1
0
mirror of https://github.com/postgres/postgres.git synced 2025-12-22 17:42:17 +03:00

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
This commit is contained in:
Alexander Korotkov
2023-12-25 00:52:42 +02:00
parent 64e77b496a
commit 12915a58ee
10 changed files with 134 additions and 9 deletions

View File

@@ -1141,6 +1141,9 @@ CREATE VIEW pg_stat_checkpointer AS
SELECT
pg_stat_get_checkpointer_num_timed() AS num_timed,
pg_stat_get_checkpointer_num_requested() AS num_requested,
pg_stat_get_checkpointer_restartpoints_timed() AS restartpoints_timed,
pg_stat_get_checkpointer_restartpoints_requested() AS restartpoints_req,
pg_stat_get_checkpointer_restartpoints_performed() AS restartpoints_done,
pg_stat_get_checkpointer_write_time() AS write_time,
pg_stat_get_checkpointer_sync_time() AS sync_time,
pg_stat_get_checkpointer_buffers_written() AS buffers_written,

View File

@@ -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
{

View File

@@ -49,6 +49,9 @@ pgstat_report_checkpointer(void)
#define CHECKPOINTER_ACC(fld) stats_shmem->stats.fld += PendingCheckpointerStats.fld
CHECKPOINTER_ACC(num_timed);
CHECKPOINTER_ACC(num_requested);
CHECKPOINTER_ACC(restartpoints_timed);
CHECKPOINTER_ACC(restartpoints_requested);
CHECKPOINTER_ACC(restartpoints_performed);
CHECKPOINTER_ACC(write_time);
CHECKPOINTER_ACC(sync_time);
CHECKPOINTER_ACC(buffers_written);
@@ -116,6 +119,9 @@ pgstat_checkpointer_snapshot_cb(void)
#define CHECKPOINTER_COMP(fld) pgStatLocal.snapshot.checkpointer.fld -= reset.fld;
CHECKPOINTER_COMP(num_timed);
CHECKPOINTER_COMP(num_requested);
CHECKPOINTER_COMP(restartpoints_timed);
CHECKPOINTER_COMP(restartpoints_requested);
CHECKPOINTER_COMP(restartpoints_performed);
CHECKPOINTER_COMP(write_time);
CHECKPOINTER_COMP(sync_time);
CHECKPOINTER_COMP(buffers_written);

View File

@@ -1193,6 +1193,24 @@ pg_stat_get_checkpointer_num_requested(PG_FUNCTION_ARGS)
PG_RETURN_INT64(pgstat_fetch_stat_checkpointer()->num_requested);
}
Datum
pg_stat_get_checkpointer_restartpoints_timed(PG_FUNCTION_ARGS)
{
PG_RETURN_INT64(pgstat_fetch_stat_checkpointer()->restartpoints_timed);
}
Datum
pg_stat_get_checkpointer_restartpoints_requested(PG_FUNCTION_ARGS)
{
PG_RETURN_INT64(pgstat_fetch_stat_checkpointer()->restartpoints_requested);
}
Datum
pg_stat_get_checkpointer_restartpoints_performed(PG_FUNCTION_ARGS)
{
PG_RETURN_INT64(pgstat_fetch_stat_checkpointer()->restartpoints_performed);
}
Datum
pg_stat_get_checkpointer_buffers_written(PG_FUNCTION_ARGS)
{

View File

@@ -57,6 +57,6 @@
*/
/* yyyymmddN */
#define CATALOG_VERSION_NO 202312211
#define CATALOG_VERSION_NO 202312251
#endif

View File

@@ -5721,6 +5721,21 @@
proname => 'pg_stat_get_checkpointer_num_requested', provolatile => 's',
proparallel => 'r', prorettype => 'int8', proargtypes => '',
prosrc => 'pg_stat_get_checkpointer_num_requested' },
{ oid => '8743',
descr => 'statistics: number of timed restartpoints started by the checkpointer',
proname => 'pg_stat_get_checkpointer_restartpoints_timed', provolatile => 's',
proparallel => 'r', prorettype => 'int8', proargtypes => '',
prosrc => 'pg_stat_get_checkpointer_restartpoints_timed' },
{ oid => '8744',
descr => 'statistics: number of backend requested restartpoints started by the checkpointer',
proname => 'pg_stat_get_checkpointer_restartpoints_requested', provolatile => 's',
proparallel => 'r', prorettype => 'int8', proargtypes => '',
prosrc => 'pg_stat_get_checkpointer_restartpoints_requested' },
{ oid => '8745',
descr => 'statistics: number of backend performed restartpoints',
proname => 'pg_stat_get_checkpointer_restartpoints_performed', provolatile => 's',
proparallel => 'r', prorettype => 'int8', proargtypes => '',
prosrc => 'pg_stat_get_checkpointer_restartpoints_performed' },
{ oid => '2771',
descr => 'statistics: number of buffers written by the checkpointer',
proname => 'pg_stat_get_checkpointer_buffers_written', provolatile => 's',

View File

@@ -262,6 +262,9 @@ typedef struct PgStat_CheckpointerStats
{
PgStat_Counter num_timed;
PgStat_Counter num_requested;
PgStat_Counter restartpoints_timed;
PgStat_Counter restartpoints_requested;
PgStat_Counter restartpoints_performed;
PgStat_Counter write_time; /* times in milliseconds */
PgStat_Counter sync_time;
PgStat_Counter buffers_written;

View File

@@ -1822,6 +1822,9 @@ pg_stat_bgwriter| SELECT pg_stat_get_bgwriter_buf_written_clean() AS buffers_cle
pg_stat_get_bgwriter_stat_reset_time() AS stats_reset;
pg_stat_checkpointer| SELECT pg_stat_get_checkpointer_num_timed() AS num_timed,
pg_stat_get_checkpointer_num_requested() AS num_requested,
pg_stat_get_checkpointer_restartpoints_timed() AS restartpoints_timed,
pg_stat_get_checkpointer_restartpoints_requested() AS restartpoints_req,
pg_stat_get_checkpointer_restartpoints_performed() AS restartpoints_done,
pg_stat_get_checkpointer_write_time() AS write_time,
pg_stat_get_checkpointer_sync_time() AS sync_time,
pg_stat_get_checkpointer_buffers_written() AS buffers_written,