Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[misc][distributed] fix benign error in is_in_the_same_node #5512

Merged
merged 3 commits into from
Jun 14, 2024
Merged

[misc][distributed] fix benign error in is_in_the_same_node #5512

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
af0e16c
fix benign error
youkaichao Jun 13, 2024
f52ad5f
Merge branch 'main' into fix_benign_error
youkaichao Jun 13, 2024
74bf481
fix format
youkaichao Jun 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 10 additions & 10 deletions vllm/distributed/parallel_state.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,8 +23,9 @@
from collections import namedtuple
from contextlib import contextmanager, nullcontext
from dataclasses import dataclass
from multiprocessing import resource_tracker, shared_memory
from multiprocessing import shared_memory
from typing import Any, Dict, List, Optional, Tuple, Union
from unittest.mock import patch

import torch
from torch.distributed import Backend, ProcessGroup
Expand Down Expand Up @@ -744,7 +745,12 @@ def is_in_the_same_node(pg: ProcessGroup):
src=ranks[0],
group=pg)
name = recv[0]
shm = shared_memory.SharedMemory(name=name)
# fix to https://stackoverflow.com/q/62748654/9191338
# Python incorrectly tracks shared memory even if it is not
# created by the process. The following patch is a workaround.
with patch("multiprocessing.resource_tracker.register",
lambda *args, **kwargs: None):
shm = shared_memory.SharedMemory(name=name)
if shm.buf[:len(magic_message)] == magic_message:
is_in_the_same_node[rank] = 1
except Exception as e:
Expand All @@ -757,14 +763,8 @@ def is_in_the_same_node(pg: ProcessGroup):

# clean up the shared memory segment
with contextlib.suppress(OSError):
if rank == 0:
if shm:
shm.unlink()
else:
if shm:
# fix to https://stackoverflow.com/q/62748654/9191338
resource_tracker.unregister(
shm._name, "shared_memory") # type: ignore[attr-defined]
if rank == 0 and shm:
shm.unlink()
torch.distributed.all_reduce(is_in_the_same_node, group=pg)

return is_in_the_same_node.sum().item() == world_size
Loading