Merge pull request #444 from jmhbnz/backport-failpoints-injection-2

ahrtr · web-flow · commit 4a1773274ac0 · 2023-03-31T06:20:08.000+08:00
[1.3] Backport perform unmap when mlock fails or both meta pages corrupted
diff --git a/db.go b/db.go
@@ -424,7 +424,7 @@ func (db *DB) hasSyncedFreelist() bool {
 
 // mmap opens the underlying memory-mapped file and initializes the meta references.
 // minsz is the minimum size that the new mmap can be.
-func (db *DB) mmap(minsz int) error {
+func (db *DB) mmap(minsz int) (err error) {
 	db.mmaplock.Lock()
 	defer db.mmaplock.Unlock()
 
@@ -459,17 +459,27 @@ func (db *DB) mmap(minsz int) error {
 	}
 
 	// Unmap existing data before continuing.
-	if err := db.munmap(); err != nil {
+	if err = db.munmap(); err != nil {
 		return err
 	}
 
 	// Memory-map the data file as a byte slice.
 	// gofail: var mapError string
 	// return errors.New(mapError)
-	if err := mmap(db, size); err != nil {
+	if err = mmap(db, size); err != nil {
 		return err
 	}
 
+	// Perform unmmap on any error to reset all data fields:
+	// dataref, data, datasz, meta0 and meta1.
+	defer func() {
+		if err != nil {
+			if unmapErr := db.munmap(); unmapErr != nil {
+				err = fmt.Errorf("%w; rollback unmap also failed: %v", err, unmapErr)
+			}
+		}
+	}()
+
 	if db.Mlock {
 		// Don't allow swapping of data file
 		if err := db.mlock(fileSize); err != nil {
@@ -553,13 +563,17 @@ func (db *DB) mmapSize(size int) (int, error) {
 }
 
 func (db *DB) munlock(fileSize int) error {
+	// gofail: var munlockError string
+	// return errors.New(munlockError)
 	if err := munlock(db, fileSize); err != nil {
 		return fmt.Errorf("munlock error: " + err.Error())
 	}
 	return nil
 }
 
 func (db *DB) mlock(fileSize int) error {
+	// gofail: var mlockError string
+	// return errors.New(mlockError)
 	if err := mlock(db, fileSize); err != nil {
 		return fmt.Errorf("mlock error: " + err.Error())
 	}
diff --git a/tests/failpoint/db_failpoint_test.go b/tests/failpoint/db_failpoint_test.go
@@ -1,13 +1,15 @@
 package failpoint
 
 import (
+	"fmt"
 	"path/filepath"
 	"testing"
 	"time"
 
 	"github.com/stretchr/testify/require"
 
 	bolt "go.etcd.io/bbolt"
+	"go.etcd.io/bbolt/internal/btesting"
 	gofail "go.etcd.io/gofail/runtime"
 )
 
@@ -46,3 +48,49 @@ func TestFailpoint_UnmapFail_DbClose(t *testing.T) {
 	err = db.Close()
 	require.NoError(t, err)
 }
+
+func TestFailpoint_mLockFail(t *testing.T) {
+	err := gofail.Enable("mlockError", `return("mlock somehow failed")`)
+	require.NoError(t, err)
+
+	f := filepath.Join(t.TempDir(), "db")
+	_, err = bolt.Open(f, 0666, &bolt.Options{Mlock: true})
+	require.Error(t, err)
+	require.ErrorContains(t, err, "mlock somehow failed")
+
+	// It should work after disabling the failpoint.
+	err = gofail.Disable("mlockError")
+	require.NoError(t, err)
+
+	_, err = bolt.Open(f, 0666, &bolt.Options{Mlock: true})
+	require.NoError(t, err)
+}
+
+func TestFailpoint_mLockFail_When_remap(t *testing.T) {
+	db := btesting.MustCreateDB(t)
+	db.Mlock = true
+
+	err := gofail.Enable("mlockError", `return("mlock somehow failed in allocate")`)
+	require.NoError(t, err)
+
+	err = db.Fill([]byte("data"), 1, 10000,
+		func(tx int, k int) []byte { return []byte(fmt.Sprintf("%04d", k)) },
+		func(tx int, k int) []byte { return make([]byte, 100) },
+	)
+
+	require.Error(t, err)
+	require.ErrorContains(t, err, "mlock somehow failed in allocate")
+
+	// It should work after disabling the failpoint.
+	err = gofail.Disable("mlockError")
+	require.NoError(t, err)
+	db.MustClose()
+	db.MustReopen()
+
+	err = db.Fill([]byte("data"), 1, 10000,
+		func(tx int, k int) []byte { return []byte(fmt.Sprintf("%04d", k)) },
+		func(tx int, k int) []byte { return make([]byte, 100) },
+	)
+
+	require.NoError(t, err)
+}
