mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-10-28 06:00:38 +00:00
d04ee1d131
* fix(harness): keep timestamped output-name fallbacks distinct `output_name_candidates()` sampled `datetime.now(UTC)` inside the yield loop, so its five timestamped fallbacks were only distinct when the host clock advanced between two generator steps. On a coarse clock (Windows advances in sub-millisecond steps) all five produced the same name, and the capture tools lost retries before failing with `could not reserve an output filename`. Sample the clock once when the first fallback is reached and offset each attempt by one microsecond, so distinctness no longer depends on the host clock. Add a regression test that freezes the clock, and update the exhaustion test to hold all five distinct stamps. * docs: describe the coarse clock accurately --------- Co-authored-by: PerryLink <255665900+PerryLink@users.noreply.github.com>
34 lines
1.5 KiB
Python
34 lines
1.5 KiB
Python
"""Collision-free output file names shared by the capture tools."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from collections.abc import Iterator
|
|
from datetime import UTC, datetime, timedelta
|
|
from pathlib import Path
|
|
|
|
# Cap collision-suffix probing so a saturated outputs directory cannot spin forever.
|
|
MAX_COLLISION_PROBES = 1000
|
|
# Retry bound for the timestamped fallback: each attempt offsets one clock sample,
|
|
# so the bound does not depend on the host clock advancing between yields.
|
|
MAX_TIMESTAMP_ATTEMPTS = 5
|
|
|
|
|
|
def output_name_candidates(name: str) -> Iterator[str]:
|
|
"""Yield *name*, then ``stem-1`` .. ``stem-1000``, then timestamped fallbacks.
|
|
|
|
Callers claim each candidate atomically and move on when it is taken; the
|
|
generator never checks the filesystem, so naming cannot race the claim.
|
|
The clock is sampled lazily, once, when the first fallback is reached; each
|
|
later fallback offsets that sample by one microsecond. A host clock whose
|
|
tick is coarser than the microsecond stamp (for example Windows' ~15 ms
|
|
system-time tick) therefore cannot repeat a stamp inside one burst, and
|
|
every fallback stays a distinct candidate.
|
|
"""
|
|
yield name
|
|
stem, suffix = Path(name).stem, Path(name).suffix
|
|
for index in range(1, MAX_COLLISION_PROBES + 1):
|
|
yield f"{stem}-{index}{suffix}"
|
|
stamp = datetime.now(UTC)
|
|
for attempt in range(MAX_TIMESTAMP_ATTEMPTS):
|
|
yield f"{stem}-{(stamp + timedelta(microseconds=attempt)).strftime('%Y%m%d-%H%M%S-%f')}{suffix}"
|