a master only job despit on_pull_request is set to True
|
||||
on_pull_request=True,
|
||||
ciflow_config=CIFlowConfig(
|
||||
enabled=True,
|
||||
trigger_action_only=True,
|
||||
labels={LABEL_CIFLOW_LINUX, LABEL_CIFLOW_CPU},
|
||||
),
|
||||
),
|
||||
CIWorkflow(
|
||||
arch="linux",
|
||||
build_environment="parallelnative-linux-xenial-py3.6-gcc5.4",
|
||||
docker_image_base=f"{DOCKER_REGISTRY}/pytorch/pytorch-linux-xenial-py3.6-gcc5.4",
|
||||
test_runner_type=LINUX_CPU_TEST_RUNNER,
|
||||
# This is a master only job despit on_pull_request is set to True
|
||||
on_pull_request=True,
|
||||
ciflow_config=CIFlowConfig(
|
||||
enabled=True,
|
||||
trigger_action_only=True,
|
||||
labels={LABEL_CIFLOW_LINUX, LABEL_CIFLOW_CPU},
|
||||
),
|
||||
),
|
||||
# CIWorkflow(
|
||||
# arch="linux",
|
||||
# build_environment="paralleltbb-linux-xenial-py3.6-gcc5.4",
|
||||
# docker_image_base=f"{DOCKER_REGISTRY}/pytorch/pytorch-linux-xenial-py3.6-gcc5.4",
|
||||
# test_runner_type=LINUX_CPU_TEST_RUNNER,
|
||||
# ),
|
||||
# CIWorkflow(
|
||||
# arch="linux",
|
||||
# build_environment="parallelnative-linux-xenial-py3.6-gcc5.4",
|
||||
# docker_image_base=f"{DOCKER_REGISTRY}/pytorch/pytorch-linux-xenial-py3.6-gcc5.4",
|
||||
# test_runner_type=LINUX_CPU_TEST_RUNNER,
|
||||
# ),
|
||||
# CIWorkflow(
|
||||
# arch="linux",
|
||||
# build_environment="pure_torch-linux-xenial-py3.6-gcc5.4",
|
||||
|
|
|
|||
430
.github/workflows/generated-parallelnative-linux-xenial-py3.6-gcc5.4.yml
generated
vendored
430
.github/workflows/generated-parallelnative-linux-xenial-py3.6-gcc5.4.yml
generated
vendored
|
|
@ -1,430 +0,0 @@
|
|||
# @generated DO NOT EDIT MANUALLY
|
||||
|
||||
# Template is at: .github/templates/linux_ci_workflow.yml.j2
|
||||
# Generation script: .github/scripts/generate_ci_workflows.py
|
||||
name: parallelnative-linux-xenial-py3.6-gcc5.4
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
types: [unassigned]
|
||||
push:
|
||||
branches:
|
||||
- master
|
||||
- release/*
|
||||
workflow_dispatch:
|
||||
|
||||
env:
|
||||
BUILD_ENVIRONMENT: parallelnative-linux-xenial-py3.6-gcc5.4
|
||||
DOCKER_IMAGE_BASE: 308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/pytorch-linux-xenial-py3.6-gcc5.4
|
||||
SCCACHE_BUCKET: ossci-compiler-cache-circleci-v2
|
||||
TORCH_CUDA_ARCH_LIST: 5.2
|
||||
IN_CI: 1
|
||||
# This is used for the phase of adding wheel tests only, will be removed once completed
|
||||
IN_WHEEL_TEST: 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: parallelnative-linux-xenial-py3.6-gcc5.4-${{ github.event.pull_request.number || github.sha }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
ciflow_should_run:
|
||||
runs-on: ubuntu-18.04
|
||||
if: ${{ (github.event_name != 'pull_request') || (github.event.action !='unassigned') || (contains(github.event.pull_request.labels.*.name, 'ciflow/all') || contains(github.event.pull_request.labels.*.name, 'ciflow/cpu') || contains(github.event.pull_request.labels.*.name, 'ciflow/linux')) }}
|
||||
steps:
|
||||
- name: noop
|
||||
run: echo running ciflow_should_run
|
||||
calculate-docker-image:
|
||||
if: ${{ github.repository_owner == 'pytorch' }}
|
||||
runs-on: linux.2xlarge
|
||||
needs: [ciflow_should_run]
|
||||
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:?}/*"
|
||||
rm -f ~/.ssh/authorized_keys
|
||||
- name: Checkout PyTorch
|
||||
uses: actions/checkout@v2
|
||||
with:
|
||||
# deep clone, to allow use of git merge-base
|
||||
fetch-depth: 0
|
||||
- name: Display EC2 information
|
||||
shell: bash
|
||||
run: |
|
||||
.github/scripts/display_ec2_information.sh
|
||||
- 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, ciflow_should_run]
|
||||
env:
|
||||
DOCKER_IMAGE: ${{ needs.calculate-docker-image.outputs.docker_image }}
|
||||
JOB_BASE_NAME: parallelnative-linux-xenial-py3.6-gcc5.4-build
|
||||
steps:
|
||||
- name: Log in to ECR
|
||||
run: |
|
||||
aws ecr get-login --no-include-email --region us-east-1 > /tmp/ecr-login.sh
|
||||
bash /tmp/ecr-login.sh
|
||||
rm /tmp/ecr-login.sh
|
||||
- name: Chown workspace
|
||||
run: |
|
||||
# Ensure the working directory gets chowned back to the current user
|
||||
docker run --rm -v "$(pwd)":/v -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .
|
||||
- name: Clean workspace
|
||||
run: |
|
||||
rm -rf "${GITHUB_WORKSPACE:?}/*"
|
||||
rm -f ~/.ssh/authorized_keys
|
||||
- name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
|
||||
uses: seemethere/add-github-ssh-key@v1
|
||||
with:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
- name: Checkout PyTorch
|
||||
uses: actions/checkout@v2
|
||||
with:
|
||||
fetch-depth: 0 # deep clone, to allow sharding to use git rev-list
|
||||
submodules: recursive
|
||||
- name: Display EC2 information
|
||||
shell: bash
|
||||
run: |
|
||||
.github/scripts/display_ec2_information.sh
|
||||
- name: Pull docker image
|
||||
run: |
|
||||
docker pull "${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 \
|
||||
-e http_proxy="http://internal-tf-lb-20210727220640487900000002-835786077.us-east-1.elb.amazonaws.com:3128" -e https_proxy="http://internal-tf-lb-20210727220640487900000002-835786077.us-east-1.elb.amazonaws.com:3128" -e no_proxy="localhost,127.0.0.1,amazonaws.com,s3.amazonaws.com,169.254.169.254,169.254.170.2,/var/run/docker.sock" \
|
||||
--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: Parse ref
|
||||
id: parse-ref
|
||||
run: .github/scripts/parse_ref.py
|
||||
- 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 -1 -r artifacts.zip dist/ build/custom_test_artifacts build/lib build/bin .pytorch-test-times.json
|
||||
- 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: Hold runner for 2 hours or until ssh sessions have drained
|
||||
# Always hold for active ssh sessions
|
||||
if: always()
|
||||
run: .github/scripts/wait_for_ssh_to_drain.sh
|
||||
- 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
|
||||
needs: [ciflow_should_run]
|
||||
env:
|
||||
TEST_RUNNER_TYPE: linux.2xlarge
|
||||
ENABLE_DISTRIBUTED_TEST: 1
|
||||
ENABLE_JIT_LEGACY_TEST: ''
|
||||
ENABLE_MULTIGPU_TEST: ''
|
||||
ENABLE_NOGPU_NO_AVX_TEST: ''
|
||||
ENABLE_NOGPU_NO_AVX2_TEST: ''
|
||||
ENABLE_SLOW_TEST: ''
|
||||
NUM_TEST_SHARDS: 1
|
||||
MULTIGPU_RUNNER_TYPE: linux.16xlarge.nvidia.gpu
|
||||
NOGPU_RUNNER_TYPE: linux.2xlarge
|
||||
PR_BODY: ${{ github.event.pull_request.body }}
|
||||
outputs:
|
||||
matrix: ${{ steps.set-matrix.outputs.matrix }}
|
||||
render-matrix: ${{ steps.set-matrix.outputs.render-matrix }}
|
||||
ignore-disabled-issues: ${{ steps.set-matrix.outputs.ignore-disabled-issues }}
|
||||
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:
|
||||
needs: [calculate-docker-image, build, generate-test-matrix, ciflow_should_run]
|
||||
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: parallelnative-linux-xenial-py3.6-gcc5.4-test
|
||||
TEST_CONFIG: ${{ matrix.config }}
|
||||
SHARD_NUMBER: ${{ matrix.shard }}
|
||||
NUM_TEST_SHARDS: ${{ matrix.num_shards }}
|
||||
PYTORCH_IGNORE_DISABLED_ISSUES: ${{ needs.generate-test-matrix.outputs.ignore-disabled-issues }}
|
||||
CONTINUE_THROUGH_ERROR: ${{ github.repository_owner == 'pytorch' && (github.event_name == 'push' || github.event_name == 'schedule') }}
|
||||
steps:
|
||||
- name: Log in to ECR
|
||||
run: |
|
||||
aws ecr get-login --no-include-email --region us-east-1 > /tmp/ecr-login.sh
|
||||
bash /tmp/ecr-login.sh
|
||||
rm /tmp/ecr-login.sh
|
||||
- name: Chown workspace
|
||||
run: |
|
||||
# Ensure the working directory gets chowned back to the current user
|
||||
docker run --rm -v "$(pwd)/../":/v -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .
|
||||
- name: Clean workspace
|
||||
run: |
|
||||
rm -rf "${GITHUB_WORKSPACE:?}/*"
|
||||
rm -f ~/.ssh/authorized_keys
|
||||
- name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
|
||||
uses: seemethere/add-github-ssh-key@v1
|
||||
with:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
- name: Checkout PyTorch
|
||||
uses: actions/checkout@v2
|
||||
with:
|
||||
fetch-depth: 0 # deep clone, to allow sharding to use git rev-list
|
||||
submodules: recursive
|
||||
- name: Display EC2 information
|
||||
shell: bash
|
||||
run: |
|
||||
.github/scripts/display_ec2_information.sh
|
||||
- name: Pull docker image
|
||||
run: |
|
||||
docker pull "${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
|
||||
env:
|
||||
BUILD_ENVIRONMENT: parallelnative-linux-xenial-py3.6-gcc5.4-${{ matrix.config }}
|
||||
PR_NUMBER: ${{ github.event.pull_request.number }}
|
||||
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 \
|
||||
${GPU_FLAG:-} \
|
||||
-e BUILD_ENVIRONMENT \
|
||||
-e PR_NUMBER \
|
||||
-e CUSTOM_TEST_ARTIFACT_BUILD_DIR \
|
||||
-e GITHUB_ACTIONS \
|
||||
-e IN_CI \
|
||||
-e IN_WHEEL_TEST \
|
||||
-e SHARD_NUMBER \
|
||||
-e JOB_BASE_NAME \
|
||||
-e TEST_CONFIG \
|
||||
-e NUM_TEST_SHARDS \
|
||||
-e PYTORCH_IGNORE_DISABLED_ISSUES \
|
||||
-e CONTINUE_THROUGH_ERROR \
|
||||
-e MAX_JOBS="$(nproc --ignore=2)" \
|
||||
-e SCCACHE_BUCKET \
|
||||
-e http_proxy="http://internal-tf-lb-20210727220640487900000002-835786077.us-east-1.elb.amazonaws.com:3128" -e https_proxy="http://internal-tf-lb-20210727220640487900000002-835786077.us-east-1.elb.amazonaws.com:3128" -e no_proxy="localhost,127.0.0.1,amazonaws.com,s3.amazonaws.com,169.254.169.254,169.254.170.2,/var/run/docker.sock" \
|
||||
--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()
|
||||
env:
|
||||
COMMIT_SHA1: ${{ github.event.pull_request.head.sha || github.sha }}
|
||||
WORKFLOW_ID: '${{ github.run_id }}_${{ github.run_number }}'
|
||||
run: |
|
||||
# Remove any previous test reports if they exist
|
||||
rm -f test-reports-*.zip
|
||||
zip -r "test-reports-${COMMIT_SHA1}-${WORKFLOW_ID}.zip" test -i '*.xml'
|
||||
- uses: actions/upload-artifact@v2
|
||||
name: Store PyTorch Test Reports
|
||||
if: always()
|
||||
with:
|
||||
name: test-reports-${{ 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: 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: parallelnative-linux-xenial-py3.6-gcc5.4-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 }}_${{ github.run_number }}'
|
||||
shell: bash
|
||||
run: |
|
||||
python3 -m pip install -r requirements.txt
|
||||
python3 -m pip install boto3==1.16.34
|
||||
python3 -m tools.stats.print_test_stats --upload-to-s3 --compare-with-s3 test
|
||||
- name: Hold runner for 2 hours or until ssh sessions have drained
|
||||
# Always hold for active ssh sessions
|
||||
if: always()
|
||||
run: .github/scripts/wait_for_ssh_to_drain.sh
|
||||
- name: Clean up docker images
|
||||
if: always()
|
||||
run: |
|
||||
# Ensure the working directory gets chowned back to the current user
|
||||
docker run --rm -v "$(pwd)":/v -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .
|
||||
# Prune all of the docker images
|
||||
docker system prune -af
|
||||
430
.github/workflows/generated-paralleltbb-linux-xenial-py3.6-gcc5.4.yml
generated
vendored
430
.github/workflows/generated-paralleltbb-linux-xenial-py3.6-gcc5.4.yml
generated
vendored
|
|
@ -1,430 +0,0 @@
|
|||
# @generated DO NOT EDIT MANUALLY
|
||||
|
||||
# Template is at: .github/templates/linux_ci_workflow.yml.j2
|
||||
# Generation script: .github/scripts/generate_ci_workflows.py
|
||||
name: paralleltbb-linux-xenial-py3.6-gcc5.4
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
types: [unassigned]
|
||||
push:
|
||||
branches:
|
||||
- master
|
||||
- release/*
|
||||
workflow_dispatch:
|
||||
|
||||
env:
|
||||
BUILD_ENVIRONMENT: paralleltbb-linux-xenial-py3.6-gcc5.4
|
||||
DOCKER_IMAGE_BASE: 308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/pytorch-linux-xenial-py3.6-gcc5.4
|
||||
SCCACHE_BUCKET: ossci-compiler-cache-circleci-v2
|
||||
TORCH_CUDA_ARCH_LIST: 5.2
|
||||
IN_CI: 1
|
||||
# This is used for the phase of adding wheel tests only, will be removed once completed
|
||||
IN_WHEEL_TEST: 1
|
||||
# Used for custom_opertor, jit_hooks, custom_backend, see .jenkins/pytorch/build.sh
|
||||
CUSTOM_TEST_ARTIFACT_BUILD_DIR: build/custom_test_artifacts
|
||||
ALPINE_IMAGE: "308535385114.dkr.ecr.us-east-1.amazonaws.com/tool/alpine"
|
||||
|
||||
concurrency:
|
||||
group: paralleltbb-linux-xenial-py3.6-gcc5.4-${{ github.event.pull_request.number || github.sha }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
ciflow_should_run:
|
||||
runs-on: ubuntu-18.04
|
||||
if: ${{ (github.event_name != 'pull_request') || (github.event.action !='unassigned') || (contains(github.event.pull_request.labels.*.name, 'ciflow/all') || contains(github.event.pull_request.labels.*.name, 'ciflow/cpu') || contains(github.event.pull_request.labels.*.name, 'ciflow/linux')) }}
|
||||
steps:
|
||||
- name: noop
|
||||
run: echo running ciflow_should_run
|
||||
calculate-docker-image:
|
||||
if: ${{ github.repository_owner == 'pytorch' }}
|
||||
runs-on: linux.2xlarge
|
||||
needs: [ciflow_should_run]
|
||||
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:?}/*"
|
||||
rm -f ~/.ssh/authorized_keys
|
||||
- name: Checkout PyTorch
|
||||
uses: actions/checkout@v2
|
||||
with:
|
||||
# deep clone, to allow use of git merge-base
|
||||
fetch-depth: 0
|
||||
- name: Display EC2 information
|
||||
shell: bash
|
||||
run: |
|
||||
.github/scripts/display_ec2_information.sh
|
||||
- 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, ciflow_should_run]
|
||||
env:
|
||||
DOCKER_IMAGE: ${{ needs.calculate-docker-image.outputs.docker_image }}
|
||||
JOB_BASE_NAME: paralleltbb-linux-xenial-py3.6-gcc5.4-build
|
||||
steps:
|
||||
- name: Log in to ECR
|
||||
run: |
|
||||
aws ecr get-login --no-include-email --region us-east-1 > /tmp/ecr-login.sh
|
||||
bash /tmp/ecr-login.sh
|
||||
rm /tmp/ecr-login.sh
|
||||
- name: Chown workspace
|
||||
run: |
|
||||
# Ensure the working directory gets chowned back to the current user
|
||||
docker run --rm -v "$(pwd)":/v -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .
|
||||
- name: Clean workspace
|
||||
run: |
|
||||
rm -rf "${GITHUB_WORKSPACE:?}/*"
|
||||
rm -f ~/.ssh/authorized_keys
|
||||
- name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
|
||||
uses: seemethere/add-github-ssh-key@v1
|
||||
with:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
- name: Checkout PyTorch
|
||||
uses: actions/checkout@v2
|
||||
with:
|
||||
fetch-depth: 0 # deep clone, to allow sharding to use git rev-list
|
||||
submodules: recursive
|
||||
- name: Display EC2 information
|
||||
shell: bash
|
||||
run: |
|
||||
.github/scripts/display_ec2_information.sh
|
||||
- name: Pull docker image
|
||||
run: |
|
||||
docker pull "${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 \
|
||||
-e http_proxy="http://internal-tf-lb-20210727220640487900000002-835786077.us-east-1.elb.amazonaws.com:3128" -e https_proxy="http://internal-tf-lb-20210727220640487900000002-835786077.us-east-1.elb.amazonaws.com:3128" -e no_proxy="localhost,127.0.0.1,amazonaws.com,s3.amazonaws.com,169.254.169.254,169.254.170.2,/var/run/docker.sock" \
|
||||
--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: Parse ref
|
||||
id: parse-ref
|
||||
run: .github/scripts/parse_ref.py
|
||||
- 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 -1 -r artifacts.zip dist/ build/custom_test_artifacts build/lib build/bin .pytorch-test-times.json
|
||||
- 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: Hold runner for 2 hours or until ssh sessions have drained
|
||||
# Always hold for active ssh sessions
|
||||
if: always()
|
||||
run: .github/scripts/wait_for_ssh_to_drain.sh
|
||||
- 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
|
||||
needs: [ciflow_should_run]
|
||||
env:
|
||||
TEST_RUNNER_TYPE: linux.2xlarge
|
||||
ENABLE_DISTRIBUTED_TEST: 1
|
||||
ENABLE_JIT_LEGACY_TEST: ''
|
||||
ENABLE_MULTIGPU_TEST: ''
|
||||
ENABLE_NOGPU_NO_AVX_TEST: ''
|
||||
ENABLE_NOGPU_NO_AVX2_TEST: ''
|
||||
ENABLE_SLOW_TEST: ''
|
||||
NUM_TEST_SHARDS: 1
|
||||
MULTIGPU_RUNNER_TYPE: linux.16xlarge.nvidia.gpu
|
||||
NOGPU_RUNNER_TYPE: linux.2xlarge
|
||||
PR_BODY: ${{ github.event.pull_request.body }}
|
||||
outputs:
|
||||
matrix: ${{ steps.set-matrix.outputs.matrix }}
|
||||
render-matrix: ${{ steps.set-matrix.outputs.render-matrix }}
|
||||
ignore-disabled-issues: ${{ steps.set-matrix.outputs.ignore-disabled-issues }}
|
||||
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:
|
||||
needs: [calculate-docker-image, build, generate-test-matrix, ciflow_should_run]
|
||||
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: paralleltbb-linux-xenial-py3.6-gcc5.4-test
|
||||
TEST_CONFIG: ${{ matrix.config }}
|
||||
SHARD_NUMBER: ${{ matrix.shard }}
|
||||
NUM_TEST_SHARDS: ${{ matrix.num_shards }}
|
||||
PYTORCH_IGNORE_DISABLED_ISSUES: ${{ needs.generate-test-matrix.outputs.ignore-disabled-issues }}
|
||||
CONTINUE_THROUGH_ERROR: ${{ github.repository_owner == 'pytorch' && (github.event_name == 'push' || github.event_name == 'schedule') }}
|
||||
steps:
|
||||
- name: Log in to ECR
|
||||
run: |
|
||||
aws ecr get-login --no-include-email --region us-east-1 > /tmp/ecr-login.sh
|
||||
bash /tmp/ecr-login.sh
|
||||
rm /tmp/ecr-login.sh
|
||||
- name: Chown workspace
|
||||
run: |
|
||||
# Ensure the working directory gets chowned back to the current user
|
||||
docker run --rm -v "$(pwd)/../":/v -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .
|
||||
- name: Clean workspace
|
||||
run: |
|
||||
rm -rf "${GITHUB_WORKSPACE:?}/*"
|
||||
rm -f ~/.ssh/authorized_keys
|
||||
- name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
|
||||
uses: seemethere/add-github-ssh-key@v1
|
||||
with:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
- name: Checkout PyTorch
|
||||
uses: actions/checkout@v2
|
||||
with:
|
||||
fetch-depth: 0 # deep clone, to allow sharding to use git rev-list
|
||||
submodules: recursive
|
||||
- name: Display EC2 information
|
||||
shell: bash
|
||||
run: |
|
||||
.github/scripts/display_ec2_information.sh
|
||||
- name: Pull docker image
|
||||
run: |
|
||||
docker pull "${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
|
||||
env:
|
||||
BUILD_ENVIRONMENT: paralleltbb-linux-xenial-py3.6-gcc5.4-${{ matrix.config }}
|
||||
PR_NUMBER: ${{ github.event.pull_request.number }}
|
||||
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 \
|
||||
${GPU_FLAG:-} \
|
||||
-e BUILD_ENVIRONMENT \
|
||||
-e PR_NUMBER \
|
||||
-e CUSTOM_TEST_ARTIFACT_BUILD_DIR \
|
||||
-e GITHUB_ACTIONS \
|
||||
-e IN_CI \
|
||||
-e IN_WHEEL_TEST \
|
||||
-e SHARD_NUMBER \
|
||||
-e JOB_BASE_NAME \
|
||||
-e TEST_CONFIG \
|
||||
-e NUM_TEST_SHARDS \
|
||||
-e PYTORCH_IGNORE_DISABLED_ISSUES \
|
||||
-e CONTINUE_THROUGH_ERROR \
|
||||
-e MAX_JOBS="$(nproc --ignore=2)" \
|
||||
-e SCCACHE_BUCKET \
|
||||
-e http_proxy="http://internal-tf-lb-20210727220640487900000002-835786077.us-east-1.elb.amazonaws.com:3128" -e https_proxy="http://internal-tf-lb-20210727220640487900000002-835786077.us-east-1.elb.amazonaws.com:3128" -e no_proxy="localhost,127.0.0.1,amazonaws.com,s3.amazonaws.com,169.254.169.254,169.254.170.2,/var/run/docker.sock" \
|
||||
--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()
|
||||
env:
|
||||
COMMIT_SHA1: ${{ github.event.pull_request.head.sha || github.sha }}
|
||||
WORKFLOW_ID: '${{ github.run_id }}_${{ github.run_number }}'
|
||||
run: |
|
||||
# Remove any previous test reports if they exist
|
||||
rm -f test-reports-*.zip
|
||||
zip -r "test-reports-${COMMIT_SHA1}-${WORKFLOW_ID}.zip" test -i '*.xml'
|
||||
- uses: actions/upload-artifact@v2
|
||||
name: Store PyTorch Test Reports
|
||||
if: always()
|
||||
with:
|
||||
name: test-reports-${{ 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: 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: paralleltbb-linux-xenial-py3.6-gcc5.4-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 }}_${{ github.run_number }}'
|
||||
shell: bash
|
||||
run: |
|
||||
python3 -m pip install -r requirements.txt
|
||||
python3 -m pip install boto3==1.16.34
|
||||
python3 -m tools.stats.print_test_stats --upload-to-s3 --compare-with-s3 test
|
||||
- name: Hold runner for 2 hours or until ssh sessions have drained
|
||||
# Always hold for active ssh sessions
|
||||
if: always()
|
||||
run: .github/scripts/wait_for_ssh_to_drain.sh
|
||||
- name: Clean up docker images
|
||||
if: always()
|
||||
run: |
|
||||
# Ensure the working directory gets chowned back to the current user
|
||||
docker run --rm -v "$(pwd)":/v -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .
|
||||
# Prune all of the docker images
|
||||
docker system prune -af
|
||||
Loading…
Reference in New Issue
Block a user