From: Robert Haas <rhaas@postgresql.org>
Date: Thu, 11 Dec 2025 20:37:56 +0000 (-0500)
Subject: Prune the list of non-unique semijoins.
X-Git-Url: http://git.postgresql.org/gitweb/?a=commitdiff_plain;h=refs%2Fheads%2Fpgpa_semijoin;p=users%2Frhaas%2Fpostgres.git

Prune the list of non-unique semijoins.
Test the list of unique semijoins.

This causes a bunch of breakage, all of which I believe to be due
to eager aggregation.
---

diff --git a/contrib/pg_plan_advice/pgpa_walker.c b/contrib/pg_plan_advice/pgpa_walker.c
index d5493bc0b8..318fddc9e3 100644
--- a/contrib/pg_plan_advice/pgpa_walker.c
+++ b/contrib/pg_plan_advice/pgpa_walker.c
@@ -72,6 +72,8 @@ pgpa_plan_walker(pgpa_plan_walker_context *walker, PlannedStmt *pstmt,
 				 List *sj_unique_rels)
 {
 	ListCell   *lc;
+	List	   *sj_unique_rtis = NULL;
+	List	   *sj_nonunique_qfs = NULL;
 
 	/* Initialization. */
 	memset(walker, 0, sizeof(pgpa_plan_walker_context));
@@ -88,6 +90,75 @@ pgpa_plan_walker(pgpa_plan_walker_context *walker, PlannedStmt *pstmt,
 		if (plan != NULL)
 			pgpa_walk_recursively(walker, plan, 0, NULL, NIL, false);
 	}
+
+	/* Adjust RTIs from sj_unique_rels for the flattened range table. */
+	foreach_ptr(pgpa_sj_unique_rel, ur, sj_unique_rels)
+	{
+		int		rtindex = -1;
+		int		rtoffset = 0;
+		bool	dummy = false;
+		Bitmapset *relids = NULL;
+
+		/* If this is a subplan, find the range table offset. */
+		if (ur->plan_name != NULL)
+		{
+			foreach_node(SubPlanRTInfo, rtinfo, pstmt->subrtinfos)
+			{
+				if (strcmp(ur->plan_name, rtinfo->plan_name) == 0)
+				{
+					rtoffset = rtinfo->rtoffset;
+					dummy = rtinfo->dummy;
+					break;
+				}
+			}
+
+			if (rtoffset == 0)
+				elog(ERROR, "no rtoffset for plan %s", ur->plan_name);
+		}
+
+		/* If this entry pertains to a dummy subquery, ignore it. */
+		if (dummy)
+			continue;
+
+		/* Offset each entry from the original set. */
+		while ((rtindex = bms_next_member(ur->relids, rtindex)) >= 0)
+			relids = bms_add_member(relids, rtindex + rtoffset);
+
+		/* Store the resulting set. */
+		sj_unique_rtis = lappend(sj_unique_rtis, relids);
+	}
+
+	/*
+	 * Remove any non-unique semjoin query features for which making the
+	 * rel unique wasn't considered.
+	 */
+	foreach_ptr(pgpa_query_feature, qf,
+				walker->query_features[PGPAQF_SEMIJOIN_NON_UNIQUE])
+	{
+		if (list_member(sj_unique_rtis, qf->relids))
+			sj_nonunique_qfs = lappend(sj_nonunique_qfs, qf);
+	}
+	walker->query_features[PGPAQF_SEMIJOIN_NON_UNIQUE] = sj_nonunique_qfs;
+
+	/*
+	 * If we find any cases where analysis of the Plan tree shows that the
+	 * semijoin was made unique but this possibility was never observed to
+	 * be considered during planning, then we have a bug somewhere.
+	 */
+	foreach_ptr(pgpa_query_feature, qf,
+				walker->query_features[PGPAQF_SEMIJOIN_UNIQUE])
+	{
+		if (!list_member(sj_unique_rtis, qf->relids))
+		{
+			StringInfoData	buf;
+
+			initStringInfo(&buf);
+			outBitmapset(&buf, qf->relids);
+			elog(ERROR,
+				 "unique semijoin found for relids %s but not observed during planning",
+				 buf.data);
+		}
+	}
 }
 
 /*