From: Robert Haas <rhaas@postgresql.org>
Date: Thu, 11 Dec 2025 19:40:52 +0000 (-0500)
Subject: add sj_unique_rels list to plan walker
X-Git-Url: http://git.postgresql.org/gitweb/static/gitweb.js?a=commitdiff_plain;h=ab698ad4b5afeb7fbb1c54efeba1ef391f2bbd52;p=users%2Frhaas%2Fpostgres.git

add sj_unique_rels list to plan walker
---

diff --git a/contrib/pg_plan_advice/pgpa_planner.c b/contrib/pg_plan_advice/pgpa_planner.c
index c75bb779cb..8e87c4cb75 100644
--- a/contrib/pg_plan_advice/pgpa_planner.c
+++ b/contrib/pg_plan_advice/pgpa_planner.c
@@ -82,6 +82,7 @@ typedef struct pgpa_planner_state
 	bool		generate_advice_string;
 	pgpa_trove *trove;
 	MemoryContext trove_cxt;
+	List	   *sj_unique_rels;
 
 #ifdef USE_ASSERT_CHECKING
 	pgpa_ri_check_hash *ri_check_hash;
@@ -425,6 +426,49 @@ pgpa_join_path_setup(PlannerInfo *root, RelOptInfo *joinrel,
 
 	Assert(bms_membership(joinrel->relids) == BMS_MULTIPLE);
 
+	/*
+	 * If we're considering implementing a semijoin by making one side unique,
+	 * make a note of it in the pgpa_planner_state. See comments for
+	 * pgpa_sj_unique_rel for why we do this.
+	 */
+	if (jointype == JOIN_UNIQUE_OUTER || jointype == JOIN_UNIQUE_INNER)
+	{
+		pgpa_planner_state *pps;
+		RelOptInfo *uniquerel;
+
+		uniquerel = jointype == JOIN_UNIQUE_OUTER ? outerrel : innerrel;
+		pps = GetPlannerGlobalExtensionState(root->glob, planner_extension_id);
+		if (pps->generate_advice_string)
+		{
+			bool	found = false;
+
+			/* Avoid adding duplicates. */
+			foreach_ptr(pgpa_sj_unique_rel, ur, pps->sj_unique_rels)
+			{
+				/*
+				 * We should always use the same pointer for the same plan
+				 * name, so we need not use strcmp() here.
+				 */
+				if (root->plan_name == ur->plan_name &&
+					bms_equal(uniquerel->relids, ur->relids))
+				{
+					found = true;
+					break;
+				}
+			}
+
+			/* If not a duplicate, append to the list. */
+			if (!found)
+			{
+				pgpa_sj_unique_rel *ur = palloc_object(pgpa_sj_unique_rel);
+
+				ur->plan_name = root->plan_name;
+				ur->relids = uniquerel->relids;
+				pps->sj_unique_rels = lappend(pps->sj_unique_rels, ur);
+			}
+		}
+	}
+
 	/* Get our private state information for this join. */
 	pjs = pgpa_get_join_state(root, joinrel, outerrel, innerrel);
 
@@ -558,7 +602,7 @@ pgpa_planner_shutdown(PlannerGlobal *glob, Query *parse,
 	do_advice_feedback = (trove != NULL && es != NULL);
 	if (generate_advice_string || do_advice_feedback)
 	{
-		pgpa_plan_walker(&walker, pstmt);
+		pgpa_plan_walker(&walker, pstmt, pps->sj_unique_rels);
 		rt_identifiers = pgpa_create_identifiers_for_planned_stmt(pstmt);
 	}
 
diff --git a/contrib/pg_plan_advice/pgpa_walker.c b/contrib/pg_plan_advice/pgpa_walker.c
index db8cc4352c..d5493bc0b8 100644
--- a/contrib/pg_plan_advice/pgpa_walker.c
+++ b/contrib/pg_plan_advice/pgpa_walker.c
@@ -63,9 +63,13 @@ static Index pgpa_walker_get_rti(Index rtable_length,
  * Top-level entrypoint for the plan tree walk.
  *
  * Populates walker based on a traversal of the Plan trees in pstmt.
+ *
+ * sj_unique_rels is a list of pgpa_sj_unique_rel objects, one for each
+ * relation we considered making unique as part of semijoin planning.
  */
 void
-pgpa_plan_walker(pgpa_plan_walker_context *walker, PlannedStmt *pstmt)
+pgpa_plan_walker(pgpa_plan_walker_context *walker, PlannedStmt *pstmt,
+				 List *sj_unique_rels)
 {
 	ListCell   *lc;
 
diff --git a/contrib/pg_plan_advice/pgpa_walker.h b/contrib/pg_plan_advice/pgpa_walker.h
index f244f4428a..b91a36ca3d 100644
--- a/contrib/pg_plan_advice/pgpa_walker.h
+++ b/contrib/pg_plan_advice/pgpa_walker.h
@@ -16,6 +16,24 @@
 #include "pgpa_join.h"
 #include "pgpa_scan.h"
 
+/*
+ * When generating advice, we should emit either SEMIJOIN_UNIQUE advice or
+ * SEMIJOIN_NON_UNIQUE advice for each semijoin depending on whether we chose
+ * to implement it as a semijoin or whether we instead chose to make the
+ * nullable side unique and then perform an inner join. When the make-unique
+ * strategy is not chosen, it's not easy to tell from the final plan tree
+ * whether it was considered. That's awkward, because we don't want to emit
+ * useless SEMIJOIN_NON_UNIQUE advice when there was no decision to be made.
+ *
+ * To avoid that, during planning, we create a pgpa_sj_unique_rel for each
+ * relation that we considered making unique for purposes of semijoin planning.
+ */
+typedef struct pgpa_sj_unique_rel
+{
+	char	   *plan_name;
+	Bitmapset  *relids;
+} pgpa_sj_unique_rel;
+
 /*
  * We use the term "query feature" to refer to plan nodes that are interesting
  * in the following way: to generate advice, we'll need to know the set of
@@ -103,7 +121,8 @@ typedef struct pgpa_plan_walker_context
 } pgpa_plan_walker_context;
 
 extern void pgpa_plan_walker(pgpa_plan_walker_context *walker,
-							 PlannedStmt *pstmt);
+							 PlannedStmt *pstmt,
+							 List *sj_unique_rels);
 
 extern void pgpa_add_future_feature(pgpa_plan_walker_context *walker,
 									pgpa_qf_type type,