Go on past cache entries the reconciliation pass cannot read (closes #343)

The walk of each storage directory returned the error of an entry it
could not read. The pass then stopped before its later checks, and the
same entry stopped every later pass. Now reconcileFiles skips a
directory it cannot list and a file whose info it cannot read. It logs
a warning naming the path and the error, and the walk goes on. It reads
each file's info itself and hands it to reconcileVariantFile and
reconcileSourceFile. A cancelled context still stops the walk with its
error. README.md says so under Storage.

Model: opus-5-5

README.md

@@ -256,6 +256,10 @@ Each look also drops the rows of variants whose files are missing. When pixa
 cannot read a variant file's size for another reason, it keeps the variant's
 row. It logs a warning naming the variant key and the error.
 
+During a look, pixa skips any file or directory in the cache that it cannot
+read. It logs a warning naming the path and the error, and goes on with the rest
+of the look.
+
 pixa's target is 1-5k r/s, which has not been measured at that rate (see Load
 Test). Toward it, a cache hit opens the variant's file and nothing else, and
 makes no database call. The content type comes from the file's first bytes,

TODO.md

@@ -30,6 +30,14 @@ P2: security: per-origin rate limiting
 
 # Completed Steps
 
+- 2026-10-27 the reconciliation pass skips a directory it cannot list and a file
+  whose info it cannot read, and goes on (closes #343). It returned the error,
+  so one such entry stopped every pass before its later checks.
+    - Each skipped entry gets the warning "skipped unreadable entry in cache
+      directory", with its path and the error.
+    - `reconcileFiles` reads each file's info and hands it to
+      `reconcileVariantFile` and `reconcileSourceFile`.
+    - A cancelled context still stops the walk with its error.
 - 2026-10-26 the reconciliation pass drops a variant's accounting row only when
   its file is missing (closes #340). Any other error reading the file's size
   keeps the row. It dropped the row on any error and logged the file as missing.

internal/imgcache/eviction.go

@@ -515,12 +515,14 @@ func (c *Cache) reconcileAccounting(ctx context.Context) error {
 }
 
 // reconcileFiles walks baseDir, one of the cache's storage directories,
-// sweeping stale temp files and passing each other file, with its name, to
-// reconcileFile. Once ctx is cancelled it stops at the next file and
-// returns ctx's error.
+// sweeping stale temp files and passing each other file, with its info and
+// name, to reconcileFile. It skips a directory it cannot list and a file
+// whose info it cannot read. Each gets a warning naming its path and the
+// error, and the walk goes on, so one such entry does not stop the pass.
+// Once ctx is cancelled it stops at the next file and returns ctx's error.
 func (c *Cache) reconcileFiles(
 	ctx context.Context, baseDir string,
-	reconcileFile func(path string, entry fs.DirEntry, name string) error,
+	reconcileFile func(path string, info fs.FileInfo, name string) error,
 ) error {
 	return filepath.WalkDir(
 		baseDir,
@@ -529,8 +531,15 @@ func (c *Cache) reconcileFiles(
 				return ctx.Err()
 			}
 
-			if err != nil || entry.IsDir() {
-				return err
+			if err != nil {
+				c.log.Warn("skipped unreadable entry in cache directory",
+					"path", path, "error", err)
+
+				return nil
+			}
+
+			if entry.IsDir() {
+				return nil
 			}
 
 			name := entry.Name()
@@ -541,7 +550,15 @@ func (c *Cache) reconcileFiles(
 				return nil
 			}
 
-			return reconcileFile(path, entry, name)
+			info, err := entry.Info()
+			if err != nil {
+				c.log.Warn("skipped unreadable entry in cache directory",
+					"path", path, "error", err)
+
+				return nil
+			}
+
+			return reconcileFile(path, info, name)
 		},
 	)
 }
@@ -551,8 +568,8 @@ func (c *Cache) reconcileFiles(
 // and sweeping stale temp files.
 func (c *Cache) reconcileVariantFiles(ctx context.Context) error {
 	return c.reconcileFiles(ctx, c.variants.baseDir,
-		func(path string, entry fs.DirEntry, name string) error {
-			return c.reconcileVariantFile(ctx, path, entry, imagerequest.VariantKey(name))
+		func(path string, info fs.FileInfo, name string) error {
+			return c.reconcileVariantFile(ctx, path, info, imagerequest.VariantKey(name))
 		})
 }
 
@@ -562,16 +579,11 @@ func (c *Cache) reconcileVariantFiles(ctx context.Context) error {
 // crash or a restored snapshot can leave it, is removed with its row and
 // a warning naming it, so the variant is converted again.
 func (c *Cache) reconcileVariantFile(
-	ctx context.Context, path string, entry fs.DirEntry, cacheKey imagerequest.VariantKey,
+	ctx context.Context, path string, info fs.FileInfo, cacheKey imagerequest.VariantKey,
 ) error {
-	info, err := entry.Info()
-	if err != nil {
-		return fmt.Errorf("failed to stat variant file: %w", err)
-	}
-
 	var recordedSize int64
 
-	err = c.db.QueryRowContext(ctx,
+	err := c.db.QueryRowContext(ctx,
 		`SELECT size_bytes FROM variant_content WHERE cache_key = ?`, string(cacheKey),
 	).Scan(&recordedSize)
 
@@ -714,8 +726,8 @@ func queryStringColumn[T ~string](
 // and sweeping stale temp files.
 func (c *Cache) reconcileSourceFiles(ctx context.Context) error {
 	return c.reconcileFiles(ctx, c.srcContent.baseDir,
-		func(path string, entry fs.DirEntry, name string) error {
-			return c.reconcileSourceFile(ctx, path, entry, imagerequest.SourceKey(name))
+		func(path string, info fs.FileInfo, name string) error {
+			return c.reconcileSourceFile(ctx, path, info, imagerequest.SourceKey(name))
 		})
 }
 
@@ -726,16 +738,11 @@ func (c *Cache) reconcileSourceFiles(ctx context.Context) error {
 // is removed with its row and a warning naming it, so the source is
 // fetched again.
 func (c *Cache) reconcileSourceFile(
-	ctx context.Context, path string, entry fs.DirEntry, key imagerequest.SourceKey,
+	ctx context.Context, path string, info fs.FileInfo, key imagerequest.SourceKey,
 ) error {
-	info, err := entry.Info()
-	if err != nil {
-		return fmt.Errorf("failed to stat source content file: %w", err)
-	}
-
 	var recordedSize int64
 
-	err = c.db.QueryRowContext(ctx,
+	err := c.db.QueryRowContext(ctx,
 		`SELECT size_bytes FROM source_content WHERE source_key = ?`,
 		string(key),
 	).Scan(&recordedSize)

internal/imgcache/eviction_internal_test.go

@@ -9,8 +9,10 @@ import (
 	"log/slog"
 	"os"
 	"path/filepath"
+	"slices"
 	"strings"
 	"sync"
+	"syscall"
 	"testing"
 	"time"
 
@@ -785,6 +787,136 @@ func TestReconcileVariantRowsDropsOnlyRowsOfMissingFiles(t *testing.T) {
 	}
 }
 
+// makeEntriesTooLongToRead makes a chain of directories inside dir, each
+// named with 255 zeros, the longest name Linux allows. Linux refuses a path
+// of 4096 bytes or more, and the chain goes as deep as it can below that.
+// In its deepest directory it makes a directory and a file whose paths
+// reach that length. Even root can then neither list that directory nor
+// read the file's info. It returns their two paths. It makes them through
+// an os.Root, which names one directory at a time, as no call may name
+// the whole path.
+func makeEntriesTooLongToRead(t *testing.T, dir string) []string {
+	t.Helper()
+
+	name := strings.Repeat("0", 255)
+	deepest := dir
+
+	for len(filepath.Join(deepest, name)) < 4096 {
+		deepest = filepath.Join(deepest, name)
+	}
+
+	chain, err := filepath.Rel(dir, deepest)
+	if err != nil {
+		t.Fatalf("filepath.Rel() error = %v", err)
+	}
+
+	root, err := os.OpenRoot(dir)
+	if err != nil {
+		t.Fatalf("os.OpenRoot(%s) error = %v", dir, err)
+	}
+
+	defer func() { _ = root.Close() }()
+
+	err = root.MkdirAll(filepath.Join(chain, name), StorageDirPerm)
+	if err != nil {
+		t.Fatalf("failed to make a directory too deep to list: %v", err)
+	}
+
+	fileName := strings.Repeat("1", 255)
+
+	err = root.WriteFile(filepath.Join(chain, fileName), []byte("unreadable"),
+		StorageFilePerm)
+	if err != nil {
+		t.Fatalf("failed to make a file too deep to read: %v", err)
+	}
+
+	return []string{filepath.Join(deepest, name), filepath.Join(deepest, fileName)}
+}
+
+// TestReconciliationGoesOnPastEntriesItCannotRead puts, in each storage
+// directory, a directory the pass cannot list and a file whose info it
+// cannot read. The pass walks each directory in name order, so it reaches
+// them before the cache's files, whose keys start with a letter. It must
+// log a warning naming each one's path and the error, and still do the
+// rest of its work:
+//   - adopt a variant file that has no row
+//   - drop the row of a variant whose file is missing
+//   - remove a source file that has no row
+//   - correct a wrong total cache usage
+func TestReconciliationGoesOnPastEntriesItCannotRead(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1<<30)
+	ctx := t.Context()
+
+	untrackedVariant := []byte("variant with no row")
+
+	err := cache.variants.Write(string(testVariantKeyOne), untrackedVariant)
+	if err != nil {
+		t.Fatalf("failed to write a variant file with no row: %v", err)
+	}
+
+	storeEvictionTestVariant(t, cache, testVariantKeyTwo, []byte("variant two"))
+
+	err = os.Remove(cache.variants.keyToPath(string(testVariantKeyTwo)))
+	if err != nil {
+		t.Fatalf("failed to remove the second variant's file: %v", err)
+	}
+
+	untrackedSourceKey := "ffeeddcc0001"
+
+	err = cache.srcContent.Write(untrackedSourceKey, []byte("source with no row"))
+	if err != nil {
+		t.Fatalf("failed to write a source file with no row: %v", err)
+	}
+
+	_, err = cache.db.ExecContext(ctx,
+		`UPDATE cache_usage SET total_size_bytes = 1 WHERE id = 1`)
+	if err != nil {
+		t.Fatalf("failed to set a wrong total: %v", err)
+	}
+
+	unreadable := slices.Concat(
+		makeEntriesTooLongToRead(t, cache.variants.baseDir),
+		makeEntriesTooLongToRead(t, cache.srcContent.baseDir),
+	)
+
+	logs := reconcileAsAtStartup(t, cache)
+
+	for _, path := range unreadable {
+		assertWarningNames(t, logs, path)
+
+		if !strings.Contains(logs, path+": "+syscall.ENAMETOOLONG.Error()) {
+			t.Errorf("no log line gives the error reading %s", path)
+		}
+	}
+
+	rowQuery := `SELECT COUNT(*) FROM variant_content WHERE cache_key = ?`
+
+	if n := countRows(t, cache, rowQuery, string(testVariantKeyOne)); n != 1 {
+		t.Errorf("the variant file with no row got %d rows, want 1", n)
+	}
+
+	if n := countRows(t, cache, rowQuery, string(testVariantKeyTwo)); n != 0 {
+		t.Errorf("the variant with no file kept %d rows, want 0", n)
+	}
+
+	_, err = os.Stat(cache.srcContent.keyToPath(untrackedSourceKey))
+	if err == nil {
+		t.Error("the source file with no row is still on disk")
+	}
+
+	usage, err := cache.UsageBytes(ctx)
+	if err != nil {
+		t.Fatalf("UsageBytes() error = %v", err)
+	}
+
+	if usage != int64(len(untrackedVariant)) {
+		t.Errorf("UsageBytes() = %d, want %d, the size of the adopted variant",
+			usage, len(untrackedVariant))
+	}
+}
+
 // TestPeriodicReconciliationAdoptsFileThatAppearsAfterStartup proves
 // reconciliation is not a one-shot startup-only pass: it must also run
 // on the periodic ticker, so a variant file that lands on disk with no