Delete expired negative cache rows in batches

CleanExpired deletes at most 1000 expired rows per statement and starts
no further statement once its context ends, so a request on the one
database connection waits behind one batch at most.

Model: opus-5-5

TODO.md

@@ -36,7 +36,9 @@ P2: security: per-origin rate limiting
   after that, so a client asking for a new missing path each time added rows
   that stayed for good. The eviction goroutine now calls `CleanExpired` at
   startup and on each periodic tick, every 5 minutes in pixad, so a row stays at
-  most about 10 minutes. It runs with the disk cache disabled
+  most about 10 minutes. `CleanExpired` deletes at most 1000 rows per statement,
+  so a request waits behind 1000 deletions at most, however many rows have
+  expired. The goroutine runs with the disk cache disabled
   (`cache_max_bytes: 0`) too, where it does nothing else, as the negative cache
   is used either way.
 - 2026-10-13 `fit=outside` no longer makes an output above 8192 on a side

internal/imgcache/cache.go

@@ -32,6 +32,12 @@ const httpStatusOK = 200
 // variant not among them is served as before, reading its .meta file.
 const metaCacheSize = 10000
 
+// cleanExpiredBatchSize is the most expired negative cache rows one
+// statement of CleanExpired deletes. Each batch is a statement of its
+// own, so a request waits behind one batch at most, however many rows
+// have expired.
+const cleanExpiredBatchSize = 1000
+
 // CacheConfig holds cache configuration.
 type CacheConfig struct {
 	StateDir    string
@@ -483,20 +489,27 @@ func (c *Cache) GetSourceContent(
 	return c.srcContent.LoadWithSize(contentHash)
 }
 
-// CleanExpired removes the negative cache rows past their expiry. The
+// CleanExpired removes the negative cache rows past their expiry, one
-// eviction goroutine calls it at startup and on every periodic tick, so
+// batch per statement, until none is left. Once ctx ends it starts no
-// a row stays at most NegativeTTL plus one eviction interval, whether or
+// further batch and returns ctx's error. The eviction goroutine calls it
-// not its URL is requested again.
+// at startup and on every periodic tick, so a row stays about
+// NegativeTTL plus one eviction interval, whether or not its URL is
+// requested again.
 func (c *Cache) CleanExpired(ctx context.Context) error {
-	// Clean expired negative cache entries
+	for {
-	_, err := c.db.ExecContext(ctx, `
+		if ctx.Err() != nil {
-		DELETE FROM negative_cache WHERE expires_at < CURRENT_TIMESTAMP
+			return ctx.Err()
-	`)
+		}
-	if err != nil {
-		return fmt.Errorf("failed to clean negative cache: %w", err)
-	}
 
-	return nil
+		deleted, err := c.cleanExpiredBatch(ctx)
+		if err != nil {
+			return err
+		}
+
+		if deleted < cleanExpiredBatchSize {
+			return nil
+		}
+	}
 }
 
 // Stats returns cache statistics.
@@ -760,3 +773,27 @@ func (c *Cache) checkNegativeCache(
 
 	return true, nil
 }
+
+// cleanExpiredBatch deletes up to cleanExpiredBatchSize negative cache
+// rows past their expiry in one statement, and returns how many it
+// deleted. DELETE ... LIMIT needs a SQLite build option, so the subquery
+// picks the rows.
+func (c *Cache) cleanExpiredBatch(ctx context.Context) (int64, error) {
+	result, err := c.db.ExecContext(ctx, `
+		DELETE FROM negative_cache WHERE id IN (
+			SELECT id FROM negative_cache
+			WHERE expires_at < CURRENT_TIMESTAMP
+			LIMIT ?
+		)
+	`, cleanExpiredBatchSize)
+	if err != nil {
+		return 0, fmt.Errorf("failed to clean negative cache: %w", err)
+	}
+
+	deleted, err := result.RowsAffected()
+	if err != nil {
+		return 0, fmt.Errorf("failed to count cleaned negative cache rows: %w", err)
+	}
+
+	return deleted, nil
+}