Marginal hack to avoid spending a lot of time in find_join_rel during

large planning problems: when the list of join rels gets too long, make
an auxiliary hash table that hashes on the identifying Bitmapset.

src/backend/optimizer/geqo/geqo_eval.c

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/backend/optimizer/geqo/geqo_eval.c,v 1.74 2005/06/05 22:32:55 tgl Exp $
+ * $PostgreSQL: pgsql/src/backend/optimizer/geqo/geqo_eval.c,v 1.75 2005/06/08 23:02:04 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -47,7 +47,8 @@ geqo_eval(Gene *tour, int num_gene, GeqoEvalData *evaldata)
 	MemoryContext oldcxt;
 	RelOptInfo *joinrel;
 	Cost		fitness;
-	List	   *savelist;
+	int			savelength;
+	struct HTAB *savehash;
 
 	/*
 	 * Because gimme_tree considers both left- and right-sided trees,
@@ -83,13 +84,19 @@ geqo_eval(Gene *tour, int num_gene, GeqoEvalData *evaldata)
 	 * gimme_tree will add entries to root->join_rel_list, which may or may
 	 * not already contain some entries.  The newly added entries will be
 	 * recycled by the MemoryContextDelete below, so we must ensure that
-	 * the list is restored to its former state before exiting.  With the
-	 * new List implementation, the easiest way is to make a duplicate list
-	 * that gimme_tree can modify.
+	 * the list is restored to its former state before exiting.  We can
+	 * do this by truncating the list to its original length.  NOTE this
+	 * assumes that any added entries are appended at the end!
+	 *
+	 * We also must take care not to mess up the outer join_rel_hash,
+	 * if there is one.  We can do this by just temporarily setting the
+	 * link to NULL.  (If we are dealing with enough join rels, which we
+	 * very likely are, a new hash table will get built and used locally.)
 	 */
-	savelist = evaldata->root->join_rel_list;
+	savelength = list_length(evaldata->root->join_rel_list);
+	savehash = evaldata->root->join_rel_hash;
 
-	evaldata->root->join_rel_list = list_copy(savelist);
+	evaldata->root->join_rel_hash = NULL;
 
 	/* construct the best path for the given combination of relations */
 	joinrel = gimme_tree(tour, num_gene, evaldata);
@@ -105,8 +112,13 @@ geqo_eval(Gene *tour, int num_gene, GeqoEvalData *evaldata)
 	else
 		fitness = DBL_MAX;
 
-	/* restore join_rel_list */
-	evaldata->root->join_rel_list = savelist;
+	/*
+	 * Restore join_rel_list to its former state, and put back original
+	 * hashtable if any.
+	 */
+	evaldata->root->join_rel_list = list_truncate(evaldata->root->join_rel_list,
+												  savelength);
+	evaldata->root->join_rel_hash = savehash;
 
 	/* release all the memory acquired within gimme_tree */
 	MemoryContextSwitchTo(oldcxt);

src/backend/optimizer/geqo/geqo_main.c

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/backend/optimizer/geqo/geqo_main.c,v 1.49 2005/06/05 22:32:55 tgl Exp $
+ * $PostgreSQL: pgsql/src/backend/optimizer/geqo/geqo_main.c,v 1.50 2005/06/08 23:02:04 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -252,7 +252,6 @@ geqo(PlannerInfo *root, int number_of_rels, List *initial_rels)
 	 */
 	best_tour = (Gene *) pool->data[0].string;
 
-	/* root->join_rel_list will be modified during this ! */
 	best_rel = gimme_tree(best_tour, pool->string_length, &evaldata);
 
 	if (best_rel == NULL)

src/backend/optimizer/plan/planmain.c

@@ -14,7 +14,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/optimizer/plan/planmain.c,v 1.83 2005/06/06 04:13:35 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/optimizer/plan/planmain.c,v 1.84 2005/06/08 23:02:04 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -116,6 +116,7 @@ query_planner(PlannerInfo *root, List *tlist, double tuple_fraction,
 	root->base_rel_array = (RelOptInfo **)
 		palloc0(root->base_rel_array_size * sizeof(RelOptInfo *));
 	root->join_rel_list = NIL;
+	root->join_rel_hash = NULL;
 	root->equi_key_list = NIL;
 
 	/*

src/backend/optimizer/util/relnode.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/optimizer/util/relnode.c,v 1.68 2005/06/06 04:13:36 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/optimizer/util/relnode.c,v 1.69 2005/06/08 23:02:05 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -21,8 +21,15 @@
 #include "optimizer/restrictinfo.h"
 #include "optimizer/tlist.h"
 #include "parser/parsetree.h"
+#include "utils/hsearch.h"
 
 
+typedef struct JoinHashEntry
+{
+	Relids		join_relids;	/* hash key --- MUST BE FIRST */
+	RelOptInfo *join_rel;
+} JoinHashEntry;
+
 static RelOptInfo *make_reloptinfo(PlannerInfo *root, int relid,
 								   RelOptKind reloptkind);
 static void build_joinrel_tlist(PlannerInfo *root, RelOptInfo *joinrel,
@@ -197,6 +204,47 @@ find_base_rel(PlannerInfo *root, int relid)
 	return NULL;				/* keep compiler quiet */
 }
 
+/*
+ * build_join_rel_hash
+ *	  Construct the auxiliary hash table for join relations.
+ */
+static void
+build_join_rel_hash(PlannerInfo *root)
+{
+	HTAB	   *hashtab;
+	HASHCTL		hash_ctl;
+	ListCell   *l;
+
+	/* Create the hash table */
+	MemSet(&hash_ctl, 0, sizeof(hash_ctl));
+	hash_ctl.keysize = sizeof(Relids);
+	hash_ctl.entrysize = sizeof(JoinHashEntry);
+	hash_ctl.hash = bitmap_hash;
+	hash_ctl.match = bitmap_match;
+	hash_ctl.hcxt = CurrentMemoryContext;
+	hashtab = hash_create("JoinRelHashTable",
+						  256L,
+						  &hash_ctl,
+						  HASH_ELEM | HASH_FUNCTION | HASH_COMPARE | HASH_CONTEXT);
+
+	/* Insert all the already-existing joinrels */
+	foreach(l, root->join_rel_list)
+	{
+		RelOptInfo *rel = (RelOptInfo *) lfirst(l);
+		JoinHashEntry *hentry;
+		bool		found;
+
+		hentry = (JoinHashEntry *) hash_search(hashtab,
+											   &(rel->relids),
+											   HASH_ENTER,
+											   &found);
+		Assert(!found);
+		hentry->join_rel = rel;
+	}
+
+	root->join_rel_hash = hashtab;
+}
+
 /*
  * find_join_rel
  *	  Returns relation entry corresponding to 'relids' (a set of RT indexes),
@@ -205,14 +253,44 @@ find_base_rel(PlannerInfo *root, int relid)
 RelOptInfo *
 find_join_rel(PlannerInfo *root, Relids relids)
 {
-	ListCell   *l;
+	/*
+	 * Switch to using hash lookup when list grows "too long".  The threshold
+	 * is arbitrary and is known only here.
+	 */
+	if (!root->join_rel_hash && list_length(root->join_rel_list) > 32)
+		build_join_rel_hash(root);
 
-	foreach(l, root->join_rel_list)
+	/*
+	 * Use either hashtable lookup or linear search, as appropriate.
+	 *
+	 * Note: the seemingly redundant hashkey variable is used to avoid
+	 * taking the address of relids; unless the compiler is exceedingly
+	 * smart, doing so would force relids out of a register and thus
+	 * probably slow down the list-search case.
+	 */
+	if (root->join_rel_hash)
 	{
-		RelOptInfo *rel = (RelOptInfo *) lfirst(l);
+		Relids		hashkey = relids;
+		JoinHashEntry *hentry;
 
-		if (bms_equal(rel->relids, relids))
-			return rel;
+		hentry = (JoinHashEntry *) hash_search(root->join_rel_hash,
+											   &hashkey,
+											   HASH_FIND,
+											   NULL);
+		if (hentry)
+			return hentry->join_rel;
+	}
+	else
+	{
+		ListCell   *l;
+
+		foreach(l, root->join_rel_list)
+		{
+			RelOptInfo *rel = (RelOptInfo *) lfirst(l);
+
+			if (bms_equal(rel->relids, relids))
+				return rel;
+		}
 	}
 
 	return NULL;
@@ -329,9 +407,24 @@ build_join_rel(PlannerInfo *root,
 							   jointype, restrictlist);
 
 	/*
-	 * Add the joinrel to the query's joinrel list.
+	 * Add the joinrel to the query's joinrel list, and store it into
+	 * the auxiliary hashtable if there is one.  NB: GEQO requires us
+	 * to append the new joinrel to the end of the list!
 	 */
-	root->join_rel_list = lcons(joinrel, root->join_rel_list);
+	root->join_rel_list = lappend(root->join_rel_list, joinrel);
+
+	if (root->join_rel_hash)
+	{
+		JoinHashEntry *hentry;
+		bool		found;
+
+		hentry = (JoinHashEntry *) hash_search(root->join_rel_hash,
+											   &(joinrel->relids),
+											   HASH_ENTER,
+											   &found);
+		Assert(!found);
+		hentry->join_rel = joinrel;
+	}
 
 	return joinrel;
 }