Skip to content

[distributed_test_c10d]: Enable disabled ROCm tests.#50629

Closed
jaglinux wants to merge 2 commits intopytorch:masterfrom
jaglinux:origin/enable_distributed_c10
Closed

[distributed_test_c10d]: Enable disabled ROCm tests.#50629
jaglinux wants to merge 2 commits intopytorch:masterfrom
jaglinux:origin/enable_distributed_c10

Conversation

@jaglinux
Copy link
Copy Markdown
Contributor

Signed-off-by: Jagadish Krishnamoorthy jagdish.krishna@gmail.com

Signed-off-by: Jagadish Krishnamoorthy <jagdish.krishna@gmail.com>
@facebook-github-bot facebook-github-bot added the oncall: distributed Add this issue/PR to distributed oncall triage queue label Jan 15, 2021
@jaglinux
Copy link
Copy Markdown
Contributor Author

cc: @jeffdaily

Copy link
Copy Markdown
Contributor

@rohan-varma rohan-varma left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for this! I assume that the CI jobs passing such as ci/circleci: docker-pytorch-linux-bionic-rocm3.9-py3.6 indicates that the tests are running as expected?

Also, could you fix the lint issue:
{
path: 'test/distributed/test_c10d.py',
start_line: 28,
end_line: 28,
start_column: 1,
end_column: 1,
annotation_level: 'failure',
message: "[F401] 'torch.testing._internal.common_distributed.skip_if_rocm_single_process' imported but unused"
}

Will land after that.

Signed-off-by: Jagadish Krishnamoorthy <jagdish.krishna@gmail.com>
@jaglinux
Copy link
Copy Markdown
Contributor Author

Thanks for this! I assume that the CI jobs passing such as ci/circleci: docker-pytorch-linux-bionic-rocm3.9-py3.6 indicates that the tests are running as expected?

Also, could you fix the lint issue:
{
path: 'test/distributed/test_c10d.py',
start_line: 28,
end_line: 28,
start_column: 1,
end_column: 1,
annotation_level: 'failure',
message: "[F401] 'torch.testing._internal.common_distributed.skip_if_rocm_single_process' imported but unused"
}

Will land after that.

Thanks for the review comments.
Yes, it should affect only ROCm tests which is passing.

Copy link
Copy Markdown
Contributor

@facebook-github-bot facebook-github-bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@rohan-varma has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

@rohan-varma
Copy link
Copy Markdown
Contributor

Failure looks unrelated - RuntimeError: test_tensor_creation_ops failed!

@facebook-github-bot
Copy link
Copy Markdown
Contributor

@rohan-varma merged this pull request in 7e05d07.

facebook-github-bot pushed a commit that referenced this pull request Feb 24, 2021
Summary:
The Flake8 job has been passing on `master` despite giving warnings for [over a month](https://github.com/pytorch/pytorch/runs/1716124347). This is because it has been using a regex that doesn't recognize error codes starting with multiple letters, such as those used by [flake8-executable](https://pypi.org/project/flake8-executable/). This PR corrects the regex, and also adds another step at the end of the job which asserts that Flake8 actually gave no error output, in case similar regex issues appear in the future.

Tagging the following people to ask what to do to fix these `EXE002` warnings:

- #50629 authored by jaglinux, approved by rohan-varma
  - `test/distributed/test_c10d.py`
- #51262 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/__init__.py`
  - `torch/utils/data/datapipes/iter/loadfilesfromdisk.py`
  - `torch/utils/data/datapipes/iter/listdirfiles.py`
  - `torch/utils/data/datapipes/iter/__init__.py`
  - `torch/utils/data/datapipes/utils/__init__.py`
  - `torch/utils/data/datapipes/utils/common.py`
- #51398 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/readfilesfromtar.py`
- #51599 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/readfilesfromzip.py`
- #51704 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/routeddecoder.py`
  - `torch/utils/data/datapipes/utils/decoder.py`
- #51709 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/groupbykey.py`

Specifically, the question is: for each of those files, should we remove the execute permissions, or should we add a shebang? And if the latter, which shebang?

Pull Request resolved: #52750

Test Plan:
The **Lint / flake8-py3** job in GitHub Actions:

- [this run](https://github.com/pytorch/pytorch/runs/1972039886) failed, showing that the new regex catches these warnings properly
- [this run](https://github.com/pytorch/pytorch/runs/1972393293) succeeded and gave no output in the "Run flake8" step, showing that this PR fixed all Flake8 warnings
- [this run](https://github.com/pytorch/pytorch/pull/52755/checks?check_run_id=1972414849) (in #52755) failed, showing that the new last step of the job successfully catches Flake8 warnings even without the regex fix

Reviewed By: walterddr, janeyx99

Differential Revision: D26637307

Pulled By: samestep

fbshipit-source-id: 572af6a3bbe57f5e9bd47f19f37c39db90f7b804
walterddr pushed a commit to walterddr/pytorch that referenced this pull request Feb 25, 2021
Summary:
The Flake8 job has been passing on `master` despite giving warnings for [over a month](https://github.com/pytorch/pytorch/runs/1716124347). This is because it has been using a regex that doesn't recognize error codes starting with multiple letters, such as those used by [flake8-executable](https://pypi.org/project/flake8-executable/). This PR corrects the regex, and also adds another step at the end of the job which asserts that Flake8 actually gave no error output, in case similar regex issues appear in the future.

Tagging the following people to ask what to do to fix these `EXE002` warnings:

- pytorch#50629 authored by jaglinux, approved by rohan-varma
  - `test/distributed/test_c10d.py`
- pytorch#51262 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/__init__.py`
  - `torch/utils/data/datapipes/iter/loadfilesfromdisk.py`
  - `torch/utils/data/datapipes/iter/listdirfiles.py`
  - `torch/utils/data/datapipes/iter/__init__.py`
  - `torch/utils/data/datapipes/utils/__init__.py`
  - `torch/utils/data/datapipes/utils/common.py`
- pytorch#51398 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/readfilesfromtar.py`
- pytorch#51599 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/readfilesfromzip.py`
- pytorch#51704 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/routeddecoder.py`
  - `torch/utils/data/datapipes/utils/decoder.py`
- pytorch#51709 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/groupbykey.py`

Specifically, the question is: for each of those files, should we remove the execute permissions, or should we add a shebang? And if the latter, which shebang?

Pull Request resolved: pytorch#52750

Test Plan:
The **Lint / flake8-py3** job in GitHub Actions:

- [this run](https://github.com/pytorch/pytorch/runs/1972039886) failed, showing that the new regex catches these warnings properly
- [this run](https://github.com/pytorch/pytorch/runs/1972393293) succeeded and gave no output in the "Run flake8" step, showing that this PR fixed all Flake8 warnings
- [this run](https://github.com/pytorch/pytorch/pull/52755/checks?check_run_id=1972414849) (in pytorch#52755) failed, showing that the new last step of the job successfully catches Flake8 warnings even without the regex fix

Reviewed By: walterddr, janeyx99

Differential Revision: D26637307

Pulled By: samestep

fbshipit-source-id: 572af6a3bbe57f5e9bd47f19f37c39db90f7b804
malfet pushed a commit that referenced this pull request Feb 26, 2021
Summary:
The Flake8 job has been passing on `master` despite giving warnings for [over a month](https://github.com/pytorch/pytorch/runs/1716124347). This is because it has been using a regex that doesn't recognize error codes starting with multiple letters, such as those used by [flake8-executable](https://pypi.org/project/flake8-executable/). This PR corrects the regex, and also adds another step at the end of the job which asserts that Flake8 actually gave no error output, in case similar regex issues appear in the future.

Tagging the following people to ask what to do to fix these `EXE002` warnings:

- #50629 authored by jaglinux, approved by rohan-varma
  - `test/distributed/test_c10d.py`
- #51262 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/__init__.py`
  - `torch/utils/data/datapipes/iter/loadfilesfromdisk.py`
  - `torch/utils/data/datapipes/iter/listdirfiles.py`
  - `torch/utils/data/datapipes/iter/__init__.py`
  - `torch/utils/data/datapipes/utils/__init__.py`
  - `torch/utils/data/datapipes/utils/common.py`
- #51398 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/readfilesfromtar.py`
- #51599 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/readfilesfromzip.py`
- #51704 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/routeddecoder.py`
  - `torch/utils/data/datapipes/utils/decoder.py`
- #51709 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/groupbykey.py`

Specifically, the question is: for each of those files, should we remove the execute permissions, or should we add a shebang? And if the latter, which shebang?

Pull Request resolved: #52750

Test Plan:
The **Lint / flake8-py3** job in GitHub Actions:

- [this run](https://github.com/pytorch/pytorch/runs/1972039886) failed, showing that the new regex catches these warnings properly
- [this run](https://github.com/pytorch/pytorch/runs/1972393293) succeeded and gave no output in the "Run flake8" step, showing that this PR fixed all Flake8 warnings
- [this run](https://github.com/pytorch/pytorch/pull/52755/checks?check_run_id=1972414849) (in #52755) failed, showing that the new last step of the job successfully catches Flake8 warnings even without the regex fix

Reviewed By: walterddr, janeyx99

Differential Revision: D26637307

Pulled By: samestep

fbshipit-source-id: 572af6a3bbe57f5e9bd47f19f37c39db90f7b804

Co-authored-by: Sam Estep <sestep@fb.com>
aocsa pushed a commit to Quansight/pytorch that referenced this pull request Mar 15, 2021
Summary:
The Flake8 job has been passing on `master` despite giving warnings for [over a month](https://github.com/pytorch/pytorch/runs/1716124347). This is because it has been using a regex that doesn't recognize error codes starting with multiple letters, such as those used by [flake8-executable](https://pypi.org/project/flake8-executable/). This PR corrects the regex, and also adds another step at the end of the job which asserts that Flake8 actually gave no error output, in case similar regex issues appear in the future.

Tagging the following people to ask what to do to fix these `EXE002` warnings:

- pytorch#50629 authored by jaglinux, approved by rohan-varma
  - `test/distributed/test_c10d.py`
- pytorch#51262 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/__init__.py`
  - `torch/utils/data/datapipes/iter/loadfilesfromdisk.py`
  - `torch/utils/data/datapipes/iter/listdirfiles.py`
  - `torch/utils/data/datapipes/iter/__init__.py`
  - `torch/utils/data/datapipes/utils/__init__.py`
  - `torch/utils/data/datapipes/utils/common.py`
- pytorch#51398 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/readfilesfromtar.py`
- pytorch#51599 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/readfilesfromzip.py`
- pytorch#51704 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/routeddecoder.py`
  - `torch/utils/data/datapipes/utils/decoder.py`
- pytorch#51709 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/groupbykey.py`

Specifically, the question is: for each of those files, should we remove the execute permissions, or should we add a shebang? And if the latter, which shebang?

Pull Request resolved: pytorch#52750

Test Plan:
The **Lint / flake8-py3** job in GitHub Actions:

- [this run](https://github.com/pytorch/pytorch/runs/1972039886) failed, showing that the new regex catches these warnings properly
- [this run](https://github.com/pytorch/pytorch/runs/1972393293) succeeded and gave no output in the "Run flake8" step, showing that this PR fixed all Flake8 warnings
- [this run](https://github.com/pytorch/pytorch/pull/52755/checks?check_run_id=1972414849) (in pytorch#52755) failed, showing that the new last step of the job successfully catches Flake8 warnings even without the regex fix

Reviewed By: walterddr, janeyx99

Differential Revision: D26637307

Pulled By: samestep

fbshipit-source-id: 572af6a3bbe57f5e9bd47f19f37c39db90f7b804
xsacha pushed a commit to xsacha/pytorch that referenced this pull request Mar 31, 2021
Summary:
The Flake8 job has been passing on `master` despite giving warnings for [over a month](https://github.com/pytorch/pytorch/runs/1716124347). This is because it has been using a regex that doesn't recognize error codes starting with multiple letters, such as those used by [flake8-executable](https://pypi.org/project/flake8-executable/). This PR corrects the regex, and also adds another step at the end of the job which asserts that Flake8 actually gave no error output, in case similar regex issues appear in the future.

Tagging the following people to ask what to do to fix these `EXE002` warnings:

- pytorch#50629 authored by jaglinux, approved by rohan-varma
  - `test/distributed/test_c10d.py`
- pytorch#51262 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/__init__.py`
  - `torch/utils/data/datapipes/iter/loadfilesfromdisk.py`
  - `torch/utils/data/datapipes/iter/listdirfiles.py`
  - `torch/utils/data/datapipes/iter/__init__.py`
  - `torch/utils/data/datapipes/utils/__init__.py`
  - `torch/utils/data/datapipes/utils/common.py`
- pytorch#51398 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/readfilesfromtar.py`
- pytorch#51599 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/readfilesfromzip.py`
- pytorch#51704 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/routeddecoder.py`
  - `torch/utils/data/datapipes/utils/decoder.py`
- pytorch#51709 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/groupbykey.py`

Specifically, the question is: for each of those files, should we remove the execute permissions, or should we add a shebang? And if the latter, which shebang?

Pull Request resolved: pytorch#52750

Test Plan:
The **Lint / flake8-py3** job in GitHub Actions:

- [this run](https://github.com/pytorch/pytorch/runs/1972039886) failed, showing that the new regex catches these warnings properly
- [this run](https://github.com/pytorch/pytorch/runs/1972393293) succeeded and gave no output in the "Run flake8" step, showing that this PR fixed all Flake8 warnings
- [this run](https://github.com/pytorch/pytorch/pull/52755/checks?check_run_id=1972414849) (in pytorch#52755) failed, showing that the new last step of the job successfully catches Flake8 warnings even without the regex fix

Reviewed By: walterddr, janeyx99

Differential Revision: D26637307

Pulled By: samestep

fbshipit-source-id: 572af6a3bbe57f5e9bd47f19f37c39db90f7b804
laurentdupin pushed a commit to laurentdupin/pytorch that referenced this pull request Apr 24, 2026
Summary:
Signed-off-by: Jagadish Krishnamoorthy <jagdish.krishna@gmail.com>

Pull Request resolved: pytorch#50629

Reviewed By: albanD

Differential Revision: D25935005

Pulled By: rohan-varma

fbshipit-source-id: e0969afecac2f319833189a7a8897d78068a2cda
laurentdupin pushed a commit to laurentdupin/pytorch that referenced this pull request Apr 24, 2026
Summary:
The Flake8 job has been passing on `master` despite giving warnings for [over a month](https://github.com/pytorch/pytorch/runs/1716124347). This is because it has been using a regex that doesn't recognize error codes starting with multiple letters, such as those used by [flake8-executable](https://pypi.org/project/flake8-executable/). This PR corrects the regex, and also adds another step at the end of the job which asserts that Flake8 actually gave no error output, in case similar regex issues appear in the future.

Tagging the following people to ask what to do to fix these `EXE002` warnings:

- pytorch#50629 authored by jaglinux, approved by rohan-varma
  - `test/distributed/test_c10d.py`
- pytorch#51262 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/__init__.py`
  - `torch/utils/data/datapipes/iter/loadfilesfromdisk.py`
  - `torch/utils/data/datapipes/iter/listdirfiles.py`
  - `torch/utils/data/datapipes/iter/__init__.py`
  - `torch/utils/data/datapipes/utils/__init__.py`
  - `torch/utils/data/datapipes/utils/common.py`
- pytorch#51398 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/readfilesfromtar.py`
- pytorch#51599 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/readfilesfromzip.py`
- pytorch#51704 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/routeddecoder.py`
  - `torch/utils/data/datapipes/utils/decoder.py`
- pytorch#51709 authored by glaringlee, approved by ejguan
  - `torch/utils/data/datapipes/iter/groupbykey.py`

Specifically, the question is: for each of those files, should we remove the execute permissions, or should we add a shebang? And if the latter, which shebang?

Pull Request resolved: pytorch#52750

Test Plan:
The **Lint / flake8-py3** job in GitHub Actions:

- [this run](https://github.com/pytorch/pytorch/runs/1972039886) failed, showing that the new regex catches these warnings properly
- [this run](https://github.com/pytorch/pytorch/runs/1972393293) succeeded and gave no output in the "Run flake8" step, showing that this PR fixed all Flake8 warnings
- [this run](https://github.com/pytorch/pytorch/pull/52755/checks?check_run_id=1972414849) (in pytorch#52755) failed, showing that the new last step of the job successfully catches Flake8 warnings even without the regex fix

Reviewed By: walterddr, janeyx99

Differential Revision: D26637307

Pulled By: samestep

fbshipit-source-id: 572af6a3bbe57f5e9bd47f19f37c39db90f7b804
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

cla signed Merged oncall: distributed Add this issue/PR to distributed oncall triage queue open source

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants