Add some checkpoint and redo LSNs to a couple of recovery errors

michaelpq · michaelpq · commit f500ba07fa9d · 2024-03-11T09:08:05.000+09:00
Two FATALs and one PANIC gain details about the LSNs they fail at: - When restoring from a backup_label, the FATAL log generated when not finding the checkpoint record now reports its LSN. - When restoring from a backup_label, the FATAL log generated when not finding the redo record referenced by a checkpoint record now shows both the redo and checkpoint record LSNs. - When not restoring from a backup_label, the PANIC error generated when not finding the checkpoint record now reports its LSN. This information is useful when debugging corruption issues, and these LSNs may not show up in the logs depending on the level of logging configured in the backend. Author: David Steele Discussion: https://postgr.es/m/0e90da89-77ca-4ccf-872c-9626d755e288@pgmasters.net
diff --git a/src/backend/access/transam/xlogrecovery.c b/src/backend/access/transam/xlogrecovery.c
@@ -646,7 +646,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr,
 				if (!ReadRecord(xlogprefetcher, LOG, false,
 								checkPoint.ThisTimeLineID))
 					ereport(FATAL,
-							(errmsg("could not find redo location referenced by checkpoint record"),
+							(errmsg("could not find redo location %X/%X referenced by checkpoint record at %X/%X",
+									LSN_FORMAT_ARGS(checkPoint.redo), LSN_FORMAT_ARGS(CheckPointLoc)),
 							 errhint("If you are restoring from a backup, touch \"%s/recovery.signal\" or \"%s/standby.signal\" and add required recovery options.\n"
 									 "If you are not restoring from a backup, try removing the file \"%s/backup_label\".\n"
 									 "Be careful: removing \"%s/backup_label\" will result in a corrupt cluster if restoring from a backup.",
@@ -656,7 +657,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr,
 		else
 		{
 			ereport(FATAL,
-					(errmsg("could not locate required checkpoint record"),
+					(errmsg("could not locate required checkpoint record at %X/%X",
+							LSN_FORMAT_ARGS(CheckPointLoc)),
 					 errhint("If you are restoring from a backup, touch \"%s/recovery.signal\" or \"%s/standby.signal\" and add required recovery options.\n"
 							 "If you are not restoring from a backup, try removing the file \"%s/backup_label\".\n"
 							 "Be careful: removing \"%s/backup_label\" will result in a corrupt cluster if restoring from a backup.",
@@ -790,7 +792,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr,
 			 * simplify processing around checkpoints.
 			 */
 			ereport(PANIC,
-					(errmsg("could not locate a valid checkpoint record")));
+					(errmsg("could not locate a valid checkpoint record at %X/%X",
+							LSN_FORMAT_ARGS(CheckPointLoc))));
 		}
 		memcpy(&checkPoint, XLogRecGetData(xlogreader), sizeof(CheckPoint));
 		wasShutdown = ((record->xl_info & ~XLR_INFO_MASK) == XLOG_CHECKPOINT_SHUTDOWN);
