Make pg_receivexlog and pg_basebackup -X stream work across timeline switches.

This mirrors the changes done earlier to the server in standby mode. When
receivelog reaches the end of a timeline, as reported by the server, it
fetches the timeline history file of the next timeline, and restarts
streaming from the new timeline by issuing a new START_STREAMING command.

When pg_receivexlog crosses a timeline, it leaves the .partial suffix on the
last segment on the old timeline. This helps you to tell apart a partial
segment left in the directory because of a timeline switch, and a completed
segment. If you just follow a single server, it won't make a difference, but
it can be significant in more complicated scenarios where new WAL is still
generated on the old timeline.

This includes two small changes to the streaming replication protocol:
First, when you reach the end of timeline while streaming, the server now
sends the TLI of the next timeline in the server's history to the client.
pg_receivexlog uses that as the next timeline, so that it doesn't need to
parse the timeline history file like a standby server does. Second, when
BASE_BACKUP command sends the begin and end WAL positions, it now also sends
the timeline IDs corresponding the positions.

1 files changed, 21 insertions, 3 deletions

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index ac2b26b4982..90ba32ef0f5 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -4930,7 +4930,7 @@ StartupXLOG(void)
 		 * tliSwitchPoint will throw an error if the checkpoint's timeline
 		 * is not in expectedTLEs at all.
 		 */
-		switchpoint = tliSwitchPoint(ControlFile->checkPointCopy.ThisTimeLineID, expectedTLEs);
+		switchpoint = tliSwitchPoint(ControlFile->checkPointCopy.ThisTimeLineID, expectedTLEs, NULL);
 		ereport(FATAL,
 				(errmsg("requested timeline %u is not a child of this server's history",
 						recoveryTargetTLI),
@@ -7870,16 +7870,21 @@ XLogFileNameP(TimeLineID tli, XLogSegNo segno)
  * non-exclusive backups active at the same time, and they don't conflict
  * with an exclusive backup either.
  *
+ * Returns the minimum WAL position that must be present to restore from this
+ * backup, and the corresponding timeline ID in *starttli_p.
+ *
  * Every successfully started non-exclusive backup must be stopped by calling
  * do_pg_stop_backup() or do_pg_abort_backup().
  */
 XLogRecPtr
-do_pg_start_backup(const char *backupidstr, bool fast, char **labelfile)
+do_pg_start_backup(const char *backupidstr, bool fast, TimeLineID *starttli_p,
+				   char **labelfile)
 {
 	bool		exclusive = (labelfile == NULL);
 	bool		backup_started_in_recovery = false;
 	XLogRecPtr	checkpointloc;
 	XLogRecPtr	startpoint;
+	TimeLineID	starttli;
 	pg_time_t	stamp_time;
 	char		strfbuf[128];
 	char		xlogfilename[MAXFNAMELEN];
@@ -8021,6 +8026,7 @@ do_pg_start_backup(const char *backupidstr, bool fast, char **labelfile)
 			LWLockAcquire(ControlFileLock, LW_SHARED);
 			checkpointloc = ControlFile->checkPoint;
 			startpoint = ControlFile->checkPointCopy.redo;
+			starttli = ControlFile->checkPointCopy.ThisTimeLineID;
 			checkpointfpw = ControlFile->checkPointCopy.fullPageWrites;
 			LWLockRelease(ControlFileLock);
 
@@ -8154,6 +8160,8 @@ do_pg_start_backup(const char *backupidstr, bool fast, char **labelfile)
 	/*
 	 * We're done.  As a convenience, return the starting WAL location.
 	 */
+	if (starttli_p)
+		*starttli_p = starttli;
 	return startpoint;
 }
 
@@ -8190,14 +8198,18 @@ pg_start_backup_callback(int code, Datum arg)
 
  * If labelfile is NULL, this stops an exclusive backup. Otherwise this stops
  * the non-exclusive backup specified by 'labelfile'.
+ *
+ * Returns the last WAL position that must be present to restore from this
+ * backup, and the corresponding timeline ID in *stoptli_p.
  */
 XLogRecPtr
-do_pg_stop_backup(char *labelfile, bool waitforarchive)
+do_pg_stop_backup(char *labelfile, bool waitforarchive, TimeLineID *stoptli_p)
 {
 	bool		exclusive = (labelfile == NULL);
 	bool		backup_started_in_recovery = false;
 	XLogRecPtr	startpoint;
 	XLogRecPtr	stoppoint;
+	TimeLineID	stoptli;
 	XLogRecData rdata;
 	pg_time_t	stamp_time;
 	char		strfbuf[128];
@@ -8401,8 +8413,11 @@ do_pg_stop_backup(char *labelfile, bool waitforarchive)
 
 		LWLockAcquire(ControlFileLock, LW_SHARED);
 		stoppoint = ControlFile->minRecoveryPoint;
+		stoptli = ControlFile->minRecoveryPointTLI;
 		LWLockRelease(ControlFileLock);
 
+		if (stoptli_p)
+			*stoptli_p = stoptli;
 		return stoppoint;
 	}
 
@@ -8414,6 +8429,7 @@ do_pg_stop_backup(char *labelfile, bool waitforarchive)
 	rdata.buffer = InvalidBuffer;
 	rdata.next = NULL;
 	stoppoint = XLogInsert(RM_XLOG_ID, XLOG_BACKUP_END, &rdata);
+	stoptli = ThisTimeLineID;
 
 	/*
 	 * Force a switch to a new xlog segment file, so that the backup is valid
@@ -8529,6 +8545,8 @@ do_pg_stop_backup(char *labelfile, bool waitforarchive)
 	/*
 	 * We're done.  As a convenience, return the ending WAL location.
 	 */
+	if (stoptli_p)
+		*stoptli_p = stoptli;
 	return stoppoint;
 }