Remove expired negative cache rows in the eviction loop (closes #244)

A negative cache row was deleted only when its URL was requested again, so a client asking for a new missing path each time grew the database without limit. The eviction goroutine now removes expired rows at startup and on every tick, so a row stays about NegativeTTL plus one eviction interval. It deletes at most 1000 rows per statement, so a request on the one database connection waits behind one batch at most. The goroutine now also runs when the disk cache is disabled, since the negative cache is used either way. Model: opus-5-5
2026-10-15 15:02:27 +02:00
parent 2790125cb2
commit 69f65d4302
5 changed files with 327 additions and 19 deletions
@@ -3,6 +3,7 @@ package imgcache
 import (
 	"context"
 	"errors"
+	"strconv"
 	"testing"
 	"time"
 )
@@ -159,6 +160,242 @@ func TestService_Get_ServesCachedVariantOfNegativeCachedURL(t *testing.T) {
 	}
 }

+// TestEvictionLoopRemovesExpiredNegativeCacheRows stores a failed fetch
+// that expires a second later and starts the eviction loop with a short
+// interval: a later tick must remove its row although its URL is never
+// requested again, and must keep a row that has not expired. It runs
+// with the disk cache enabled and disabled, as the negative cache is
+// used either way.
+func TestEvictionLoopRemovesExpiredNegativeCacheRows(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name             string
+		disableDiskCache bool
+	}{
+		{name: "disk cache enabled", disableDiskCache: false},
+		{name: "disk cache disabled", disableDiskCache: true},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			cache, err := NewCache(evictionTestDB(t), CacheConfig{
+				StateDir:         t.TempDir(),
+				NegativeTTL:      time.Second,
+				DisableDiskCache: tt.disableDiskCache,
+			})
+			if err != nil {
+				t.Fatalf("failed to create cache: %v", err)
+			}
+
+			expired := &ImageRequest{
+				SourceHost: testHostExample, SourcePath: "/gone.jpg",
+			}
+
+			err = cache.StoreNegative(t.Context(), expired, 404, "not found")
+			if err != nil {
+				t.Fatalf("StoreNegative failed: %v", err)
+			}
+
+			const notExpiredPath = "/later.jpg"
+
+			_, err = cache.db.ExecContext(t.Context(), `
+				INSERT INTO negative_cache
+					(source_host, source_path, status_code, expires_at)
+				VALUES (?, ?, 404, datetime('now', '+1 hour'))
+			`, testHostExample, notExpiredPath)
+			if err != nil {
+				t.Fatalf("failed to insert a row that has not expired: %v", err)
+			}
+
+			started := time.Now()
+
+			cache.StartEviction(100 * time.Millisecond)
+			defer func() { _ = cache.StopEviction(t.Context()) }()
+
+			for negativeCacheRowCount(t, cache, expired.SourcePath) > 0 {
+				if time.Since(started) > 10*time.Second {
+					t.Fatal("the expired row is still in negative_cache")
+				}
+
+				time.Sleep(50 * time.Millisecond)
+			}
+
+			t.Logf("the expired row was removed %s after the loop started",
+				time.Since(started))
+
+			if negativeCacheRowCount(t, cache, notExpiredPath) != 1 {
+				t.Error("the row that has not expired was removed")
+			}
+		})
+	}
+}
+
+// negativeCacheRowCount returns how many negative_cache rows hold
+// sourcePath.
+func negativeCacheRowCount(tb testing.TB, cache *Cache, sourcePath string) int {
+	tb.Helper()
+
+	var count int
+
+	err := cache.db.QueryRowContext(tb.Context(),
+		`SELECT COUNT(*) FROM negative_cache WHERE source_path = ?`,
+		sourcePath,
+	).Scan(&count)
+	if err != nil {
+		tb.Fatalf("failed to count negative_cache rows: %v", err)
+	}
+
+	return count
+}
+
+// TestCleanExpiredDeletesInBatches stores one expired negative cache row
+// more than one batch holds, and one row that has not expired. One
+// statement must delete one batch and no more, so a request waits behind
+// one batch at most; CleanExpired must then remove the expired row left
+// over and keep the row that has not expired.
+func TestCleanExpiredDeletesInBatches(t *testing.T) {
+	t.Parallel()
+
+	cache, err := NewCache(evictionTestDB(t), CacheConfig{StateDir: t.TempDir()})
+	if err != nil {
+		t.Fatalf("failed to create cache: %v", err)
+	}
+
+	ctx := t.Context()
+
+	insertExpiredNegativeCacheRows(t, cache, cleanExpiredBatchSize+1)
+
+	const notExpiredPath = "/later.jpg"
+
+	_, err = cache.db.ExecContext(ctx, `
+		INSERT INTO negative_cache
+			(source_host, source_path, status_code, expires_at)
+		VALUES (?, ?, 404, datetime('now', '+1 hour'))
+	`, testHostExample, notExpiredPath)
+	if err != nil {
+		t.Fatalf("failed to insert a row that has not expired: %v", err)
+	}
+
+	deleted, err := cache.cleanExpiredBatch(ctx)
+	if err != nil {
+		t.Fatalf("cleanExpiredBatch failed: %v", err)
+	}
+
+	t.Logf("one statement deleted %d of %d expired rows",
+		deleted, cleanExpiredBatchSize+1)
+
+	if deleted != cleanExpiredBatchSize {
+		t.Errorf("one statement deleted %d rows, want %d",
+			deleted, cleanExpiredBatchSize)
+	}
+
+	err = cache.CleanExpired(ctx)
+	if err != nil {
+		t.Fatalf("CleanExpired failed: %v", err)
+	}
+
+	if count := negativeCacheTableRowCount(t, cache); count != 1 {
+		t.Errorf("negative_cache holds %d rows after CleanExpired, want 1", count)
+	}
+
+	if negativeCacheRowCount(t, cache, notExpiredPath) != 1 {
+		t.Error("the row that has not expired was removed")
+	}
+}
+
+// TestCleanExpiredRemovesMoreThanOneBatch stores one expired negative
+// cache row more than one batch holds and calls CleanExpired once: it
+// must remove them all, so it fails if CleanExpired stops after its
+// first batch.
+func TestCleanExpiredRemovesMoreThanOneBatch(t *testing.T) {
+	t.Parallel()
+
+	cache, err := NewCache(evictionTestDB(t), CacheConfig{StateDir: t.TempDir()})
+	if err != nil {
+		t.Fatalf("failed to create cache: %v", err)
+	}
+
+	insertExpiredNegativeCacheRows(t, cache, cleanExpiredBatchSize+1)
+
+	before := negativeCacheTableRowCount(t, cache)
+
+	err = cache.CleanExpired(t.Context())
+	if err != nil {
+		t.Fatalf("CleanExpired failed: %v", err)
+	}
+
+	after := negativeCacheTableRowCount(t, cache)
+
+	t.Logf("CleanExpired removed %d of %d expired rows, %d per batch",
+		before-after, before, cleanExpiredBatchSize)
+
+	if after != 0 {
+		t.Errorf("negative_cache holds %d rows after CleanExpired, want 0", after)
+	}
+}
+
+// TestCleanExpiredStopsOnceContextEnds runs CleanExpired with a context
+// that has already ended: it must return the context's error and delete
+// no row.
+func TestCleanExpiredStopsOnceContextEnds(t *testing.T) {
+	t.Parallel()
+
+	cache, err := NewCache(evictionTestDB(t), CacheConfig{StateDir: t.TempDir()})
+	if err != nil {
+		t.Fatalf("failed to create cache: %v", err)
+	}
+
+	insertExpiredNegativeCacheRows(t, cache, 1)
+
+	ctx, cancel := context.WithCancel(t.Context())
+	cancel()
+
+	err = cache.CleanExpired(ctx)
+	if !errors.Is(err, context.Canceled) {
+		t.Errorf("CleanExpired() error = %v, want context.Canceled", err)
+	}
+
+	if count := negativeCacheTableRowCount(t, cache); count != 1 {
+		t.Errorf("negative_cache holds %d rows, want the expired row kept", count)
+	}
+}
+
+// insertExpiredNegativeCacheRows inserts count negative_cache rows that
+// expired an hour ago, each for a different source path.
+func insertExpiredNegativeCacheRows(t *testing.T, cache *Cache, count int) {
+	t.Helper()
+
+	for i := range count {
+		_, err := cache.db.ExecContext(t.Context(), `
+			INSERT INTO negative_cache
+				(source_host, source_path, status_code, expires_at)
+			VALUES (?, ?, 404, datetime('now', '-1 hour'))
+		`, testHostExample, "/expired/"+strconv.Itoa(i)+".jpg")
+		if err != nil {
+			t.Fatalf("failed to insert an expired row: %v", err)
+		}
+	}
+}
+
+// negativeCacheTableRowCount returns how many rows negative_cache holds.
+func negativeCacheTableRowCount(tb testing.TB, cache *Cache) int {
+	tb.Helper()
+
+	var count int
+
+	err := cache.db.QueryRowContext(tb.Context(),
+		`SELECT COUNT(*) FROM negative_cache`,
+	).Scan(&count)
+	if err != nil {
+		tb.Fatalf("failed to count negative_cache rows: %v", err)
+	}
+
+	return count
+}
+
 func TestService_Get_ReturnsErrorForNegativeCachedURL(t *testing.T) {
 	t.Parallel()