v6-0006-Build-grouped-relations-out-of-base-relations.patch

From 667c3c7de368090dd106c3a199874c20c4639bcb Mon Sep 17 00:00:00 2001
From: Richard Guo <guofenglinux@gmail.com>
Date: Wed, 28 Feb 2024 10:03:41 +0800
Subject: [PATCH v6 6/9] Build grouped relations out of base relations

This commit builds grouped relations for each base relation if possible,
and generates aggregation paths for the grouped base relations.
---
 src/backend/optimizer/path/allpaths.c |  91 +++++++++++++++++++++++
 src/backend/optimizer/util/relnode.c  | 101 ++++++++++++++++++++++++++
 src/include/optimizer/pathnode.h      |   4 +
 3 files changed, 196 insertions(+)

diff --git a/src/backend/optimizer/path/allpaths.c b/src/backend/optimizer/path/allpaths.c
index 3f3dbc486e..ef699ab630 100644
--- a/src/backend/optimizer/path/allpaths.c
+++ b/src/backend/optimizer/path/allpaths.c
@@ -93,6 +93,7 @@ join_search_hook_type join_search_hook = NULL;
 
 static void set_base_rel_consider_startup(PlannerInfo *root);
 static void set_base_rel_sizes(PlannerInfo *root);
+static void setup_base_grouped_rels(PlannerInfo *root);
 static void set_base_rel_pathlists(PlannerInfo *root);
 static void set_rel_size(PlannerInfo *root, RelOptInfo *rel,
 						 Index rti, RangeTblEntry *rte);
@@ -117,6 +118,7 @@ static void set_append_rel_size(PlannerInfo *root, RelOptInfo *rel,
 								Index rti, RangeTblEntry *rte);
 static void set_append_rel_pathlist(PlannerInfo *root, RelOptInfo *rel,
 									Index rti, RangeTblEntry *rte);
+static void set_grouped_rel_pathlist(PlannerInfo *root, RelOptInfo *rel);
 static void generate_orderedappend_paths(PlannerInfo *root, RelOptInfo *rel,
 										 List *live_childrels,
 										 List *all_child_pathkeys);
@@ -185,6 +187,11 @@ make_one_rel(PlannerInfo *root, List *joinlist)
 	 */
 	set_base_rel_sizes(root);
 
+	/*
+	 * Build grouped base relations for each base rel if possible.
+	 */
+	setup_base_grouped_rels(root);
+
 	/*
 	 * We should now have size estimates for every actual table involved in
 	 * the query, and we also know which if any have been deleted from the
@@ -326,6 +333,59 @@ set_base_rel_sizes(PlannerInfo *root)
 	}
 }
 
+/*
+ * setup_base_grouped_rels
+ *	  For each "plain" base relation build a grouped base relation if eager
+ *	  aggregation is possible and if this relation can produce grouped paths.
+ */
+static void
+setup_base_grouped_rels(PlannerInfo *root)
+{
+	Index		rti;
+
+	/*
+	 * If there are no aggregate expressions or grouping expressions, eager
+	 * aggregation is not possible.
+	 */
+	if (root->agg_clause_list == NIL ||
+		root->group_expr_list == NIL)
+		return;
+
+	/*
+	 * Eager aggregation only makes sense if there are multiple base rels in
+	 * the query.
+	 */
+	if (bms_membership(root->all_baserels) != BMS_MULTIPLE)
+		return;
+
+	for (rti = 1; rti < root->simple_rel_array_size; rti++)
+	{
+		RelOptInfo	   *rel = root->simple_rel_array[rti];
+		RelOptInfo	   *rel_grouped;
+		RelAggInfo	   *agg_info;
+
+		/* there may be empty slots corresponding to non-baserel RTEs */
+		if (rel == NULL)
+			continue;
+
+		Assert(rel->relid == rti); /* sanity check on array */
+
+		/*
+		 * Ignore RTEs that are not simple rels.  Note that we need to consider
+		 * "other rels" here.
+		 */
+		if (!IS_SIMPLE_REL(rel))
+			continue;
+
+		rel_grouped = build_simple_grouped_rel(root, rel->relid, &agg_info);
+		if (rel_grouped)
+		{
+			/* Make the grouped relation available for joining. */
+			add_grouped_rel(root, rel_grouped, agg_info);
+		}
+	}
+}
+
 /*
  * set_base_rel_pathlists
  *	  Finds all paths available for scanning each base-relation entry.
@@ -562,6 +622,15 @@ set_rel_pathlist(PlannerInfo *root, RelOptInfo *rel,
 	/* Now find the cheapest of the paths for this rel */
 	set_cheapest(rel);
 
+	/*
+	 * If a grouped relation for this rel exists, build partial aggregation
+	 * paths for it.
+	 *
+	 * Note that this can only happen after we've called set_cheapest() for
+	 * this base rel, because we need its cheapest paths.
+	 */
+	set_grouped_rel_pathlist(root, rel);
+
 #ifdef OPTIMIZER_DEBUG
 	pprint(rel);
 #endif
@@ -1289,6 +1358,28 @@ set_append_rel_pathlist(PlannerInfo *root, RelOptInfo *rel,
 	add_paths_to_append_rel(root, rel, live_childrels);
 }
 
+/*
+ * set_grouped_rel_pathlist
+ *	  If a grouped relation for the given 'rel' exists, build partial
+ *	  aggregation paths for it.
+ */
+static void
+set_grouped_rel_pathlist(PlannerInfo *root, RelOptInfo *rel)
+{
+	RelOptInfo   *rel_grouped;
+	RelAggInfo   *agg_info;
+
+	/* Add paths to the grouped base relation if one exists. */
+	rel_grouped = find_grouped_rel(root, rel->relids,
+								   &agg_info);
+	if (rel_grouped)
+	{
+		generate_grouped_paths(root, rel_grouped, rel,
+							   agg_info);
+		set_cheapest(rel_grouped);
+	}
+}
+
 
 /*
  * add_paths_to_append_rel
diff --git a/src/backend/optimizer/util/relnode.c b/src/backend/optimizer/util/relnode.c
index c6e2d417a8..b14f99a9ea 100644
--- a/src/backend/optimizer/util/relnode.c
+++ b/src/backend/optimizer/util/relnode.c
@@ -16,6 +16,7 @@
 
 #include <limits.h>
 
+#include "catalog/pg_constraint.h"
 #include "miscadmin.h"
 #include "nodes/nodeFuncs.h"
 #include "optimizer/appendinfo.h"
@@ -27,12 +28,15 @@
 #include "optimizer/paths.h"
 #include "optimizer/placeholder.h"
 #include "optimizer/plancat.h"
+#include "optimizer/planner.h"
 #include "optimizer/restrictinfo.h"
 #include "optimizer/tlist.h"
+#include "parser/parse_oper.h"
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteManip.h"
 #include "utils/hsearch.h"
 #include "utils/lsyscache.h"
+#include "utils/selfuncs.h"
 
 
 /*
@@ -418,6 +422,103 @@ build_simple_rel(PlannerInfo *root, int relid, RelOptInfo *parent)
 	return rel;
 }
 
+/*
+ * build_simple_grouped_rel
+ *	  Construct a new RelOptInfo for a grouped base relation out of an existing
+ *	  non-grouped base relation.
+ *
+ * On success, the new RelOptInfo is returned and the corresponding RelAggInfo
+ * is stored in *agg_info_p.
+ */
+RelOptInfo *
+build_simple_grouped_rel(PlannerInfo *root, int relid,
+						 RelAggInfo **agg_info_p)
+{
+	RelOptInfo	   *rel_plain;
+	RelOptInfo	   *rel_grouped;
+	RelAggInfo	   *agg_info;
+
+	/*
+	 * We should have available aggregate expressions and grouping expressions,
+	 * otherwise we cannot reach here.
+	 */
+	Assert(root->agg_clause_list != NIL);
+	Assert(root->group_expr_list != NIL);
+
+	rel_plain = root->simple_rel_array[relid];
+	Assert(rel_plain != NULL);
+	Assert(IS_SIMPLE_REL(rel_plain));
+
+	/* nothing to do for dummy rel */
+	if (IS_DUMMY_REL(rel_plain))
+		return NULL;
+
+	/*
+	 * Prepare the information we need to create grouped paths for this base
+	 * relation.
+	 */
+	agg_info = create_rel_agg_info(root, rel_plain);
+	if (agg_info == NULL)
+		return NULL;
+
+	/* build a grouped relation out of the plain relation */
+	rel_grouped = build_grouped_rel(root, rel_plain);
+	rel_grouped->reltarget = agg_info->target;
+	rel_grouped->rows = agg_info->grouped_rows;
+
+	/* return the RelAggInfo structure */
+	*agg_info_p = agg_info;
+
+	return rel_grouped;
+}
+
+/*
+ * build_grouped_rel
+ *	  Build a grouped relation by flat copying a plain relation and resetting
+ *	  the necessary fields.
+ */
+RelOptInfo *
+build_grouped_rel(PlannerInfo *root, RelOptInfo *rel_plain)
+{
+	RelOptInfo   *rel_grouped;
+
+	rel_grouped = makeNode(RelOptInfo);
+	memcpy(rel_grouped, rel_plain, sizeof(RelOptInfo));
+
+	/*
+	 * clear path info
+	 */
+	rel_grouped->pathlist = NIL;
+	rel_grouped->ppilist = NIL;
+	rel_grouped->partial_pathlist = NIL;
+	rel_grouped->cheapest_startup_path = NULL;
+	rel_grouped->cheapest_total_path = NULL;
+	rel_grouped->cheapest_unique_path = NULL;
+	rel_grouped->cheapest_parameterized_paths = NIL;
+
+	/*
+	 * clear partition info
+	 */
+	rel_grouped->part_scheme = NULL;
+	rel_grouped->nparts = -1;
+	rel_grouped->boundinfo = NULL;
+	rel_grouped->partbounds_merged = false;
+	rel_grouped->partition_qual = NIL;
+	rel_grouped->part_rels = NULL;
+	rel_grouped->live_parts = NULL;
+	rel_grouped->all_partrels = NULL;
+	rel_grouped->partexprs = NULL;
+	rel_grouped->nullable_partexprs = NULL;
+	rel_grouped->consider_partitionwise_join = false;
+
+	/*
+	 * clear size estimates
+	 */
+	rel_grouped->rows = 0;
+
+	return rel_grouped;
+}
+
 /*
  * find_base_rel
  *	  Find a base or otherrel relation entry, which must already exist.
diff --git a/src/include/optimizer/pathnode.h b/src/include/optimizer/pathnode.h
index d973bff8ff..d4b4499db3 100644
--- a/src/include/optimizer/pathnode.h
+++ b/src/include/optimizer/pathnode.h
@@ -309,6 +309,10 @@ extern void setup_simple_rel_arrays(PlannerInfo *root);
 extern void expand_planner_arrays(PlannerInfo *root, int add_size);
 extern RelOptInfo *build_simple_rel(PlannerInfo *root, int relid,
 									RelOptInfo *parent);
+extern RelOptInfo *build_simple_grouped_rel(PlannerInfo *root, int relid,
+											RelAggInfo **agg_info_p);
+extern RelOptInfo *build_grouped_rel(PlannerInfo *root,
+									 RelOptInfo *rel_plain);
 extern RelOptInfo *find_base_rel(PlannerInfo *root, int relid);
 extern RelOptInfo *find_base_rel_noerr(PlannerInfo *root, int relid);
 extern RelOptInfo *find_base_rel_ignore_join(PlannerInfo *root, int relid);
-- 
2.31.0