fix: make WAL segment directory fsync failure fatal (C6)
Per design §3.2 line 248-272, segment directory fsync is a hard requirement for durable-ready state, not best-effort. rename is atomic in memory but not guaranteed to survive power loss without a directory fsync. The previous code silently swallowed both os.Open(dir) and dirFD.Sync() errors, leaving WAL writer to confirm batches as durable when their segment might not exist after a crash. Failure propagation: - Initial segment creation: NewSegmentWriter fails -> NewSegmentManager fails -> DB.Open fails (user sees error, no data promise violated). - Rotation during AppendBatch: NewSegmentWriter fails -> AppendBatch fails -> WalWriter.stopWithError(ErrCommitUnknown) -> write-stopped (per design line 272). Changes: - wal/segment_writer.go: extract dirFsync helper (Open -> f.Stat -> IsDir -> f.Sync, avoiding TOCTOU window), replace silent swallow with fatal error; on failure clean up resources (fd.Close + os.Remove) and surface cleanup errors via errors.Join so nothing is silently lost. - wal/dir_fsync_test.go (new): unit test the helper with valid dir, non-existent dir (fails at os.Open), and not-a-dir (fails at IsDir). - wal/segment_writer_test.go: add TestNewSegmentWriterDirFsyncFailure (injects failure via package-level dirFsyncFn override; documents the not-parallel-safe constraint), TestNewSegmentWriterNormalPathStillWorks (regression), and TestNewSegmentWriterRetryAfterDirFsyncFailure (verifies cleanup is effective for retry). - wal/segment_manager_test.go: add TestSegmentManagerRotateFailsOnDirFsyncFailure (fills segment until rotation triggers, injects failure, verifies propagation through AppendBatch path) and TestNewSegmentManagerFailsOnDirFsyncFailure (covers the DB.Open failure path). dirFsyncFn injection note: tests that override this package-level var must not use t.Parallel(). All existing wal tests run serially within the package; this is the lightest mechanism that doesn't require interface indirection in production code. Verified: each new test fails on pre-fix code (silent swallow returned nil error) and passes after the fix. Full suite green including go test -race ./... . Audit context: docs/audit-3.2.md C6 (Oracle-verified bg_ef425776).
This commit is contained in:
@@ -1,8 +1,10 @@
|
||||
package wal
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/dailz/go-kv/config"
|
||||
@@ -239,3 +241,67 @@ func itoa(n uint64) string {
|
||||
}
|
||||
return string(buf[i:])
|
||||
}
|
||||
|
||||
// Regression guard for C6: NewSegmentManager must propagate dir fsync
|
||||
// failure from initial segment creation. This is the DB.Open failure path.
|
||||
func TestNewSegmentManagerFailsOnDirFsyncFailure(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
cfg := tinyWalConfig()
|
||||
|
||||
orig := dirFsyncFn
|
||||
dirFsyncFn = func(string) error { return errors.New("simulated dir fsync failure") }
|
||||
t.Cleanup(func() { dirFsyncFn = orig })
|
||||
|
||||
sm, err := NewSegmentManager(dir, 0, 0, cfg)
|
||||
if err == nil {
|
||||
if sm != nil {
|
||||
sm.Close()
|
||||
}
|
||||
t.Fatal("NewSegmentManager: expected error on dir fsync failure, got nil")
|
||||
}
|
||||
if !strings.Contains(err.Error(), "create initial segment") {
|
||||
t.Errorf("error should be wrapped as 'create initial segment', got: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// Regression guard for C6: SegmentManager.AppendBatch must propagate
|
||||
// rotation failure (which now includes dir fsync failure) as error.
|
||||
//
|
||||
// Note: C8 (segment_manager.go:64-66 passes byte offset as startSequence)
|
||||
// makes multi-segment recovery broken, but this test only verifies error
|
||||
// propagation through AppendBatch; it does not exercise recovery.
|
||||
func TestSegmentManagerRotateFailsOnDirFsyncFailure(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
cfg := tinyWalConfig()
|
||||
|
||||
sm, err := NewSegmentManager(dir, 0, 0, cfg)
|
||||
if err != nil {
|
||||
t.Fatalf("NewSegmentManager: %v", err)
|
||||
}
|
||||
defer sm.Close()
|
||||
|
||||
encoded, err := EncodeWalBatch(0, []*WalEntry{
|
||||
{OpType: OpPut, ValueKind: VKInline, Key: []byte("k"), Value: []byte("v")},
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("EncodeWalBatch: %v", err)
|
||||
}
|
||||
|
||||
// Fill the active segment until next AppendBatch would trigger rotation.
|
||||
// segment_manager.go:62 triggers rotate when
|
||||
// RemainingPayload() < len(encoded) + 2*PhysicalRecordHeaderSize
|
||||
worstCaseSize := uint64(len(encoded)) + 2*uint64(PhysicalRecordHeaderSize)
|
||||
for sm.RemainingPayload() >= worstCaseSize {
|
||||
if err := sm.AppendBatch(encoded); err != nil {
|
||||
t.Fatalf("fill AppendBatch: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
orig := dirFsyncFn
|
||||
dirFsyncFn = func(string) error { return errors.New("simulated dir fsync failure") }
|
||||
t.Cleanup(func() { dirFsyncFn = orig })
|
||||
|
||||
if err := sm.AppendBatch(encoded); err == nil {
|
||||
t.Fatal("AppendBatch: expected rotation failure, got nil")
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user