Bug fix: Use target tablet from health stats cache when checking replication status (vitessio#14436) (#128)

Signed-off-by: Austen Lacy <[email protected]>
Co-authored-by: Austen Lacy <[email protected]>

Author: austenLacy

go/test/endtoend/cluster/cluster_process.go

@@ -896,6 +896,11 @@ func (cluster *LocalProcessCluster) VtctlclientGetTablet(tablet *Vttablet) (*top
 	return &ti, nil
 }
 
+func (cluster *LocalProcessCluster) VtctlclientChangeTabletType(tablet *Vttablet, tabletType topodatapb.TabletType) error {
+	_, err := cluster.VtctlclientProcess.ExecuteCommandWithOutput("ChangeTabletType", "--", tablet.Alias, tabletType.String())
+	return err
+}
+
 // Teardown brings down the cluster by invoking teardown for individual processes
 func (cluster *LocalProcessCluster) Teardown() {
 	PanicHandler(nil)

go/test/endtoend/tabletgateway/vtgate_test.go

@@ -29,6 +29,7 @@ import (
 	"time"
 
 	"vitess.io/vitess/go/test/endtoend/utils"
+	"vitess.io/vitess/go/vt/proto/topodata"
 
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
@@ -69,6 +70,34 @@ func TestVtgateReplicationStatusCheck(t *testing.T) {
 	assert.Equal(t, expectNumRows, numRows, fmt.Sprintf("wrong number of results from show vitess_replication_status. Expected %d, got %d", expectNumRows, numRows))
 }
 
+func TestVtgateReplicationStatusCheckWithTabletTypeChange(t *testing.T) {
+	defer cluster.PanicHandler(t)
+	// Healthcheck interval on tablet is set to 1s, so sleep for 2s
+	time.Sleep(2 * time.Second)
+	verifyVtgateVariables(t, clusterInstance.VtgateProcess.VerifyURL)
+	ctx := context.Background()
+	conn, err := mysql.Connect(ctx, &vtParams)
+	require.NoError(t, err)
+	defer conn.Close()
+
+	// Only returns rows for REPLICA and RDONLY tablets -- so should be 2 of them
+	qr := utils.Exec(t, conn, "show vitess_replication_status like '%'")
+	expectNumRows := 2
+	numRows := len(qr.Rows)
+	assert.Equal(t, expectNumRows, numRows, fmt.Sprintf("wrong number of results from show vitess_replication_status. Expected %d, got %d", expectNumRows, numRows))
+
+	// change the RDONLY tablet to SPARE
+	rdOnlyTablet := clusterInstance.Keyspaces[0].Shards[0].Rdonly()
+	err = clusterInstance.VtctlclientChangeTabletType(rdOnlyTablet, topodata.TabletType_SPARE)
+	require.NoError(t, err)
+
+	// Only returns rows for REPLICA and RDONLY tablets -- so should be 1 of them since we updated 1 to spare
+	qr = utils.Exec(t, conn, "show vitess_replication_status like '%'")
+	expectNumRows = 1
+	numRows = len(qr.Rows)
+	assert.Equal(t, expectNumRows, numRows, fmt.Sprintf("wrong number of results from show vitess_replication_status. Expected %d, got %d", expectNumRows, numRows))
+}
+
 func verifyVtgateVariables(t *testing.T, url string) {
 	resp, err := http.Get(url)
 	require.NoError(t, err)

go/vt/vtgate/executor.go

@@ -848,14 +848,14 @@ func (e *Executor) showVitessReplicationStatus(ctx context.Context, filter *sqlp
 	for _, s := range status {
 		for _, ts := range s.TabletsStats {
 			// We only want to show REPLICA and RDONLY tablets
-			if ts.Tablet.Type != topodatapb.TabletType_REPLICA && ts.Tablet.Type != topodatapb.TabletType_RDONLY {
+			if ts.Target.TabletType != topodatapb.TabletType_REPLICA && ts.Target.TabletType != topodatapb.TabletType_RDONLY {
 				continue
 			}
 
 			// Allow people to filter by Keyspace and Shard using a LIKE clause
 			if filter != nil {
 				ksFilterRegex := sqlparser.LikeToRegexp(filter.Like)
-				keyspaceShardStr := fmt.Sprintf("%s/%s", ts.Tablet.Keyspace, ts.Tablet.Shard)
+				keyspaceShardStr := fmt.Sprintf("%s/%s", ts.Target.Keyspace, ts.Target.Shard)
 				if !ksFilterRegex.MatchString(keyspaceShardStr) {
 					continue
 				}