pg_ctl promote

Fujii Masao, reviewed by Robert Haas, Stephen Frost, and Magnus Hagander.

src/backend/access/transam/xlog.c

@@ -62,6 +62,7 @@
 /* File path names (all relative to $PGDATA) */
 #define RECOVERY_COMMAND_FILE	"recovery.conf"
 #define RECOVERY_COMMAND_DONE	"recovery.done"
+#define PROMOTE_SIGNAL_FILE	"promote"
 
 
 /* User-settable parameters */
@@ -565,6 +566,7 @@ typedef struct xl_restore_point
  */
 static volatile sig_atomic_t got_SIGHUP = false;
 static volatile sig_atomic_t shutdown_requested = false;
+static volatile sig_atomic_t promote_triggered = false;
 
 /*
  * Flag set when executing a restore command, to tell SIGTERM signal handler
@@ -9669,6 +9671,14 @@ StartupProcSigUsr1Handler(SIGNAL_ARGS)
 	latch_sigusr1_handler();
 }
 
+/* SIGUSR2: set flag to finish recovery */
+static void
+StartupProcTriggerHandler(SIGNAL_ARGS)
+{
+	promote_triggered = true;
+	WakeupRecovery();
+}
+
 /* SIGHUP: set flag to re-read config file at next convenient time */
 static void
 StartupProcSigHupHandler(SIGNAL_ARGS)
@@ -9746,7 +9756,7 @@ StartupProcessMain(void)
 		pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, StartupProcSigUsr1Handler);
-	pqsignal(SIGUSR2, SIG_IGN);
+	pqsignal(SIGUSR2, StartupProcTriggerHandler);
 
 	/*
 	 * Reset some signals that are accepted by postmaster but not here
@@ -10192,9 +10202,9 @@ emode_for_corrupt_record(int emode, XLogRecPtr RecPtr)
 }
 
 /*
- * Check to see if the trigger file exists. If it does, request postmaster
- * to shut down walreceiver, wait for it to exit, remove the trigger
- * file, and return true.
+ * Check to see whether the user-specified trigger file exists and whether a
+ * promote request has arrived.  If either condition holds, request postmaster
+ * to shut down walreceiver, wait for it to exit, and return true.
  */
 static bool
 CheckForStandbyTrigger(void)
@@ -10205,6 +10215,16 @@ CheckForStandbyTrigger(void)
 	if (triggered)
 		return true;
 
+	if (promote_triggered)
+	{
+		ereport(LOG,
+				(errmsg("received promote request")));
+		ShutdownWalRcv();
+		promote_triggered = false;
+		triggered = true;
+		return true;
+	}
+
 	if (TriggerFile == NULL)
 		return false;
 
@@ -10220,6 +10240,27 @@ CheckForStandbyTrigger(void)
 	return false;
 }
 
+/*
+ * Check to see if a promote request has arrived. Should be
+ * called by postmaster after receiving SIGUSR1.
+ */
+bool
+CheckPromoteSignal(void)
+{
+	struct stat stat_buf;
+
+	if (stat(PROMOTE_SIGNAL_FILE, &stat_buf) == 0)
+	{
+		/*
+		 * Since we are in a signal handler, it's not safe
+		 * to elog. We silently ignore any error from unlink.
+		 */
+		unlink(PROMOTE_SIGNAL_FILE);
+		return true;
+	}
+	return false;
+}
+
 /*
  * Wake up startup process to replay newly arrived WAL, or to notice that
  * failover has been requested.

src/backend/postmaster/postmaster.c

@@ -4284,6 +4284,14 @@ sigusr1_handler(SIGNAL_ARGS)
 		WalReceiverPID = StartWalReceiver();
 	}
 
+	if (CheckPromoteSignal() && StartupPID != 0 &&
+		(pmState == PM_STARTUP || pmState == PM_RECOVERY ||
+		 pmState == PM_HOT_STANDBY || pmState == PM_WAIT_READONLY))
+	{
+		/* Tell startup process to finish recovery */
+		signal_child(StartupPID, SIGUSR2);
+	}
+
 	PG_SETMASK(&UnBlockSig);
 
 	errno = save_errno;

src/bin/pg_ctl/pg_ctl.c

@@ -62,6 +62,7 @@ typedef enum
 	START_COMMAND,
 	STOP_COMMAND,
 	RESTART_COMMAND,
+	PROMOTE_COMMAND,
 	RELOAD_COMMAND,
 	STATUS_COMMAND,
 	KILL_COMMAND,
@@ -96,6 +97,7 @@ static char postopts_file[MAXPGPATH];
 static char pid_file[MAXPGPATH];
 static char backup_file[MAXPGPATH];
 static char recovery_file[MAXPGPATH];
+static char promote_file[MAXPGPATH];
 
 #if defined(WIN32) || defined(__CYGWIN__)
 static DWORD pgctl_start_type = SERVICE_AUTO_START;
@@ -124,6 +126,7 @@ static void do_init(void);
 static void do_start(void);
 static void do_stop(void);
 static void do_restart(void);
+static void do_promote(void);
 static void do_reload(void);
 static void do_status(void);
 static void do_kill(pgpid_t pid);
@@ -872,7 +875,7 @@ do_stop(void)
 
 
 /*
- *	restart/reload routines
+ *	restart/promote/reload routines
  */
 
 static void
@@ -965,6 +968,66 @@ do_restart(void)
 	do_start();
 }
 
+static void
+do_promote(void)
+{
+	FILE	   *prmfile;
+	pgpid_t		pid;
+	struct stat statbuf;
+
+	pid = get_pgpid();
+
+	if (pid == 0)				/* no pid file */
+	{
+		write_stderr(_("%s: PID file \"%s\" does not exist\n"), progname, pid_file);
+		write_stderr(_("Is server running?\n"));
+		exit(1);
+	}
+	else if (pid < 0)			/* standalone backend, not postmaster */
+	{
+		pid = -pid;
+		write_stderr(_("%s: cannot promote server; "
+					   "single-user server is running (PID: %ld)\n"),
+					 progname, pid);
+		exit(1);
+	}
+
+	/* If recovery.conf doesn't exist, the server is not in standby mode */
+	if (stat(recovery_file, &statbuf) != 0)
+	{
+		write_stderr(_("%s: cannot promote server; "
+					   "server is not in standby mode\n"),
+					 progname);
+		exit(1);
+	}
+
+	if ((prmfile = fopen(promote_file, "w")) == NULL)
+	{
+		write_stderr(_("%s: could not create promote signal file \"%s\": %s\n"),
+					 progname, promote_file, strerror(errno));
+		exit(1);
+	}
+	if (fclose(prmfile))
+	{
+		write_stderr(_("%s: could not write promote signal file \"%s\": %s\n"),
+					 progname, promote_file, strerror(errno));
+		exit(1);
+	}
+
+	sig = SIGUSR1;
+	if (kill((pid_t) pid, sig) != 0)
+	{
+		write_stderr(_("%s: could not send promote signal (PID: %ld): %s\n"),
+					 progname, pid, strerror(errno));
+		if (unlink(promote_file) != 0)
+			write_stderr(_("%s: could not remove promote signal file \"%s\": %s\n"),
+						 progname, promote_file, strerror(errno));
+		exit(1);
+	}
+
+	print_msg(_("server promoting\n"));
+}
+
 
 static void
 do_reload(void)
@@ -1617,7 +1680,7 @@ do_advice(void)
 static void
 do_help(void)
 {
-	printf(_("%s is a utility to start, stop, restart, reload configuration files,\n"
+	printf(_("%s is a utility to start, stop, restart, promote, reload configuration files,\n"
 			 "report the status of a PostgreSQL server, or signal a PostgreSQL process.\n\n"), progname);
 	printf(_("Usage:\n"));
 	printf(_("  %s init[db]               [-D DATADIR] [-s] [-o \"OPTIONS\"]\n"), progname);
@@ -1625,6 +1688,7 @@ do_help(void)
 	printf(_("  %s stop    [-W] [-t SECS] [-D DATADIR] [-s] [-m SHUTDOWN-MODE]\n"), progname);
 	printf(_("  %s restart [-w] [-t SECS] [-D DATADIR] [-s] [-m SHUTDOWN-MODE]\n"
 			 "                 [-o \"OPTIONS\"]\n"), progname);
+	printf(_("  %s promote [-D DATADIR] [-s]\n"), progname);
 	printf(_("  %s reload  [-D DATADIR] [-s]\n"), progname);
 	printf(_("  %s status  [-D DATADIR]\n"), progname);
 	printf(_("  %s kill    SIGNALNAME PID\n"), progname);
@@ -1950,6 +2014,8 @@ main(int argc, char **argv)
 				ctl_command = STOP_COMMAND;
 			else if (strcmp(argv[optind], "restart") == 0)
 				ctl_command = RESTART_COMMAND;
+			else if (strcmp(argv[optind], "promote") == 0)
+				ctl_command = PROMOTE_COMMAND;
 			else if (strcmp(argv[optind], "reload") == 0)
 				ctl_command = RELOAD_COMMAND;
 			else if (strcmp(argv[optind], "status") == 0)
@@ -2036,6 +2102,7 @@ main(int argc, char **argv)
 		snprintf(pid_file, MAXPGPATH, "%s/postmaster.pid", pg_data);
 		snprintf(backup_file, MAXPGPATH, "%s/backup_label", pg_data);
 		snprintf(recovery_file, MAXPGPATH, "%s/recovery.conf", pg_data);
+		snprintf(promote_file, MAXPGPATH, "%s/promote", pg_data);
 	}
 
 	switch (ctl_command)
@@ -2055,6 +2122,9 @@ main(int argc, char **argv)
 		case RESTART_COMMAND:
 			do_restart();
 			break;
+		case PROMOTE_COMMAND:
+			do_promote();
+			break;
 		case RELOAD_COMMAND:
 			do_reload();
 			break;

src/include/access/xlog.h

@@ -313,6 +313,7 @@ extern TimeLineID GetRecoveryTargetTLI(void);
 
 extern void HandleStartupProcInterrupts(void);
 extern void StartupProcessMain(void);
+extern bool CheckPromoteSignal(void);
 extern void WakeupRecovery(void);
 
 /*