Store and compare file mtimes in nanoseconds (closes #226)
check / check (push) Waiting to run
check / check (push) Waiting to run
The files table held mtime in whole seconds and the scanner compared whole seconds. A file rewritten with its size unchanged and a new mtime in the same second as the indexed one was treated as unchanged, and every later snapshot restored the old content. mtime is now stored as nanoseconds since the Unix epoch and compared at that precision. A local index written before this change holds seconds in mtime: its next backup re-chunks every file once, and a restore of a snapshot made before it sets mtimes near 1970. An mtime outside the years 1678 to 2262 does not fit in int64 nanoseconds; it is stored wrong and restored wrong. Model: opus-5-5
This commit is contained in:
@@ -54,16 +54,16 @@ func (r *FileRepository) Create(ctx context.Context, tx *sql.Tx, file *File) err
|
||||
if tx != nil {
|
||||
LogSQL("Execute", query,
|
||||
file.ID.String(), file.Path.String(), file.SourcePath.String(),
|
||||
file.MTime.Unix(), file.Size, file.Mode, file.UID, file.GID,
|
||||
file.MTime.UnixNano(), file.Size, file.Mode, file.UID, file.GID,
|
||||
file.LinkTarget.String())
|
||||
err = tx.QueryRowContext(ctx, query,
|
||||
file.ID.String(), file.Path.String(), file.SourcePath.String(),
|
||||
file.MTime.Unix(), file.Size, file.Mode, file.UID, file.GID,
|
||||
file.MTime.UnixNano(), file.Size, file.Mode, file.UID, file.GID,
|
||||
file.LinkTarget.String()).Scan(&idStr)
|
||||
} else {
|
||||
err = r.db.QueryRowWithLog(ctx, query,
|
||||
file.ID.String(), file.Path.String(), file.SourcePath.String(),
|
||||
file.MTime.Unix(), file.Size, file.Mode, file.UID, file.GID,
|
||||
file.MTime.UnixNano(), file.Size, file.Mode, file.UID, file.GID,
|
||||
file.LinkTarget.String()).Scan(&idStr)
|
||||
}
|
||||
|
||||
@@ -164,7 +164,7 @@ func (r *FileRepository) ListModifiedSince(
|
||||
ORDER BY path
|
||||
`
|
||||
|
||||
rows, err := r.db.conn.QueryContext(ctx, query, since.Unix())
|
||||
rows, err := r.db.conn.QueryContext(ctx, query, since.UnixNano())
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("querying files: %w", err)
|
||||
}
|
||||
@@ -392,7 +392,7 @@ func (r *FileRepository) CreateBatch(
|
||||
|
||||
args = append(args,
|
||||
f.ID.String(), f.Path.String(), f.SourcePath.String(),
|
||||
f.MTime.Unix(), f.Size, f.Mode, f.UID, f.GID,
|
||||
f.MTime.UnixNano(), f.Size, f.Mode, f.UID, f.GID,
|
||||
f.LinkTarget.String())
|
||||
}
|
||||
|
||||
@@ -460,7 +460,7 @@ func (r *FileRepository) scanFileFrom(row fileRowScanner) (*File, error) {
|
||||
var (
|
||||
file File
|
||||
idStr, pathStr, sourcePathStr string
|
||||
mtimeUnix int64
|
||||
mtimeUnixNano int64
|
||||
linkTarget sql.NullString
|
||||
)
|
||||
|
||||
@@ -468,7 +468,7 @@ func (r *FileRepository) scanFileFrom(row fileRowScanner) (*File, error) {
|
||||
&idStr,
|
||||
&pathStr,
|
||||
&sourcePathStr,
|
||||
&mtimeUnix,
|
||||
&mtimeUnixNano,
|
||||
&file.Size,
|
||||
&file.Mode,
|
||||
&file.UID,
|
||||
@@ -487,7 +487,7 @@ func (r *FileRepository) scanFileFrom(row fileRowScanner) (*File, error) {
|
||||
file.Path = types.FilePath(pathStr)
|
||||
file.SourcePath = types.SourcePath(sourcePathStr)
|
||||
|
||||
file.MTime = time.Unix(mtimeUnix, 0).UTC()
|
||||
file.MTime = time.Unix(0, mtimeUnixNano).UTC()
|
||||
if linkTarget.Valid {
|
||||
file.LinkTarget = types.FilePath(linkTarget.String)
|
||||
}
|
||||
|
||||
@@ -606,8 +606,7 @@ func TestTimezoneHandling(t *testing.T) {
|
||||
t.Skip("timezone not available")
|
||||
}
|
||||
|
||||
// Use Truncate to remove sub-second precision since we store as Unix timestamps
|
||||
nyTime := time.Now().In(loc).Truncate(time.Second)
|
||||
nyTime := time.Now().In(loc)
|
||||
file := &File{
|
||||
Path: "/timezone-test.txt",
|
||||
MTime: nyTime,
|
||||
|
||||
@@ -6,7 +6,7 @@ CREATE TABLE IF NOT EXISTS files (
|
||||
id TEXT PRIMARY KEY, -- UUID
|
||||
path TEXT NOT NULL UNIQUE,
|
||||
source_path TEXT NOT NULL DEFAULT '', -- The source directory this file came from (for restore path stripping)
|
||||
mtime INTEGER NOT NULL,
|
||||
mtime INTEGER NOT NULL, -- nanoseconds since the Unix epoch
|
||||
size INTEGER NOT NULL,
|
||||
mode INTEGER NOT NULL,
|
||||
uid INTEGER NOT NULL,
|
||||
|
||||
@@ -1221,7 +1221,7 @@ func (s *Scanner) checkFileInMemory(
|
||||
|
||||
// Check if file has changed
|
||||
if existingFile.Size != file.Size ||
|
||||
existingFile.MTime.Unix() != file.MTime.Unix() ||
|
||||
existingFile.MTime.UnixNano() != file.MTime.UnixNano() ||
|
||||
existingFile.Mode != file.Mode ||
|
||||
existingFile.UID != file.UID ||
|
||||
existingFile.GID != file.GID {
|
||||
|
||||
@@ -0,0 +1,73 @@
|
||||
package vaultik_test
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"context"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/spf13/afero"
|
||||
"github.com/stretchr/testify/require"
|
||||
"sneak.berlin/go/vaultik/internal/database"
|
||||
"sneak.berlin/go/vaultik/internal/log"
|
||||
"sneak.berlin/go/vaultik/internal/storage"
|
||||
"sneak.berlin/go/vaultik/internal/vaultik"
|
||||
)
|
||||
|
||||
// A file rewritten with its size unchanged and a new mtime in the same
|
||||
// second as the mtime the index holds must still be backed up. See
|
||||
// https://git.eeqj.de/sneak/vaultik/issues/226.
|
||||
//
|
||||
//nolint:paralleltest // installs the global logger via log.Initialize
|
||||
func TestBackupOfSameSecondRewriteRestoresNewContent(t *testing.T) {
|
||||
log.Initialize(log.Config{})
|
||||
|
||||
fs := afero.NewOsFs()
|
||||
tempDir := t.TempDir()
|
||||
dataDir := filepath.Join(tempDir, "src")
|
||||
storeDir := filepath.Join(tempDir, "remote")
|
||||
restoreDir := filepath.Join(tempDir, "restored")
|
||||
dbPath := filepath.Join(tempDir, "index.sqlite")
|
||||
rewrittenPath := filepath.Join(dataDir, "small.txt")
|
||||
|
||||
ctx := context.Background()
|
||||
files := writeFaultSourceTree(t, fs, dataDir)
|
||||
cfg := changedFileConfig(dataDir, dbPath)
|
||||
|
||||
firstMTime := time.Date(2026, time.January, 2, 3, 4, 5, 0, time.UTC).
|
||||
Add(100 * time.Millisecond)
|
||||
secondMTime := firstMTime.Add(800 * time.Millisecond)
|
||||
|
||||
require.NoError(t, fs.Chtimes(rewrittenPath, firstMTime, firstMTime))
|
||||
|
||||
store, err := storage.NewFileStorer(storeDir)
|
||||
require.NoError(t, err)
|
||||
|
||||
db, err := database.New(ctx, dbPath)
|
||||
require.NoError(t, err)
|
||||
|
||||
repos := database.NewRepositories(db)
|
||||
v := newBackupVaultik(ctx, cfg, store, repos, db, fs)
|
||||
|
||||
require.NoError(t, backUp(v, "first"))
|
||||
|
||||
// Upper-casing ASCII text keeps its size.
|
||||
files[rewrittenPath] = bytes.ToUpper(files[rewrittenPath])
|
||||
require.NoError(t, afero.WriteFile(fs, rewrittenPath, files[rewrittenPath], 0o644))
|
||||
require.NoError(t, fs.Chtimes(rewrittenPath, secondMTime, secondMTime))
|
||||
|
||||
require.NoError(t, backUp(v, "second"))
|
||||
|
||||
id := localSnapshotID(ctx, t, repos, "second")
|
||||
require.NoError(t, db.Close())
|
||||
|
||||
reader := newReaderVaultik(ctx, cfg, store, nil, fs)
|
||||
require.NoError(t, reader.Restore(&vaultik.RestoreOptions{
|
||||
SnapshotID: id,
|
||||
TargetDir: restoreDir,
|
||||
Verify: true,
|
||||
}))
|
||||
|
||||
assertRestoredTree(t, fs, restoreDir, files)
|
||||
}
|
||||
Reference in New Issue
Block a user