Skip to content

Commit

Permalink
Revert "feat(python): Raise an error when users try to use Polars API…
Browse files Browse the repository at this point in the history
… in a fork()-without-execve() child (#19149)"

This reverts commit 48bc09b.
  • Loading branch information
nameexhaustion committed Oct 11, 2024
1 parent 194b31e commit fc2ee20
Show file tree
Hide file tree
Showing 2 changed files with 0 additions and 57 deletions.
35 changes: 0 additions & 35 deletions py-polars/polars/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -414,38 +414,3 @@ def __getattr__(name: str) -> Any:

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


# fork() breaks Polars thread pool. Instead of silently hanging when users do
# this, e.g. by using multiprocessing's footgun default setting on Linux, warn
# them instead:
def __install_postfork_hook() -> None:
def fail(*args: Any, **kwargs: Any) -> 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.
"""
raise RuntimeError(message)

def post_hook_child() -> None:
# Switch most public Polars API to fail when called. This won't catch
# _all_ edge cases, but does make it more likely users get told they
# tried to do something broken.
for name in __all__:
if callable(globals()[name]):
globals()[name] = fail

import os

if hasattr(os, "register_at_fork"):
os.register_at_fork(after_in_child=post_hook_child)


__install_postfork_hook()
22 changes: 0 additions & 22 deletions py-polars/tests/unit/test_polars_import.py
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 @@ -99,23 +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() -> pl.Series:
return pl.Series([1, 2, 3])


@pytest.mark.filterwarnings("ignore")
@pytest.mark.skipif(not hasattr(os, "fork"), reason="Requires fork()")
def test_fork_safety() -> None:
# Using fork()-based multiprocessing shouldn't work:
with (
multiprocessing.get_context("fork").Pool(1) as pool,
pytest.raises(RuntimeError, match=r"Using fork\(\) can cause Polars"),
):
pool.apply(run_in_child)

# Using forkserver and spawn context should not error out:
for context in ["spawn", "forkserver"]:
with multiprocessing.get_context(context).Pool(1) as pool:
pool.apply(run_in_child)

0 comments on commit fc2ee20

Please sign in to comment.