cjw/Oxicloud
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity

fix(ref_count): use SQL to correct ref_count on cascading deletion

Browse Source 
then dedup_gc will trigger blob life cycle and ensure chunk deletions
This commit is contained in:
Edouard Vanbelle
2026-08-23 22:44:39 +02:00
parent 2760fe9efc
commit 0f29614a3b
4 changed files with 198 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/infrastructure/repositories/pg/file_blob_write_repository.rs
+13 -2
View File
@@ -1024,10 +1024,21 @@ impl FileWritePort for FileBlobWriteRepository {
DomainError::internal_error("FileBlobWrite", format!("fetch blob_hash: {e}"))
})?;
// DELETE fires trg_files_decrement_blob_ref → storage.blobs.ref_count--
// DELETE fires `trg_files_decrement_blob_ref` — post-2026-08-23
// it dispatches manifest-first (see migration
// `20261017000000_file_delete_trigger_manifest_aware.sql`):
// decrements `chunk_manifests.ref_count` if the hash names a
// manifest (walking chunks on last-ref), else falls back to
// `storage.blobs.ref_count`. Counter state after this call is
// already correct.
self.delete_file(file_id).await?;
// If the blob is now unreferenced, remove disk file + thumbnails.
// Physical cleanup only. `cleanup_if_orphaned` was previously
// manifest-aware and did counter compensation for the old
// trigger's over-decrement; after the trigger rewrite it's a
// legacy-blob-eager-reap helper — safe to keep calling
// unconditionally (no-op for CDC hashes; reaps legacy blobs
// that reached ref_count = 0).
if let Some(hash) = blob_hash {
self.dedup.cleanup_if_orphaned(&hash).await;
}
src/infrastructure/services/dedup_service.rs
+42 -60
View File
@@ -1959,66 +1959,48 @@ impl DedupService {
pub async fn cleanup_if_orphaned(&self, hash: &str) {
let short = &hash[..hash.len().min(12)];
// ── CDC manifest path (must run FIRST) ───────────────────
// For single-chunk CDC files file_hash == chunk_hash, so the PG
// trigger on storage.files already decremented storage.blobs.ref_count
// when this function is called. try_dedup_hit increments
// chunk_manifests.ref_count but NOT storage.blobs.ref_count, so
// blobs.ref_count can reach 0 while the manifest still has ref_count > 1
// (other files sharing the same blob). Checking the manifest first
// prevents premature blob + manifest deletion.
let manifest = sqlx::query_as::<_, (i32, Vec<String>)>(
"SELECT ref_count, chunk_hashes \
FROM storage.chunk_manifests WHERE file_hash = $1",
)
.bind(hash)
.fetch_optional(self.pool.as_ref())
.await
.unwrap_or(None);
if let Some((ref_count, chunk_hashes)) = manifest {
if ref_count <= 1 {
// Last reference — remove manifest and all its chunks.
if let Err(e) = self
.remove_manifest_reference(hash, ref_count, &chunk_hashes)
.await
{
tracing::warn!("cleanup_if_orphaned: manifest cleanup failed for {short}: {e}");
}
} else {
// Other files still share this blob: just decrement the manifest
// counter and undo the PG trigger's premature chunk ref_count
// decrement (blobs.ref_count is chunk-level; the manifest is the
// authoritative file-level counter).
sqlx::query(
"UPDATE storage.chunk_manifests \
SET ref_count = ref_count - 1 WHERE file_hash = $1",
)
.bind(hash)
.execute(self.pool.as_ref())
.await
.ok();
// Undo the PG trigger's decrement of storage.blobs.ref_count.
// The trigger fired with blob_hash = file_hash, so only the row
// WHERE hash = file_hash is affected. For single-chunk files
// file_hash == chunk_hash and that row exists; for multi-chunk
// files file_hash is not in storage.blobs, making this a no-op.
sqlx::query("UPDATE storage.blobs SET ref_count = ref_count + 1 WHERE hash = $1")
.bind(hash)
.execute(self.pool.as_ref())
.await
.ok();
tracing::debug!(
"cleanup_if_orphaned: manifest {short} ref_count {ref_count}→{}",
ref_count - 1
);
}
return;
}
// ── Legacy blob path (no manifest) ───────────────────────
// 2026-08-23 refactor: this function used to compensate for the
// OLD PG trigger `trg_files_decrement_blob_ref` unconditionally
// decrementing `storage.blobs.ref_count`, which was wrong for
// CDC files (their `blob_hash` names a `chunk_manifests.file_hash`,
// not a chunk-in-a-manifest). The compensation branches would:
// * Decrement `chunk_manifests.ref_count` a SECOND time (the
// trigger having wrongly touched blobs, not the manifest);
// * Undo the trigger's blob decrement (rc > 1 branch);
// * Call `remove_manifest_reference` (rc <= 1 branch), which
// deletes manifest + dereferences chunks — again duplicating
// work the trigger should own.
//
// Migration `20261017000000_file_delete_trigger_manifest_aware.sql`
// rewrote the trigger to be manifest-aware, so it now correctly
// decrements EITHER the manifest OR the blob depending on which
// one the hash names, walks chunks on last-ref manifest delete,
// and leaves the counters in a consistent state without any
// compensation call. Running the old compensation ON TOP of the
// new trigger causes double-decrement / double-delete and is
// exactly what broke `dedup_blob_cleanup.hurl` step 7
// (`ref_count == 1` observed 0 after purging one of two dedup
// uploads).
//
// What remains here: **physical cleanup only**. If the trigger
// brought a LEGACY whole-file blob to ref_count = 0 and no
// manifest still references it (either directly via file_hash or
// indirectly as a chunk in another manifest's chunk_hashes[]),
// reap the DB row and the backend file eagerly. For CDC chunks
// whose ref_count reached 0 via the trigger's last-ref manifest
// path, `dedup_gc` handles physical reap with a grace window
// against re-upload races.
//
// Callers can keep invoking `cleanup_if_orphaned` unconditionally
// — for CDC paths it's a cheap no-op (manifest still exists OR
// the hash never had a blob row), for legacy paths it reaps.
let deleted_blob = sqlx::query_scalar::<_, String>(
"DELETE FROM storage.blobs WHERE hash = $1 AND ref_count <= 0 RETURNING hash",
"DELETE FROM storage.blobs \
WHERE hash = $1 \
AND ref_count <= 0 \
AND NOT EXISTS (SELECT 1 FROM storage.chunk_manifests \
WHERE $1 = ANY(chunk_hashes)) \
RETURNING hash",
)
.bind(hash)
.fetch_optional(self.pool.as_ref())
@@ -2030,7 +2012,7 @@ impl DedupService {
tracing::warn!("cleanup_if_orphaned: disk delete failed for {short}: {e}");
}
self.fire_blob_hooks(hash);
tracing::info!("cleanup_if_orphaned: removed orphaned blob {short}");
tracing::info!("cleanup_if_orphaned: removed orphaned legacy blob {short}");
}
}