Fix a couple of oversights associated with the "physical tlist" optimization:

we had several code paths where a physical tlist could be used for the input
to a Sort node, which is a dumb idea because any unneeded table columns will
increase the volume of data the sort has to push around.

(Unfortunately the easy-looking fix of calling disuse_physical_tlist during
make_sort_xxx doesn't work because in most cases we're already committed to
the current input tlist --- it's been marked with sort column numbers, or
we've built grouping column numbers using it, etc.  The tlist has to be
selected properly at the calling level before we start constructing sort-col
information.  This is easy enough to do, we were just failing to take the
point into consideration.)

Back-patch to 8.3.  I believe the problem probably exists clear back to 7.4
when the physical tlist optimization was added, but I'm afraid to back-patch
further than 8.3 without a great deal more study than I want to put into it.
The code in this area has drifted a lot over time.  The real-world importance
of these code paths is uncertain anyway --- I think in many cases we'd
probably prefer hash-based methods.

diff --git a/src/backend/optimizer/plan/createplan.c b/src/backend/optimizer/plan/createplan.c
index aafa7b539ffc193b2ef3af0be590b677adfe1715..0c3abbd9b4c6ac960379a5ee8c69ba06435a6533 100644 (file)
--- a/src/backend/optimizer/plan/createplan.c
+++ b/src/backend/optimizer/plan/createplan.c
@@ -10,7 +10,7 @@
  *
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/optimizer/plan/createplan.c,v 1.237 2008/01/01 19:45:50 momjian Exp $
+ *   $PostgreSQL: pgsql/src/backend/optimizer/plan/createplan.c,v 1.237.2.1 2008/04/17 21:22:23 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -124,6 +124,7 @@ static MergeJoin *make_mergejoin(List *tlist,
 static Sort *make_sort(PlannerInfo *root, Plan *lefttree, int numCols,
          AttrNumber *sortColIdx, Oid *sortOperators, bool *nullsFirst,
          double limit_tuples);
+static Material *make_material(Plan *lefttree);
 
 
 /*
@@ -626,12 +627,14 @@ create_unique_plan(PlannerInfo *root, UniquePath *best_path)
     * add any such expressions to the subplan's tlist.
     *
     * The subplan may have a "physical" tlist if it is a simple scan plan.
-    * This should be left as-is if we don't need to add any expressions;
+    * If we're going to sort, this should be reduced to the regular tlist,
+    * so that we don't sort more data than we need to.  For hashing, the
+    * tlist should be left as-is if we don't need to add any expressions;
     * but if we do have to add expressions, then a projection step will be
-    * needed at runtime anyway, and so we may as well remove unneeded items.
+    * needed at runtime anyway, so we may as well remove unneeded items.
     * Therefore newtlist starts from build_relation_tlist() not just a
     * copy of the subplan's tlist; and we don't install it into the subplan
-    * unless stuff has to be added.
+    * unless we are sorting or stuff has to be added.
     *
     * To find the correct list of values to unique-ify, we look in the
     * information saved for IN expressions.  If this code is ever used in
@@ -679,7 +682,7 @@ create_unique_plan(PlannerInfo *root, UniquePath *best_path)
        }
    }
 
-   if (newitems)
+   if (newitems || best_path->umethod == UNIQUE_PATH_SORT)
    {
        /*
         * If the top plan node can't do projections, we need to add a Result
@@ -2991,7 +2994,7 @@ make_sort_from_groupcols(PlannerInfo *root,
                     sortColIdx, sortOperators, nullsFirst, -1.0);
 }
 
-Material *
+static Material *
 make_material(Plan *lefttree)
 {
    Material   *node = makeNode(Material);

diff --git a/src/backend/optimizer/plan/planner.c b/src/backend/optimizer/plan/planner.c
index cf26483007ed4a54354784b90e9b09b1d613fb8d..0d8560fd7d19674cf7d62372e83e7ccc961da618 100644 (file)
--- a/src/backend/optimizer/plan/planner.c
+++ b/src/backend/optimizer/plan/planner.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/optimizer/plan/planner.c,v 1.226.2.3 2008/04/01 00:48:44 tgl Exp $
+ *   $PostgreSQL: pgsql/src/backend/optimizer/plan/planner.c,v 1.226.2.4 2008/04/17 21:22:23 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -950,9 +950,23 @@ grouping_planner(PlannerInfo *root, double tuple_fraction)
             * Normal case --- create a plan according to query_planner's
             * results.
             */
+           bool    need_sort_for_grouping = false;
+
            result_plan = create_plan(root, best_path);
            current_pathkeys = best_path->pathkeys;
 
+           /* Detect if we'll need an explicit sort for grouping */
+           if (parse->groupClause && !use_hashed_grouping &&
+               !pathkeys_contained_in(group_pathkeys, current_pathkeys))
+           {
+               need_sort_for_grouping = true;
+               /*
+                * Always override query_planner's tlist, so that we don't
+                * sort useless data from a "physical" tlist.
+                */
+               need_tlist_eval = true;
+           }
+
            /*
             * create_plan() returns a plan with just a "flat" tlist of
             * required Vars.  Usually we need to insert the sub_tlist as the
@@ -1047,8 +1061,7 @@ grouping_planner(PlannerInfo *root, double tuple_fraction)
 
                if (parse->groupClause)
                {
-                   if (!pathkeys_contained_in(group_pathkeys,
-                                              current_pathkeys))
+                   if (need_sort_for_grouping)
                    {
                        result_plan = (Plan *)
                            make_sort_from_groupcols(root,
@@ -1091,7 +1104,7 @@ grouping_planner(PlannerInfo *root, double tuple_fraction)
                 * Add an explicit sort if we couldn't make the path come out
                 * the way the GROUP node needs it.
                 */
-               if (!pathkeys_contained_in(group_pathkeys, current_pathkeys))
+               if (need_sort_for_grouping)
                {
                    result_plan = (Plan *)
                        make_sort_from_groupcols(root,

diff --git a/src/include/optimizer/planmain.h b/src/include/optimizer/planmain.h
index f51a399caabfc39974c7f60f8fbe1c32b3ba7a62..d6b5fd58655219d6be2358f66b79e46efd0e6d15 100644 (file)
--- a/src/include/optimizer/planmain.h
+++ b/src/include/optimizer/planmain.h
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/optimizer/planmain.h,v 1.106 2008/01/01 19:45:58 momjian Exp $
+ * $PostgreSQL: pgsql/src/include/optimizer/planmain.h,v 1.106.2.1 2008/04/17 21:22:23 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,7 +53,6 @@ extern Group *make_group(PlannerInfo *root, List *tlist, List *qual,
           int numGroupCols, AttrNumber *grpColIdx, Oid *grpOperators,
           double numGroups,
           Plan *lefttree);
-extern Material *make_material(Plan *lefttree);
 extern Plan *materialize_finished_plan(Plan *subplan);
 extern Unique *make_unique(Plan *lefttree, List *distinctList);
 extern Limit *make_limit(Plan *lefttree, Node *limitOffset, Node *limitCount,