Skip to content

Log exceptions in P2P shuffle tasks #7442

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

Merged
fjetter merged 3 commits into from
Jan 5, 2023
Merged

Log exceptions in P2P shuffle tasks #7442

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
de760a0
Log exception
hendrikmakait Jan 3, 2023
5861481
nicer logging
hendrikmakait Jan 3, 2023
6e57cd3
Add FIXME
hendrikmakait Jan 4, 2023
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
18 changes: 15 additions & 3 deletions distributed/shuffle/_shuffle.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,11 @@ def shuffle_transfer(
input, id, npartitions=npartitions, column=column
)
except Exception:
raise RuntimeError(f"shuffle_transfer failed during shuffle {id}")
msg = f"shuffle_transfer failed during shuffle {id}"
# FIXME: Use exception chaining instead of logging the traceback.
# This has previously led to spurious recursion errors
logger.error(msg, exc_info=True)
raise RuntimeError(msg)


def shuffle_unpack(
Expand All @@ -58,14 +62,22 @@ def shuffle_unpack(
try:
return _get_worker_extension().get_output_partition(id, output_partition)
except Exception:
raise RuntimeError(f"shuffle_unpack failed during shuffle {id}")
msg = f"shuffle_unpack failed during shuffle {id}"
# FIXME: Use exception chaining instead of logging the traceback.
# This has previously led to spurious recursion errors
logger.error(msg, exc_info=True)
raise RuntimeError(msg)


def shuffle_barrier(id: ShuffleId, transfers: list[None]) -> None:
try:
return _get_worker_extension().barrier(id)
except Exception:
raise RuntimeError(f"shuffle_barrier failed during shuffle {id}")
msg = f"shuffle_barrier failed during shuffle {id}"
# FIXME: Use exception chaining instead of logging the traceback.
# This has previously led to spurious recursion errors
logger.error(msg, exc_info=True)
raise RuntimeError(msg)


def rearrange_by_column_p2p(
Expand Down