* core.c
* Routines copied from PostgreSQL core distribution.
*
+ * The main purpose of this files is having access to static functions in core.
+ * Another purpose is tweaking functions behavior by replacing part of them by
+ * macro definitions. See at the end of pg_hint_plan.c for details. Anyway,
+ * this file *must* contain required functions without making any change.
+ *
+ * This file contains the following functions from corresponding files.
+ *
* src/backend/optimizer/path/allpaths.c
- * set_append_rel_pathlist()
- * generate_mergeappend_paths()
- * get_cheapest_parameterized_child_path()
- * accumulate_append_subpath()
- * standard_join_search()
+ *
+ * public functions:
+ * standard_join_search(): This funcion is not static. The reason for
+ * including this function is make_rels_by_clause_joins. In order to
+ * avoid generating apparently unwanted join combination, we decided to
+ * change the behavior of make_join_rel, which is called under this
+ * function.
+ *
+ * static functions:
+ * set_plain_rel_pathlist()
+ * set_append_rel_pathlist()
+ * create_plain_partial_paths()
*
* src/backend/optimizer/path/joinrels.c
- * join_search_one_level()
+ *
+ * public functions:
+ * join_search_one_level(): We have to modify this to call my definition of
+ * make_rels_by_clause_joins.
+ *
+ * static functions:
* make_rels_by_clause_joins()
* make_rels_by_clauseless_joins()
* join_is_legal()
* has_join_restriction()
- * is_dummy_rel()
- * mark_dummy_rel()
* restriction_is_constant_false()
+ * build_child_join_sjinfo()
+ * get_matching_part_pairs()
+ * compute_partition_bounds()
+ * try_partitionwise_join()
*
- * Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*-------------------------------------------------------------------------
*/
+static void populate_joinrel_with_paths(PlannerInfo *root, RelOptInfo *rel1,
+ RelOptInfo *rel2, RelOptInfo *joinrel,
+ SpecialJoinInfo *sjinfo, List *restrictlist);
+
+/*
+ * set_plain_rel_pathlist
+ * Build access paths for a plain relation (no subquery, no inheritance)
+ */
+static void
+set_plain_rel_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
+{
+ Relids required_outer;
+
+ /*
+ * We don't support pushing join clauses into the quals of a seqscan, but
+ * it could still have required parameterization due to LATERAL refs in
+ * its tlist.
+ */
+ required_outer = rel->lateral_relids;
+
+ /* Consider sequential scan */
+ add_path(rel, create_seqscan_path(root, rel, required_outer, 0));
+
+ /* If appropriate, consider parallel sequential scan */
+ if (rel->consider_parallel && required_outer == NULL)
+ create_plain_partial_paths(root, rel);
+
+ /* Consider index scans */
+ create_index_paths(root, rel);
+
+ /* Consider TID scans */
+ create_tidscan_paths(root, rel);
+}
+
+
/*
* set_append_rel_pathlist
* Build access paths for an "append relation"
{
int parentRTindex = rti;
List *live_childrels = NIL;
- List *subpaths = NIL;
- bool subpaths_valid = true;
- List *partial_subpaths = NIL;
- bool partial_subpaths_valid = true;
- List *all_child_pathkeys = NIL;
- List *all_child_outers = NIL;
ListCell *l;
/*
* Generate access paths for each member relation, and remember the
- * cheapest path for each one. Also, identify all pathkeys (orderings)
- * and parameterizations (required_outer sets) available for the member
- * relations.
+ * non-dummy children.
*/
foreach(l, root->append_rel_list)
{
int childRTindex;
RangeTblEntry *childRTE;
RelOptInfo *childrel;
- ListCell *lcp;
/* append_rel_list contains all append rels; ignore others */
if (appinfo->parent_relid != parentRTindex)
if (IS_DUMMY_REL(childrel))
continue;
+ /* Bubble up childrel's partitioned children. */
+ if (rel->part_scheme)
+ rel->partitioned_child_rels =
+ list_concat(rel->partitioned_child_rels,
+ childrel->partitioned_child_rels);
+
/*
* Child is live, so add it to the live_childrels list for use below.
*/
live_childrels = lappend(live_childrels, childrel);
-
- /*
- * If child has an unparameterized cheapest-total path, add that to
- * the unparameterized Append path we are constructing for the parent.
- * If not, there's no workable unparameterized path.
- */
- if (childrel->cheapest_total_path->param_info == NULL)
- subpaths = accumulate_append_subpath(subpaths,
- childrel->cheapest_total_path);
- else
- subpaths_valid = false;
-
- /* Same idea, but for a partial plan. */
- if (childrel->partial_pathlist != NIL)
- partial_subpaths = accumulate_append_subpath(partial_subpaths,
- linitial(childrel->partial_pathlist));
- else
- partial_subpaths_valid = false;
-
- /*
- * Collect lists of all the available path orderings and
- * parameterizations for all the children. We use these as a
- * heuristic to indicate which sort orderings and parameterizations we
- * should build Append and MergeAppend paths for.
- */
- foreach(lcp, childrel->pathlist)
- {
- Path *childpath = (Path *) lfirst(lcp);
- List *childkeys = childpath->pathkeys;
- Relids childouter = PATH_REQ_OUTER(childpath);
-
- /* Unsorted paths don't contribute to pathkey list */
- if (childkeys != NIL)
- {
- ListCell *lpk;
- bool found = false;
-
- /* Have we already seen this ordering? */
- foreach(lpk, all_child_pathkeys)
- {
- List *existing_pathkeys = (List *) lfirst(lpk);
-
- if (compare_pathkeys(existing_pathkeys,
- childkeys) == PATHKEYS_EQUAL)
- {
- found = true;
- break;
- }
- }
- if (!found)
- {
- /* No, so add it to all_child_pathkeys */
- all_child_pathkeys = lappend(all_child_pathkeys,
- childkeys);
- }
- }
-
- /* Unparameterized paths don't contribute to param-set list */
- if (childouter)
- {
- ListCell *lco;
- bool found = false;
-
- /* Have we already seen this param set? */
- foreach(lco, all_child_outers)
- {
- Relids existing_outers = (Relids) lfirst(lco);
-
- if (bms_equal(existing_outers, childouter))
- {
- found = true;
- break;
- }
- }
- if (!found)
- {
- /* No, so add it to all_child_outers */
- all_child_outers = lappend(all_child_outers,
- childouter);
- }
- }
- }
- }
-
- /*
- * If we found unparameterized paths for all children, build an unordered,
- * unparameterized Append path for the rel. (Note: this is correct even
- * if we have zero or one live subpath due to constraint exclusion.)
- */
- if (subpaths_valid)
- add_path(rel, (Path *) create_append_path(rel, subpaths, NULL, 0));
-
- /*
- * Consider an append of partial unordered, unparameterized partial paths.
- */
- if (partial_subpaths_valid)
- {
- AppendPath *appendpath;
- ListCell *lc;
- int parallel_workers = 0;
-
- /*
- * Decide on the number of workers to request for this append path.
- * For now, we just use the maximum value from among the members. It
- * might be useful to use a higher number if the Append node were
- * smart enough to spread out the workers, but it currently isn't.
- */
- foreach(lc, partial_subpaths)
- {
- Path *path = lfirst(lc);
-
- parallel_workers = Max(parallel_workers, path->parallel_workers);
- }
- Assert(parallel_workers > 0);
-
- /* Generate a partial append path. */
- appendpath = create_append_path(rel, partial_subpaths, NULL,
- parallel_workers);
- add_partial_path(rel, (Path *) appendpath);
- }
-
- /*
- * Also build unparameterized MergeAppend paths based on the collected
- * list of child pathkeys.
- */
- if (subpaths_valid)
- generate_mergeappend_paths(root, rel, live_childrels,
- all_child_pathkeys);
-
- /*
- * Build Append paths for each parameterization seen among the child rels.
- * (This may look pretty expensive, but in most cases of practical
- * interest, the child rels will expose mostly the same parameterizations,
- * so that not that many cases actually get considered here.)
- *
- * The Append node itself cannot enforce quals, so all qual checking must
- * be done in the child paths. This means that to have a parameterized
- * Append path, we must have the exact same parameterization for each
- * child path; otherwise some children might be failing to check the
- * moved-down quals. To make them match up, we can try to increase the
- * parameterization of lesser-parameterized paths.
- */
- foreach(l, all_child_outers)
- {
- Relids required_outer = (Relids) lfirst(l);
- ListCell *lcr;
-
- /* Select the child paths for an Append with this parameterization */
- subpaths = NIL;
- subpaths_valid = true;
- foreach(lcr, live_childrels)
- {
- RelOptInfo *childrel = (RelOptInfo *) lfirst(lcr);
- Path *subpath;
-
- subpath = get_cheapest_parameterized_child_path(root,
- childrel,
- required_outer);
- if (subpath == NULL)
- {
- /* failed to make a suitable path for this child */
- subpaths_valid = false;
- break;
- }
- subpaths = accumulate_append_subpath(subpaths, subpath);
- }
-
- if (subpaths_valid)
- add_path(rel, (Path *)
- create_append_path(rel, subpaths, required_outer, 0));
- }
-}
-
-/*
- * generate_mergeappend_paths
- * Generate MergeAppend paths for an append relation
- *
- * Generate a path for each ordering (pathkey list) appearing in
- * all_child_pathkeys.
- *
- * We consider both cheapest-startup and cheapest-total cases, ie, for each
- * interesting ordering, collect all the cheapest startup subpaths and all the
- * cheapest total paths, and build a MergeAppend path for each case.
- *
- * We don't currently generate any parameterized MergeAppend paths. While
- * it would not take much more code here to do so, it's very unclear that it
- * is worth the planning cycles to investigate such paths: there's little
- * use for an ordered path on the inside of a nestloop. In fact, it's likely
- * that the current coding of add_path would reject such paths out of hand,
- * because add_path gives no credit for sort ordering of parameterized paths,
- * and a parameterized MergeAppend is going to be more expensive than the
- * corresponding parameterized Append path. If we ever try harder to support
- * parameterized mergejoin plans, it might be worth adding support for
- * parameterized MergeAppends to feed such joins. (See notes in
- * optimizer/README for why that might not ever happen, though.)
- */
-static void
-generate_mergeappend_paths(PlannerInfo *root, RelOptInfo *rel,
- List *live_childrels,
- List *all_child_pathkeys)
-{
- ListCell *lcp;
-
- foreach(lcp, all_child_pathkeys)
- {
- List *pathkeys = (List *) lfirst(lcp);
- List *startup_subpaths = NIL;
- List *total_subpaths = NIL;
- bool startup_neq_total = false;
- ListCell *lcr;
-
- /* Select the child paths for this ordering... */
- foreach(lcr, live_childrels)
- {
- RelOptInfo *childrel = (RelOptInfo *) lfirst(lcr);
- Path *cheapest_startup,
- *cheapest_total;
-
- /* Locate the right paths, if they are available. */
- cheapest_startup =
- get_cheapest_path_for_pathkeys(childrel->pathlist,
- pathkeys,
- NULL,
- STARTUP_COST);
- cheapest_total =
- get_cheapest_path_for_pathkeys(childrel->pathlist,
- pathkeys,
- NULL,
- TOTAL_COST);
-
- /*
- * If we can't find any paths with the right order just use the
- * cheapest-total path; we'll have to sort it later.
- */
- if (cheapest_startup == NULL || cheapest_total == NULL)
- {
- cheapest_startup = cheapest_total =
- childrel->cheapest_total_path;
- /* Assert we do have an unparameterized path for this child */
- Assert(cheapest_total->param_info == NULL);
- }
-
- /*
- * Notice whether we actually have different paths for the
- * "cheapest" and "total" cases; frequently there will be no point
- * in two create_merge_append_path() calls.
- */
- if (cheapest_startup != cheapest_total)
- startup_neq_total = true;
-
- startup_subpaths =
- accumulate_append_subpath(startup_subpaths, cheapest_startup);
- total_subpaths =
- accumulate_append_subpath(total_subpaths, cheapest_total);
- }
-
- /* ... and build the MergeAppend paths */
- add_path(rel, (Path *) create_merge_append_path(root,
- rel,
- startup_subpaths,
- pathkeys,
- NULL));
- if (startup_neq_total)
- add_path(rel, (Path *) create_merge_append_path(root,
- rel,
- total_subpaths,
- pathkeys,
- NULL));
- }
-}
-
-/*
- * get_cheapest_parameterized_child_path
- * Get cheapest path for this relation that has exactly the requested
- * parameterization.
- *
- * Returns NULL if unable to create such a path.
- */
-static Path *
-get_cheapest_parameterized_child_path(PlannerInfo *root, RelOptInfo *rel,
- Relids required_outer)
-{
- Path *cheapest;
- ListCell *lc;
-
- /*
- * Look up the cheapest existing path with no more than the needed
- * parameterization. If it has exactly the needed parameterization, we're
- * done.
- */
- cheapest = get_cheapest_path_for_pathkeys(rel->pathlist,
- NIL,
- required_outer,
- TOTAL_COST);
- Assert(cheapest != NULL);
- if (bms_equal(PATH_REQ_OUTER(cheapest), required_outer))
- return cheapest;
-
- /*
- * Otherwise, we can "reparameterize" an existing path to match the given
- * parameterization, which effectively means pushing down additional
- * joinquals to be checked within the path's scan. However, some existing
- * paths might check the available joinquals already while others don't;
- * therefore, it's not clear which existing path will be cheapest after
- * reparameterization. We have to go through them all and find out.
- */
- cheapest = NULL;
- foreach(lc, rel->pathlist)
- {
- Path *path = (Path *) lfirst(lc);
-
- /* Can't use it if it needs more than requested parameterization */
- if (!bms_is_subset(PATH_REQ_OUTER(path), required_outer))
- continue;
-
- /*
- * Reparameterization can only increase the path's cost, so if it's
- * already more expensive than the current cheapest, forget it.
- */
- if (cheapest != NULL &&
- compare_path_costs(cheapest, path, TOTAL_COST) <= 0)
- continue;
-
- /* Reparameterize if needed, then recheck cost */
- if (!bms_equal(PATH_REQ_OUTER(path), required_outer))
- {
- path = reparameterize_path(root, path, required_outer, 1.0);
- if (path == NULL)
- continue; /* failed to reparameterize this one */
- Assert(bms_equal(PATH_REQ_OUTER(path), required_outer));
-
- if (cheapest != NULL &&
- compare_path_costs(cheapest, path, TOTAL_COST) <= 0)
- continue;
- }
-
- /* We have a new best path */
- cheapest = path;
}
- /* Return the best path, or NULL if we found no suitable candidate */
- return cheapest;
+ /* Add paths to the append relation. */
+ add_paths_to_append_rel(root, rel, live_childrels);
}
-/*
- * accumulate_append_subpath
- * Add a subpath to the list being built for an Append or MergeAppend
- *
- * It's possible that the child is itself an Append or MergeAppend path, in
- * which case we can "cut out the middleman" and just add its child paths to
- * our own list. (We don't try to do this earlier because we need to apply
- * both levels of transformation to the quals.)
- *
- * Note that if we omit a child MergeAppend in this way, we are effectively
- * omitting a sort step, which seems fine: if the parent is to be an Append,
- * its result would be unsorted anyway, while if the parent is to be a
- * MergeAppend, there's no point in a separate sort on a child.
- */
-static List *
-accumulate_append_subpath(List *subpaths, Path *path)
-{
- if (IsA(path, AppendPath))
- {
- AppendPath *apath = (AppendPath *) path;
-
- /* list_copy is important here to avoid sharing list substructure */
- return list_concat(subpaths, list_copy(apath->subpaths));
- }
- else if (IsA(path, MergeAppendPath))
- {
- MergeAppendPath *mpath = (MergeAppendPath *) path;
-
- /* list_copy is important here to avoid sharing list substructure */
- return list_concat(subpaths, list_copy(mpath->subpaths));
- }
- else
- return lappend(subpaths, path);
-}
/*
* standard_join_search
join_search_one_level(root, lev);
/*
- * Run generate_gather_paths() for each just-processed joinrel. We
- * could not do this earlier because both regular and partial paths
- * can get added to a particular joinrel at multiple times within
- * join_search_one_level. After that, we're done creating paths for
- * the joinrel, so run set_cheapest().
+ * Run generate_partitionwise_join_paths() and generate_gather_paths()
+ * for each just-processed joinrel. We could not do this earlier
+ * because both regular and partial paths can get added to a
+ * particular joinrel at multiple times within join_search_one_level.
+ *
+ * After that, we're done creating paths for the joinrel, so run
+ * set_cheapest().
*/
foreach(lc, root->join_rel_level[lev])
{
rel = (RelOptInfo *) lfirst(lc);
- /* Create GatherPaths for any useful partial paths for rel */
- generate_gather_paths(root, rel);
+ /* Create paths for partitionwise joins. */
+ generate_partitionwise_join_paths(root, rel);
+
+ /*
+ * Except for the topmost scan/join rel, consider gathering
+ * partial paths. We'll do the same for the topmost scan/join rel
+ * once we know the final targetlist (see grouping_planner).
+ */
+ if (lev < levels_needed)
+ generate_useful_gather_paths(root, rel, false);
/* Find and save the cheapest paths for this rel */
set_cheapest(rel);
return rel;
}
+
/*
* create_plain_partial_paths
* Build partial access paths for parallel scan of a plain relation
{
int parallel_workers;
- parallel_workers = compute_parallel_worker(rel, rel->pages);
+ parallel_workers = compute_parallel_worker(rel, rel->pages, -1,
+ max_parallel_workers_per_gather);
/* If any limit was set to zero, the user doesn't want a parallel scan. */
if (parallel_workers <= 0)
add_partial_path(rel, create_seqscan_path(root, rel, NULL, parallel_workers));
}
-/*
- * Compute the number of parallel workers that should be used to scan a
- * relation. "pages" is the number of pages from the relation that we
- * expect to scan.
- */
-static int
-compute_parallel_worker(RelOptInfo *rel, BlockNumber pages)
-{
- int parallel_workers;
-
- /*
- * If the user has set the parallel_workers reloption, use that; otherwise
- * select a default number of workers.
- */
- if (rel->rel_parallel_workers != -1)
- parallel_workers = rel->rel_parallel_workers;
- else
- {
- int parallel_threshold;
-
- /*
- * If this relation is too small to be worth a parallel scan, just
- * return without doing anything ... unless it's an inheritance child.
- * In that case, we want to generate a parallel path here anyway. It
- * might not be worthwhile just for this relation, but when combined
- * with all of its inheritance siblings it may well pay off.
- */
- if (pages < (BlockNumber) min_parallel_relation_size &&
- rel->reloptkind == RELOPT_BASEREL)
- return 0;
-
- /*
- * Select the number of workers based on the log of the size of the
- * relation. This probably needs to be a good deal more
- * sophisticated, but we need something here for now. Note that the
- * upper limit of the min_parallel_relation_size GUC is chosen to
- * prevent overflow here.
- */
- parallel_workers = 1;
- parallel_threshold = Max(min_parallel_relation_size, 1);
- while (pages >= (BlockNumber) (parallel_threshold * 3))
- {
- parallel_workers++;
- parallel_threshold *= 3;
- if (parallel_threshold > INT_MAX / 3)
- break; /* avoid overflow */
- }
- }
-
- /*
- * In no case use more than max_parallel_workers_per_gather workers.
- */
- parallel_workers = Min(parallel_workers, max_parallel_workers_per_gather);
-
- return parallel_workers;
-}
-
/*
* join_search_one_level
* to each initial rel they don't already include but have a join
* clause or restriction with.
*/
+ List *other_rels_list;
ListCell *other_rels;
if (level == 2) /* consider remaining initial rels */
- other_rels = lnext(r);
- else /* consider all initial rels */
- other_rels = list_head(joinrels[1]);
+ {
+ other_rels_list = joinrels[level - 1];
+ other_rels = lnext(other_rels_list, r);
+ }
+ else /* consider all initial rels */
+ {
+ other_rels_list = joinrels[1];
+ other_rels = list_head(other_rels_list);
+ }
make_rels_by_clause_joins(root,
old_rel,
+ other_rels_list,
other_rels);
}
else
*/
make_rels_by_clauseless_joins(root,
old_rel,
- list_head(joinrels[1]));
+ joinrels[1]);
}
}
foreach(r, joinrels[k])
{
RelOptInfo *old_rel = (RelOptInfo *) lfirst(r);
+ List *other_rels_list;
ListCell *other_rels;
ListCell *r2;
continue;
if (k == other_level)
- other_rels = lnext(r); /* only consider remaining rels */
+ {
+ /* only consider remaining rels */
+ other_rels_list = joinrels[k];
+ other_rels = lnext(other_rels_list, r);
+ }
else
- other_rels = list_head(joinrels[other_level]);
+ {
+ other_rels_list = joinrels[other_level];
+ other_rels = list_head(other_rels_list);
+ }
- for_each_cell(r2, other_rels)
+ for_each_cell(r2, other_rels_list, other_rels)
{
RelOptInfo *new_rel = (RelOptInfo *) lfirst(r2);
make_rels_by_clauseless_joins(root,
old_rel,
- list_head(joinrels[1]));
+ joinrels[1]);
}
/*----------
}
}
+
/*
* make_rels_by_clause_joins
* Build joins between the given relation 'old_rel' and other relations
* automatically ensures that each new joinrel is only added to the list once.
*
* 'old_rel' is the relation entry for the relation to be joined
- * 'other_rels': the first cell in a linked list containing the other
+ * 'other_rels_list': a list containing the other
* rels to be considered for joining
+ * 'other_rels': the first cell to be considered
*
* Currently, this is only used with initial rels in other_rels, but it
* will work for joining to joinrels too.
static void
make_rels_by_clause_joins(PlannerInfo *root,
RelOptInfo *old_rel,
+ List *other_rels_list,
ListCell *other_rels)
{
ListCell *l;
- for_each_cell(l, other_rels)
+ for_each_cell(l, other_rels_list, other_rels)
{
RelOptInfo *other_rel = (RelOptInfo *) lfirst(l);
}
}
+
/*
* make_rels_by_clauseless_joins
* Given a relation 'old_rel' and a list of other relations
* The join rels are returned in root->join_rel_level[join_cur_level].
*
* 'old_rel' is the relation entry for the relation to be joined
- * 'other_rels': the first cell of a linked list containing the
- * other rels to be considered for joining
+ * 'other_rels': a list containing the other rels to be considered for joining
*
* Currently, this is only used with initial rels in other_rels, but it would
* work for joining to joinrels too.
static void
make_rels_by_clauseless_joins(PlannerInfo *root,
RelOptInfo *old_rel,
- ListCell *other_rels)
+ List *other_rels)
{
ListCell *l;
- for_each_cell(l, other_rels)
+ foreach(l, other_rels)
{
RelOptInfo *other_rel = (RelOptInfo *) lfirst(l);
}
}
+
/*
* join_is_legal
* Determine whether a proposed join is legal given the query's
*
* On success, *sjinfo_p is set to NULL if this is to be a plain inner join,
* else it's set to point to the associated SpecialJoinInfo node. Also,
- * *reversed_p is set TRUE if the given relations need to be swapped to
+ * *reversed_p is set true if the given relations need to be swapped to
* match the SpecialJoinInfo node.
*/
static bool
{
SpecialJoinInfo *sjinfo = (SpecialJoinInfo *) lfirst(l);
+ /* ignore full joins --- their ordering is predetermined */
+ if (sjinfo->jointype == JOIN_FULL)
+ continue;
+
if (bms_overlap(sjinfo->min_lefthand, join_plus_rhs) &&
!bms_is_subset(sjinfo->min_righthand, join_plus_rhs))
{
join_plus_rhs = bms_add_members(join_plus_rhs,
- sjinfo->min_righthand);
- more = true;
- }
- /* full joins constrain both sides symmetrically */
- if (sjinfo->jointype == JOIN_FULL &&
- bms_overlap(sjinfo->min_righthand, join_plus_rhs) &&
- !bms_is_subset(sjinfo->min_lefthand, join_plus_rhs))
- {
- join_plus_rhs = bms_add_members(join_plus_rhs,
- sjinfo->min_lefthand);
+ sjinfo->min_righthand);
more = true;
}
}
return true;
}
+
/*
* has_join_restriction
* Detect whether the specified relation has join-order restrictions,
return false;
}
-/*
- * is_dummy_rel --- has relation been proven empty?
- */
-static bool
-is_dummy_rel(RelOptInfo *rel)
-{
- return IS_DUMMY_REL(rel);
-}
-
-/*
- * Mark a relation as proven empty.
- *
- * During GEQO planning, this can get invoked more than once on the same
- * baserel struct, so it's worth checking to see if the rel is already marked
- * dummy.
- *
- * Also, when called during GEQO join planning, we are in a short-lived
- * memory context. We must make sure that the dummy path attached to a
- * baserel survives the GEQO cycle, else the baserel is trashed for future
- * GEQO cycles. On the other hand, when we are marking a joinrel during GEQO,
- * we don't want the dummy path to clutter the main planning context. Upshot
- * is that the best solution is to explicitly make the dummy path in the same
- * context the given RelOptInfo is in.
- */
-static void
-mark_dummy_rel(RelOptInfo *rel)
-{
- MemoryContext oldcontext;
-
- /* Already marked? */
- if (is_dummy_rel(rel))
- return;
-
- /* No, so choose correct context to make the dummy path in */
- oldcontext = MemoryContextSwitchTo(GetMemoryChunkContext(rel));
-
- /* Set dummy size estimate */
- rel->rows = 0;
-
- /* Evict any previously chosen paths */
- rel->pathlist = NIL;
- rel->partial_pathlist = NIL;
-
- /* Set up the dummy path */
- add_path(rel, (Path *) create_append_path(rel, NIL, NULL, 0));
-
- /* Set or update cheapest_total_path and related fields */
- set_cheapest(rel);
-
- MemoryContextSwitchTo(oldcontext);
-}
/*
* restriction_is_constant_false --- is a restrictlist just FALSE?
* decide there's no match for an outer row, which is pretty stupid. So,
* we need to detect the case.
*
- * If only_pushed_down is TRUE, then consider only pushed-down quals.
+ * If only_pushed_down is true, then consider only quals that are pushed-down
+ * from the point of view of the joinrel.
*/
static bool
-restriction_is_constant_false(List *restrictlist, bool only_pushed_down)
+restriction_is_constant_false(List *restrictlist,
+ RelOptInfo *joinrel,
+ bool only_pushed_down)
{
ListCell *lc;
*/
foreach(lc, restrictlist)
{
- RestrictInfo *rinfo = (RestrictInfo *) lfirst(lc);
+ RestrictInfo *rinfo = lfirst_node(RestrictInfo, lc);
- Assert(IsA(rinfo, RestrictInfo));
- if (only_pushed_down && !rinfo->is_pushed_down)
+ if (only_pushed_down && !RINFO_IS_PUSHED_DOWN(rinfo, joinrel->relids))
continue;
if (rinfo->clause && IsA(rinfo->clause, Const))
}
return false;
}
+
+
+/*
+ * Construct the SpecialJoinInfo for a child-join by translating
+ * SpecialJoinInfo for the join between parents. left_relids and right_relids
+ * are the relids of left and right side of the join respectively.
+ */
+static SpecialJoinInfo *
+build_child_join_sjinfo(PlannerInfo *root, SpecialJoinInfo *parent_sjinfo,
+ Relids left_relids, Relids right_relids)
+{
+ SpecialJoinInfo *sjinfo = makeNode(SpecialJoinInfo);
+ AppendRelInfo **left_appinfos;
+ int left_nappinfos;
+ AppendRelInfo **right_appinfos;
+ int right_nappinfos;
+
+ memcpy(sjinfo, parent_sjinfo, sizeof(SpecialJoinInfo));
+ left_appinfos = find_appinfos_by_relids(root, left_relids,
+ &left_nappinfos);
+ right_appinfos = find_appinfos_by_relids(root, right_relids,
+ &right_nappinfos);
+
+ sjinfo->min_lefthand = adjust_child_relids(sjinfo->min_lefthand,
+ left_nappinfos, left_appinfos);
+ sjinfo->min_righthand = adjust_child_relids(sjinfo->min_righthand,
+ right_nappinfos,
+ right_appinfos);
+ sjinfo->syn_lefthand = adjust_child_relids(sjinfo->syn_lefthand,
+ left_nappinfos, left_appinfos);
+ sjinfo->syn_righthand = adjust_child_relids(sjinfo->syn_righthand,
+ right_nappinfos,
+ right_appinfos);
+ sjinfo->semi_rhs_exprs = (List *) adjust_appendrel_attrs(root,
+ (Node *) sjinfo->semi_rhs_exprs,
+ right_nappinfos,
+ right_appinfos);
+
+ pfree(left_appinfos);
+ pfree(right_appinfos);
+
+ return sjinfo;
+}
+
+
+/*
+ * get_matching_part_pairs
+ * Generate pairs of partitions to be joined from inputs
+ */
+static void
+get_matching_part_pairs(PlannerInfo *root, RelOptInfo *joinrel,
+ RelOptInfo *rel1, RelOptInfo *rel2,
+ List **parts1, List **parts2)
+{
+ bool rel1_is_simple = IS_SIMPLE_REL(rel1);
+ bool rel2_is_simple = IS_SIMPLE_REL(rel2);
+ int cnt_parts;
+
+ *parts1 = NIL;
+ *parts2 = NIL;
+
+ for (cnt_parts = 0; cnt_parts < joinrel->nparts; cnt_parts++)
+ {
+ RelOptInfo *child_joinrel = joinrel->part_rels[cnt_parts];
+ RelOptInfo *child_rel1;
+ RelOptInfo *child_rel2;
+ Relids child_relids1;
+ Relids child_relids2;
+
+ /*
+ * If this segment of the join is empty, it means that this segment
+ * was ignored when previously creating child-join paths for it in
+ * try_partitionwise_join() as it would not contribute to the join
+ * result, due to one or both inputs being empty; add NULL to each of
+ * the given lists so that this segment will be ignored again in that
+ * function.
+ */
+ if (!child_joinrel)
+ {
+ *parts1 = lappend(*parts1, NULL);
+ *parts2 = lappend(*parts2, NULL);
+ continue;
+ }
+
+ /*
+ * Get a relids set of partition(s) involved in this join segment that
+ * are from the rel1 side.
+ */
+ child_relids1 = bms_intersect(child_joinrel->relids,
+ rel1->all_partrels);
+ Assert(bms_num_members(child_relids1) == bms_num_members(rel1->relids));
+
+ /*
+ * Get a child rel for rel1 with the relids. Note that we should have
+ * the child rel even if rel1 is a join rel, because in that case the
+ * partitions specified in the relids would have matching/overlapping
+ * boundaries, so the specified partitions should be considered as
+ * ones to be joined when planning partitionwise joins of rel1,
+ * meaning that the child rel would have been built by the time we get
+ * here.
+ */
+ if (rel1_is_simple)
+ {
+ int varno = bms_singleton_member(child_relids1);
+
+ child_rel1 = find_base_rel(root, varno);
+ }
+ else
+ child_rel1 = find_join_rel(root, child_relids1);
+ Assert(child_rel1);
+
+ /*
+ * Get a relids set of partition(s) involved in this join segment that
+ * are from the rel2 side.
+ */
+ child_relids2 = bms_intersect(child_joinrel->relids,
+ rel2->all_partrels);
+ Assert(bms_num_members(child_relids2) == bms_num_members(rel2->relids));
+
+ /*
+ * Get a child rel for rel2 with the relids. See above comments.
+ */
+ if (rel2_is_simple)
+ {
+ int varno = bms_singleton_member(child_relids2);
+
+ child_rel2 = find_base_rel(root, varno);
+ }
+ else
+ child_rel2 = find_join_rel(root, child_relids2);
+ Assert(child_rel2);
+
+ /*
+ * The join of rel1 and rel2 is legal, so is the join of the child
+ * rels obtained above; add them to the given lists as a join pair
+ * producing this join segment.
+ */
+ *parts1 = lappend(*parts1, child_rel1);
+ *parts2 = lappend(*parts2, child_rel2);
+ }
+}
+
+
+/*
+ * compute_partition_bounds
+ * Compute the partition bounds for a join rel from those for inputs
+ */
+static void
+compute_partition_bounds(PlannerInfo *root, RelOptInfo *rel1,
+ RelOptInfo *rel2, RelOptInfo *joinrel,
+ SpecialJoinInfo *parent_sjinfo,
+ List **parts1, List **parts2)
+{
+ /*
+ * If we don't have the partition bounds for the join rel yet, try to
+ * compute those along with pairs of partitions to be joined.
+ */
+ if (joinrel->nparts == -1)
+ {
+ PartitionScheme part_scheme = joinrel->part_scheme;
+ PartitionBoundInfo boundinfo = NULL;
+ int nparts = 0;
+
+ Assert(joinrel->boundinfo == NULL);
+ Assert(joinrel->part_rels == NULL);
+
+ /*
+ * See if the partition bounds for inputs are exactly the same, in
+ * which case we don't need to work hard: the join rel have the same
+ * partition bounds as inputs, and the partitions with the same
+ * cardinal positions form the pairs.
+ *
+ * Note: even in cases where one or both inputs have merged bounds, it
+ * would be possible for both the bounds to be exactly the same, but
+ * it seems unlikely to be worth the cycles to check.
+ */
+ if (!rel1->partbounds_merged &&
+ !rel2->partbounds_merged &&
+ rel1->nparts == rel2->nparts &&
+ partition_bounds_equal(part_scheme->partnatts,
+ part_scheme->parttyplen,
+ part_scheme->parttypbyval,
+ rel1->boundinfo, rel2->boundinfo))
+ {
+ boundinfo = rel1->boundinfo;
+ nparts = rel1->nparts;
+ }
+ else
+ {
+ /* Try merging the partition bounds for inputs. */
+ boundinfo = partition_bounds_merge(part_scheme->partnatts,
+ part_scheme->partsupfunc,
+ part_scheme->partcollation,
+ rel1, rel2,
+ parent_sjinfo->jointype,
+ parts1, parts2);
+ if (boundinfo == NULL)
+ {
+ joinrel->nparts = 0;
+ return;
+ }
+ nparts = list_length(*parts1);
+ joinrel->partbounds_merged = true;
+ }
+
+ Assert(nparts > 0);
+ joinrel->boundinfo = boundinfo;
+ joinrel->nparts = nparts;
+ joinrel->part_rels =
+ (RelOptInfo **) palloc0(sizeof(RelOptInfo *) * nparts);
+ }
+ else
+ {
+ Assert(joinrel->nparts > 0);
+ Assert(joinrel->boundinfo);
+ Assert(joinrel->part_rels);
+
+ /*
+ * If the join rel's partbounds_merged flag is true, it means inputs
+ * are not guaranteed to have the same partition bounds, therefore we
+ * can't assume that the partitions at the same cardinal positions
+ * form the pairs; let get_matching_part_pairs() generate the pairs.
+ * Otherwise, nothing to do since we can assume that.
+ */
+ if (joinrel->partbounds_merged)
+ {
+ get_matching_part_pairs(root, joinrel, rel1, rel2,
+ parts1, parts2);
+ Assert(list_length(*parts1) == joinrel->nparts);
+ Assert(list_length(*parts2) == joinrel->nparts);
+ }
+ }
+}
+
+
+/*
+ * Assess whether join between given two partitioned relations can be broken
+ * down into joins between matching partitions; a technique called
+ * "partitionwise join"
+ *
+ * Partitionwise join is possible when a. Joining relations have same
+ * partitioning scheme b. There exists an equi-join between the partition keys
+ * of the two relations.
+ *
+ * Partitionwise join is planned as follows (details: optimizer/README.)
+ *
+ * 1. Create the RelOptInfos for joins between matching partitions i.e
+ * child-joins and add paths to them.
+ *
+ * 2. Construct Append or MergeAppend paths across the set of child joins.
+ * This second phase is implemented by generate_partitionwise_join_paths().
+ *
+ * The RelOptInfo, SpecialJoinInfo and restrictlist for each child join are
+ * obtained by translating the respective parent join structures.
+ */
+static void
+try_partitionwise_join(PlannerInfo *root, RelOptInfo *rel1, RelOptInfo *rel2,
+ RelOptInfo *joinrel, SpecialJoinInfo *parent_sjinfo,
+ List *parent_restrictlist)
+{
+ bool rel1_is_simple = IS_SIMPLE_REL(rel1);
+ bool rel2_is_simple = IS_SIMPLE_REL(rel2);
+ List *parts1 = NIL;
+ List *parts2 = NIL;
+ ListCell *lcr1 = NULL;
+ ListCell *lcr2 = NULL;
+ int cnt_parts;
+
+ /* Guard against stack overflow due to overly deep partition hierarchy. */
+ check_stack_depth();
+
+ /* Nothing to do, if the join relation is not partitioned. */
+ if (joinrel->part_scheme == NULL || joinrel->nparts == 0)
+ return;
+
+ /* The join relation should have consider_partitionwise_join set. */
+ Assert(joinrel->consider_partitionwise_join);
+
+ /*
+ * We can not perform partitionwise join if either of the joining
+ * relations is not partitioned.
+ */
+ if (!IS_PARTITIONED_REL(rel1) || !IS_PARTITIONED_REL(rel2))
+ return;
+
+ Assert(REL_HAS_ALL_PART_PROPS(rel1) && REL_HAS_ALL_PART_PROPS(rel2));
+
+ /* The joining relations should have consider_partitionwise_join set. */
+ Assert(rel1->consider_partitionwise_join &&
+ rel2->consider_partitionwise_join);
+
+ /*
+ * The partition scheme of the join relation should match that of the
+ * joining relations.
+ */
+ Assert(joinrel->part_scheme == rel1->part_scheme &&
+ joinrel->part_scheme == rel2->part_scheme);
+
+ Assert(!(joinrel->partbounds_merged && (joinrel->nparts <= 0)));
+
+ compute_partition_bounds(root, rel1, rel2, joinrel, parent_sjinfo,
+ &parts1, &parts2);
+
+ if (joinrel->partbounds_merged)
+ {
+ lcr1 = list_head(parts1);
+ lcr2 = list_head(parts2);
+ }
+
+ /*
+ * Create child-join relations for this partitioned join, if those don't
+ * exist. Add paths to child-joins for a pair of child relations
+ * corresponding to the given pair of parent relations.
+ */
+ for (cnt_parts = 0; cnt_parts < joinrel->nparts; cnt_parts++)
+ {
+ RelOptInfo *child_rel1;
+ RelOptInfo *child_rel2;
+ bool rel1_empty;
+ bool rel2_empty;
+ SpecialJoinInfo *child_sjinfo;
+ List *child_restrictlist;
+ RelOptInfo *child_joinrel;
+ Relids child_joinrelids;
+ AppendRelInfo **appinfos;
+ int nappinfos;
+
+ if (joinrel->partbounds_merged)
+ {
+ child_rel1 = lfirst_node(RelOptInfo, lcr1);
+ child_rel2 = lfirst_node(RelOptInfo, lcr2);
+ lcr1 = lnext(parts1, lcr1);
+ lcr2 = lnext(parts2, lcr2);
+ }
+ else
+ {
+ child_rel1 = rel1->part_rels[cnt_parts];
+ child_rel2 = rel2->part_rels[cnt_parts];
+ }
+
+ rel1_empty = (child_rel1 == NULL || IS_DUMMY_REL(child_rel1));
+ rel2_empty = (child_rel2 == NULL || IS_DUMMY_REL(child_rel2));
+
+ /*
+ * Check for cases where we can prove that this segment of the join
+ * returns no rows, due to one or both inputs being empty (including
+ * inputs that have been pruned away entirely). If so just ignore it.
+ * These rules are equivalent to populate_joinrel_with_paths's rules
+ * for dummy input relations.
+ */
+ switch (parent_sjinfo->jointype)
+ {
+ case JOIN_INNER:
+ case JOIN_SEMI:
+ if (rel1_empty || rel2_empty)
+ continue; /* ignore this join segment */
+ break;
+ case JOIN_LEFT:
+ case JOIN_ANTI:
+ if (rel1_empty)
+ continue; /* ignore this join segment */
+ break;
+ case JOIN_FULL:
+ if (rel1_empty && rel2_empty)
+ continue; /* ignore this join segment */
+ break;
+ default:
+ /* other values not expected here */
+ elog(ERROR, "unrecognized join type: %d",
+ (int) parent_sjinfo->jointype);
+ break;
+ }
+
+ /*
+ * If a child has been pruned entirely then we can't generate paths
+ * for it, so we have to reject partitionwise joining unless we were
+ * able to eliminate this partition above.
+ */
+ if (child_rel1 == NULL || child_rel2 == NULL)
+ {
+ /*
+ * Mark the joinrel as unpartitioned so that later functions treat
+ * it correctly.
+ */
+ joinrel->nparts = 0;
+ return;
+ }
+
+ /*
+ * If a leaf relation has consider_partitionwise_join=false, it means
+ * that it's a dummy relation for which we skipped setting up tlist
+ * expressions and adding EC members in set_append_rel_size(), so
+ * again we have to fail here.
+ */
+ if (rel1_is_simple && !child_rel1->consider_partitionwise_join)
+ {
+ Assert(child_rel1->reloptkind == RELOPT_OTHER_MEMBER_REL);
+ Assert(IS_DUMMY_REL(child_rel1));
+ joinrel->nparts = 0;
+ return;
+ }
+ if (rel2_is_simple && !child_rel2->consider_partitionwise_join)
+ {
+ Assert(child_rel2->reloptkind == RELOPT_OTHER_MEMBER_REL);
+ Assert(IS_DUMMY_REL(child_rel2));
+ joinrel->nparts = 0;
+ return;
+ }
+
+ /* We should never try to join two overlapping sets of rels. */
+ Assert(!bms_overlap(child_rel1->relids, child_rel2->relids));
+ child_joinrelids = bms_union(child_rel1->relids, child_rel2->relids);
+ appinfos = find_appinfos_by_relids(root, child_joinrelids, &nappinfos);
+
+ /*
+ * Construct SpecialJoinInfo from parent join relations's
+ * SpecialJoinInfo.
+ */
+ child_sjinfo = build_child_join_sjinfo(root, parent_sjinfo,
+ child_rel1->relids,
+ child_rel2->relids);
+
+ /*
+ * Construct restrictions applicable to the child join from those
+ * applicable to the parent join.
+ */
+ child_restrictlist =
+ (List *) adjust_appendrel_attrs(root,
+ (Node *) parent_restrictlist,
+ nappinfos, appinfos);
+ pfree(appinfos);
+
+ child_joinrel = joinrel->part_rels[cnt_parts];
+ if (!child_joinrel)
+ {
+ child_joinrel = build_child_join_rel(root, child_rel1, child_rel2,
+ joinrel, child_restrictlist,
+ child_sjinfo,
+ child_sjinfo->jointype);
+ joinrel->part_rels[cnt_parts] = child_joinrel;
+ joinrel->all_partrels = bms_add_members(joinrel->all_partrels,
+ child_joinrel->relids);
+ }
+
+ Assert(bms_equal(child_joinrel->relids, child_joinrelids));
+
+ populate_joinrel_with_paths(root, child_rel1, child_rel2,
+ child_joinrel, child_sjinfo,
+ child_restrictlist);
+ }
+}
OSDN Git Service
