1
0
mirror of https://github.com/postgres/postgres.git synced 2025-06-27 23:21:58 +03:00

Make the planner estimate costs for nestloop inner indexscans on the basis

that the Mackert-Lohmann formula applies across all the repetitions of the
nestloop, not just each scan independently.  We use the M-L formula to
estimate the number of pages fetched from the index as well as from the table;
that isn't what it was designed for, but it seems reasonably applicable
anyway.  This makes large numbers of repetitions look much cheaper than
before, which accords with many reports we've received of overestimation
of the cost of a nestloop.  Also, change the index access cost model to
charge random_page_cost per index leaf page touched, while explicitly
not counting anything for access to metapage or upper tree pages.  This
may all need tweaking after we get some field experience, but in simple
tests it seems to be giving saner results than before.  The main thing
is to get the infrastructure in place to let cost_index() and amcostestimate
functions take repeated scans into account at all.  Per my recent proposal.

Note: this patch changes pg_proc.h, but I did not force initdb because
the changes are basically cosmetic --- the system does not look into
pg_proc to decide how to call an index amcostestimate function, and
there's no way to call such a function from SQL at all.
This commit is contained in:
Tom Lane
2006-06-06 17:59:58 +00:00
parent 05631354f3
commit 8a30cc2127
14 changed files with 340 additions and 202 deletions

View File

@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
* $PostgreSQL: pgsql/src/backend/optimizer/path/joinpath.c,v 1.103 2006/03/05 15:58:28 momjian Exp $
* $PostgreSQL: pgsql/src/backend/optimizer/path/joinpath.c,v 1.104 2006/06/06 17:59:57 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@ -36,7 +36,7 @@ static void hash_inner_and_outer(PlannerInfo *root, RelOptInfo *joinrel,
RelOptInfo *outerrel, RelOptInfo *innerrel,
List *restrictlist, JoinType jointype);
static Path *best_appendrel_indexscan(PlannerInfo *root, RelOptInfo *rel,
Relids outer_relids, JoinType jointype);
RelOptInfo *outer_rel, JoinType jointype);
static List *select_mergejoin_clauses(RelOptInfo *joinrel,
RelOptInfo *outerrel,
RelOptInfo *innerrel,
@ -401,12 +401,10 @@ match_unsorted_outer(PlannerInfo *root,
{
if (IsA(inner_cheapest_total, AppendPath))
bestinnerjoin = best_appendrel_indexscan(root, innerrel,
outerrel->relids,
jointype);
outerrel, jointype);
else if (innerrel->rtekind == RTE_RELATION)
bestinnerjoin = best_inner_indexscan(root, innerrel,
outerrel->relids,
jointype);
outerrel, jointype);
}
}
@ -791,13 +789,13 @@ hash_inner_and_outer(PlannerInfo *root,
/*
* best_appendrel_indexscan
* Finds the best available set of inner indexscans for a nestloop join
* with the given append relation on the inside and the given outer_relids
* with the given append relation on the inside and the given outer_rel
* outside. Returns an AppendPath comprising the best inner scans, or
* NULL if there are no possible inner indexscans.
*/
static Path *
best_appendrel_indexscan(PlannerInfo *root, RelOptInfo *rel,
Relids outer_relids, JoinType jointype)
RelOptInfo *outer_rel, JoinType jointype)
{
int parentRTindex = rel->relid;
List *append_paths = NIL;
@ -832,7 +830,7 @@ best_appendrel_indexscan(PlannerInfo *root, RelOptInfo *rel,
* Get the best innerjoin indexpath (if any) for this child rel.
*/
bestinnerjoin = best_inner_indexscan(root, childrel,
outer_relids, jointype);
outer_rel, jointype);
/*
* If no luck on an indexpath for this rel, we'll still consider