Add --test-on-replica-skip-replica-stop flag

Author: pbitty

go/base/context.go

@@ -82,14 +82,14 @@ type MigrationContext struct {
 	ServeSocketFile string
 	ServeTCPPort    int64
 
-	Noop                     bool
-	TestOnReplica            bool
-	MigrateOnReplica         bool
-	ManualReplicationControl bool
-	OkToDropTable            bool
-	InitiallyDropOldTable    bool
-	InitiallyDropGhostTable  bool
-	CutOverType              CutOver
+	Noop                         bool
+	TestOnReplica                bool
+	MigrateOnReplica             bool
+	TestOnReplicaSkipReplicaStop bool
+	OkToDropTable                bool
+	InitiallyDropOldTable        bool
+	InitiallyDropGhostTable      bool
+	CutOverType                  CutOver
 
 	TableEngine               string
 	RowsEstimate              int64

go/cmd/gh-ost/main.go

@@ -60,8 +60,8 @@ func main() {
 	flag.BoolVar(&migrationContext.SkipRenamedColumns, "skip-renamed-columns", false, "in case your `ALTER` statement renames columns, gh-ost will note that and offer its interpretation of the rename. By default gh-ost does not proceed to execute. This flag tells gh-ost to skip the renamed columns, i.e. to treat what gh-ost thinks are renamed columns as unrelated columns. NOTE: you may lose column data")
 
 	executeFlag := flag.Bool("execute", false, "actually execute the alter & migrate the table. Default is noop: do some tests and exit")
-	testOnReplicaWithManualReplicationControl := flag.Bool("test-on-replica-manual-replication-control", false, "Same as --test-on-replica, but waits for replication to be stopped, instead of stopping it automatically. (Useful in RDS.)")
 	flag.BoolVar(&migrationContext.TestOnReplica, "test-on-replica", false, "Have the migration run on a replica, not on the master. At the end of migration replication is stopped, and tables are swapped and immediately swap-revert. Replication remains stopped and you can compare the two tables for building trust")
+	flag.BoolVar(&migrationContext.TestOnReplicaSkipReplicaStop, "test-on-replica-skip-replica-stop", false, "When --test-on-replica is enabled, do not issue commands stop replication (requires --test-on-replica)")
 	flag.BoolVar(&migrationContext.MigrateOnReplica, "migrate-on-replica", false, "Have the migration run on a replica, not on the master. This will do the full migration on the replica including cut-over (as opposed to --test-on-replica)")
 
 	flag.BoolVar(&migrationContext.OkToDropTable, "ok-to-drop-table", false, "Shall the tool drop the old table at end of operation. DROPping tables can be a long locking operation, which is why I'm not doing it by default. I'm an online tool, yes?")
@@ -150,13 +150,13 @@ func main() {
 	if migrationContext.SwitchToRowBinlogFormat && migrationContext.AssumeRBR {
 		log.Fatalf("--switch-to-rbr and --assume-rbr are mutually exclusive")
 	}
-	if *testOnReplicaWithManualReplicationControl {
-		if migrationContext.TestOnReplica {
-			log.Fatalf("--test-on-replica-manual-replication-control and --test-on-replica are mutually exclusive")
+	if migrationContext.TestOnReplicaSkipReplicaStop {
+		if !migrationContext.TestOnReplica {
+			log.Fatalf("--test-on-replica-skip-replica-stop requires --test-on-replica to be enabled")
 		}
-		migrationContext.TestOnReplica = true
-		migrationContext.ManualReplicationControl = true
+		log.Warning("--test-on-replica-skip-replica-stop enabled. We will not stop replication before cut-over. Ensure you have a plugin that does this.")
 	}
+
 	switch *cutOver {
 	case "atomic", "default", "":
 		migrationContext.CutOverType = base.CutOverAtomic

go/logic/applier.go

@@ -566,32 +566,10 @@ func (this *Applier) StartSlaveSQLThread() error {
 	return nil
 }
 
-func (this *Applier) isReplicationStopped() bool {
-	query := `show slave status`
-	replicationStopped := false
-
-	err := sqlutils.QueryRowsMap(this.db, query, func(rowMap sqlutils.RowMap) error {
-		replicationStopped = rowMap["Slave_IO_Running"].String == "No" && rowMap["Slave_SQL_Running"].String == "No"
-		return nil
-	})
-
-	if err != nil {
-		return false
-	}
-	return replicationStopped
-}
-
 // StopReplication is used by `--test-on-replica` and stops replication.
 func (this *Applier) StopReplication() error {
-	if this.migrationContext.ManualReplicationControl {
-		for {
-			log.Info("Waiting for replication to stop...")
-			if this.isReplicationStopped() {
-				log.Info("Replication stopped.")
-				break
-			}
-			time.Sleep(5 * time.Second)
-		}
+	if this.migrationContext.TestOnReplicaSkipReplicaStop {
+		log.Warningf("--test-on-replica-skip-replica-stop enabled, we are not stopping replication.")
 	} else {
 		if err := this.StopSlaveIOThread(); err != nil {
 			return err