pytorch/.github/workflows/_linux-build.yml
Catherine Lee f16be5e0d4 Reordering tests experiment (#106347)
Companion with https://github.com/pytorch/test-infra/pull/4424

Uses the file rating generated by the test infra PR to re order tests.  For each test file, sum the file ratings from the changed files in the PR, and put the tests in order of sum.

A lot of tests are probably going to end up as "prioritized" since it takes anything with a rating > 0 right now.

Sharding is done twice, once on the prioritized tests, and once on the general/non prioritized tests.  Prioritized tests have an order, so they should be sharded according to that order, while general tests don't have an order and are sharded by test time, which should result in more balanced shards.

I'll change the metric name before I merge, i want to quarantine my testing stuff from actual results

Pull Request resolved: https://github.com/pytorch/pytorch/pull/106347
Approved by: https://github.com/ZainRizvi
2023-08-16 18:23:09 +00:00

196 lines
7.2 KiB
YAML

name: linux-build
on:
workflow_call:
inputs:
build-environment:
required: true
type: string
description: Top-level label for what's being built/tested.
docker-image-name:
required: true
type: string
description: Name of the base docker image to build with.
build-generates-artifacts:
required: false
type: boolean
default: true
description: If set, upload generated build artifacts.
build-with-debug:
required: false
type: boolean
default: false
description: If set, build in debug mode.
sync-tag:
required: false
type: string
default: ""
description: |
If this is set, our linter will use this to make sure that every other
job with the same `sync-tag` is identical.
cuda-arch-list:
required: false
type: string
default: "5.2"
description: |
List of CUDA architectures CI build should target.
runner:
required: false
type: string
default: "linux.2xlarge"
description: |
List of CUDA architectures CI build should target.
test-matrix:
required: false
type: string
description: |
An option JSON description of what test configs to run later on. This
is moved here from the Linux test workflow so that we can apply filter
logic using test-config labels earlier and skip unnecessary builds
secrets:
HUGGING_FACE_HUB_TOKEN:
required: false
description: |
HF Auth token to avoid rate limits when downloading models or datasets from hub
outputs:
docker-image:
value: ${{ jobs.build.outputs.docker-image }}
description: The docker image containing the built PyTorch.
test-matrix:
value: ${{ jobs.build.outputs.test-matrix }}
description: An optional JSON description of what test configs to run later on.
jobs:
build:
# Don't run on forked repos
if: github.repository_owner == 'pytorch'
runs-on: ${{ inputs.runner }}
timeout-minutes: 240
outputs:
docker-image: ${{ steps.calculate-docker-image.outputs.docker-image }}
test-matrix: ${{ steps.filter.outputs.test-matrix }}
steps:
- name: Setup SSH (Click me for login details)
uses: pytorch/test-infra/.github/actions/setup-ssh@main
with:
github-secret: ${{ secrets.GITHUB_TOKEN }}
# [pytorch repo ref]
# Use a pytorch/pytorch reference instead of a reference to the local
# checkout because when we run this action we don't *have* a local
# checkout. In other cases you should prefer a local checkout.
- name: Checkout PyTorch
uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
- name: Setup Linux
uses: ./.github/actions/setup-linux
- name: Calculate docker image
id: calculate-docker-image
uses: pytorch/test-infra/.github/actions/calculate-docker-image@main
with:
docker-image-name: ${{ inputs.docker-image-name }}
- name: Pull docker image
uses: pytorch/test-infra/.github/actions/pull-docker-image@main
with:
docker-image: ${{ steps.calculate-docker-image.outputs.docker-image }}
- name: Parse ref
id: parse-ref
run: .github/scripts/parse_ref.py
- name: Get workflow job id
id: get-job-id
uses: ./.github/actions/get-workflow-job-id
if: always()
with:
github-token: ${{ secrets.GITHUB_TOKEN }}
# Apply the filter logic to the build step too if the test-config label is already there
- name: Select all requested test configurations (if the test matrix is available)
id: filter
uses: ./.github/actions/filter-test-configs
with:
github-token: ${{ secrets.GITHUB_TOKEN }}
test-matrix: ${{ inputs.test-matrix }}
- name: Build
if: steps.filter.outputs.is-test-matrix-empty == 'False' || inputs.test-matrix == ''
id: build
env:
BUILD_ENVIRONMENT: ${{ inputs.build-environment }}
BRANCH: ${{ steps.parse-ref.outputs.branch }}
# TODO duplicated
AWS_DEFAULT_REGION: us-east-1
PR_NUMBER: ${{ github.event.pull_request.number }}
SHA1: ${{ github.event.pull_request.head.sha || github.sha }}
SCCACHE_BUCKET: ossci-compiler-cache-circleci-v2
SCCACHE_S3_KEY_PREFIX: ${{ github.workflow }}
XLA_CLANG_CACHE_S3_BUCKET_NAME: ossci-compiler-clang-cache-circleci-xla
PR_LABELS: ${{ toJson(github.event.pull_request.labels.*.name) }}
TORCH_CUDA_ARCH_LIST: ${{ inputs.cuda-arch-list }}
DOCKER_IMAGE: ${{ steps.calculate-docker-image.outputs.docker-image }}
XLA_CUDA: ${{ contains(inputs.build-environment, 'xla') && '0' || '' }}
DEBUG: ${{ inputs.build-with-debug && '1' || '0' }}
OUR_GITHUB_JOB_ID: ${{ steps.get-job-id.outputs.job-id }}
HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
run: |
# detached container should get cleaned up by teardown_ec2_linux
container_name=$(docker run \
-e BUILD_ENVIRONMENT \
-e MAX_JOBS="$(nproc --ignore=2)" \
-e AWS_DEFAULT_REGION \
-e PR_NUMBER \
-e SHA1 \
-e BRANCH \
-e SCCACHE_BUCKET \
-e SCCACHE_S3_KEY_PREFIX \
-e XLA_CUDA \
-e XLA_CLANG_CACHE_S3_BUCKET_NAME \
-e SKIP_SCCACHE_INITIALIZATION=1 \
-e TORCH_CUDA_ARCH_LIST \
-e PR_LABELS \
-e OUR_GITHUB_JOB_ID \
-e HUGGING_FACE_HUB_TOKEN \
--env-file="/tmp/github_env_${GITHUB_RUN_ID}" \
--security-opt seccomp=unconfined \
--cap-add=SYS_PTRACE \
--tty \
--detach \
--user jenkins \
-v "${GITHUB_WORKSPACE}:/var/lib/jenkins/workspace" \
-w /var/lib/jenkins/workspace \
"${DOCKER_IMAGE}"
)
docker exec -t "${container_name}" sh -c '.ci/pytorch/build.sh'
- name: Archive artifacts into zip
if: inputs.build-generates-artifacts && steps.build.outcome != 'skipped'
run: |
zip -1 -r artifacts.zip dist/ build/custom_test_artifacts build/lib build/bin .pytorch-test-times.json .pytorch-test-file-ratings.json
- name: Store PyTorch Build Artifacts on S3
uses: seemethere/upload-artifact-s3@v5
if: inputs.build-generates-artifacts && steps.build.outcome != 'skipped'
with:
name: ${{ inputs.build-environment }}
retention-days: 14
if-no-files-found: error
path: artifacts.zip
- name: Upload sccache stats
if: steps.build.outcome != 'skipped'
uses: seemethere/upload-artifact-s3@v5
with:
s3-prefix: |
${{ github.repository }}/${{ github.run_id }}/${{ github.run_attempt }}/artifact
retention-days: 365
if-no-files-found: warn
path: sccache-stats-*.json
- name: Teardown Linux
uses: pytorch/test-infra/.github/actions/teardown-linux@main
if: always()