mirror of
https://github.com/zebrajr/pytorch.git
synced 2025-12-07 12:21:27 +01:00
ba75cedfc5
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/53172 Pull Request resolved: https://github.com/pytorch/elastic/pull/141 Upstreams two modules to torch: 1. `torchelastic.rendezvous` 2. `torchelastic.utils` These modules were chosen as `[1/n]` since they are the leaf modules in torchelastic. ==== NOTES: ==== 1. I'm disabling etcd_rendezvous and etcd_server tests in CIRCLECI for the moment since I need to edit the test dockers to contain the etcd server binary (there's 4-5 test dockers - one for each platform so this is going to take some time for me to set up the environments and test) - T85992919. 2. I've fixed all lint errors on python files but there are ones on the cpp files on the ZeusRendezvous. I took a look at them, and I don't want to fix the linter errors right now for 2 major reasons: 1. Some of them are more than formatting changes (e.g. std::move vs pass by value) and I don't want to introduce bundled changes with the move 1. The old rendezvous code (the one we forked from in caffe2/fb) has the same problems and I think its better for us to deal with this when we deprecate caffe2/fb/rendezvous in favor of the one in torchelastic -T86012579. Test Plan: ``` buck test mode/dev-nosan //caffe2/torch/distributed/elastic/utils/test/... buck test mode/dev-nosan //caffe2/torch/distributed/elastic/utils/data/test/... buck test mode/dev-nosan //caffe2/torch/distributed/elastic/rendezvous/test/... buck test mode/dev-nosan //caffe2/torch/distributed/elastic/rendezvous/fb/... buck test mode/dev-nosan //pytorch/elastic/torchelastic/... ``` \+ Sandcastle Reviewed By: H-Huang Differential Revision: D26718746 fbshipit-source-id: 67cc0350c3d847221cb3c3038f98f47915362f51
86 lines
2.5 KiB
Python
86 lines
2.5 KiB
Python
#!/usr/bin/env python3
|
|
|
|
# Copyright (c) Facebook, Inc. and its affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the BSD-style license found in the
|
|
# LICENSE file in the root directory of this source tree.
|
|
import unittest
|
|
from typing import Tuple
|
|
|
|
from torch.distributed.elastic.rendezvous import (
|
|
RendezvousHandler,
|
|
RendezvousHandlerFactory,
|
|
RendezvousParameters,
|
|
)
|
|
|
|
|
|
def create_mock_rdzv_handler(ignored: RendezvousParameters) -> RendezvousHandler:
|
|
return MockRendezvousHandler()
|
|
|
|
|
|
class MockRendezvousHandler(RendezvousHandler):
|
|
def next_rendezvous(
|
|
self,
|
|
# pyre-ignore[11]: Annotation `Store` is not defined as a type.
|
|
) -> Tuple["torch.distributed.Store", int, int]: # noqa F821
|
|
raise NotImplementedError()
|
|
|
|
def get_backend(self) -> str:
|
|
return "mock"
|
|
|
|
def is_closed(self) -> bool:
|
|
return False
|
|
|
|
def set_closed(self):
|
|
pass
|
|
|
|
def num_nodes_waiting(self) -> int:
|
|
return -1
|
|
|
|
def get_run_id(self) -> str:
|
|
return ""
|
|
|
|
|
|
class RendezvousHandlerFactoryTest(unittest.TestCase):
|
|
def test_double_registration(self):
|
|
factory = RendezvousHandlerFactory()
|
|
factory.register("mock", create_mock_rdzv_handler)
|
|
with self.assertRaises(ValueError):
|
|
factory.register("mock", create_mock_rdzv_handler)
|
|
|
|
def test_no_factory_method_found(self):
|
|
factory = RendezvousHandlerFactory()
|
|
rdzv_params = RendezvousParameters(
|
|
backend="mock", endpoint="", run_id="foobar", min_nodes=1, max_nodes=2
|
|
)
|
|
|
|
with self.assertRaises(ValueError):
|
|
factory.create_handler(rdzv_params)
|
|
|
|
def test_create_handler(self):
|
|
rdzv_params = RendezvousParameters(
|
|
backend="mock", endpoint="", run_id="foobar", min_nodes=1, max_nodes=2
|
|
)
|
|
|
|
factory = RendezvousHandlerFactory()
|
|
factory.register("mock", create_mock_rdzv_handler)
|
|
mock_rdzv_handler = factory.create_handler(rdzv_params)
|
|
self.assertTrue(isinstance(mock_rdzv_handler, MockRendezvousHandler))
|
|
|
|
|
|
class RendezvousParametersTest(unittest.TestCase):
|
|
def test_get_or_default(self):
|
|
|
|
params = RendezvousParameters(
|
|
backend="foobar",
|
|
endpoint="localhost",
|
|
run_id="1234",
|
|
min_nodes=1,
|
|
max_nodes=1,
|
|
timeout1=10,
|
|
)
|
|
|
|
self.assertEqual(10, params.get("timeout1", 20))
|
|
self.assertEqual(60, params.get("timeout2", 60))
|