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

refactor: Don't warn on fork hook #20309

Merged
merged 2 commits into from
Dec 16, 2024
Merged

refactor: Don't warn on fork hook #20309

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
31bbc3b
refactor: Don't warn on fork hook
ritchie46 Dec 16, 2024
1af3cae
test
ritchie46 Dec 16, 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
40 changes: 0 additions & 40 deletions py-polars/polars/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -433,43 +433,3 @@ def __getattr__(name: str) -> Any:

msg = f"module {__name__!r} has no attribute {name!r}"
raise AttributeError(msg)


# fork() breaks Polars thread pool, so warn users who might be doing this.
# Keep track so that we warn only once
_WARNED = False


def __install_postfork_hook() -> None:
message = """\
Using fork() can cause Polars to deadlock in the child process.
In addition, using fork() with Python in general is a recipe for mysterious
deadlocks and crashes.
The most likely reason you are seeing this error is because you are using the
multiprocessing module on Linux, which uses fork() by default. This will be
fixed in Python 3.14. Until then, you want to use the "spawn" context instead.
See https://docs.pola.rs/user-guide/misc/multiprocessing/ for details.
If you really know what you're doing, you can silence this warning with the warning module
or by setting POLARS_ALLOW_FORKING_THREAD=1.
"""
import os

if os.environ.get("POLARS_ALLOW_FORKING_THREAD") == "1":
return None

def before_hook() -> None:
global _WARNED
if not _WARNED:
import warnings

warnings.warn(message, RuntimeWarning, stacklevel=2)
_WARNED = True

if hasattr(os, "register_at_fork"):
os.register_at_fork(before=before_hook)


__install_postfork_hook()
31 changes: 0 additions & 31 deletions py-polars/tests/unit/test_polars_import.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,6 @@
from __future__ import annotations

import compileall
import multiprocessing
import os
import subprocess
import sys
from pathlib import Path
Expand Down Expand Up @@ -99,32 +97,3 @@ def test_polars_import() -> None:
import_time_ms = polars_import_time // 1_000
msg = f"Possible import speed regression; took {import_time_ms}ms\n{df_import}"
raise AssertionError(msg)


def run_in_child() -> int:
return 123


@pytest.mark.skipif(not hasattr(os, "fork"), reason="Requires fork()")
def test_fork_safety(recwarn: pytest.WarningsRecorder) -> None:
def get_num_fork_warnings() -> int:
fork_warnings = 0
for warning in recwarn:
if issubclass(warning.category, RuntimeWarning) and str(
warning.message
).startswith("Using fork() can cause Polars"):
fork_warnings += 1
return fork_warnings

assert get_num_fork_warnings() == 0

# Using forkserver and spawn context should not do any of our warning:
for context in ["spawn", "forkserver"]:
with multiprocessing.get_context(context).Pool(1) as pool:
assert pool.apply(run_in_child) == 123
assert get_num_fork_warnings() == 0

# Using fork()-based multiprocessing should raise a warning:
with multiprocessing.get_context("fork").Pool(1) as pool:
assert pool.apply(run_in_child) == 123
assert get_num_fork_warnings() == 1
Loading