perf: unified per-artist indexing — discography + image in parallel

Restructure indexOneArtist to run LB discography fetches and MB
artist image resolution concurrently. They use different rate
limiters (LB: 3 req/s, MB: 1 req/s) so they overlap without
contention.

Per artist, the indexer now runs two parallel pipelines:
  LB pipeline: top-release-groups + top-recordings
  MB pipeline: url-rels → Wikidata P18 → Wikimedia image fetch

All artist images are pre-cached during the index build instead
of being resolved on-demand during search. Total build time
drops from ~105 min (sequential) to ~63 min (parallel, MB-bound).

SearchIndex now takes ArtistImageProvider as a dependency. The
Service constructor creates artistImg before the index so both
can share it.
This commit is contained in:
yonlu committed 2026-03-26 08:54:43 -04:00
1 parent 963269b753
commit c9b3c86f37
2 files changed
+37 -3

No files matched your search

+1 -1
View File
@@ -36,11 +36,11 @@ func NewExploreService(logger *slog.Logger, db *database.DB) *Service {
limiter := NewRateLimiter()
mb := NewMusicBrainzClient(cache, logger.WithGroup("musicbrainz"))
lb := NewListenBrainzClient(limiter, cache, logger.WithGroup("listenbrainz"))
index := NewSearchIndex(db, lb, logger.WithGroup("search-index"))
artProxy := NewCoverArtProxy(db, limiter)
artistImg := NewArtistImageProvider(
db, cache, NewRateLimiter(), logger.WithGroup("artist-image"),
)
index := NewSearchIndex(db, lb, artistImg, logger.WithGroup("search-index"))
logger.Info("explore service created")
+36 -2
View File
@@ -104,6 +104,7 @@ type lbSitewideArtist struct {
type SearchIndex struct {
db *database.DB
lb *ListenBrainzClient
artistImg *ArtistImageProvider
logger *slog.Logger
cancel context.CancelFunc
@@ -119,11 +120,13 @@ type SearchIndex struct {
func NewSearchIndex(
db *database.DB,
lb *ListenBrainzClient,
artistImg *ArtistImageProvider,
logger *slog.Logger,
) *SearchIndex {
return &SearchIndex{
db: db,
lb: lb,
artistImg: artistImg,
logger: logger,
done: make(chan struct{}),
}
@@ -932,9 +935,40 @@ func (si *SearchIndex) indexOneArtist(
}
rgLimit, recLimit := si.scaledLimits(artist.ListenCount)
rgs := si.fetchTopReleaseGroups(ctx, lb, artist, rgLimit)
recs := si.fetchTopRecordings(ctx, lb, artist, recLimit)
// Run LB discography fetches and MB artist image resolution
// concurrently — they use different rate limiters so they
// don't block each other.
var (
rgs []SearchIndexResult
recs []SearchIndexResult
wg sync.WaitGroup
)
// LB pipeline: top release groups + top recordings.
wg.Add(1)
go func() {
defer wg.Done()
rgs = si.fetchTopReleaseGroups(ctx, lb, artist, rgLimit)
recs = si.fetchTopRecordings(ctx, lb, artist, recLimit)
}()
// MB pipeline: resolve + cache artist image (uses MB rate limiter).
wg.Add(1)
go func() {
defer wg.Done()
if si.artistImg != nil {
si.artistImg.GetArtistImage(artist.ArtistMBID)
}
}()
wg.Wait()
// Batch write discography results.
all := make([]SearchIndexResult, 0, len(rgs)+len(recs))
all = append(all, rgs...)
all = append(all, recs...)