/*
* sort_inner_and_outer
* Create mergejoin join paths by explicitly sorting both the outer and
* inner join relations on each available merge ordering.
*
* 'joinrel' is the join relation
* 'outerrel' is the outer join relation
* 'innerrel' is the inner join relation
* 'restrictlist' contains all of the RestrictInfo nodes for restriction
* clauses that apply to this join
* 'mergeclause_list' is a list of RestrictInfo nodes for available
* mergejoin clauses in this join
* 'jointype' is the type of join to do
*/
static void
sort_inner_and_outer(PlannerInfo *root,
RelOptInfo *joinrel,
RelOptInfo *outerrel,
RelOptInfo *innerrel,
List *restrictlist,
List *mergeclause_list,
JoinType jointype)
{
bool useallclauses;
Path *outer_path;
Path *inner_path;
List *all_pathkeys;
ListCell *l;
/*
* If we are doing a right or full join, we must use *all* the
* mergeclauses as join clauses, else we will not have a valid plan.
*/
switch (jointype)
{
case JOIN_INNER:
case JOIN_LEFT:
case JOIN_IN:
case JOIN_UNIQUE_OUTER:
case JOIN_UNIQUE_INNER:
useallclauses = false;
break;
case JOIN_RIGHT:
case JOIN_FULL:
useallclauses = true;
break;
default:
elog(ERROR, "unrecognized join type: %d",
(int) jointype);
useallclauses = false; /* keep compiler quiet */
break;
}
/*
* We only consider the cheapest-total-cost input paths, since we are
* assuming here that a sort is required. We will consider
* cheapest-startup-cost input paths later, and only if they don't need a
* sort.
*
* If unique-ification is requested, do it and then handle as a plain
* inner join.
*/
outer_path = outerrel->cheapest_total_path;
inner_path = innerrel->cheapest_total_path;
if (jointype == JOIN_UNIQUE_OUTER)
{
outer_path = (Path *) create_unique_path(root, outerrel, outer_path);
jointype = JOIN_INNER;
}
else if (jointype == JOIN_UNIQUE_INNER)
{
inner_path = (Path *) create_unique_path(root, innerrel, inner_path);
jointype = JOIN_INNER;
}
/*
* Each possible ordering of the available mergejoin clauses will generate
* a differently-sorted result path at essentially the same cost. We have
* no basis for choosing one over another at this level of joining, but
* some sort orders may be more useful than others for higher-level
* mergejoins, so it's worth considering multiple orderings.
*
* Actually, it's not quite true that every mergeclause ordering will
* generate a different path order, because some of the clauses may be
* partially redundant (refer to the same EquivalenceClasses). Therefore,
* what we do is convert the mergeclause list to a list of canonical
* pathkeys, and then consider different orderings of the pathkeys.
*
* Generating a path for *every* permutation of the pathkeys doesn't seem
* like a winning strategy; the cost in planning time is too high. For
* now, we generate one path for each pathkey, listing that pathkey first
* and the rest in random order. This should allow at least a one-clause
* mergejoin without re-sorting against any other possible mergejoin
* partner path. But if we've not guessed the right ordering of secondary
* keys, we may end up evaluating clauses as qpquals when they could have
* been done as mergeclauses. (In practice, it's rare that there's more
* than two or three mergeclauses, so expending a huge amount of thought
* on that is probably not worth it.)
*
* The pathkey order returned by select_outer_pathkeys_for_merge() has
* some heuristics behind it (see that function), so be sure to try it
* exactly as-is as well as making variants.
*/
all_pathkeys = select_outer_pathkeys_for_merge(root,
mergeclause_list,
joinrel);
foreach(l, all_pathkeys)
{
List *front_pathkey = (List *) lfirst(l);
List *cur_mergeclauses;
List *outerkeys;
List *innerkeys;
List *merge_pathkeys;
/* Make a pathkey list with this guy first */
if (l != list_head(all_pathkeys))
outerkeys = lcons(front_pathkey,
list_delete_ptr(list_copy(all_pathkeys),
front_pathkey));
else
outerkeys = all_pathkeys; /* no work at first one... */
/* Sort the mergeclauses into the corresponding ordering */
cur_mergeclauses = find_mergeclauses_for_pathkeys(root,
outerkeys,
true,
mergeclause_list);
/* Should have used them all... */
Assert(list_length(cur_mergeclauses) == list_length(mergeclause_list));
/* Build sort pathkeys for the inner side */
innerkeys = make_inner_pathkeys_for_merge(root,
cur_mergeclauses,
outerkeys);
/* Build pathkeys representing output sort order */
merge_pathkeys = build_join_pathkeys(root, joinrel, jointype,
outerkeys);
/*
* And now we can make the path.
*
* Note: it's possible that the cheapest paths will already be sorted
* properly. create_mergejoin_path will detect that case and suppress
* an explicit sort step, so we needn't do so here.
*/
add_path(joinrel, (Path *)
create_mergejoin_path(root,
joinrel,
jointype,
outer_path,
inner_path,
restrictlist,
merge_pathkeys,
cur_mergeclauses,
outerkeys,
innerkeys));
}
/*
* sort_inner_and_outer
* Create mergejoin join paths by explicitly sorting both the outer and
* inner join relations on each available merge ordering.
*
* 'joinrel' is the join relation
* 'outerrel' is the outer join relation
* 'innerrel' is the inner join relation
* 'restrictlist' contains all of the RestrictInfo nodes for restriction
* clauses that apply to this join
* 'mergeclause_list' is a list of RestrictInfo nodes for available
* mergejoin clauses in this join
* 'jointype' is the type of join to do
*/
static void
sort_inner_and_outer(PlannerInfo *root,
RelOptInfo *joinrel,
RelOptInfo *outerrel,
RelOptInfo *innerrel,
List *restrictlist,
List *mergeclause_list,
JoinType jointype)
{
bool useallclauses;
Path *outer_path;
Path *inner_path;
List *all_pathkeys;
ListCell *l;
/*
* If we are doing a right or full join, we must use *all* the
* mergeclauses as join clauses, else we will not have a valid plan.
*/
switch (jointype)
{
case JOIN_INNER:
case JOIN_LEFT:
case JOIN_LASJ:
case JOIN_LASJ_NOTIN:
useallclauses = false;
break;
case JOIN_RIGHT:
case JOIN_FULL:
useallclauses = true;
break;
default:
elog(ERROR, "unrecognized join type: %d",
(int) jointype);
useallclauses = false; /* keep compiler quiet */
break;
}
/*
* We only consider the cheapest-total-cost input paths, since we are
* assuming here that a sort is required. We will consider
* cheapest-startup-cost input paths later, and only if they don't need a
* sort.
*/
outer_path = outerrel->cheapest_total_path;
inner_path = innerrel->cheapest_total_path;
/*
* Each possible ordering of the available mergejoin clauses will generate
* a differently-sorted result path at essentially the same cost. We have
* no basis for choosing one over another at this level of joining, but
* some sort orders may be more useful than others for higher-level
* mergejoins, so it's worth considering multiple orderings.
*
* Actually, it's not quite true that every mergeclause ordering will
* generate a different path order, because some of the clauses may be
* redundant. Therefore, what we do is convert the mergeclause list to a
* list of canonical pathkeys, and then consider different orderings of
* the pathkeys.
*
* Generating a path for *every* permutation of the pathkeys doesn't seem
* like a winning strategy; the cost in planning time is too high. For
* now, we generate one path for each pathkey, listing that pathkey first
* and the rest in random order. This should allow at least a one-clause
* mergejoin without re-sorting against any other possible mergejoin
* partner path. But if we've not guessed the right ordering of secondary
* keys, we may end up evaluating clauses as qpquals when they could have
* been done as mergeclauses. We need to figure out a better way. (Two
* possible approaches: look at all the relevant index relations to
* suggest plausible sort orders, or make just one output path and somehow
* mark it as having a sort-order that can be rearranged freely.)
*/
all_pathkeys = make_pathkeys_for_mergeclauses(root,
mergeclause_list,
outerrel);
foreach(l, all_pathkeys)
{
List *front_pathkey = (List *) lfirst(l);
List *cur_pathkeys;
List *cur_mergeclauses;
List *outerkeys;
List *innerkeys;
List *merge_pathkeys;
/* Make a pathkey list with this guy first. */
if (l != list_head(all_pathkeys))
cur_pathkeys = lcons(front_pathkey,
list_delete_ptr(list_copy(all_pathkeys),
front_pathkey));
else
cur_pathkeys = all_pathkeys; /* no work at first one... */
/*
* Select mergeclause(s) that match this sort ordering. If we had
* redundant merge clauses then we will get a subset of the original
* clause list. There had better be some match, however...
*/
cur_mergeclauses = find_mergeclauses_for_pathkeys(root,
cur_pathkeys,
mergeclause_list);
Assert(cur_mergeclauses != NIL);
/* Forget it if can't use all the clauses in right/full join */
if (useallclauses &&
list_length(cur_mergeclauses) != list_length(mergeclause_list))
continue;
/*
* Build sort pathkeys for both sides.
*
* Note: it's possible that the cheapest paths will already be sorted
* properly. create_mergejoin_path will detect that case and suppress
* an explicit sort step, so we needn't do so here.
*/
outerkeys = make_pathkeys_for_mergeclauses(root,
cur_mergeclauses,
outerrel);
innerkeys = make_pathkeys_for_mergeclauses(root,
cur_mergeclauses,
innerrel);
/* Build pathkeys representing output sort order. */
merge_pathkeys = build_join_pathkeys(root, joinrel, jointype,
outerkeys);
/*
* And now we can make the path.
*/
add_path(root, joinrel, (Path *)
create_mergejoin_path(root,
joinrel,
jointype,
outer_path,
inner_path,
restrictlist,
merge_pathkeys,
cur_mergeclauses,
mergeclause_list,
outerkeys,
innerkeys));
}