navidrome/persistence/artwork_queue_repository_test.go
Deluan 9349c54ac5 perf(scanner): stop reprocessing album and artist artwork on every full scan
A full scan re-imports every track, so the per-entity artwork enqueue in
persistChanges fired for every album and artist in the library — measured as
100% of both on a live instance, and ~8.5k artists / ~16.7k Deezer fetches on a
96k-file library. Re-importing a track is no evidence the art changed: artist
art has no track-content source at all, and the albums re-derived to identical
hashes across three consecutive scans.

Enqueue through EnqueueIfMissing on a full scan, which anti-joins item_artwork
so only entities that never resolved are queued. Incremental scans keep the
unconditional Enqueue, where a re-import does mean the file changed. Doing this
at the enqueue site rather than skipping it wholesale keeps a first scan filling
in covers as it walks, instead of stalling every cover until the scan ends.

EnqueueMissing grows a priority argument and runs once at end of scan, so an
entity phase 1 never saw still resolves, at Scan priority rather than dropping
to Recheck behind the backfill.
2026-07-28 21:39:12 -04:00

258 lines
11 KiB
Go

package persistence
import (
"context"
"time"
"github.com/Masterminds/squirrel"
"github.com/navidrome/navidrome/model"
"github.com/navidrome/navidrome/utils/slice"
. "github.com/onsi/ginkgo/v2"
. "github.com/onsi/gomega"
"github.com/pocketbase/dbx"
)
var _ = Describe("ArtworkQueueRepository", func() {
var repo model.ArtworkQueueRepository
item := func(kind, id string, prio int) model.ArtworkQueueItem {
return model.ArtworkQueueItem{ItemKind: kind, ItemID: id,
ImageType: model.ImageTypePrimary, Priority: prio}
}
// Writes the post-failure state directly: the production path, MarkFailedIfUnchanged, needs
// a retry_at only a dequeue can hand it.
backOff := func(kind, id string, retryAt time.Time) {
GinkgoHelper()
r := repo.(*artworkQueueRepository)
_, err := r.executeSQL(squirrel.Update(r.tableName).
Set("attempts", squirrel.Expr("attempts + 1")).
Set("retry_at", retryAt).
Where(squirrel.Eq{"item_kind": kind, "item_id": id, "image_type": model.ImageTypePrimary}))
Expect(err).ToNot(HaveOccurred())
}
remove := func(kind, id string) {
GinkgoHelper()
r := repo.(*artworkQueueRepository)
Expect(r.delete(squirrel.Eq{"item_kind": kind, "item_id": id, "image_type": model.ImageTypePrimary})).To(Succeed())
}
BeforeEach(func() {
clearArtworkTables()
DeferCleanup(clearArtworkTables)
repo = NewArtworkQueueRepository(context.Background(), GetDBXBuilder())
})
It("enqueues and dequeues by priority then FIFO", func() {
Expect(repo.Enqueue(item("al", "low", model.ArtworkPriorityBackfill))).To(Succeed())
Expect(repo.Enqueue(item("ar", "high", model.ArtworkPriorityBump))).To(Succeed())
got, err := repo.DequeueBatch(10)
Expect(err).ToNot(HaveOccurred())
Expect(got).To(HaveLen(2))
Expect(got[0].ItemID).To(Equal("high"))
})
It("keeps the higher priority on duplicate enqueue", func() {
Expect(repo.Enqueue(item("al", "a1", model.ArtworkPriorityBump))).To(Succeed())
Expect(repo.Enqueue(item("al", "a1", model.ArtworkPriorityBackfill))).To(Succeed())
got, _ := repo.DequeueBatch(10)
Expect(got).To(HaveLen(1))
Expect(got[0].Priority).To(Equal(model.ArtworkPriorityBump))
})
It("EnqueueBump raises priority without resetting a backing-off row's retry_at", func() {
Expect(repo.Enqueue(item("al", "b1", model.ArtworkPriorityScan))).To(Succeed())
backOff("al", "b1", time.Now().Add(time.Hour))
Expect(repo.DequeueBatch(10)).To(BeEmpty())
Expect(repo.EnqueueBump(item("al", "b1", model.ArtworkPriorityBump))).To(Succeed())
Expect(repo.DequeueBatch(10)).To(BeEmpty(), "bump must not reset retry_at")
// Enqueue (scan/manual), by contrast, resets retry_at and makes it eligible now.
Expect(repo.Enqueue(item("al", "b1", model.ArtworkPriorityScan))).To(Succeed())
got, _ := repo.DequeueBatch(10)
Expect(got).To(HaveLen(1))
Expect(got[0].Priority).To(Equal(model.ArtworkPriorityBump), "bump's higher priority is preserved")
})
It("EnqueueBump inserts a brand-new row eligible immediately", func() {
Expect(repo.EnqueueBump(item("ar", "n1", model.ArtworkPriorityBump))).To(Succeed())
got, _ := repo.DequeueBatch(10)
Expect(got).To(HaveLen(1))
Expect(got[0].ItemID).To(Equal("n1"))
})
It("hides failed items until retry_at", func() {
Expect(repo.Enqueue(item("al", "f1", model.ArtworkPriorityScan))).To(Succeed())
backOff("al", "f1", time.Now().Add(time.Hour))
got, err := repo.DequeueBatch(10)
Expect(err).ToNot(HaveOccurred())
Expect(got).To(BeEmpty())
backOff("al", "f1", time.Now().Add(-time.Minute))
got, _ = repo.DequeueBatch(10)
Expect(got).To(HaveLen(1))
Expect(got[0].Attempts).To(Equal(2))
})
It("MarkFailedIfUnchanged applies backoff only while retry_at is unchanged", func() {
Expect(repo.Enqueue(item("al", "m1", model.ArtworkPriorityScan))).To(Succeed())
// Anchor retry_at in the past so it can never collide with the re-enqueue's now.
backOff("al", "m1", time.Now().Add(-time.Hour))
got, err := repo.DequeueBatch(10)
Expect(err).ToNot(HaveOccurred())
Expect(got).To(HaveLen(1))
original := got[0].RetryAt
// A concurrent scan re-enqueues, resetting retry_at to now.
Expect(repo.Enqueue(item("al", "m1", model.ArtworkPriorityScan))).To(Succeed())
future := time.Now().Add(48 * time.Hour)
Expect(repo.MarkFailedIfUnchanged("al", "m1", model.ImageTypePrimary, original, future)).To(Succeed())
got, _ = repo.DequeueBatch(10)
Expect(got).To(HaveLen(1), "the fresh re-enqueue stays immediately eligible")
Expect(got[0].Attempts).To(BeZero(), "re-enqueue clears attempts, and the stale failure must not bump them")
current := got[0].RetryAt
Expect(repo.MarkFailedIfUnchanged("al", "m1", model.ImageTypePrimary, current, future)).To(Succeed())
got, _ = repo.DequeueBatch(10)
Expect(got).To(BeEmpty(), "backed-off row is hidden until the future retry_at")
all, _ := repo.Count()
Expect(all).To(Equal(int64(1)))
})
It("Enqueue restarts the retry budget an existing row had spent", func() {
Expect(repo.Enqueue(item("al", "e1", model.ArtworkPriorityScan))).To(Succeed())
backOff("al", "e1", time.Now().Add(-time.Hour))
stale := time.Now().Add(-48 * time.Hour)
_, err := GetDBXBuilder().NewQuery("UPDATE artwork_queue SET enqueued_at = {:t} WHERE item_id = 'e1'").
Bind(dbx.Params{"t": stale}).Execute()
Expect(err).ToNot(HaveOccurred())
Expect(repo.Enqueue(item("al", "e1", model.ArtworkPriorityScan))).To(Succeed())
got, err := repo.DequeueBatch(10)
Expect(err).ToNot(HaveOccurred())
Expect(got).To(HaveLen(1))
Expect(got[0].EnqueuedAt).To(BeTemporally("~", time.Now(), time.Minute),
"a re-request must not inherit a spent 12h window and give up on its first attempt")
Expect(got[0].Attempts).To(BeZero())
})
It("deletes on completion and counts", func() {
Expect(repo.Enqueue(item("al", "c1", 0))).To(Succeed())
n, _ := repo.Count()
Expect(n).To(Equal(int64(1)))
remove("al", "c1")
n, _ = repo.Count()
Expect(n).To(BeZero())
})
It("DeleteIfUnchanged deletes only while retry_at is unchanged", func() {
Expect(repo.Enqueue(item("al", "d1", model.ArtworkPriorityScan))).To(Succeed())
// Anchor retry_at in the past so it can never collide with the re-enqueue's now.
backOff("al", "d1", time.Now().Add(-time.Hour))
got, err := repo.DequeueBatch(10)
Expect(err).ToNot(HaveOccurred())
Expect(got).To(HaveLen(1))
original := got[0].RetryAt
// A concurrent scan re-enqueues, resetting retry_at to now.
Expect(repo.Enqueue(item("al", "d1", model.ArtworkPriorityScan))).To(Succeed())
// Deleting with the stale retry_at is a no-op: the re-enqueued row survives.
Expect(repo.DeleteIfUnchanged("al", "d1", model.ImageTypePrimary, original)).To(Succeed())
n, _ := repo.Count()
Expect(n).To(Equal(int64(1)))
got, _ = repo.DequeueBatch(10)
Expect(got).To(HaveLen(1))
Expect(repo.DeleteIfUnchanged("al", "d1", model.ImageTypePrimary, got[0].RetryAt)).To(Succeed())
n, _ = repo.Count()
Expect(n).To(BeZero())
})
It("purges queue rows whose entity no longer exists, per kind", func() {
Expect(repo.Enqueue(
item("al", albumSgtPeppers.ID, model.ArtworkPriorityScan),
item("al", "no-such-album", model.ArtworkPriorityScan),
item("ar", artistKraftwerk.ID, model.ArtworkPriorityScan),
item("ar", "no-such-artist", model.ArtworkPriorityScan),
item("pl", plsBest.ID, model.ArtworkPriorityScan),
item("pl", "no-such-playlist", model.ArtworkPriorityScan),
item("ra", radioWithHomePage.ID, model.ArtworkPriorityScan),
item("ra", "no-such-radio", model.ArtworkPriorityScan),
item("mf", songDayInALife.ID, model.ArtworkPriorityScan),
item("mf", "no-such-mediafile", model.ArtworkPriorityScan),
)).To(Succeed())
purged, err := repo.PurgeDangling()
Expect(err).ToNot(HaveOccurred())
Expect(purged).To(Equal(int64(5)))
got, _ := repo.DequeueBatch(100)
ids := slice.Map(got, func(it model.ArtworkQueueItem) string { return it.ItemID })
Expect(ids).To(ConsistOf(albumSgtPeppers.ID, artistKraftwerk.ID, plsBest.ID, radioWithHomePage.ID, songDayInALife.ID))
})
It("enqueues stale absent states for recheck", func() {
awRepo := NewArtworkRepository(context.Background(), GetDBXBuilder())
old := time.Now().Add(-48 * time.Hour)
Expect(awRepo.PutItemArtwork(&model.ItemArtwork{ItemKind: "ar", ItemID: "stale1", ImageType: model.ImageTypePrimary, Hash: "", AttemptedAt: old})).To(Succeed())
Expect(awRepo.PutItemArtwork(&model.ItemArtwork{ItemKind: "ar", ItemID: "fresh1", ImageType: model.ImageTypePrimary, Hash: "", AttemptedAt: time.Now()})).To(Succeed())
Expect(awRepo.PutItemArtwork(&model.ItemArtwork{ItemKind: "ar", ItemID: "found1", ImageType: model.ImageTypePrimary, Hash: "hX", AttemptedAt: old})).To(Succeed())
n, err := repo.EnqueueStaleAbsent(model.KindArtistArtwork, time.Now().Add(-24*time.Hour))
Expect(err).ToNot(HaveOccurred())
Expect(n).To(Equal(int64(1)))
items, err := repo.DequeueBatch(10)
Expect(err).ToNot(HaveOccurred())
Expect(items).To(HaveLen(1))
Expect(items[0].ItemID).To(Equal("stale1"))
Expect(items[0].Priority).To(Equal(model.ArtworkPriorityRecheck))
})
It("enqueues entities that have no item_artwork row at all", func() {
awRepo := NewArtworkRepository(context.Background(), GetDBXBuilder())
Expect(awRepo.PutItemArtwork(&model.ItemArtwork{ItemKind: "al", ItemID: albumSgtPeppers.ID, ImageType: model.ImageTypePrimary, Hash: "hX", AttemptedAt: time.Now()})).To(Succeed())
Expect(awRepo.PutItemArtwork(&model.ItemArtwork{ItemKind: "al", ItemID: albumAbbeyRoad.ID, ImageType: model.ImageTypePrimary, Hash: "", AttemptedAt: time.Now()})).To(Succeed())
n, err := repo.EnqueueAllMissing(model.KindAlbumArtwork, model.ArtworkPriorityRecheck)
Expect(err).ToNot(HaveOccurred())
Expect(n).To(BeNumerically(">=", 1))
got, err := repo.DequeueBatch(1000)
Expect(err).ToNot(HaveOccurred())
ids := make([]string, 0, len(got))
for _, it := range got {
Expect(it.ItemKind).To(Equal("al"))
Expect(it.Priority).To(Equal(model.ArtworkPriorityRecheck))
ids = append(ids, it.ItemID)
}
Expect(ids).To(ContainElement(albumRadioactivity.ID), "an album with no row must be enqueued")
Expect(ids).ToNot(ContainElement(albumSgtPeppers.ID), "a resolved album must not be re-enqueued")
Expect(ids).ToNot(ContainElement(albumAbbeyRoad.ID), "an absent-state album must not be enqueued as missing")
})
It("does not disturb an already-queued entity when enqueueing missing rows", func() {
Expect(repo.Enqueue(item("al", albumRadioactivity.ID, model.ArtworkPriorityBump))).To(Succeed())
_, err := repo.EnqueueAllMissing(model.KindAlbumArtwork, model.ArtworkPriorityRecheck)
Expect(err).ToNot(HaveOccurred())
got, _ := repo.DequeueBatch(1000)
var count int
for _, it := range got {
if it.ItemID == albumRadioactivity.ID {
count++
Expect(it.Priority).To(Equal(model.ArtworkPriorityBump), "existing bump priority must survive")
}
}
Expect(count).To(Equal(1), "the already-queued row must not be duplicated")
})
})