mirror of
https://github.com/gabehf/Koito.git
synced 2026-04-22 12:01:52 -07:00
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:
parent
c92e93484e
commit
8ce6ec494d
21 changed files with 1294 additions and 129 deletions
15
db/migrations/000006_track_lookup.sql
Normal file
15
db/migrations/000006_track_lookup.sql
Normal file
|
|
@ -0,0 +1,15 @@
|
|||
-- +goose Up
|
||||
CREATE TABLE track_lookup (
|
||||
lookup_key TEXT NOT NULL PRIMARY KEY,
|
||||
artist_id INT NOT NULL REFERENCES artists(id) ON DELETE CASCADE,
|
||||
album_id INT NOT NULL REFERENCES releases(id) ON DELETE CASCADE,
|
||||
track_id INT NOT NULL REFERENCES tracks(id) ON DELETE CASCADE,
|
||||
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
|
||||
);
|
||||
|
||||
CREATE INDEX idx_track_lookup_track_id ON track_lookup(track_id);
|
||||
CREATE INDEX idx_track_lookup_artist_id ON track_lookup(artist_id);
|
||||
CREATE INDEX idx_track_lookup_album_id ON track_lookup(album_id);
|
||||
|
||||
-- +goose Down
|
||||
DROP TABLE IF EXISTS track_lookup;
|
||||
Loading…
Add table
Add a link
Reference in a new issue