doc/src/sgml/monitoring.sgml

@@ -2982,33 +2982,6 @@ description | Waiting for a newly initialized WAL file to reach durable storage
       </para></entry>
      </row>
 
-     <row>
-      <entry role="catalog_table_entry"><para role="column_definition">
-       <structfield>restartpoints_timed</structfield> <type>bigint</type>
-      </para>
-      <para>
-       Number of scheduled restartpoints due to timeout or after a failed attempt to perform it
-      </para></entry>
-     </row>
-
-     <row>
-      <entry role="catalog_table_entry"><para role="column_definition">
-       <structfield>restartpoints_req</structfield> <type>bigint</type>
-      </para>
-      <para>
-       Number of requested restartpoints
-      </para></entry>
-     </row>
-
-     <row>
-      <entry role="catalog_table_entry"><para role="column_definition">
-       <structfield>restartpoints_done</structfield> <type>bigint</type>
-      </para>
-      <para>
-       Number of restartpoints that have been performed
-      </para></entry>
-     </row>
-
      <row>
       <entry role="catalog_table_entry"><para role="column_definition">
        <structfield>write_time</structfield> <type>double precision</type>

doc/src/sgml/wal.sgml

@@ -655,41 +655,14 @@
    directory.
    Restartpoints can't be performed more frequently than checkpoints on the
    primary because restartpoints can only be performed at checkpoint records.
-   A restartpoint can be demanded by a schedule or by an external request.
+   A restartpoint is triggered when a checkpoint record is reached if at
-   The <structfield>restartpoints_timed</structfield> counter in the
+   least <varname>checkpoint_timeout</varname> seconds have passed since the last
-   <link linkend="monitoring-pg-stat-checkpointer-view"><structname>pg_stat_checkpointer</structname></link>
+   restartpoint, or if WAL size is about to exceed
-   view counts the first ones while the <structfield>restartpoints_req</structfield>
+   <varname>max_wal_size</varname>. However, because of limitations on when a
-   the second.
+   restartpoint can be performed, <varname>max_wal_size</varname> is often exceeded
-   A restartpoint is triggered by schedule when a checkpoint record is reached
+   during recovery, by up to one checkpoint cycle's worth of WAL.
-   if at least <xref linkend="guc-checkpoint-timeout"/> seconds have passed since
-   the last performed restartpoint or when the previous attempt to perform
-   the restartpoint has failed. In the last case, the next restartpoint
-   will be scheduled in 15 seconds.
-   A restartpoint is triggered by request due to similar reasons like checkpoint
-   but mostly if WAL size is about to exceed <xref linkend="guc-max-wal-size"/>
-   However, because of limitations on when a restartpoint can be performed,
-   <varname>max_wal_size</varname> is often exceeded during recovery,
-   by up to one checkpoint cycle's worth of WAL.
    (<varname>max_wal_size</varname> is never a hard limit anyway, so you should
    always leave plenty of headroom to avoid running out of disk space.)
-   The <structfield>restartpoints_done</structfield> counter in the
-   <link linkend="monitoring-pg-stat-checkpointer-view"><structname>pg_stat_checkpointer</structname></link>
-   view counts the restartpoints that have really been performed.
-  </para>
-
-  <para>
-   In some cases, when the WAL size on the primary increases quickly,
-   for instance during massive INSERT,
-   the <structfield>restartpoints_req</structfield> counter on the standby
-   may demonstrate a peak growth.
-   This occurs because requests to create a new restartpoint due to increased
-   XLOG consumption cannot be performed because the safe checkpoint record
-   since the last restartpoint has not yet been replayed on the standby.
-   This behavior is normal and does not lead to an increase in system resource
-   consumption.
-   Only the <structfield>restartpoints_done</structfield>
-   counter among the restartpoint-related ones indicates that noticeable system
-   resources have been spent.
   </para>
 
   <para>

src/backend/catalog/system_views.sql

@@ -1141,9 +1141,6 @@ 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,

src/backend/optimizer/plan/analyzejoins.c

@@ -453,7 +453,7 @@ remove_rel_from_query(PlannerInfo *root, RelOptInfo *rel,
 	{
 		PlaceHolderInfo *phinfo = (PlaceHolderInfo *) lfirst(l);
 
-		Assert(sjinfo == NULL || !bms_is_member(relid, phinfo->ph_lateral));
+		Assert(!bms_is_member(relid, phinfo->ph_lateral));
 		if (bms_is_subset(phinfo->ph_needed, joinrelids) &&
 			bms_is_member(relid, phinfo->ph_eval_at) &&
 			!bms_is_member(ojrelid, phinfo->ph_eval_at))
@@ -472,8 +472,6 @@ remove_rel_from_query(PlannerInfo *root, RelOptInfo *rel,
 			phinfo->ph_needed = replace_relid(phinfo->ph_needed, relid, subst);
 			phinfo->ph_needed = replace_relid(phinfo->ph_needed, ojrelid, subst);
 			/* ph_needed might or might not become empty */
-			phinfo->ph_lateral = replace_relid(phinfo->ph_lateral, relid, subst);
-			/* ph_lateral might or might not be empty */
 			phv->phrels = replace_relid(phv->phrels, relid, subst);
 			phv->phrels = replace_relid(phv->phrels, ojrelid, subst);
 			Assert(!bms_is_empty(phv->phrels));
@@ -1458,16 +1456,7 @@ replace_varno_walker(Node *node, ReplaceVarnoContext *ctx)
 		}
 		return false;
 	}
-	else if (IsA(node, PlaceHolderVar))
+	if (IsA(node, RestrictInfo))
-	{
-		PlaceHolderVar *phv = (PlaceHolderVar *) node;
-
-		phv->phrels = replace_relid(phv->phrels, ctx->from, ctx->to);
-		phv->phnullingrels = replace_relid(phv->phnullingrels, ctx->from, ctx->to);
-
-		/* fall through to recurse into the placeholder's expression */
-	}
-	else if (IsA(node, RestrictInfo))
 	{
 		RestrictInfo *rinfo = (RestrictInfo *) node;
 		int			relid = -1;
@@ -1652,6 +1641,26 @@ update_eclasses(EquivalenceClass *ec, int from, int to)
 	ec->ec_relids = replace_relid(ec->ec_relids, from, to);
 }
 
+static bool
+sje_walker(Node *node, ReplaceVarnoContext *ctx)
+{
+	if (node == NULL)
+		return false;
+
+	if (IsA(node, Var))
+	{
+		Var		   *var = (Var *) node;
+
+		if (var->varno == ctx->from)
+		{
+			var->varno = ctx->to;
+			var->varnosyn = ctx->to;
+		}
+		return false;
+	}
+	return expression_tree_walker(node, sje_walker, (void *) ctx);
+}
+
 /*
  * Remove a relation after we have proven that it participates only in an
  * unneeded unique self join.
@@ -1859,8 +1868,7 @@ remove_self_join_rel(PlannerInfo *root, PlanRowMark *kmark, PlanRowMark *rmark,
 	}
 
 	/* Replace varno in all the query structures */
-	query_tree_walker(root->parse, replace_varno_walker, &ctx,
+	query_tree_walker(root->parse, sje_walker, &ctx, QTW_EXAMINE_SORTGROUP);
-					  QTW_EXAMINE_SORTGROUP);
 
 	/* Replace links in the planner info */
 	remove_rel_from_query(root, toRemove, toKeep->relid, NULL, NULL);
@@ -2117,8 +2125,20 @@ remove_self_joins_one_group(PlannerInfo *root, Relids relids)
 			joinrelids = bms_add_member(joinrelids, k);
 
 			/*
-			 * PHVs should not impose any constraints on removing self joins.
+			 * Be safe to do not remove tables participated in complicated PH
 			 */
+			foreach(lc, root->placeholder_list)
+			{
+				PlaceHolderInfo *phinfo = (PlaceHolderInfo *) lfirst(lc);
+
+				/* there isn't any other place to eval PHV */
+				if (bms_is_subset(phinfo->ph_eval_at, joinrelids) ||
+					bms_is_subset(phinfo->ph_needed, joinrelids) ||
+					bms_is_member(r, phinfo->ph_lateral))
+					break;
+			}
+			if (lc)
+				continue;
 
 			/*
 			 * At this stage, joininfo lists of inner and outer can contain
@@ -2186,7 +2206,7 @@ remove_self_joins_one_group(PlannerInfo *root, Relids relids)
 
 /*
  * Gather indexes of base relations from the joinlist and try to eliminate self
- * joins.
+ * joins. To avoid complexity, limit the max power of this set by a GUC.
  */
 static Relids
 remove_self_joins_recurse(PlannerInfo *root, List *joinlist, Relids toRemove)

src/backend/postmaster/checkpointer.c

@@ -340,8 +340,6 @@ 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);
@@ -360,7 +358,7 @@ CheckpointerMain(void)
 		if (((volatile CheckpointerShmemStruct *) CheckpointerShmem)->ckpt_flags)
 		{
 			do_checkpoint = true;
-			chkpt_or_rstpt_requested = true;
+			PendingCheckpointerStats.num_requested++;
 		}
 
 		/*
@@ -374,7 +372,7 @@ CheckpointerMain(void)
 		if (elapsed_secs >= CheckPointTimeout)
 		{
 			if (!do_checkpoint)
-				chkpt_or_rstpt_timed = true;
+				PendingCheckpointerStats.num_timed++;
 			do_checkpoint = true;
 			flags |= CHECKPOINT_CAUSE_TIME;
 		}
@@ -410,24 +408,6 @@ 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
@@ -491,9 +471,6 @@ CheckpointerMain(void)
 				 * checkpoints happen at a predictable spacing.
 				 */
 				last_checkpoint_time = now;
-
-				if (do_restartpoint)
-					PendingCheckpointerStats.restartpoints_performed++;
 			}
 			else
 			{

src/backend/utils/activity/pgstat_checkpointer.c

@@ -49,9 +49,6 @@ 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);
@@ -119,9 +116,6 @@ 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);

src/backend/utils/adt/pgstatfuncs.c

@@ -1193,24 +1193,6 @@ 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)
 {

src/common/blkreftable.c

@@ -265,7 +265,7 @@ BlockRefTableSetLimitBlock(BlockRefTable *brtab,
 						   BlockNumber limit_block)
 {
 	BlockRefTableEntry *brtentry;
-	BlockRefTableKey key = {{0}};	/* make sure any padding is zero */
+	BlockRefTableKey key = {0}; /* make sure any padding is zero */
 	bool		found;
 
 	memcpy(&key.rlocator, rlocator, sizeof(RelFileLocator));
@@ -300,7 +300,7 @@ BlockRefTableMarkBlockModified(BlockRefTable *brtab,
 							   BlockNumber blknum)
 {
 	BlockRefTableEntry *brtentry;
-	BlockRefTableKey key = {{0}};	/* make sure any padding is zero */
+	BlockRefTableKey key = {0}; /* make sure any padding is zero */
 	bool		found;
 #ifndef FRONTEND
 	MemoryContext oldcontext = MemoryContextSwitchTo(brtab->mcxt);
@@ -340,7 +340,7 @@ BlockRefTableEntry *
 BlockRefTableGetEntry(BlockRefTable *brtab, const RelFileLocator *rlocator,
 					  ForkNumber forknum, BlockNumber *limit_block)
 {
-	BlockRefTableKey key = {{0}};	/* make sure any padding is zero */
+	BlockRefTableKey key = {0}; /* make sure any padding is zero */
 	BlockRefTableEntry *entry;
 
 	Assert(limit_block != NULL);
@@ -517,7 +517,7 @@ WriteBlockRefTable(BlockRefTable *brtab,
 		for (i = 0; i < brtab->hash->members; ++i)
 		{
 			BlockRefTableSerializedEntry *sentry = &sdata[i];
-			BlockRefTableKey key = {{0}};	/* make sure any padding is zero */
+			BlockRefTableKey key = {0}; /* make sure any padding is zero */
 			unsigned	j;
 
 			/* Write the serialized entry itself. */

src/include/catalog/catversion.h

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

src/include/catalog/pg_proc.dat

@@ -5721,21 +5721,6 @@
   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',

src/include/pgstat.h

@@ -262,9 +262,6 @@ 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;

src/test/regress/expected/join.out

@@ -6821,37 +6821,20 @@ on true;
                            Filter: (id IS NOT NULL)
 (8 rows)
 
--- Check that PHVs do not impose any constraints on removing self joins
+-- Check that SJE does not remove self joins if a PHV references the removed
-explain (verbose, costs off)
+-- rel laterally.
+explain (costs off)
 select * from emp1 t1 join emp1 t2 on t1.id = t2.id left join
     lateral (select t1.id as t1id, * from generate_series(1,1) t3) s on true;
-                        QUERY PLAN                        
+                    QUERY PLAN                     
-----------------------------------------------------------
+---------------------------------------------------
  Nested Loop Left Join
-   Output: t2.id, t2.code, t2.id, t2.code, (t2.id), t3.t3
+   ->  Nested Loop
-   ->  Seq Scan on public.emp1 t2
+         ->  Seq Scan on emp1 t1
-         Output: t2.id, t2.code
+         ->  Index Scan using emp1_pkey on emp1 t2
-         Filter: (t2.id IS NOT NULL)
+               Index Cond: (id = t1.id)
-   ->  Function Scan on pg_catalog.generate_series t3
+   ->  Function Scan on generate_series t3
-         Output: t3.t3, t2.id
+(6 rows)
-         Function Call: generate_series(1, 1)
-(8 rows)
-
-explain (verbose, costs off)
-select * from generate_series(1,10) t1(id) left join
-    lateral (select t1.id as t1id, t2.id from emp1 t2 join emp1 t3 on t2.id = t3.id)
-on true;
-                      QUERY PLAN                      
-------------------------------------------------------
- Nested Loop Left Join
-   Output: t1.id, (t1.id), t3.id
-   ->  Function Scan on pg_catalog.generate_series t1
-         Output: t1.id
-         Function Call: generate_series(1, 10)
-   ->  Seq Scan on public.emp1 t3
-         Output: t3.id, t1.id
-         Filter: (t3.id IS NOT NULL)
-(8 rows)
 
 -- We can remove the join even if we find the join can't duplicate rows and
 -- the base quals of each side are different.  In the following case we end up

src/test/regress/expected/rules.out

@@ -1822,9 +1822,6 @@ 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,

src/test/regress/sql/join.sql

@@ -2600,16 +2600,12 @@ select * from emp1 t1 left join
         on true)
 on true;
 
--- Check that PHVs do not impose any constraints on removing self joins
+-- Check that SJE does not remove self joins if a PHV references the removed
-explain (verbose, costs off)
+-- rel laterally.
+explain (costs off)
 select * from emp1 t1 join emp1 t2 on t1.id = t2.id left join
     lateral (select t1.id as t1id, * from generate_series(1,1) t3) s on true;
 
-explain (verbose, costs off)
-select * from generate_series(1,10) t1(id) left join
-    lateral (select t1.id as t1id, t2.id from emp1 t2 join emp1 t3 on t2.id = t3.id)
-on true;
-
 -- We can remove the join even if we find the join can't duplicate rows and
 -- the base quals of each side are different.  In the following case we end up
 -- moving quals over to s1 to make it so it can't match any rows.