mirror of
https://github.com/zebrajr/pytorch.git
synced 2025-12-06 12:20:52 +01:00
bd10fea79a
Fixes #112371 I tried to fix as many of the bugs as I could, a few I could not figure out what the proper fix for them was though and so I left them with noqas. Pull Request resolved: https://github.com/pytorch/pytorch/pull/116579 Approved by: https://github.com/ezyang
59 lines
1.7 KiB
Python
59 lines
1.7 KiB
Python
# Owner(s): ["oncall: r2p"]
|
|
|
|
# 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 os
|
|
import unittest
|
|
import sys
|
|
|
|
import etcd
|
|
from torch.distributed.elastic.rendezvous.etcd_rendezvous import (
|
|
EtcdRendezvous,
|
|
EtcdRendezvousHandler,
|
|
)
|
|
from torch.distributed.elastic.rendezvous.etcd_server import EtcdServer
|
|
|
|
if os.getenv("CIRCLECI"):
|
|
print("T85992919 temporarily disabling in circle ci", file=sys.stderr)
|
|
sys.exit(0)
|
|
|
|
class EtcdServerTest(unittest.TestCase):
|
|
def test_etcd_server_start_stop(self):
|
|
server = EtcdServer()
|
|
server.start()
|
|
|
|
try:
|
|
port = server.get_port()
|
|
host = server.get_host()
|
|
|
|
self.assertGreater(port, 0)
|
|
self.assertEqual("localhost", host)
|
|
self.assertEqual(f"{host}:{port}", server.get_endpoint())
|
|
self.assertIsNotNone(server.get_client().version)
|
|
finally:
|
|
server.stop()
|
|
|
|
def test_etcd_server_with_rendezvous(self):
|
|
server = EtcdServer()
|
|
server.start()
|
|
|
|
client = etcd.Client(server.get_host(), server.get_port())
|
|
|
|
rdzv = EtcdRendezvous(
|
|
client=client,
|
|
prefix="test",
|
|
run_id=1,
|
|
num_min_workers=1,
|
|
num_max_workers=1,
|
|
timeout=60,
|
|
last_call_timeout=30,
|
|
)
|
|
rdzv_handler = EtcdRendezvousHandler(rdzv)
|
|
store, rank, world_size = rdzv_handler.next_rendezvous()
|
|
self.assertIsNotNone(store)
|
|
self.assertEqual(0, rank)
|
|
self.assertEqual(1, world_size)
|