Skip to content

Fix race condition in chexify #271

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

Open
copybara-service wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix race condition in chexify #271

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
13 changes: 9 additions & 4 deletions chex/_src/asserts_chexify.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@
import dataclasses
import functools
import re
import threading
from typing import Any, Callable, FrozenSet

from absl import logging
Expand Down Expand Up @@ -178,6 +179,8 @@ def logp1_abs_safe(x: chex.Array) -> chex.Array:
thread_pool = futures.ThreadPoolExecutor(1, f'async_chex_{func_name}')
# A deque for futures.
async_check_futures = collections.deque()
# Protect the futures from concurrent access.
async_check_futures_lock = threading.Lock()

# Checkification.
checkified_fn = checkify.checkify(fn, errors=errors)
Expand All @@ -191,8 +194,9 @@ def _chexified_fn(*args, **kwargs):

if async_check:
# Check completed calls.
while async_check_futures and async_check_futures[0].done():
_check_error(async_check_futures.popleft().result(async_timeout))
with async_check_futures_lock:
while async_check_futures and async_check_futures[0].done():
_check_error(async_check_futures.popleft().result(async_timeout))

# Run the checkified function.
_ai.CHEXIFY_STORAGE.level += 1
Expand All @@ -214,8 +218,9 @@ def _chexified_fn(*args, **kwargs):

def _wait_checks():
if async_check:
while async_check_futures:
_check_error(async_check_futures.popleft().result(async_timeout))
with async_check_futures_lock:
while async_check_futures:
_check_error(async_check_futures.popleft().result(async_timeout))

# Add a barrier callback to the global storage.
_ai.CHEXIFY_STORAGE.wait_fns.append(_wait_checks)
Expand Down