database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-12 21:01:52 +03:00
Code Activity

Basic partition-wise join functionality.

Browse Source 
Instead of joining two partitioned tables in their entirety we can, if
it is an equi-join on the partition keys, join the matching partitions
individually.  This involves teaching the planner about "other join"
rels, which are related to regular join rels in the same way that
other member rels are related to baserels.  This can use significantly
more CPU time and memory than regular join planning, because there may
now be a set of "other" rels not only for every base relation but also
for every join relation.  In most practical cases, this probably
shouldn't be a problem, because (1) it's probably unusual to join many
tables each with many partitions using the partition keys for all
joins and (2) if you do that scenario then you probably have a big
enough machine to handle the increased memory cost of planning and (3)
the resulting plan is highly likely to be better, so what you spend in
planning you'll make up on the execution side.  All the same, for now,
turn this feature off by default.

Currently, we can only perform joins between two tables whose
partitioning schemes are absolutely identical.  It would be nice to
cope with other scenarios, such as extra partitions on one side or the
other with no match on the other side, but that will have to wait for
a future patch.

Ashutosh Bapat, reviewed and tested by Rajkumar Raghuwanshi, Amit
Langote, Rafia Sabih, Thomas Munro, Dilip Kumar, Antonin Houska, Amit
Khandekar, and by me.  A few final adjustments by me.

Discussion: http://postgr.es/m/CAFjFpRfQ8GrQvzp3jA2wnLqrHmaXna-urjm_UY9BqXj=EaDTSA@mail.gmail.com
Discussion: http://postgr.es/m/CAFjFpRcitjfrULr5jfuKWRPsGUX0LQ0k8-yG0Qw2+1LBGNpMdw@mail.gmail.com
This commit is contained in:
Robert Haas
2017-10-06 11:11:10 -04:00
parent fe9ba28ee8
commit f49842d1ee
34 changed files with 4089 additions and 140 deletions
Download Patch File Download Diff File Expand all files Collapse all files

102
src/backend/optimizer/path/joinpath.c
View File

@ -26,9 +26,19 @@
/* Hook for plugins to get control in add_paths_to_joinrel() */
set_join_pathlist_hook_type set_join_pathlist_hook = NULL;
#define PATH_PARAM_BY_REL(path, rel) \
/*
* Paths parameterized by the parent can be considered to be parameterized by
* any of its child.
*/
#define PATH_PARAM_BY_PARENT(path, rel) \
((path)->param_info && bms_overlap(PATH_REQ_OUTER(path), \
(rel)->top_parent_relids))
#define PATH_PARAM_BY_REL_SELF(path, rel) \
((path)->param_info && bms_overlap(PATH_REQ_OUTER(path), (rel)->relids))
#define PATH_PARAM_BY_REL(path, rel) \
(PATH_PARAM_BY_REL_SELF(path, rel) || PATH_PARAM_BY_PARENT(path, rel))
static void try_partial_mergejoin_path(PlannerInfo *root,
RelOptInfo *joinrel,
Path *outer_path,
@ -115,6 +125,19 @@ add_paths_to_joinrel(PlannerInfo *root,
JoinPathExtraData extra;
bool mergejoin_allowed = true;
ListCell *lc;
Relids joinrelids;
/*
* PlannerInfo doesn't contain the SpecialJoinInfos created for joins
* between child relations, even if there is a SpecialJoinInfo node for
* the join between the topmost parents. So, while calculating Relids set
* representing the restriction, consider relids of topmost parent of
* partitions.
*/
if (joinrel->reloptkind == RELOPT_OTHER_JOINREL)
joinrelids = joinrel->top_parent_relids;
else
joinrelids = joinrel->relids;
extra.restrictlist = restrictlist;
extra.mergeclause_list = NIL;
@ -211,16 +234,16 @@ add_paths_to_joinrel(PlannerInfo *root,
* join has already been proven legal.) If the SJ is relevant, it
* presents constraints for joining to anything not in its RHS.
*/
if (bms_overlap(joinrel->relids, sjinfo2->min_righthand) &&
!bms_overlap(joinrel->relids, sjinfo2->min_lefthand))
if (bms_overlap(joinrelids, sjinfo2->min_righthand) &&
!bms_overlap(joinrelids, sjinfo2->min_lefthand))
extra.param_source_rels = bms_join(extra.param_source_rels,
bms_difference(root->all_baserels,
sjinfo2->min_righthand));
/* full joins constrain both sides symmetrically */
if (sjinfo2->jointype == JOIN_FULL &&
bms_overlap(joinrel->relids, sjinfo2->min_lefthand) &&
!bms_overlap(joinrel->relids, sjinfo2->min_righthand))
bms_overlap(joinrelids, sjinfo2->min_lefthand) &&
!bms_overlap(joinrelids, sjinfo2->min_righthand))
extra.param_source_rels = bms_join(extra.param_source_rels,
bms_difference(root->all_baserels,
sjinfo2->min_lefthand));
@ -347,11 +370,25 @@ try_nestloop_path(PlannerInfo *root,
JoinCostWorkspace workspace;
RelOptInfo *innerrel = inner_path->parent;
RelOptInfo *outerrel = outer_path->parent;
Relids innerrelids = innerrel->relids;
Relids outerrelids = outerrel->relids;
Relids innerrelids;
Relids outerrelids;
Relids inner_paramrels = PATH_REQ_OUTER(inner_path);
Relids outer_paramrels = PATH_REQ_OUTER(outer_path);
/*
* Paths are parameterized by top-level parents, so run parameterization
* tests on the parent relids.
*/
if (innerrel->top_parent_relids)
innerrelids = innerrel->top_parent_relids;
else
innerrelids = innerrel->relids;
if (outerrel->top_parent_relids)
outerrelids = outerrel->top_parent_relids;
else
outerrelids = outerrel->relids;
/*
* Check to see if proposed path is still parameterized, and reject if the
* parameterization wouldn't be sensible --- unless allow_star_schema_join
@ -387,6 +424,27 @@ try_nestloop_path(PlannerInfo *root,
workspace.startup_cost, workspace.total_cost,
pathkeys, required_outer))
{
/*
* If the inner path is parameterized, it is parameterized by the
* topmost parent of the outer rel, not the outer rel itself. Fix
* that.
*/
if (PATH_PARAM_BY_PARENT(inner_path, outer_path->parent))
{
inner_path = reparameterize_path_by_child(root, inner_path,
outer_path->parent);
/*
* If we could not translate the path, we can't create nest loop
* path.
*/
if (!inner_path)
{
bms_free(required_outer);
return;
}
}
add_path(joinrel, (Path *)
create_nestloop_path(root,
joinrel,
@ -432,8 +490,20 @@ try_partial_nestloop_path(PlannerInfo *root,
if (inner_path->param_info != NULL)
{
Relids inner_paramrels = inner_path->param_info->ppi_req_outer;
RelOptInfo *outerrel = outer_path->parent;
Relids outerrelids;
if (!bms_is_subset(inner_paramrels, outer_path->parent->relids))
/*
* The inner and outer paths are parameterized, if at all, by the top
* level parents, not the child relations, so we must use those relids
* for our paramaterization tests.
*/
if (outerrel->top_parent_relids)
outerrelids = outerrel->top_parent_relids;
else
outerrelids = outerrel->relids;
if (!bms_is_subset(inner_paramrels, outerrelids))
return;
}
@ -446,6 +516,22 @@ try_partial_nestloop_path(PlannerInfo *root,
if (!add_partial_path_precheck(joinrel, workspace.total_cost, pathkeys))
return;
/*
* If the inner path is parameterized, it is parameterized by the topmost
* parent of the outer rel, not the outer rel itself. Fix that.
*/
if (PATH_PARAM_BY_PARENT(inner_path, outer_path->parent))
{
inner_path = reparameterize_path_by_child(root, inner_path,
outer_path->parent);
/*
* If we could not translate the path, we can't create nest loop path.
*/
if (!inner_path)
return;
}
/* Might be good enough to be worth trying, so let's try it. */
add_partial_path(joinrel, (Path *)
create_nestloop_path(root,