Go on past cache entries the reconciliation pass cannot read (closes #343) #344

Merged
clawbot merged 2 commits from issue-343-reconcile-walk-goes-on into next 2026-10-27 02:24:15 +01:00
4 changed files with 257 additions and 33 deletions
+5
View File
@@ -256,6 +256,11 @@ 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 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. row. It logs a warning naming the variant key and the error.
During a look, pixa skips a directory it cannot list and a file whose size it
cannot read. It logs a warning naming the path and the error, and goes on with
the rest of the look. A file renamed or removed after pixa listed its directory
gets no warning.
pixa's target is 1-5k r/s, which has not been measured at that rate (see Load 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 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, makes no database call. The content type comes from the file's first bytes,
+11
View File
@@ -30,6 +30,17 @@ P2: security: per-origin rate limiting
# Completed Steps # 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 stopped before its
later checks at a directory it could not list, or at a source or variant file
whose info it could not read.
- It logs the warning "skipped unreadable entry in cache directory", with
the path and the error.
- A file renamed or removed after its directory was listed gets no warning.
- `reconcileFiles` reads each file's info once, before the temp-file check,
and hands it to `sweepStaleTempFile`, `reconcileVariantFile` or
`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 - 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 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. keeps the row. It dropped the row on any error and logged the file as missing.
+40 -33
View File
@@ -515,12 +515,15 @@ func (c *Cache) reconcileAccounting(ctx context.Context) error {
} }
// reconcileFiles walks baseDir, one of the cache's storage directories, // reconcileFiles walks baseDir, one of the cache's storage directories,
// sweeping stale temp files and passing each other file, with its name, to // sweeping stale temp files and passing each other file, with its info and
// reconcileFile. Once ctx is cancelled it stops at the next file and // name, to reconcileFile. It skips a directory it cannot list and a file
// returns ctx's error. // whose info it cannot read, so one such entry does not stop the pass. It
// logs a warning naming the path and the error. A file renamed or removed
// after its directory was listed is skipped with no warning. Once ctx is
// cancelled it stops at the next file and returns ctx's error.
func (c *Cache) reconcileFiles( func (c *Cache) reconcileFiles(
ctx context.Context, baseDir string, 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 { ) error {
return filepath.WalkDir( return filepath.WalkDir(
baseDir, baseDir,
@@ -529,19 +532,38 @@ func (c *Cache) reconcileFiles(
return ctx.Err() return ctx.Err()
} }
if err != nil || entry.IsDir() { if err != nil {
return err c.log.Warn("skipped unreadable entry in cache directory",
"path", path, "error", err)
return nil
}
if entry.IsDir() {
return nil
}
info, err := entry.Info()
if errors.Is(err, fs.ErrNotExist) {
return nil
}
if err != nil {
c.log.Warn("skipped unreadable entry in cache directory",
"path", path, "error", err)
return nil
} }
name := entry.Name() name := entry.Name()
if strings.HasPrefix(name, tempFilePrefix) { if strings.HasPrefix(name, tempFilePrefix) {
c.sweepStaleTempFile(path, entry) c.sweepStaleTempFile(path, info)
return nil return nil
} }
return reconcileFile(path, entry, name) return reconcileFile(path, info, name)
}, },
) )
} }
@@ -551,8 +573,8 @@ func (c *Cache) reconcileFiles(
// and sweeping stale temp files. // and sweeping stale temp files.
func (c *Cache) reconcileVariantFiles(ctx context.Context) error { func (c *Cache) reconcileVariantFiles(ctx context.Context) error {
return c.reconcileFiles(ctx, c.variants.baseDir, return c.reconcileFiles(ctx, c.variants.baseDir,
func(path string, entry fs.DirEntry, name string) error { func(path string, info fs.FileInfo, name string) error {
return c.reconcileVariantFile(ctx, path, entry, imagerequest.VariantKey(name)) return c.reconcileVariantFile(ctx, path, info, imagerequest.VariantKey(name))
}) })
} }
@@ -562,16 +584,11 @@ func (c *Cache) reconcileVariantFiles(ctx context.Context) error {
// crash or a restored snapshot can leave it, is removed with its row and // crash or a restored snapshot can leave it, is removed with its row and
// a warning naming it, so the variant is converted again. // a warning naming it, so the variant is converted again.
func (c *Cache) reconcileVariantFile( 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 { ) error {
info, err := entry.Info()
if err != nil {
return fmt.Errorf("failed to stat variant file: %w", err)
}
var recordedSize int64 var recordedSize int64
err = c.db.QueryRowContext(ctx, err := c.db.QueryRowContext(ctx,
`SELECT size_bytes FROM variant_content WHERE cache_key = ?`, string(cacheKey), `SELECT size_bytes FROM variant_content WHERE cache_key = ?`, string(cacheKey),
).Scan(&recordedSize) ).Scan(&recordedSize)
@@ -714,8 +731,8 @@ func queryStringColumn[T ~string](
// and sweeping stale temp files. // and sweeping stale temp files.
func (c *Cache) reconcileSourceFiles(ctx context.Context) error { func (c *Cache) reconcileSourceFiles(ctx context.Context) error {
return c.reconcileFiles(ctx, c.srcContent.baseDir, return c.reconcileFiles(ctx, c.srcContent.baseDir,
func(path string, entry fs.DirEntry, name string) error { func(path string, info fs.FileInfo, name string) error {
return c.reconcileSourceFile(ctx, path, entry, imagerequest.SourceKey(name)) return c.reconcileSourceFile(ctx, path, info, imagerequest.SourceKey(name))
}) })
} }
@@ -726,16 +743,11 @@ func (c *Cache) reconcileSourceFiles(ctx context.Context) error {
// is removed with its row and a warning naming it, so the source is // is removed with its row and a warning naming it, so the source is
// fetched again. // fetched again.
func (c *Cache) reconcileSourceFile( 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 { ) error {
info, err := entry.Info()
if err != nil {
return fmt.Errorf("failed to stat source content file: %w", err)
}
var recordedSize int64 var recordedSize int64
err = c.db.QueryRowContext(ctx, err := c.db.QueryRowContext(ctx,
`SELECT size_bytes FROM source_content WHERE source_key = ?`, `SELECT size_bytes FROM source_content WHERE source_key = ?`,
string(key), string(key),
).Scan(&recordedSize) ).Scan(&recordedSize)
@@ -900,17 +912,12 @@ func (c *Cache) correctUsageTotal(
// sweepStaleTempFile removes a temp file left behind by a crashed // sweepStaleTempFile removes a temp file left behind by a crashed
// write once it is old enough that no in-flight store can own it. // write once it is old enough that no in-flight store can own it.
func (c *Cache) sweepStaleTempFile(path string, entry fs.DirEntry) { func (c *Cache) sweepStaleTempFile(path string, info fs.FileInfo) {
info, err := entry.Info()
if err != nil {
return
}
if time.Since(info.ModTime()) < staleTempFileAge { if time.Since(info.ModTime()) < staleTempFileAge {
return return
} }
err = os.Remove(path) err := os.Remove(path)
if err != nil && !os.IsNotExist(err) { if err != nil && !os.IsNotExist(err) {
c.log.Warn("failed to remove stale temp file", "path", path, "error", err) c.log.Warn("failed to remove stale temp file", "path", path, "error", err)
+201
View File
@@ -9,8 +9,10 @@ import (
"log/slog" "log/slog"
"os" "os"
"path/filepath" "path/filepath"
"slices"
"strings" "strings"
"sync" "sync"
"syscall"
"testing" "testing"
"time" "time"
@@ -785,6 +787,205 @@ func TestReconcileVariantRowsDropsOnlyRowsOfMissingFiles(t *testing.T) {
} }
} }
// openDirectoryNearPathLimit 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.
// It returns the chain's deepest directory as an os.Root, closed when the
// test ends. An entry made through it with a 255-byte name has a path even
// the root user cannot read. The os.Root can make that entry because it
// names the entry only by its name, not by the whole path.
func openDirectoryNearPathLimit(t *testing.T, dir string) *os.Root {
t.Helper()
name := strings.Repeat("0", 255)
deepest := dir
for len(filepath.Join(deepest, name)) < 4096 {
deepest = filepath.Join(deepest, name)
}
err := os.MkdirAll(deepest, StorageDirPerm)
if err != nil {
t.Fatalf("failed to make a chain of directories: %v", err)
}
root, err := os.OpenRoot(deepest)
if err != nil {
t.Fatalf("os.OpenRoot(%s) error = %v", deepest, err)
}
t.Cleanup(func() { _ = root.Close() })
return root
}
// makeEntriesTooLongToRead makes a new directory and a new file in the
// deepest directory of the chain that openDirectoryNearPathLimit makes
// inside dir. Even the root user can then neither list the new directory
// nor read the new file's info. It returns the paths of the new directory
// and the new file.
func makeEntriesTooLongToRead(t *testing.T, dir string) []string {
t.Helper()
deepest := openDirectoryNearPathLimit(t, dir)
dirName := strings.Repeat("0", 255)
err := deepest.Mkdir(dirName, StorageDirPerm)
if err != nil {
t.Fatalf("failed to make a directory too deep to list: %v", err)
}
fileName := strings.Repeat("1", 255)
err = deepest.WriteFile(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(), dirName),
filepath.Join(deepest.Name(), fileName),
}
}
// makeTempFileTooLongToRead makes a temp file in the deepest directory of
// the chain that openDirectoryNearPathLimit makes inside dir. Even the
// root user then cannot read the temp file's info. It returns the temp
// file's path.
func makeTempFileTooLongToRead(t *testing.T, dir string) string {
t.Helper()
deepest := openDirectoryNearPathLimit(t, dir)
name := tempFilePrefix + strings.Repeat("1", 255-len(tempFilePrefix))
err := deepest.WriteFile(name, []byte("partial"), StorageFilePerm)
if err != nil {
t.Fatalf("failed to make a temp file too deep to read: %v", err)
}
return filepath.Join(deepest.Name(), name)
}
// assertSkippedEntryWarning checks that logs hold the warning "skipped
// unreadable entry in cache directory" naming path, with the error
// ENAMETOOLONG for that path.
func assertSkippedEntryWarning(t *testing.T, logs, path string) {
t.Helper()
for line := range strings.Lines(logs) {
if strings.Contains(line, `"level":"WARN"`) &&
strings.Contains(line, `"msg":"skipped unreadable entry in cache directory"`) &&
strings.Contains(line, `"path":"`+path+`"`) &&
strings.Contains(line, path+": "+syscall.ENAMETOOLONG.Error()) {
return
}
}
t.Errorf("no warning %q names %s with the error %q",
"skipped unreadable entry in cache directory", path, syscall.ENAMETOOLONG)
}
// 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 {
assertSkippedEntryWarning(t, logs, 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))
}
}
// TestReconciliationWarnsOfTempFilesWhoseInfoItCannotRead puts, in each
// storage directory, a temp file whose info the pass cannot read. The
// pass must log a warning naming each one's path and the error, as it
// does for any other file whose info it cannot read.
func TestReconciliationWarnsOfTempFilesWhoseInfoItCannotRead(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
unreadable := []string{
makeTempFileTooLongToRead(t, cache.variants.baseDir),
makeTempFileTooLongToRead(t, cache.srcContent.baseDir),
}
logs := reconcileAsAtStartup(t, cache)
for _, path := range unreadable {
assertSkippedEntryWarning(t, logs, path)
}
}
// TestPeriodicReconciliationAdoptsFileThatAppearsAfterStartup proves // TestPeriodicReconciliationAdoptsFileThatAppearsAfterStartup proves
// reconciliation is not a one-shot startup-only pass: it must also run // 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 // on the periodic ticker, so a variant file that lands on disk with no