Count each file, byte and upload once in backup statistics (closes #225)
check / check (push) Waiting to run

The scanner added a changed file's bytes again for each new chunk and
counted a file as unchanged for each chunk already stored. It now
counts files and bytes once, in the scan phase, and counts its own
uploads, so a --cron run, which has no progress reporter, records
them. The blob count no longer adds earlier paths' blobs again.

The snapshots row now stores the size of all files in total_size and
the referenced blobs' sizes in blob_size, blob_uncompressed_size and
compression_ratio, as docs/DATAMODEL.md says. Those sizes come from
one query, and a failed query fails the snapshot. DATAMODEL.md now
says chunk_count and blob_count count what the run added.

Removed UpdateSnapshotStats and GetCountBySnapshot, which nothing
calls any more.

Model: opus-5-5
This commit was merged in pull request #254.
This commit is contained in:
2026-10-07 02:59:27 +02:00
parent 85d4ef118d
commit 49eed7a3e5
12 changed files with 471 additions and 172 deletions
+5 -23
View File
@@ -154,26 +154,6 @@ func (sm *SnapshotManager) CreateSnapshotWithName(
return snapshotID, nil
}
// UpdateSnapshotStats updates the statistics for a snapshot during backup
func (sm *SnapshotManager) UpdateSnapshotStats(
ctx context.Context, snapshotID string, stats BackupStats,
) error {
err := sm.repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
return sm.repos.Snapshots.UpdateCounts(ctx, tx, snapshotID,
int64(stats.FilesScanned),
int64(stats.ChunksCreated),
int64(stats.BlobsCreated),
stats.BytesScanned,
stats.BytesUploaded,
)
})
if err != nil {
return fmt.Errorf("updating snapshot stats: %w", err)
}
return nil
}
// UpdateSnapshotStatsExtended updates snapshot statistics with extended metrics.
// This includes compression level, uncompressed blob size, and upload duration.
func (sm *SnapshotManager) UpdateSnapshotStatsExtended(
@@ -185,8 +165,8 @@ func (sm *SnapshotManager) UpdateSnapshotStatsExtended(
int64(stats.FilesScanned),
int64(stats.ChunksCreated),
int64(stats.BlobsCreated),
stats.BytesScanned,
stats.BytesUploaded,
stats.TotalSize,
stats.BlobSize,
)
if err != nil {
return err
@@ -196,6 +176,7 @@ func (sm *SnapshotManager) UpdateSnapshotStatsExtended(
return sm.repos.Snapshots.UpdateExtendedStats(ctx, tx, snapshotID,
stats.BlobUncompressedSize,
stats.CompressionLevel,
stats.BytesUploaded,
stats.UploadDurationMs,
)
})
@@ -890,7 +871,7 @@ func (sm *SnapshotManager) getFileSize(path string) int64 {
// BackupStats contains statistics from a backup operation
type BackupStats struct {
FilesScanned int
BytesScanned int64
TotalSize int64 // Total size of all files examined
ChunksCreated int
BlobsCreated int
BytesUploaded int64
@@ -900,6 +881,7 @@ type BackupStats struct {
type ExtendedBackupStats struct {
BackupStats
BlobSize int64 // Total compressed size of all referenced blobs
BlobUncompressedSize int64 // Total uncompressed size of all referenced blobs
CompressionLevel int // Compression level used for this snapshot
UploadDurationMs int64 // Total milliseconds spent uploading to S3