From: Tom Lane Date: Thu, 7 Nov 2013 18:13:19 +0000 (-0500) Subject: Fix generation of MergeAppend plans for optimized min/max on expressions. X-Git-Tag: REL9_2_6~38 X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=aa8a2c3a612a867fc5348bd6ff68f619212e3c1b;p=postgresql Fix generation of MergeAppend plans for optimized min/max on expressions. Before jamming a desired targetlist into a plan node, one really ought to make sure the plan node can handle projections, and insert a buffering Result plan node if not. planagg.c forgot to do this, which is a hangover from the days when it only dealt with IndexScan plan types. MergeAppend doesn't project though, not to mention that it gets unhappy if you remove its possibly-resjunk sort columns. The code accidentally failed to fail for cases in which the min/max argument was a simple Var, because the new targetlist would be equivalent to the original "flat" tlist anyway. For any more complex case, it's been broken since 9.1 where we introduced the ability to optimize min/max using MergeAppend, as reported by Raphael Bauduin. Fix by duplicating the logic from grouping_planner that decides whether we need a Result node. In 9.2 and 9.1, this requires back-porting the tlist_same_exprs() function introduced in commit 4387cf956b9eb13aad569634e0c4df081d76e2e3, else we'd uselessly add a Result node in cases that worked before. It's rather tempting to back-patch that whole commit so that we can avoid extra Result nodes in mainline cases too; but I'll refrain, since that code hasn't really seen all that much field testing yet. --- diff --git a/src/backend/optimizer/plan/planagg.c b/src/backend/optimizer/plan/planagg.c index 83e96556ae..72bb96cd8a 100644 --- a/src/backend/optimizer/plan/planagg.c +++ b/src/backend/optimizer/plan/planagg.c @@ -38,6 +38,7 @@ #include "optimizer/planmain.h" #include "optimizer/planner.h" #include "optimizer/subselect.h" +#include "optimizer/tlist.h" #include "parser/parsetree.h" #include "parser/parse_clause.h" #include "utils/lsyscache.h" @@ -525,7 +526,27 @@ make_agg_subplan(PlannerInfo *root, MinMaxAggInfo *mminfo) */ plan = create_plan(subroot, mminfo->path); - plan->targetlist = subparse->targetList; + /* + * If the top-level plan node is one that cannot do expression evaluation + * and its existing target list isn't already what we need, we must insert + * a Result node to project the desired tlist. + */ + if (!is_projection_capable_plan(plan) && + !tlist_same_exprs(subparse->targetList, plan->targetlist)) + { + plan = (Plan *) make_result(subroot, + subparse->targetList, + NULL, + plan); + } + else + { + /* + * Otherwise, just replace the subplan's flat tlist with the desired + * tlist. + */ + plan->targetlist = subparse->targetList; + } plan = (Plan *) make_limit(plan, subparse->limitOffset, diff --git a/src/backend/optimizer/util/tlist.c b/src/backend/optimizer/util/tlist.c index 5c80bccbb2..2d32a6bb68 100644 --- a/src/backend/optimizer/util/tlist.c +++ b/src/backend/optimizer/util/tlist.c @@ -187,6 +187,43 @@ get_tlist_exprs(List *tlist, bool includeJunk) } +/* + * tlist_same_exprs + * Check whether two target lists contain the same expressions + * + * Note: this function is used to decide whether it's safe to jam a new tlist + * into a non-projection-capable plan node. Obviously we can't do that unless + * the node's tlist shows it already returns the column values we want. + * However, we can ignore the TargetEntry attributes resname, ressortgroupref, + * resorigtbl, resorigcol, and resjunk, because those are only labelings that + * don't affect the row values computed by the node. (Moreover, if we didn't + * ignore them, we'd frequently fail to make the desired optimization, since + * the planner tends to not bother to make resname etc. valid in intermediate + * plan nodes.) Note that on success, the caller must still jam the desired + * tlist into the plan node, else it won't have the desired labeling fields. + */ +bool +tlist_same_exprs(List *tlist1, List *tlist2) +{ + ListCell *lc1, + *lc2; + + if (list_length(tlist1) != list_length(tlist2)) + return false; /* not same length, so can't match */ + + forboth(lc1, tlist1, lc2, tlist2) + { + TargetEntry *tle1 = (TargetEntry *) lfirst(lc1); + TargetEntry *tle2 = (TargetEntry *) lfirst(lc2); + + if (!equal(tle1->expr, tle2->expr)) + return false; + } + + return true; +} + + /* * Does tlist have same output datatypes as listed in colTypes? * diff --git a/src/include/optimizer/tlist.h b/src/include/optimizer/tlist.h index 01bec54dba..e683e2d742 100644 --- a/src/include/optimizer/tlist.h +++ b/src/include/optimizer/tlist.h @@ -26,6 +26,9 @@ extern List *flatten_tlist(List *tlist, PVCAggregateBehavior aggbehavior, extern List *add_to_flat_tlist(List *tlist, List *exprs); extern List *get_tlist_exprs(List *tlist, bool includeJunk); + +extern bool tlist_same_exprs(List *tlist1, List *tlist2); + extern bool tlist_same_datatypes(List *tlist, List *colTypes, bool junkOK); extern bool tlist_same_collations(List *tlist, List *colCollations, bool junkOK); diff --git a/src/test/regress/expected/inherit.out b/src/test/regress/expected/inherit.out index c81fdb8428..08a25c42e4 100644 --- a/src/test/regress/expected/inherit.out +++ b/src/test/regress/expected/inherit.out @@ -1216,6 +1216,28 @@ select * from matest0 order by 1-id; 1 | Test 1 (6 rows) +explain (verbose, costs off) select min(1-id) from matest0; + QUERY PLAN +------------------------------------------------ + Aggregate + Output: min((1 - public.matest0.id)) + -> Append + -> Seq Scan on public.matest0 + Output: public.matest0.id + -> Seq Scan on public.matest1 matest0 + Output: public.matest0.id + -> Seq Scan on public.matest2 matest0 + Output: public.matest0.id + -> Seq Scan on public.matest3 matest0 + Output: public.matest0.id +(11 rows) + +select min(1-id) from matest0; + min +----- + -5 +(1 row) + reset enable_indexscan; set enable_seqscan = off; -- plan with fewest seqscans should be merge explain (verbose, costs off) select * from matest0 order by 1-id; @@ -1249,6 +1271,42 @@ select * from matest0 order by 1-id; 1 | Test 1 (6 rows) +explain (verbose, costs off) select min(1-id) from matest0; + QUERY PLAN +-------------------------------------------------------------------------------------- + Result + Output: $0 + InitPlan 1 (returns $0) + -> Limit + Output: ((1 - public.matest0.id)) + -> Result + Output: ((1 - public.matest0.id)) + -> Merge Append + Sort Key: ((1 - public.matest0.id)) + -> Index Scan using matest0i on public.matest0 + Output: public.matest0.id, (1 - public.matest0.id) + Index Cond: ((1 - public.matest0.id) IS NOT NULL) + -> Index Scan using matest1i on public.matest1 matest0 + Output: public.matest0.id, (1 - public.matest0.id) + Index Cond: ((1 - public.matest0.id) IS NOT NULL) + -> Sort + Output: public.matest0.id, ((1 - public.matest0.id)) + Sort Key: ((1 - public.matest0.id)) + -> Bitmap Heap Scan on public.matest2 matest0 + Output: public.matest0.id, (1 - public.matest0.id) + Filter: ((1 - public.matest0.id) IS NOT NULL) + -> Bitmap Index Scan on matest2_pkey + -> Index Scan using matest3i on public.matest3 matest0 + Output: public.matest0.id, (1 - public.matest0.id) + Index Cond: ((1 - public.matest0.id) IS NOT NULL) +(25 rows) + +select min(1-id) from matest0; + min +----- + -5 +(1 row) + reset enable_seqscan; drop table matest0 cascade; NOTICE: drop cascades to 3 other objects diff --git a/src/test/regress/sql/inherit.sql b/src/test/regress/sql/inherit.sql index 29c1e59fd0..1914bdea9b 100644 --- a/src/test/regress/sql/inherit.sql +++ b/src/test/regress/sql/inherit.sql @@ -382,11 +382,15 @@ insert into matest3 (name) values ('Test 6'); set enable_indexscan = off; -- force use of seqscan/sort, so no merge explain (verbose, costs off) select * from matest0 order by 1-id; select * from matest0 order by 1-id; +explain (verbose, costs off) select min(1-id) from matest0; +select min(1-id) from matest0; reset enable_indexscan; set enable_seqscan = off; -- plan with fewest seqscans should be merge explain (verbose, costs off) select * from matest0 order by 1-id; select * from matest0 order by 1-id; +explain (verbose, costs off) select min(1-id) from matest0; +select min(1-id) from matest0; reset enable_seqscan; drop table matest0 cascade;