new command line flag: postpone-shutdown-flag-file, new server command; 'state'

doc/command-line-flags.md

@@ -169,6 +169,10 @@ Indicate a file name, such that the final [cut-over](cut-over.md) step does not
 When this flag is set, `gh-ost` expects the file to exist on startup, or else tries to create it. `gh-ost` exits with error if the file does not exist and `gh-ost` is unable to create it.
 With this flag set, the migration will cut-over upon deletion of the file or upon `cut-over` [interactive command](interactive-commands.md).
 
+### postpone-shutdown-flag-file
+
+If indicated file exists, and assuming execution is successful, `gh-ost` will wait after cut-over, and after running the success hooks, instead of exiting. This can be useful in state based environments where we may wish to ask `gh-ost` wat the state of the migration is, as opposed to assuming it reports the state via hooks. This gives a controller/operator the chance to communicate to `gh-ost` and confirm that the migration is successful. See also the `state` server command.
+
 ### replica-server-id
 
 Defaults to 99999. If you run multiple migrations then you must provide a different, unique `--replica-server-id` for each `gh-ost` process.

doc/interactive-commands.md

@@ -17,6 +17,7 @@ Both interfaces may serve at the same time. Both respond to simple text command,
 - `help`: shows a brief list of available commands
 - `status`: returns a detailed status summary of migration progress and configuration
 - `sup`: returns a brief status summary of migration progress
+- `state`: returns `Running` or `Complete`. For the latter, see `--postpone-shutdown-flag-file`
 - `coordinates`: returns recent (though not exactly up to date) binary log coordinates of the inspected server
 - `chunk-size=<newsize>`: modify the `chunk-size`; applies on next running copy-iteration
 - `dml-batch-size=<newsize>`: modify the `dml-batch-size`; applies on next applying of binary log events

go/base/context.go

@@ -36,6 +36,14 @@ const (
 
 type CutOver int
 
+type MigrationState string
+
+const (
+	MigrationStateRunning  MigrationState = "Running"
+	MigrationStateComplete MigrationState = "Complete"
+	MigrationStateFailed   MigrationState = "Failed"
+)
+
 const (
 	CutOverAtomic CutOver = iota
 	CutOverTwoStep
@@ -129,6 +137,7 @@ type MigrationContext struct {
 	CriticalLoadIntervalMilliseconds    int64
 	CriticalLoadHibernateSeconds        int64
 	PostponeCutOverFlagFile             string
+	PostponeShutdownFlagFile            string
 	CutOverLockTimeoutSeconds           int64
 	CutOverExponentialBackoff           bool
 	ExponentialBackoffMaxInterval       int64
@@ -729,6 +738,13 @@ func (this *MigrationContext) AddThrottleControlReplicaKey(key mysql.InstanceKey
 	return nil
 }
 
+func (this *MigrationContext) GetMigrationState() MigrationState {
+	if atomic.LoadInt64(&this.CutOverCompleteFlag) > 0 {
+		return MigrationStateComplete
+	}
+	return MigrationStateRunning
+}
+
 // ApplyCredentials sorts out the credentials between the config file and the CLI flags
 func (this *MigrationContext) ApplyCredentials() {
 	this.configMutex.Lock()

go/cmd/gh-ost/main.go

@@ -112,6 +112,7 @@ func main() {
 	flag.StringVar(&migrationContext.ThrottleFlagFile, "throttle-flag-file", "", "operation pauses when this file exists; hint: use a file that is specific to the table being altered")
 	flag.StringVar(&migrationContext.ThrottleAdditionalFlagFile, "throttle-additional-flag-file", "/tmp/gh-ost.throttle", "operation pauses when this file exists; hint: keep default, use for throttling multiple gh-ost operations")
 	flag.StringVar(&migrationContext.PostponeCutOverFlagFile, "postpone-cut-over-flag-file", "", "while this file exists, migration will postpone the final stage of swapping tables, and will keep on syncing the ghost table. Cut-over/swapping would be ready to perform the moment the file is deleted.")
+	flag.StringVar(&migrationContext.PostponeShutdownFlagFile, "postpone-shutdown-flag-file", "", "while this file exists gh-ost will not terminate. This does not postpone cut-over. Use case: be able to advertise that migration is complete.")
 	flag.StringVar(&migrationContext.PanicFlagFile, "panic-flag-file", "", "when this file is created, gh-ost will immediately terminate, without cleanup")
 
 	flag.BoolVar(&migrationContext.DropServeSocket, "initially-drop-socket-file", false, "Should gh-ost forcibly delete an existing socket file. Be careful: this might drop the socket file of a running migration!")

go/logic/migrator.go

@@ -419,6 +419,18 @@ func (this *Migrator) Migrate() (err error) {
 	if err := this.hooksExecutor.onSuccess(); err != nil {
 		return err
 	}
+	this.sleepWhileTrue(
+		func() (bool, error) {
+			if this.migrationContext.PostponeShutdownFlagFile == "" {
+				return false, nil
+			}
+			if base.FileExists(this.migrationContext.PostponeShutdownFlagFile) {
+				// Postpone file defined and exists!
+				return true, nil
+			}
+			return false, nil
+		},
+	)
 	this.migrationContext.Log.Infof("Done migrating %s.%s", sql.EscapeName(this.migrationContext.DatabaseName), sql.EscapeName(this.migrationContext.OriginalTableName))
 	return nil
 }

go/logic/server.go

@@ -146,6 +146,7 @@ func (this *Server) applyServerCommand(command string, writer *bufio.Writer) (pr
 			fmt.Fprint(writer, `available commands:
 status                               # Print a detailed status message
 sup                                  # Print a short status message
+state                                # Print Running|Complete
 coordinates													 # Print the currently inspected coordinates
 chunk-size=<newsize>                 # Set a new chunk-size
 dml-batch-size=<newsize>             # Set a new dml-batch-size
@@ -169,6 +170,11 @@ help                                 # This message
 		return ForcePrintStatusOnlyRule, nil
 	case "info", "status":
 		return ForcePrintStatusAndHintRule, nil
+	case "state":
+		{
+			fmt.Fprintf(writer, "%+v\n", this.migrationContext.GetMigrationState())
+			return NoPrintStatusRule, nil
+		}
 	case "coordinates":
 		{
 			if argIsQuestion || arg == "" {