Enhance checkpointer restartpoint statistics

Bhis commit introduces enhancements to the pg_stat_checkpointer view by adding
three new columns: restartpoints_timed, restartpoints_req, and
restartpoints_done. These additions aim to improve the visibility and
monitoring of restartpoint processes on replicas.

Previously, it was challenging to differentiate between successful and failed
restartpoint requests. This limitation arises because restartpoints on replicas
are dependent on checkpoint records from the primary, and cannot occur more
frequently than these checkpoints.

The new columns allow for clear distinction and tracking of restartpoint
requests, their triggers, and successful completions.  This enhancement aids
database administrators and developers in better understanding and diagnosing
issues related to restartpoint behavior, particularly in scenarios where
restartpoint requests may fail.

System catalog is changed.  Catversion is bumped.

Discussion: https://postgr.es/m/99b2ccd1-a77a-962a-0837-191cdf56c2b9%40inbox.ru
Author: Anton A. Melnikov
Reviewed-by: Kyotaro Horiguchi, Alexander Korotkov

1 files changed, 25 insertions, 2 deletions

diff --git a/src/backend/postmaster/checkpointer.c b/src/backend/postmaster/checkpointer.c
index dc2da5a2cd8..67ecb177e7e 100644
--- a/src/backend/postmaster/checkpointer.c
+++ b/src/backend/postmaster/checkpointer.c
@@ -340,6 +340,8 @@ CheckpointerMain(void)
 		pg_time_t	now;
 		int			elapsed_secs;
 		int			cur_timeout;
+		bool		chkpt_or_rstpt_requested = false;
+		bool		chkpt_or_rstpt_timed = false;
 
 		/* Clear any already-pending wakeups */
 		ResetLatch(MyLatch);
@@ -358,7 +360,7 @@ CheckpointerMain(void)
 		if (((volatile CheckpointerShmemStruct *) CheckpointerShmem)->ckpt_flags)
 		{
 			do_checkpoint = true;
-			PendingCheckpointerStats.num_requested++;
+			chkpt_or_rstpt_requested = true;
 		}
 
 		/*
@@ -372,7 +374,7 @@ CheckpointerMain(void)
 		if (elapsed_secs >= CheckPointTimeout)
 		{
 			if (!do_checkpoint)
-				PendingCheckpointerStats.num_timed++;
+				chkpt_or_rstpt_timed = true;
 			do_checkpoint = true;
 			flags |= CHECKPOINT_CAUSE_TIME;
 		}
@@ -408,6 +410,24 @@ CheckpointerMain(void)
 			if (flags & CHECKPOINT_END_OF_RECOVERY)
 				do_restartpoint = false;
 
+			if (chkpt_or_rstpt_timed)
+			{
+				chkpt_or_rstpt_timed = false;
+				if (do_restartpoint)
+					PendingCheckpointerStats.restartpoints_timed++;
+				else
+					PendingCheckpointerStats.num_timed++;
+			}
+
+			if (chkpt_or_rstpt_requested)
+			{
+				chkpt_or_rstpt_requested = false;
+				if (do_restartpoint)
+					PendingCheckpointerStats.restartpoints_requested++;
+				else
+					PendingCheckpointerStats.num_requested++;
+			}
+
 			/*
 			 * We will warn if (a) too soon since last checkpoint (whatever
 			 * caused it) and (b) somebody set the CHECKPOINT_CAUSE_XLOG flag
@@ -471,6 +491,9 @@ CheckpointerMain(void)
 				 * checkpoints happen at a predictable spacing.
 				 */
 				last_checkpoint_time = now;
+
+				if (do_restartpoint)
+					PendingCheckpointerStats.restartpoints_performed++;
 			}
 			else
 			{