Add bulk import optimization: track_lookup cache, batch inserts, BulkSubmitter

Adopts ListenBrainz-inspired patterns to speed up imports from ~24h to
under 30 minutes for 49k scrobbles.

Phase 1 - track_lookup cache table:
- New migration (000006) adds persistent entity lookup cache
- Maps normalized (artist, track, album) → (artist_id, album_id, track_id)
- SubmitListen fast path: cache hit skips 18 DB queries → 2 queries
- Cache populated after entity resolution, invalidated on merge/delete
- Benefits both live scrobbles and imports

Phase 2 - SaveListensBatch:
- New batch listen insert using pgx CopyFrom → temp table → INSERT ON CONFLICT
- Thousands of inserts per second vs one-at-a-time

Phase 3 - BulkSubmitter:
- Reusable import accelerator for all importers
- Pre-deduplicates scrobbles by (artist, track, album) in memory
- Worker pool (4 goroutines) for parallel entity creation on cache miss
- Batch listen insertion via SaveListensBatch

Phase 4 - Migrate importers:
- Maloja, Spotify, LastFM, ListenBrainz importers use BulkSubmitter
- Koito importer left as-is (already fast with pre-resolved IDs)

Phase 5 - Skip image lookups during import:
- GetArtistImage/GetAlbumImage calls fully skipped when SkipCacheImage=true
- Background tasks (FetchMissingArtistImages/FetchMissingAlbumImages) backfill

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
safierinx-a 2026-03-25 04:17:50 +05:30
parent c92e93484e
commit 8ce6ec494d
21 changed files with 1294 additions and 129 deletions

View file

@ -122,17 +122,18 @@ func createOrUpdateAlbumWithMbzReleaseID(ctx context.Context, d db.DB, opts Asso
}
}
l.Debug().Msg("Searching for album images...")
var imgid uuid.UUID
imgUrl, err := images.GetAlbumImage(ctx, images.AlbumImageOpts{
Artists: utils.UniqueIgnoringCase(slices.Concat(utils.FlattenMbzArtistCreditNames(release.ArtistCredit), utils.FlattenArtistNames(opts.Artists))),
Album: release.Title,
ReleaseMbzID: &opts.ReleaseMbzID,
})
var imgUrl string
if !opts.SkipCacheImage {
l.Debug().Msg("Searching for album images...")
imgUrl, err = images.GetAlbumImage(ctx, images.AlbumImageOpts{
Artists: utils.UniqueIgnoringCase(slices.Concat(utils.FlattenMbzArtistCreditNames(release.ArtistCredit), utils.FlattenArtistNames(opts.Artists))),
Album: release.Title,
ReleaseMbzID: &opts.ReleaseMbzID,
})
if err == nil && imgUrl != "" {
imgid = uuid.New()
if !opts.SkipCacheImage {
if err == nil && imgUrl != "" {
imgid = uuid.New()
var size ImageSize
if cfg.FullImageCacheEnabled() {
size = ImageSizeFull
@ -144,13 +145,11 @@ func createOrUpdateAlbumWithMbzReleaseID(ctx context.Context, d db.DB, opts Asso
if err != nil {
l.Err(err).Msg("createOrUpdateAlbumWithMbzReleaseID: failed to cache image")
}
} else if err != nil {
l.Debug().Msgf("createOrUpdateAlbumWithMbzReleaseID: failed to get album images for %s: %s", release.Title, err.Error())
}
}
if err != nil {
l.Debug().Msgf("createOrUpdateAlbumWithMbzReleaseID: failed to get album images for %s: %s", release.Title, err.Error())
}
album, err = d.SaveAlbum(ctx, db.SaveAlbumOpts{
Title: release.Title,
MusicBrainzID: opts.ReleaseMbzID,
@ -217,14 +216,15 @@ func matchAlbumByTitle(ctx context.Context, d db.DB, opts AssociateAlbumOpts) (*
return nil, fmt.Errorf("matchAlbumByTitle: %w", err)
} else {
var imgid uuid.UUID
imgUrl, err := images.GetAlbumImage(ctx, images.AlbumImageOpts{
Artists: utils.FlattenArtistNames(opts.Artists),
Album: opts.ReleaseName,
ReleaseMbzID: &opts.ReleaseMbzID,
})
if err == nil && imgUrl != "" {
imgid = uuid.New()
if !opts.SkipCacheImage {
var imgUrl string
if !opts.SkipCacheImage {
imgUrl, err = images.GetAlbumImage(ctx, images.AlbumImageOpts{
Artists: utils.FlattenArtistNames(opts.Artists),
Album: opts.ReleaseName,
ReleaseMbzID: &opts.ReleaseMbzID,
})
if err == nil && imgUrl != "" {
imgid = uuid.New()
var size ImageSize
if cfg.FullImageCacheEnabled() {
size = ImageSizeFull
@ -234,13 +234,12 @@ func matchAlbumByTitle(ctx context.Context, d db.DB, opts AssociateAlbumOpts) (*
l.Debug().Msg("Downloading album image from source...")
err = DownloadAndCacheImage(ctx, imgid, imgUrl, size)
if err != nil {
l.Err(err).Msg("createOrUpdateAlbumWithMbzReleaseID: failed to cache image")
l.Err(err).Msg("matchAlbumByTitle: failed to cache image")
}
} else if err != nil {
l.Debug().AnErr("error", err).Msgf("matchAlbumByTitle: failed to get album images for %s", opts.ReleaseName)
}
}
if err != nil {
l.Debug().AnErr("error", err).Msgf("matchAlbumByTitle: failed to get album images for %s", opts.ReleaseName)
}
a, err = d.SaveAlbum(ctx, db.SaveAlbumOpts{
Title: releaseName,