database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-03 20:02:46 +03:00
Code Activity

Teach planner to account for HAVING quals in aggregation plan nodes.

Browse Source 
For some reason, we have never accounted for either the evaluation cost
or the selectivity of filter conditions attached to Agg and Group nodes
(which, in practice, are always conditions from a HAVING clause).

Applying our regular selectivity logic to post-grouping conditions is a
bit bogus, but it's surely better than taking the selectivity as 1.0.
Perhaps someday the extended-statistics mechanism can be taught to provide
statistics that would help us in getting non-default estimates here.

Per a gripe from Benjamin Coutu.  This is surely a bug fix, but I'm
hesitant to back-patch because of the prospect of destabilizing existing
plan choices.  Given that it took us this long to notice the bug, it's
probably not hurting too many people in the field.

Discussion: https://postgr.es/m/20968.1509486337@sss.pgh.pa.us
This commit is contained in:
Tom Lane
2017-11-02 11:24:12 -04:00
parent c6764eb3ae
commit 7b6c075471
4 changed files with 74 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
src/backend/optimizer/util/pathnode.c
View File

@ -1374,6 +1374,11 @@ create_result_path(PlannerInfo *root, RelOptInfo *rel,
pathnode->path.startup_cost = target->cost.startup;
pathnode->path.total_cost = target->cost.startup +
cpu_tuple_cost + target->cost.per_tuple;
/*
* Add cost of qual, if any --- but we ignore its selectivity, since our
* rowcount estimate should be 1 no matter what the qual is.
*/
if (resconstantqual)
{
QualCost qual_cost;
@ -1596,6 +1601,7 @@ create_unique_path(PlannerInfo *root, RelOptInfo *rel, Path *subpath,
cost_agg(&agg_path, root,
AGG_HASHED, NULL,
numCols, pathnode->path.rows,
NIL,
subpath->startup_cost,
subpath->total_cost,
rel->rows);
@ -2592,6 +2598,7 @@ create_group_path(PlannerInfo *root,
cost_group(&pathnode->path, root,
list_length(groupClause),
numGroups,
qual,
subpath->startup_cost, subpath->total_cost,
subpath->rows);
@ -2709,6 +2716,7 @@ create_agg_path(PlannerInfo *root,
cost_agg(&pathnode->path, root,
aggstrategy, aggcosts,
list_length(groupClause), numGroups,
qual,
subpath->startup_cost, subpath->total_cost,
subpath->rows);
@ -2817,6 +2825,7 @@ create_groupingsets_path(PlannerInfo *root,
agg_costs,
numGroupCols,
rollup->numGroups,
having_qual,
subpath->startup_cost,
subpath->total_cost,
subpath->rows);
@ -2840,6 +2849,7 @@ create_groupingsets_path(PlannerInfo *root,
agg_costs,
numGroupCols,
rollup->numGroups,
having_qual,
0.0, 0.0,
subpath->rows);
if (!rollup->is_hashed)
@ -2863,6 +2873,7 @@ create_groupingsets_path(PlannerInfo *root,
agg_costs,
numGroupCols,
rollup->numGroups,
having_qual,
sort_path.startup_cost,
sort_path.total_cost,
sort_path.rows);
@ -2932,6 +2943,19 @@ create_minmaxagg_path(PlannerInfo *root,
pathnode->path.total_cost = initplan_cost + target->cost.startup +
target->cost.per_tuple + cpu_tuple_cost;
/*
* Add cost of qual, if any --- but we ignore its selectivity, since our
* rowcount estimate should be 1 no matter what the qual is.
*/
if (quals)
{
QualCost qual_cost;
cost_qual_eval(&qual_cost, quals, root);
pathnode->path.startup_cost += qual_cost.startup;
pathnode->path.total_cost += qual_cost.startup + qual_cost.per_tuple;
}
return pathnode;
}
@ -3781,6 +3805,7 @@ reparameterize_pathlist_by_child(PlannerInfo *root,
{
Path *path = reparameterize_path_by_child(root, lfirst(lc),
child_rel);
if (path == NULL)
{
list_free(result);