## Problem this PR resolves
Today, most of distributed tests are arranged like this:
```
def test_allreduce(self):
pg = self._create_process_group_nccl(store, self.opts())
pg.allreduce(tensor)
...
```
Thus, we are paying PG creation time **per test**. That's bad. But why were we doing that? Is there a constraint?
If we look deeper, we would find that most of our test cases inherit from `torch.testing._internal.common_distributed.MultiProcessTestCase`. From the name, nothing seems wrong, and probably fits distributed well. But a "problem" exists in its `setUp()` and `tearDown()` methods, which basically do the following:
```
def setUp(self):
self._spawn_processes()
def tearDown(self):
for p in self.processes:
p.terminate()
```
Since `setUp` and `tearDown` are "**test-scope fixtures"**, meaning, they are called per test, each test will have brand new processes. Of course we'd have to recreate ProcessGroup every time.
## How we are fixing it
First, obviously, we need to put a PG's lifetime into a longer scope. Python `unittest` provides such a helper, called **"class-scope fixtures."** It is embodied by a `setUpClass` method and a `tearDownClass` method (note the name difference), which are called only once for all tests in the same test class. Therefore, we would do:
```
@classmethod
def setUpClass(self):
dist.init_process_group(...)
@classmethod
def tearDownClass(self):
dist.destroy_process_group()
```
**In this PR, we create a new test template for distributed: `MultiProcContinousTest`, to hold this class-scope fixture.**
Second, we'd need to avoid per-test process spawn and terminate. That's easy, we can either:
1. launch the whole test file with `torchrun --nproc-per-node=...` or
2. use `mp.spawn()` under `if __name__ == "__main__":`.
Point is, launch the processes only once.
## Result
We moved the "positive tests" from test_c10d_nccl.py to test_c10d_ops_nccl.py.
Before this PR:
```
$ python test_c10d_nccl.py -k ProcessGroupNCCLTest
Ran 24 tests in 174.457s
```
After this PR:
```
$ torchrun --nproc-per-node 2 test_c10d_ops_nccl.py
or
$ python test_c10d_ops_nccl.py
Ran 24 tests in 16.247s
```
10X speedup.
## Limitation
For tests intended to test destroy or abort of PGs, we'd need to go back to the old style. So it would make sense to divide our tests into two classes: one for positive tests where we would reuse the PGs, and the other one for abort/destroy and negative tests like watchdog timeout.
## Next step
Migrate the tests of distributed that would fit with this test style!
Pull Request resolved: https://github.com/pytorch/pytorch/pull/125648
Approved by: https://github.com/wconstab
The linter uses libcst to check for a call to run_tests or a raised exception when the test file is run as main to ensure that all test files either get run in OSS CI or don't run and are expected to not run.
A better option instead of making this into a linter might be to add this code in run_test since there's also a list of blocklisted tests there that needs to be updated when a test file raises an exception.
This is possibly overkill since run on its own, the code takes ~1 minutes to run without the multiprocessing on all the files
Pull Request resolved: https://github.com/pytorch/pytorch/pull/114882
Approved by: https://github.com/kit1980
