fix(cache): stop fsync-hammering the SD card on unchanged data (#402)

DiskCache.set wrote every key as mkstemp -> json.dump(indent=4) ->
flush+fsync -> replace -> chmod, on the persistent cache dir — dozens
of force-flushed SD writes per minute on an API-heavy install, mostly
rewriting identical data every plugin update cycle.

- Serialize once, compact (no indent): cache files are machine-read
  only; indenting multiplied the bytes written.
- Skip the disk when the payload for a key is unchanged (adler32 map,
  per-process); refresh the file mtime instead so records relying on
  mtime for TTL don't expire early. Self-heals if the file was removed
  externally (expiry cleanup).
- Drop the per-write fsync: os.replace already guarantees readers never
  see a torn file, and cache data is re-fetchable — the flush bought
  nothing but card wear.

API unchanged; DateTimeEncoder round-trip covered by tests.


Claude-Session: https://claude.ai/code/session_01FqzC1nzTWL4kaqgMaQZFam

Co-authored-by: Chuck <chuck@example.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Chuck
2026-07-13 09:00:35 -04:00
committed by GitHub
co-authored by Chuck Claude Fable 5
parent 9e3b5f366e
commit 273d9962d1
2 changed files with 106 additions and 9 deletions
+58
View File
@@ -400,3 +400,61 @@ class TestDiskCache:
assert stats['fetch_count'] == 3
assert stats['total_fetch_time'] == 1.8
assert stats['average_fetch_time'] == pytest.approx(0.6, abs=0.01)
class TestDiskCacheWriteEconomy:
"""SD-card wear guards: identical payloads skip the disk, files are
compact, and TTL semantics survive the skip (see PR: fix/diskcache-sd-wear)."""
def test_identical_set_skips_rewrite(self, tmp_path):
import os
cache = DiskCache(cache_dir=str(tmp_path))
cache.set("k", {"data": "v"})
path = cache.get_cache_path("k")
first = os.stat(path)
os.utime(path, (first.st_atime - 100, first.st_mtime - 100)) # age it
aged_mtime = os.stat(path).st_mtime
ino_before = os.stat(path).st_ino
cache.set("k", {"data": "v"}) # identical payload
after = os.stat(path)
# mtime refreshed (TTL for mtime-based records preserved)...
assert after.st_mtime > aged_mtime
# ...but the file was NOT rewritten (same inode: no replace happened)
assert after.st_ino == ino_before
def test_changed_data_rewrites(self, tmp_path):
import os
cache = DiskCache(cache_dir=str(tmp_path))
cache.set("k", {"data": "v1"})
cache.set("k", {"data": "v2"})
assert cache.get("k") == {"data": "v2"}
def test_clear_resets_digest(self, tmp_path):
import os
cache = DiskCache(cache_dir=str(tmp_path))
cache.set("k", {"data": "v"})
cache.clear("k")
assert cache.get("k") is None
cache.set("k", {"data": "v"}) # same payload after clear must WRITE
assert cache.get("k") == {"data": "v"}
def test_skip_self_heals_when_file_deleted_externally(self, tmp_path):
import os
cache = DiskCache(cache_dir=str(tmp_path))
cache.set("k", {"data": "v"})
os.remove(cache.get_cache_path("k")) # e.g. expiry cleanup
cache.set("k", {"data": "v"}) # digest matches but file is gone
assert cache.get("k") == {"data": "v"}
def test_files_are_compact_json(self, tmp_path):
cache = DiskCache(cache_dir=str(tmp_path))
cache.set("k", {"a": 1, "b": [1, 2, 3]})
raw = open(cache.get_cache_path("k")).read()
assert "\n" not in raw.strip() # no indent
assert cache.get("k") == {"a": 1, "b": [1, 2, 3]}
def test_datetime_round_trip_still_works(self, tmp_path):
from datetime import datetime
cache = DiskCache(cache_dir=str(tmp_path))
cache.set("k", {"when": datetime(2026, 7, 12, 10, 30)})
assert cache.get("k") == {"when": "2026-07-12T10:30:00"}