Files
vaultik/internal/database/chunks_ext.go
T
clawbot 38ebfd843a
check / check (pull_request) Successful in 1m23s
check / check (push) Successful in 3m10s
Trust only uploaded blobs for deduplication (closes #148)
An interrupted blob upload left the blob's chunks, blob_chunks, and blobs rows committed before the upload was attempted, so a later run deduplicated against data that never reached storage and produced a snapshot that reported success but could not be restored.

Fix (issue option b): a chunk counts as known only when a blob holding it has uploaded_ts set, and each run drops un-uploaded blob rows and the chunks they orphan at startup, so the affected data is re-chunked and re-uploaded. A blob recorded with no remote backend is marked uploaded so the invariant holds uniformly.

The reproduction is the interrupted-upload test from #72: its t.Skip is removed and it passes against this fix, and this branch's earlier duplicate copy is dropped. The interrupted metadata-export case is split to #177.

Model: opus-4-8
2026-09-22 10:29:21 +02:00

66 lines
1.6 KiB
Go

package database
import (
"context"
"fmt"
)
// List returns every chunk in the index, ordered by chunk hash.
func (r *ChunkRepository) List(ctx context.Context) ([]*Chunk, error) {
return r.list(ctx, `
SELECT chunk_hash, size
FROM chunks
ORDER BY chunk_hash
`)
}
// ListInUploadedBlobs returns the chunks that are stored in a blob whose
// upload has completed (uploaded_ts set), ordered by chunk hash. These
// are the only chunks a backup may safely deduplicate against: a chunk
// recorded solely in a blob that was never uploaded refers to data that
// is not in remote storage, so trusting it would silently drop that data
// from later snapshots.
func (r *ChunkRepository) ListInUploadedBlobs(ctx context.Context) ([]*Chunk, error) {
return r.list(ctx, `
SELECT DISTINCT c.chunk_hash, c.size
FROM chunks c
JOIN blob_chunks bc ON c.chunk_hash = bc.chunk_hash
JOIN blobs b ON bc.blob_id = b.id
WHERE b.uploaded_ts IS NOT NULL
ORDER BY c.chunk_hash
`)
}
// list runs a chunk-selecting query and scans the (chunk_hash, size) rows.
func (r *ChunkRepository) list(ctx context.Context, query string) ([]*Chunk, error) {
rows, err := r.db.conn.QueryContext(ctx, query)
if err != nil {
return nil, fmt.Errorf("querying chunks: %w", err)
}
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
var chunks []*Chunk
for rows.Next() {
var chunk Chunk
err := rows.Scan(
&chunk.ChunkHash,
&chunk.Size,
)
if err != nil {
return nil, fmt.Errorf("scanning chunk: %w", err)
}
chunks = append(chunks, &chunk)
}
return chunks, rows.Err()
}