retoorandClaude Sonnet 5
7880bf4b31
sync_workspace (user-triggered) and the reconciler's sync_bidirectional_sync could run concurrently for the same project, and store_upload's read-then- write on a changed path meant two racing imports each wrote their own blob while only one ever got referenced - the loser leaked forever. Combined with no build-artifact exclusion, an actively-compiling workspace hit this constantly and leaked 5.9M orphan blobs (~96GB) in production before it was caught. Closes it at the root: api._sync_dir_bidirectional_locked serializes both call sites per-project (non-blocking - a project already mid-sync is simply skipped until the next tick), and IMPORT_SKIP_NAMES/IMPORT_SKIP_EXTENSIONS keep build output (build/, dist/, *.o, *.pyc, ...) out of the walk entirely. Recovering what already leaked is a separate concern: a new CLI subcommand (plus matching make targets) sweeps soft-deleted attachment/project-file blobs and any blob with zero DB reference at all, plus orphaned container workspace directories. run_maintenance_cleanup.sh wraps the existing prune/clear commands for routine disk upkeep. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01BWJy6PrMMt5hwWxQwia2rd
150 lines
5.2 KiB
Python
150 lines
5.2 KiB
Python
# retoor <retoor@molodetz.nl>
|
|
|
|
from devplacepy import attachments as att
|
|
from devplacepy.database import get_table
|
|
from devplacepy.utils import generate_uid
|
|
|
|
|
|
def _make_attachment(directory, stored_name, deleted_at=None):
|
|
uid = generate_uid()
|
|
get_table("attachments").insert(
|
|
{
|
|
"uid": uid,
|
|
"deleted_at": deleted_at,
|
|
"deleted_by": None,
|
|
"directory": directory,
|
|
"stored_name": stored_name,
|
|
"target_type": "post",
|
|
"target_uid": generate_uid(),
|
|
}
|
|
)
|
|
return uid
|
|
|
|
|
|
def _write_blob(base, directory, stored_name, content=b"data"):
|
|
file_dir = base / directory
|
|
file_dir.mkdir(parents=True, exist_ok=True)
|
|
(file_dir / stored_name).write_bytes(content)
|
|
return file_dir / stored_name
|
|
|
|
|
|
def test_purge_soft_deleted_attachments_removes_row_and_blob(local_db, tmp_path, monkeypatch):
|
|
monkeypatch.setattr(att, "ATTACHMENTS_DIR", tmp_path)
|
|
directory = "ab/cd"
|
|
stored_name = f"{generate_uid()}.png"
|
|
_write_blob(tmp_path, directory, stored_name, b"x" * 100)
|
|
uid = _make_attachment(directory, stored_name, deleted_at="2020-01-01T00:00:00+00:00")
|
|
|
|
removed, freed = att.purge_soft_deleted_attachments()
|
|
|
|
assert removed >= 1
|
|
assert freed == 100
|
|
assert get_table("attachments").find_one(uid=uid) is None
|
|
assert not (tmp_path / directory / stored_name).exists()
|
|
|
|
|
|
def test_purge_soft_deleted_attachments_dry_run_changes_nothing(local_db, tmp_path, monkeypatch):
|
|
monkeypatch.setattr(att, "ATTACHMENTS_DIR", tmp_path)
|
|
directory = "ab/cd"
|
|
stored_name = f"{generate_uid()}.png"
|
|
_write_blob(tmp_path, directory, stored_name, b"x" * 50)
|
|
uid = _make_attachment(directory, stored_name, deleted_at="2020-01-01T00:00:00+00:00")
|
|
|
|
removed, freed = att.purge_soft_deleted_attachments(dry_run=True)
|
|
|
|
assert removed >= 1
|
|
assert freed == 50
|
|
assert get_table("attachments").find_one(uid=uid) is not None
|
|
assert (tmp_path / directory / stored_name).exists()
|
|
|
|
|
|
def test_purge_soft_deleted_attachments_ignores_live_rows(local_db, tmp_path, monkeypatch):
|
|
monkeypatch.setattr(att, "ATTACHMENTS_DIR", tmp_path)
|
|
directory = "ab/cd"
|
|
stored_name = f"{generate_uid()}.png"
|
|
_write_blob(tmp_path, directory, stored_name)
|
|
uid = _make_attachment(directory, stored_name, deleted_at=None)
|
|
|
|
att.purge_soft_deleted_attachments()
|
|
|
|
assert get_table("attachments").find_one(uid=uid) is not None
|
|
assert (tmp_path / directory / stored_name).exists()
|
|
|
|
|
|
def test_purge_soft_deleted_attachments_also_removes_thumbnail(local_db, tmp_path, monkeypatch):
|
|
monkeypatch.setattr(att, "ATTACHMENTS_DIR", tmp_path)
|
|
directory = "ab/cd"
|
|
stem = generate_uid()
|
|
stored_name = f"{stem}.jpg"
|
|
_write_blob(tmp_path, directory, stored_name, b"x" * 20)
|
|
_write_blob(tmp_path, directory, f"{stem}_thumb.jpg", b"y" * 5)
|
|
_make_attachment(directory, stored_name, deleted_at="2020-01-01T00:00:00+00:00")
|
|
|
|
removed, freed = att.purge_soft_deleted_attachments()
|
|
|
|
assert removed >= 1
|
|
assert freed == 25
|
|
assert not (tmp_path / directory / f"{stem}_thumb.jpg").exists()
|
|
|
|
|
|
def test_sweep_orphan_attachment_blobs_removes_unreferenced_file(local_db, tmp_path, monkeypatch):
|
|
monkeypatch.setattr(att, "ATTACHMENTS_DIR", tmp_path)
|
|
directory = "ab/cd"
|
|
orphan_name = f"{generate_uid()}.o"
|
|
_write_blob(tmp_path, directory, orphan_name, b"y" * 30)
|
|
|
|
removed, freed = att.sweep_orphan_attachment_blobs()
|
|
|
|
assert removed == 1
|
|
assert freed == 30
|
|
assert not (tmp_path / directory / orphan_name).exists()
|
|
|
|
|
|
def test_sweep_orphan_attachment_blobs_keeps_referenced_file_and_its_thumbnail(
|
|
local_db, tmp_path, monkeypatch
|
|
):
|
|
monkeypatch.setattr(att, "ATTACHMENTS_DIR", tmp_path)
|
|
directory = "ab/cd"
|
|
stem = generate_uid()
|
|
stored_name = f"{stem}.jpg"
|
|
thumb_name = f"{stem}_thumb.jpg"
|
|
_write_blob(tmp_path, directory, stored_name)
|
|
_write_blob(tmp_path, directory, thumb_name)
|
|
_make_attachment(directory, stored_name, deleted_at=None)
|
|
|
|
removed, freed = att.sweep_orphan_attachment_blobs()
|
|
|
|
assert removed == 0
|
|
assert freed == 0
|
|
assert (tmp_path / directory / stored_name).exists()
|
|
assert (tmp_path / directory / thumb_name).exists()
|
|
|
|
|
|
def test_sweep_orphan_attachment_blobs_keeps_blob_referenced_only_by_soft_deleted_row(
|
|
local_db, tmp_path, monkeypatch
|
|
):
|
|
monkeypatch.setattr(att, "ATTACHMENTS_DIR", tmp_path)
|
|
directory = "ab/cd"
|
|
stored_name = f"{generate_uid()}.png"
|
|
_write_blob(tmp_path, directory, stored_name)
|
|
_make_attachment(directory, stored_name, deleted_at="2020-01-01T00:00:00+00:00")
|
|
|
|
removed, freed = att.sweep_orphan_attachment_blobs()
|
|
|
|
assert removed == 0
|
|
assert freed == 0
|
|
assert (tmp_path / directory / stored_name).exists()
|
|
|
|
|
|
def test_sweep_orphan_attachment_blobs_dry_run_changes_nothing(local_db, tmp_path, monkeypatch):
|
|
monkeypatch.setattr(att, "ATTACHMENTS_DIR", tmp_path)
|
|
directory = "ab/cd"
|
|
orphan_name = f"{generate_uid()}.o"
|
|
_write_blob(tmp_path, directory, orphan_name, b"z" * 10)
|
|
|
|
removed, freed = att.sweep_orphan_attachment_blobs(dry_run=True)
|
|
|
|
assert removed == 1
|
|
assert freed == 10
|
|
assert (tmp_path / directory / orphan_name).exists()
|