From 8a88942c01e73976ad93f4e99ee782839a6b4650 Mon Sep 17 00:00:00 2001 From: Yuya Watari Date: Fri, 25 Aug 2023 10:43:36 +0900 Subject: [PATCH v34 1/4] Speed up searches for child EquivalenceMembers Traditionally, child EquivalenceMembers were in the EquivalenceClass->ec_members. When we wanted to find some child members matching a request, we had to perform a linear search. This search became heavy when tables had many partitions, leading to much planning time. After this commit, child EquivalenceMembers no longer exist in ec_members. Instead, RelOptInfos have them. This change demonstrates a significant performance improvement in planning time. --- contrib/postgres_fdw/postgres_fdw.c | 15 +- src/backend/optimizer/path/equivclass.c | 449 +++++++++++++++++++----- src/backend/optimizer/path/indxpath.c | 15 +- src/backend/optimizer/path/pathkeys.c | 9 +- src/backend/optimizer/plan/createplan.c | 61 ++-- src/backend/optimizer/util/relnode.c | 16 + src/include/nodes/pathnodes.h | 79 +++++ src/include/optimizer/paths.h | 9 +- src/tools/pgindent/typedefs.list | 2 + 9 files changed, 525 insertions(+), 130 deletions(-) diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 1131a8bf77e..2eb0f16b0f6 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -7829,14 +7829,13 @@ conversion_error_callback(void *arg) EquivalenceMember * find_em_for_rel(PlannerInfo *root, EquivalenceClass *ec, RelOptInfo *rel) { - ListCell *lc; - PgFdwRelationInfo *fpinfo = (PgFdwRelationInfo *) rel->fdw_private; + EquivalenceAllMemberIterator it; + EquivalenceMember *em; - foreach(lc, ec->ec_members) + setup_eclass_all_member_iterator_for_relids(&it, root, ec, rel->relids); + while ((em = eclass_all_member_iterator_for_relids_next(&it)) != NULL) { - EquivalenceMember *em = (EquivalenceMember *) lfirst(lc); - /* * Note we require !bms_is_empty, else we'd accept constant * expressions which are not suitable for the purpose. @@ -7847,6 +7846,7 @@ find_em_for_rel(PlannerInfo *root, EquivalenceClass *ec, RelOptInfo *rel) is_foreign_expr(root, rel, em->em_expr)) return em; } + dispose_eclass_all_member_iterator_for_relids(&it); return NULL; } @@ -7900,9 +7900,8 @@ find_em_for_rel_target(PlannerInfo *root, EquivalenceClass *ec, if (em->em_is_const) continue; - /* Ignore child members */ - if (em->em_is_child) - continue; + /* Child members should not exist in ec_members */ + Assert(!em->em_is_child); /* Match if same expression (after stripping relabel) */ em_expr = em->em_expr; diff --git a/src/backend/optimizer/path/equivclass.c b/src/backend/optimizer/path/equivclass.c index 0f9ecf5ee8b..9ac15cca8fa 100644 --- a/src/backend/optimizer/path/equivclass.c +++ b/src/backend/optimizer/path/equivclass.c @@ -33,11 +33,15 @@ #include "utils/lsyscache.h" -static EquivalenceMember *add_eq_member(EquivalenceClass *ec, - Expr *expr, Relids relids, - JoinDomain *jdomain, - EquivalenceMember *parent, - Oid datatype); +static EquivalenceMember *make_eq_member(EquivalenceClass *ec, + Expr *expr, Relids relids, + JoinDomain *jdomain, + EquivalenceMember *parent, + Oid datatype); +static EquivalenceMember *add_parent_eq_member(EquivalenceClass *ec, + Expr *expr, Relids relids, + JoinDomain *jdomain, + Oid datatype); static void generate_base_implied_equalities_const(PlannerInfo *root, EquivalenceClass *ec); static void generate_base_implied_equalities_no_const(PlannerInfo *root, @@ -68,6 +72,10 @@ static bool reconsider_outer_join_clause(PlannerInfo *root, static bool reconsider_full_join_clause(PlannerInfo *root, OuterJoinClauseInfo *ojcinfo); static JoinDomain *find_join_domain(PlannerInfo *root, Relids relids); +static void add_eclass_child_members_to_iterator(EquivalenceAllMemberIterator *it, + PlannerInfo *root, + EquivalenceClass *ec, + RelOptInfo *child_rel); static Bitmapset *get_eclass_indexes_for_relids(PlannerInfo *root, Relids relids); static Bitmapset *get_common_eclass_indexes(PlannerInfo *root, Relids relids1, @@ -372,8 +380,8 @@ process_equivalence(PlannerInfo *root, else if (ec1) { /* Case 3: add item2 to ec1 */ - em2 = add_eq_member(ec1, item2, item2_relids, - jdomain, NULL, item2_type); + em2 = add_parent_eq_member(ec1, item2, item2_relids, + jdomain, item2_type); ec1->ec_sources = lappend(ec1->ec_sources, restrictinfo); ec1->ec_min_security = Min(ec1->ec_min_security, restrictinfo->security_level); @@ -389,8 +397,8 @@ process_equivalence(PlannerInfo *root, else if (ec2) { /* Case 3: add item1 to ec2 */ - em1 = add_eq_member(ec2, item1, item1_relids, - jdomain, NULL, item1_type); + em1 = add_parent_eq_member(ec2, item1, item1_relids, + jdomain, item1_type); ec2->ec_sources = lappend(ec2->ec_sources, restrictinfo); ec2->ec_min_security = Min(ec2->ec_min_security, restrictinfo->security_level); @@ -421,10 +429,10 @@ process_equivalence(PlannerInfo *root, ec->ec_min_security = restrictinfo->security_level; ec->ec_max_security = restrictinfo->security_level; ec->ec_merged = NULL; - em1 = add_eq_member(ec, item1, item1_relids, - jdomain, NULL, item1_type); - em2 = add_eq_member(ec, item2, item2_relids, - jdomain, NULL, item2_type); + em1 = add_parent_eq_member(ec, item1, item1_relids, + jdomain, item1_type); + em2 = add_parent_eq_member(ec, item2, item2_relids, + jdomain, item2_type); root->eq_classes = lappend(root->eq_classes, ec); @@ -510,11 +518,16 @@ canonicalize_ec_expression(Expr *expr, Oid req_type, Oid req_collation) } /* - * add_eq_member - build a new EquivalenceMember and add it to an EC + * make_eq_member + * + * Build a new EquivalenceMember without adding it to an EC. If 'parent' + * parameter is NULL, the result will be a parent member, otherwise a child + * member. Note that child EquivalenceMembers should not be added to its + * parent EquivalenceClass. */ static EquivalenceMember * -add_eq_member(EquivalenceClass *ec, Expr *expr, Relids relids, - JoinDomain *jdomain, EquivalenceMember *parent, Oid datatype) +make_eq_member(EquivalenceClass *ec, Expr *expr, Relids relids, + JoinDomain *jdomain, EquivalenceMember *parent, Oid datatype) { EquivalenceMember *em = makeNode(EquivalenceMember); @@ -525,6 +538,7 @@ add_eq_member(EquivalenceClass *ec, Expr *expr, Relids relids, em->em_datatype = datatype; em->em_jdomain = jdomain; em->em_parent = parent; + em->em_ec = ec; if (bms_is_empty(relids)) { @@ -545,11 +559,30 @@ add_eq_member(EquivalenceClass *ec, Expr *expr, Relids relids, { ec->ec_relids = bms_add_members(ec->ec_relids, relids); } - ec->ec_members = lappend(ec->ec_members, em); return em; } +/* + * add_parent_eq_member - build a new parent EquivalenceMember and add it to an EC + * + * Note: We don't have a function to add a child member like + * add_child_eq_member() because how to do it depends on the relations they + * are translated from. See add_child_rel_equivalences(), + * add_child_join_rel_equivalences() and add_setop_child_rel_equivalences() + * to see how to add child members. + */ +static EquivalenceMember * +add_parent_eq_member(EquivalenceClass *ec, Expr *expr, Relids relids, + JoinDomain *jdomain, Oid datatype) +{ + EquivalenceMember *em = make_eq_member(ec, expr, relids, jdomain, + NULL, datatype); + + ec->ec_members = lappend(ec->ec_members, em); + return em; +} + /* * get_eclass_for_sort_expr @@ -616,7 +649,8 @@ get_eclass_for_sort_expr(PlannerInfo *root, foreach(lc1, root->eq_classes) { EquivalenceClass *cur_ec = (EquivalenceClass *) lfirst(lc1); - ListCell *lc2; + EquivalenceAllMemberIterator it; + EquivalenceMember *cur_em; /* * Never match to a volatile EC, except when we are looking at another @@ -631,10 +665,9 @@ get_eclass_for_sort_expr(PlannerInfo *root, if (!equal(opfamilies, cur_ec->ec_opfamilies)) continue; - foreach(lc2, cur_ec->ec_members) + setup_eclass_all_member_iterator_for_relids(&it, root, cur_ec, rel); + while ((cur_em = eclass_all_member_iterator_for_relids_next(&it)) != NULL) { - EquivalenceMember *cur_em = (EquivalenceMember *) lfirst(lc2); - /* * Ignore child members unless they match the request. */ @@ -653,6 +686,7 @@ get_eclass_for_sort_expr(PlannerInfo *root, equal(expr, cur_em->em_expr)) return cur_ec; /* Match! */ } + dispose_eclass_all_member_iterator_for_relids(&it); } /* No match; does caller want a NULL result? */ @@ -689,14 +723,14 @@ get_eclass_for_sort_expr(PlannerInfo *root, */ expr_relids = pull_varnos(root, (Node *) expr); - newem = add_eq_member(newec, copyObject(expr), expr_relids, - jdomain, NULL, opcintype); + newem = add_parent_eq_member(newec, copyObject(expr), expr_relids, + jdomain, opcintype); /* - * add_eq_member doesn't check for volatile functions, set-returning - * functions, aggregates, or window functions, but such could appear in - * sort expressions; so we have to check whether its const-marking was - * correct. + * add_parent_eq_member doesn't check for volatile functions, + * set-returning functions, aggregates, or window functions, but such + * could appear in sort expressions; so we have to check whether its + * const-marking was correct. */ if (newec->ec_has_const) { @@ -760,19 +794,20 @@ get_eclass_for_sort_expr(PlannerInfo *root, * Child EC members are ignored unless they belong to given 'relids'. */ EquivalenceMember * -find_ec_member_matching_expr(EquivalenceClass *ec, +find_ec_member_matching_expr(PlannerInfo *root, EquivalenceClass *ec, Expr *expr, Relids relids) { - ListCell *lc; + EquivalenceAllMemberIterator it; + EquivalenceMember *em; /* We ignore binary-compatible relabeling on both ends */ while (expr && IsA(expr, RelabelType)) expr = ((RelabelType *) expr)->arg; - foreach(lc, ec->ec_members) + setup_eclass_all_member_iterator_for_relids(&it, root, ec, relids); + while ((em = eclass_all_member_iterator_for_relids_next(&it)) != NULL) { - EquivalenceMember *em = (EquivalenceMember *) lfirst(lc); Expr *emexpr; /* @@ -799,6 +834,7 @@ find_ec_member_matching_expr(EquivalenceClass *ec, if (equal(emexpr, expr)) return em; } + dispose_eclass_all_member_iterator_for_relids(&it); return NULL; } @@ -841,7 +877,8 @@ find_computable_ec_member(PlannerInfo *root, bool require_parallel_safe) { List *exprvars; - ListCell *lc; + EquivalenceAllMemberIterator it; + EquivalenceMember *em; /* * Pull out the Vars and quasi-Vars present in "exprs". In the typical @@ -855,9 +892,9 @@ find_computable_ec_member(PlannerInfo *root, PVC_INCLUDE_PLACEHOLDERS | PVC_INCLUDE_CONVERTROWTYPES); - foreach(lc, ec->ec_members) + setup_eclass_all_member_iterator_for_relids(&it, root, ec, relids); + while ((em = eclass_all_member_iterator_for_relids_next(&it)) != NULL) { - EquivalenceMember *em = (EquivalenceMember *) lfirst(lc); List *emvars; ListCell *lc2; @@ -901,6 +938,7 @@ find_computable_ec_member(PlannerInfo *root, return em; /* found usable expression */ } + dispose_eclass_all_member_iterator_for_relids(&it); return NULL; } @@ -939,7 +977,7 @@ relation_can_be_sorted_early(PlannerInfo *root, RelOptInfo *rel, { Expr *targetexpr = (Expr *) lfirst(lc); - em = find_ec_member_matching_expr(ec, targetexpr, rel->relids); + em = find_ec_member_matching_expr(root, ec, targetexpr, rel->relids); if (!em) continue; @@ -1564,7 +1602,8 @@ generate_join_implied_equalities_normal(PlannerInfo *root, List *new_members = NIL; List *outer_members = NIL; List *inner_members = NIL; - ListCell *lc1; + EquivalenceAllMemberIterator it; + EquivalenceMember *cur_em; /* * First, scan the EC to identify member values that are computable at the @@ -1575,10 +1614,9 @@ generate_join_implied_equalities_normal(PlannerInfo *root, * as well as to at least one input member, plus enforce at least one * outer-rel member equal to at least one inner-rel member. */ - foreach(lc1, ec->ec_members) + setup_eclass_all_member_iterator_for_relids(&it, root, ec, join_relids); + while ((cur_em = eclass_all_member_iterator_for_relids_next(&it)) != NULL) { - EquivalenceMember *cur_em = (EquivalenceMember *) lfirst(lc1); - /* * We don't need to check explicitly for child EC members. This test * against join_relids will cause them to be ignored except when @@ -1594,6 +1632,7 @@ generate_join_implied_equalities_normal(PlannerInfo *root, else new_members = lappend(new_members, cur_em); } + dispose_eclass_all_member_iterator_for_relids(&it); /* * First, select the joinclause if needed. We can equate any one outer @@ -1611,6 +1650,7 @@ generate_join_implied_equalities_normal(PlannerInfo *root, Oid best_eq_op = InvalidOid; int best_score = -1; RestrictInfo *rinfo; + ListCell *lc1; foreach(lc1, outer_members) { @@ -1685,6 +1725,7 @@ generate_join_implied_equalities_normal(PlannerInfo *root, List *old_members = list_concat(outer_members, inner_members); EquivalenceMember *prev_em = NULL; RestrictInfo *rinfo; + ListCell *lc1; /* For now, arbitrarily take the first old_member as the one to use */ if (old_members) @@ -1692,7 +1733,7 @@ generate_join_implied_equalities_normal(PlannerInfo *root, foreach(lc1, new_members) { - EquivalenceMember *cur_em = (EquivalenceMember *) lfirst(lc1); + cur_em = (EquivalenceMember *) lfirst(lc1); if (prev_em != NULL) { @@ -2405,6 +2446,7 @@ reconsider_full_join_clause(PlannerInfo *root, OuterJoinClauseInfo *ojcinfo) if (matchleft && matchright) { cur_ec->ec_members = list_delete_nth_cell(cur_ec->ec_members, coal_idx); + Assert(!bms_is_empty(coal_em->em_relids)); return true; } @@ -2526,8 +2568,8 @@ exprs_known_equal(PlannerInfo *root, Node *item1, Node *item2, Oid opfamily) { EquivalenceMember *em = (EquivalenceMember *) lfirst(lc2); - if (em->em_is_child) - continue; /* ignore children here */ + /* Child members should not exist in ec_members */ + Assert(!em->em_is_child); if (equal(item1, em->em_expr)) item1member = true; else if (equal(item2, em->em_expr)) @@ -2598,8 +2640,8 @@ match_eclasses_to_foreign_key_col(PlannerInfo *root, EquivalenceMember *em = (EquivalenceMember *) lfirst(lc2); Var *var; - if (em->em_is_child) - continue; /* ignore children here */ + /* Child members should not exist in ec_members */ + Assert(!em->em_is_child); /* EM must be a Var, possibly with RelabelType */ var = (Var *) em->em_expr; @@ -2696,6 +2738,7 @@ add_child_rel_equivalences(PlannerInfo *root, Relids top_parent_relids = child_rel->top_parent_relids; Relids child_relids = child_rel->relids; int i; + ListCell *lc; /* * EC merging should be complete already, so we can use the parent rel's @@ -2708,7 +2751,6 @@ add_child_rel_equivalences(PlannerInfo *root, while ((i = bms_next_member(parent_rel->eclass_indexes, i)) >= 0) { EquivalenceClass *cur_ec = (EquivalenceClass *) list_nth(root->eq_classes, i); - int num_members; /* * If this EC contains a volatile expression, then generating child @@ -2721,15 +2763,9 @@ add_child_rel_equivalences(PlannerInfo *root, /* Sanity check eclass_indexes only contain ECs for parent_rel */ Assert(bms_is_subset(top_parent_relids, cur_ec->ec_relids)); - /* - * We don't use foreach() here because there's no point in scanning - * newly-added child members, so we can stop after the last - * pre-existing EC member. - */ - num_members = list_length(cur_ec->ec_members); - for (int pos = 0; pos < num_members; pos++) + foreach(lc, cur_ec->ec_members) { - EquivalenceMember *cur_em = (EquivalenceMember *) list_nth(cur_ec->ec_members, pos); + EquivalenceMember *cur_em = lfirst_node(EquivalenceMember, lc); if (cur_em->em_is_const) continue; /* ignore consts here */ @@ -2742,8 +2778,8 @@ add_child_rel_equivalences(PlannerInfo *root, * combinations of children. (But add_child_join_rel_equivalences * may add targeted combinations for partitionwise-join purposes.) */ - if (cur_em->em_is_child) - continue; /* ignore children here */ + Assert(!cur_em->em_is_child); /* Child members should not exist + * in ec_members */ /* * Consider only members that reference and can be computed at @@ -2759,6 +2795,7 @@ add_child_rel_equivalences(PlannerInfo *root, /* OK, generate transformed child version */ Expr *child_expr; Relids new_relids; + EquivalenceMember *child_em; if (parent_rel->reloptkind == RELOPT_BASEREL) { @@ -2788,9 +2825,11 @@ add_child_rel_equivalences(PlannerInfo *root, top_parent_relids); new_relids = bms_add_members(new_relids, child_relids); - (void) add_eq_member(cur_ec, child_expr, new_relids, - cur_em->em_jdomain, - cur_em, cur_em->em_datatype); + child_em = make_eq_member(cur_ec, child_expr, new_relids, + cur_em->em_jdomain, + cur_em, cur_em->em_datatype); + child_rel->eclass_child_members = + lappend(child_rel->eclass_child_members, child_em); /* Record this EC index for the child rel */ child_rel->eclass_indexes = bms_add_member(child_rel->eclass_indexes, i); @@ -2819,6 +2858,7 @@ add_child_join_rel_equivalences(PlannerInfo *root, Relids child_relids = child_joinrel->relids; Bitmapset *matching_ecs; MemoryContext oldcontext; + ListCell *lc; int i; Assert(IS_JOIN_REL(child_joinrel) && IS_JOIN_REL(parent_joinrel)); @@ -2840,7 +2880,6 @@ add_child_join_rel_equivalences(PlannerInfo *root, while ((i = bms_next_member(matching_ecs, i)) >= 0) { EquivalenceClass *cur_ec = (EquivalenceClass *) list_nth(root->eq_classes, i); - int num_members; /* * If this EC contains a volatile expression, then generating child @@ -2853,15 +2892,9 @@ add_child_join_rel_equivalences(PlannerInfo *root, /* Sanity check on get_eclass_indexes_for_relids result */ Assert(bms_overlap(top_parent_relids, cur_ec->ec_relids)); - /* - * We don't use foreach() here because there's no point in scanning - * newly-added child members, so we can stop after the last - * pre-existing EC member. - */ - num_members = list_length(cur_ec->ec_members); - for (int pos = 0; pos < num_members; pos++) + foreach(lc, cur_ec->ec_members) { - EquivalenceMember *cur_em = (EquivalenceMember *) list_nth(cur_ec->ec_members, pos); + EquivalenceMember *cur_em = lfirst_node(EquivalenceMember, lc); if (cur_em->em_is_const) continue; /* ignore consts here */ @@ -2870,8 +2903,8 @@ add_child_join_rel_equivalences(PlannerInfo *root, * We consider only original EC members here, not * already-transformed child members. */ - if (cur_em->em_is_child) - continue; /* ignore children here */ + Assert(!cur_em->em_is_child); /* Child members should not exist + * in ec_members */ /* * We may ignore expressions that reference a single baserel, @@ -2886,6 +2919,8 @@ add_child_join_rel_equivalences(PlannerInfo *root, /* Yes, generate transformed child version */ Expr *child_expr; Relids new_relids; + EquivalenceMember *child_em; + int j; if (parent_joinrel->reloptkind == RELOPT_JOINREL) { @@ -2916,9 +2951,38 @@ add_child_join_rel_equivalences(PlannerInfo *root, top_parent_relids); new_relids = bms_add_members(new_relids, child_relids); - (void) add_eq_member(cur_ec, child_expr, new_relids, - cur_em->em_jdomain, - cur_em, cur_em->em_datatype); + child_em = make_eq_member(cur_ec, child_expr, new_relids, + cur_em->em_jdomain, + cur_em, cur_em->em_datatype); + child_joinrel->eclass_child_members = + lappend(child_joinrel->eclass_child_members, child_em); + + /* + * Update the corresponding inverted indexes. + */ + j = -1; + while ((j = bms_next_member(child_joinrel->relids, j)) >= 0) + { + EquivalenceClassIndexes *indexes = + &root->eclass_indexes_array[j]; + + /* + * We do not need to update the inverted index of the top + * parent relations. This is because EquivalenceMembers + * that have only such parent relations as em_relids are + * already present in the ec_members, and so cannot be + * candidates for additional iteration by + * EquivalenceAllMemberIterator. Since the iterator needs + * EquivalenceMembers whose em_relids has child relations, + * skipping the update of this inverted index allows for + * faster iteration. + */ + if (root->append_rel_array[j] == NULL) + continue; + indexes->joinrel_indexes = + bms_add_member(indexes->joinrel_indexes, + child_joinrel->join_rel_list_index); + } } } } @@ -2967,12 +3031,12 @@ add_setop_child_rel_equivalences(PlannerInfo *root, RelOptInfo *child_rel, * likewise, the JoinDomain can be that of the initial member of the * Pathkey's EquivalenceClass. */ - add_eq_member(pk->pk_eclass, - tle->expr, - child_rel->relids, - parent_em->em_jdomain, - parent_em, - exprType((Node *) tle->expr)); + add_parent_eq_member(pk->pk_eclass, + tle->expr, + child_rel->relids, + parent_em->em_jdomain, + parent_em, + exprType((Node *) tle->expr)); lc2 = lnext(setop_pathkeys, lc2); } @@ -2987,6 +3051,219 @@ add_setop_child_rel_equivalences(PlannerInfo *root, RelOptInfo *child_rel, list_length(root->eq_classes) - 1); } +/* + * setup_eclass_all_member_iterator_for_relids + * Setup an EquivalenceAllMemberIterator 'it' to iterate over all parent + * EquivalenceMembers and child members associated with the given 'ec' that + * are relevant to the specified 'relids'. + * + * This iterator returns: + * - All parent members stored directly in ec->ec_members. + * - The child members whose em_relids is a subset of the given 'relids'. + * + * Note: + * - The iterator may return false positives, i.e., child members whose + * em_relids is not a subset. So the caller must check that they satisfy + * the desired condition. + * - Once used, the caller should dispose of the iterator by calling + * dispose_eclass_all_member_iterator_for_relids(). + * + * Parameters: + * root - The PlannerInfo context. + * ec - The EquivalenceClass from which to iterate members. + * relids - The Relids used to filter for relevant child members. + */ +void +setup_eclass_all_member_iterator_for_relids(EquivalenceAllMemberIterator *it, + PlannerInfo *root, + EquivalenceClass *ec, + Relids relids) +{ + Bitmapset *matching_indexes; + int i; + + /* + * Initialize the iterator. + */ + it->index = -1; + it->modified = false; + it->ec_members = ec->ec_members; + + /* + * If there are no child relations, there is nothing to do. This + * effectively avoids regression for non-partitioned cases. + */ + if (root->append_rel_array == NULL) + return; + + /* + * EquivalenceClass->ec_members has only parent EquivalenceMembers. Child + * members are translated using child RelOptInfos and stored in them. This + * is done in add_child_rel_equivalences(), + * add_child_join_rel_equivalences(), and + * add_setop_child_rel_equivalences(). To retrieve child + * EquivalenceMembers of some parent, we need to know which RelOptInfos + * have such child members. We can know this information using indexes + * like EquivalenceClassIndexes->joinrel_indexes. + * + * We use an inverted index mechanism to quickly iterate over the members + * whose em_relids is a subset of the given 'child_relids'. The inverted + * indexes store RelOptInfo indices that have EquivalenceMembers + * mentioning them. Taking the union of these indexes allows to find which + * RelOptInfos have the EquivalenceMember we are looking for. With this + * method, the em_relids of the newly iterated ones overlap the given + * 'child_relids', but may not be subsets, so the caller must check that + * they satisfy the desired condition. + * + * The above comments are about joinrels, and for simple rels, this + * mechanism is simpler. It is sufficient to simply add the child + * EquivalenceMembers of RelOptInfo to the iterator. + * + * We need to perform these steps for each of the two types of relations. + */ + + /* + * Iterate over the given relids, adding child members for simple rels and + * taking union indexes for join rels. + */ + i = -1; + matching_indexes = NULL; + while ((i = bms_next_member(relids, i)) >= 0) + { + RelOptInfo *child_rel; + EquivalenceClassIndexes *indexes; + + /* + * If this relation is a parent, we don't have to do anything. + */ + if (root->append_rel_array[i] == NULL) + continue; + + /* + * Add child members that mention this relation to the iterator. + */ + child_rel = root->simple_rel_array[i]; + if (child_rel != NULL) + add_eclass_child_members_to_iterator(it, root, ec, child_rel); + + /* + * Union indexes for join rels. + */ + indexes = &root->eclass_indexes_array[i]; + matching_indexes = + bms_add_members(matching_indexes, indexes->joinrel_indexes); + } + + /* + * For join rels, add child members using 'matching_indexes'. + */ + i = -1; + while ((i = bms_next_member(matching_indexes, i)) >= 0) + { + RelOptInfo *child_joinrel = + list_nth_node(RelOptInfo, root->join_rel_list, i); + + Assert(child_joinrel != NULL); + + /* + * If this joinrel's Relids is not a subset of the given one, then the + * child EquivalenceMembers it holds should never be a subset either. + */ + if (bms_is_subset(child_joinrel->relids, relids)) + add_eclass_child_members_to_iterator(it, root, ec, child_joinrel); +#ifdef USE_ASSERT_CHECKING + else + { + /* + * Verify that the above comment is correct. + * + * NOTE: We may remove this assertion after the beta process. + */ + + ListCell *lc; + + foreach(lc, child_joinrel->eclass_child_members) + { + EquivalenceMember *child_em = lfirst_node(EquivalenceMember, lc); + + if (child_em->em_ec != ec) + continue; + Assert(!bms_is_subset(child_em->em_relids, relids)); + } + } +#endif + } + bms_free(matching_indexes); +} + +/* + * add_eclass_child_members_to_iterator + * Add a child EquivalenceMember referencing the given child_rel to + * the iterator from RelOptInfo. + * + * This function is expected to be called only from + * setup_eclass_all_member_iterator_for_relids(). + */ +static void +add_eclass_child_members_to_iterator(EquivalenceAllMemberIterator *it, + PlannerInfo *root, + EquivalenceClass *ec, + RelOptInfo *child_rel) +{ + ListCell *lc; + + foreach(lc, child_rel->eclass_child_members) + { + EquivalenceMember *child_em = lfirst_node(EquivalenceMember, lc); + + /* Skip unwanted EquivalenceMembers */ + if (child_em->em_ec != ec) + continue; + + /* + * If this is the first time the iterator's list has been modified, we + * need to make a copy of it. + */ + if (!it->modified) + { + it->ec_members = list_copy(it->ec_members); + it->modified = true; + } + + /* Add this child EquivalenceMember to the list */ + it->ec_members = lappend(it->ec_members, child_em); + } +} + +/* + * eclass_all_member_iterator_for_relids_next + * Get a next EquivalenceMember from an EquivalenceAllMemberIterator 'it' + * that was setup by setup_eclass_all_member_iterator_for_relids(). NULL is + * returned if there are no members left. + */ +EquivalenceMember * +eclass_all_member_iterator_for_relids_next(EquivalenceAllMemberIterator *it) +{ + if (++it->index < list_length(it->ec_members)) + return list_nth_node(EquivalenceMember, it->ec_members, it->index); + return NULL; +} + +/* + * dispose_eclass_all_member_iterator_for_relids + * Free any memory allocated by the iterator. + */ +void +dispose_eclass_all_member_iterator_for_relids(EquivalenceAllMemberIterator *it) +{ + /* + * XXX Should we use list_free()? I decided to use this style to take + * advantage of speculative execution. + */ + if (unlikely(it->modified)) + pfree(it->ec_members); +} + /* * generate_implied_equalities_for_column @@ -3041,6 +3318,7 @@ generate_implied_equalities_for_column(PlannerInfo *root, EquivalenceClass *cur_ec = (EquivalenceClass *) list_nth(root->eq_classes, i); EquivalenceMember *cur_em; ListCell *lc2; + EquivalenceAllMemberIterator it; /* Sanity check eclass_indexes only contain ECs for rel */ Assert(is_child_rel || bms_is_subset(rel->relids, cur_ec->ec_relids)); @@ -3062,15 +3340,14 @@ generate_implied_equalities_for_column(PlannerInfo *root, * corner cases, so for now we live with just reporting the first * match. See also get_eclass_for_sort_expr.) */ - cur_em = NULL; - foreach(lc2, cur_ec->ec_members) + setup_eclass_all_member_iterator_for_relids(&it, root, cur_ec, rel->relids); + while ((cur_em = eclass_all_member_iterator_for_relids_next(&it)) != NULL) { - cur_em = (EquivalenceMember *) lfirst(lc2); if (bms_equal(cur_em->em_relids, rel->relids) && callback(root, rel, cur_ec, cur_em, callback_arg)) break; - cur_em = NULL; } + dispose_eclass_all_member_iterator_for_relids(&it); if (!cur_em) continue; @@ -3085,8 +3362,8 @@ generate_implied_equalities_for_column(PlannerInfo *root, Oid eq_op; RestrictInfo *rinfo; - if (other_em->em_is_child) - continue; /* ignore children here */ + /* Child members should not exist in ec_members */ + Assert(!other_em->em_is_child); /* Make sure it'll be a join to a different rel */ if (other_em == cur_em || @@ -3304,8 +3581,8 @@ eclass_useful_for_merging(PlannerInfo *root, { EquivalenceMember *cur_em = (EquivalenceMember *) lfirst(lc); - if (cur_em->em_is_child) - continue; /* ignore children here */ + /* Child members should not exist in ec_members */ + Assert(!cur_em->em_is_child); if (!bms_overlap(cur_em->em_relids, relids)) return true; diff --git a/src/backend/optimizer/path/indxpath.c b/src/backend/optimizer/path/indxpath.c index a43ca16d683..38f7322caf9 100644 --- a/src/backend/optimizer/path/indxpath.c +++ b/src/backend/optimizer/path/indxpath.c @@ -190,7 +190,7 @@ static IndexClause *expand_indexqual_rowcompare(PlannerInfo *root, IndexOptInfo *index, Oid expr_op, bool var_on_left); -static void match_pathkeys_to_index(IndexOptInfo *index, List *pathkeys, +static void match_pathkeys_to_index(PlannerInfo *root, IndexOptInfo *index, List *pathkeys, List **orderby_clauses_p, List **clause_columns_p); static Expr *match_clause_to_ordering_op(IndexOptInfo *index, @@ -934,7 +934,7 @@ build_index_paths(PlannerInfo *root, RelOptInfo *rel, * query_pathkeys will allow an incremental sort to be considered on * the index's partially sorted results. */ - match_pathkeys_to_index(index, root->query_pathkeys, + match_pathkeys_to_index(root, index, root->query_pathkeys, &orderbyclauses, &orderbyclausecols); if (list_length(root->query_pathkeys) == list_length(orderbyclauses)) @@ -3739,7 +3739,7 @@ expand_indexqual_rowcompare(PlannerInfo *root, * item in the given 'pathkeys' list. */ static void -match_pathkeys_to_index(IndexOptInfo *index, List *pathkeys, +match_pathkeys_to_index(PlannerInfo *root, IndexOptInfo *index, List *pathkeys, List **orderby_clauses_p, List **clause_columns_p) { @@ -3756,7 +3756,8 @@ match_pathkeys_to_index(IndexOptInfo *index, List *pathkeys, { PathKey *pathkey = (PathKey *) lfirst(lc1); bool found = false; - ListCell *lc2; + EquivalenceAllMemberIterator it; + EquivalenceMember *member; /* Pathkey must request default sort order for the target opfamily */ @@ -3776,9 +3777,10 @@ match_pathkeys_to_index(IndexOptInfo *index, List *pathkeys, * be considered to match more than one pathkey list, which is OK * here. See also get_eclass_for_sort_expr.) */ - foreach(lc2, pathkey->pk_eclass->ec_members) + setup_eclass_all_member_iterator_for_relids(&it, root, pathkey->pk_eclass, + index->rel->relids); + while ((member = eclass_all_member_iterator_for_relids_next(&it)) != NULL) { - EquivalenceMember *member = (EquivalenceMember *) lfirst(lc2); int indexcol; /* No possibility of match if it references other relations */ @@ -3813,6 +3815,7 @@ match_pathkeys_to_index(IndexOptInfo *index, List *pathkeys, if (found) /* don't want to look at remaining members */ break; } + dispose_eclass_all_member_iterator_for_relids(&it); /* * Return the matches found so far when this pathkey couldn't be diff --git a/src/backend/optimizer/path/pathkeys.c b/src/backend/optimizer/path/pathkeys.c index 154eb505d75..a9419d37e2f 100644 --- a/src/backend/optimizer/path/pathkeys.c +++ b/src/backend/optimizer/path/pathkeys.c @@ -1151,8 +1151,8 @@ convert_subquery_pathkeys(PlannerInfo *root, RelOptInfo *rel, Oid sub_expr_coll = sub_eclass->ec_collation; ListCell *k; - if (sub_member->em_is_child) - continue; /* ignore children here */ + /* Child members should not exist in ec_members */ + Assert(!sub_member->em_is_child); foreach(k, subquery_tlist) { @@ -1709,8 +1709,11 @@ select_outer_pathkeys_for_merge(PlannerInfo *root, { EquivalenceMember *em = (EquivalenceMember *) lfirst(lc2); + /* Child members should not exist in ec_members */ + Assert(!em->em_is_child); + /* Potential future join partner? */ - if (!em->em_is_const && !em->em_is_child && + if (!em->em_is_const && !bms_overlap(em->em_relids, joinrel->relids)) score++; } diff --git a/src/backend/optimizer/plan/createplan.c b/src/backend/optimizer/plan/createplan.c index 75e2b0b9036..eff5d93aa3a 100644 --- a/src/backend/optimizer/plan/createplan.c +++ b/src/backend/optimizer/plan/createplan.c @@ -264,7 +264,9 @@ static IncrementalSort *make_incrementalsort(Plan *lefttree, int numCols, int nPresortedCols, AttrNumber *sortColIdx, Oid *sortOperators, Oid *collations, bool *nullsFirst); -static Plan *prepare_sort_from_pathkeys(Plan *lefttree, List *pathkeys, +static Plan *prepare_sort_from_pathkeys(PlannerInfo *root, + Plan *lefttree, + List *pathkeys, Relids relids, const AttrNumber *reqColIdx, bool adjust_tlist_in_place, @@ -273,9 +275,11 @@ static Plan *prepare_sort_from_pathkeys(Plan *lefttree, List *pathkeys, Oid **p_sortOperators, Oid **p_collations, bool **p_nullsFirst); -static Sort *make_sort_from_pathkeys(Plan *lefttree, List *pathkeys, +static Sort *make_sort_from_pathkeys(PlannerInfo *root, + Plan *lefttree, + List *pathkeys, Relids relids); -static IncrementalSort *make_incrementalsort_from_pathkeys(Plan *lefttree, +static IncrementalSort *make_incrementalsort_from_pathkeys(PlannerInfo *root, Plan *lefttree, List *pathkeys, Relids relids, int nPresortedCols); static Sort *make_sort_from_groupcols(List *groupcls, AttrNumber *grpColIdx, @@ -294,7 +298,7 @@ static Group *make_group(List *tlist, List *qual, int numGroupCols, AttrNumber *grpColIdx, Oid *grpOperators, Oid *grpCollations, Plan *lefttree); static Unique *make_unique_from_sortclauses(Plan *lefttree, List *distinctList); -static Unique *make_unique_from_pathkeys(Plan *lefttree, +static Unique *make_unique_from_pathkeys(PlannerInfo *root, Plan *lefttree, List *pathkeys, int numCols); static Gather *make_gather(List *qptlist, List *qpqual, int nworkers, int rescan_param, bool single_copy, Plan *subplan); @@ -1281,7 +1285,7 @@ create_append_plan(PlannerInfo *root, AppendPath *best_path, int flags) * function result; it must be the same plan node. However, we then * need to detect whether any tlist entries were added. */ - (void) prepare_sort_from_pathkeys((Plan *) plan, pathkeys, + (void) prepare_sort_from_pathkeys(root, (Plan *) plan, pathkeys, best_path->path.parent->relids, NULL, true, @@ -1325,7 +1329,7 @@ create_append_plan(PlannerInfo *root, AppendPath *best_path, int flags) * don't need an explicit sort, to make sure they are returning * the same sort key columns the Append expects. */ - subplan = prepare_sort_from_pathkeys(subplan, pathkeys, + subplan = prepare_sort_from_pathkeys(root, subplan, pathkeys, subpath->parent->relids, nodeSortColIdx, false, @@ -1466,7 +1470,7 @@ create_merge_append_plan(PlannerInfo *root, MergeAppendPath *best_path, * function result; it must be the same plan node. However, we then need * to detect whether any tlist entries were added. */ - (void) prepare_sort_from_pathkeys(plan, pathkeys, + (void) prepare_sort_from_pathkeys(root, plan, pathkeys, best_path->path.parent->relids, NULL, true, @@ -1497,7 +1501,7 @@ create_merge_append_plan(PlannerInfo *root, MergeAppendPath *best_path, subplan = create_plan_recurse(root, subpath, CP_EXACT_TLIST); /* Compute sort column info, and adjust subplan's tlist as needed */ - subplan = prepare_sort_from_pathkeys(subplan, pathkeys, + subplan = prepare_sort_from_pathkeys(root, subplan, pathkeys, subpath->parent->relids, node->sortColIdx, false, @@ -1979,7 +1983,7 @@ create_gather_merge_plan(PlannerInfo *root, GatherMergePath *best_path) Assert(pathkeys != NIL); /* Compute sort column info, and adjust subplan's tlist as needed */ - subplan = prepare_sort_from_pathkeys(subplan, pathkeys, + subplan = prepare_sort_from_pathkeys(root, subplan, pathkeys, best_path->subpath->parent->relids, gm_plan->sortColIdx, false, @@ -2193,7 +2197,7 @@ create_sort_plan(PlannerInfo *root, SortPath *best_path, int flags) * relids. Thus, if this sort path is based on a child relation, we must * pass its relids. */ - plan = make_sort_from_pathkeys(subplan, best_path->path.pathkeys, + plan = make_sort_from_pathkeys(root, subplan, best_path->path.pathkeys, IS_OTHER_REL(best_path->subpath->parent) ? best_path->path.parent->relids : NULL); @@ -2217,7 +2221,7 @@ create_incrementalsort_plan(PlannerInfo *root, IncrementalSortPath *best_path, /* See comments in create_sort_plan() above */ subplan = create_plan_recurse(root, best_path->spath.subpath, flags | CP_SMALL_TLIST); - plan = make_incrementalsort_from_pathkeys(subplan, + plan = make_incrementalsort_from_pathkeys(root, subplan, best_path->spath.path.pathkeys, IS_OTHER_REL(best_path->spath.subpath->parent) ? best_path->spath.path.parent->relids : NULL, @@ -2286,7 +2290,7 @@ create_upper_unique_plan(PlannerInfo *root, UpperUniquePath *best_path, int flag subplan = create_plan_recurse(root, best_path->subpath, flags | CP_LABEL_TLIST); - plan = make_unique_from_pathkeys(subplan, + plan = make_unique_from_pathkeys(root, subplan, best_path->path.pathkeys, best_path->numkeys); @@ -4544,7 +4548,8 @@ create_mergejoin_plan(PlannerInfo *root, if (!use_incremental_sort) { sort_plan = (Plan *) - make_sort_from_pathkeys(outer_plan, + make_sort_from_pathkeys(root, + outer_plan, best_path->outersortkeys, outer_relids); @@ -4553,7 +4558,8 @@ create_mergejoin_plan(PlannerInfo *root, else { sort_plan = (Plan *) - make_incrementalsort_from_pathkeys(outer_plan, + make_incrementalsort_from_pathkeys(root, + outer_plan, best_path->outersortkeys, outer_relids, presorted_keys); @@ -4578,7 +4584,7 @@ create_mergejoin_plan(PlannerInfo *root, */ Relids inner_relids = inner_path->parent->relids; - Sort *sort = make_sort_from_pathkeys(inner_plan, + Sort *sort = make_sort_from_pathkeys(root, inner_plan, best_path->innersortkeys, inner_relids); @@ -6228,7 +6234,7 @@ make_incrementalsort(Plan *lefttree, int numCols, int nPresortedCols, * or a Result stacked atop lefttree). */ static Plan * -prepare_sort_from_pathkeys(Plan *lefttree, List *pathkeys, +prepare_sort_from_pathkeys(PlannerInfo *root, Plan *lefttree, List *pathkeys, Relids relids, const AttrNumber *reqColIdx, bool adjust_tlist_in_place, @@ -6295,7 +6301,7 @@ prepare_sort_from_pathkeys(Plan *lefttree, List *pathkeys, tle = get_tle_by_resno(tlist, reqColIdx[numsortkeys]); if (tle) { - em = find_ec_member_matching_expr(ec, tle->expr, relids); + em = find_ec_member_matching_expr(root, ec, tle->expr, relids); if (em) { /* found expr at right place in tlist */ @@ -6323,7 +6329,7 @@ prepare_sort_from_pathkeys(Plan *lefttree, List *pathkeys, foreach(j, tlist) { tle = (TargetEntry *) lfirst(j); - em = find_ec_member_matching_expr(ec, tle->expr, relids); + em = find_ec_member_matching_expr(root, ec, tle->expr, relids); if (em) { /* found expr already in tlist */ @@ -6339,7 +6345,7 @@ prepare_sort_from_pathkeys(Plan *lefttree, List *pathkeys, /* * No matching tlist item; look for a computable expression. */ - em = find_computable_ec_member(NULL, ec, tlist, relids, false); + em = find_computable_ec_member(root, ec, tlist, relids, false); if (!em) elog(ERROR, "could not find pathkey item to sort"); pk_datatype = em->em_datatype; @@ -6410,7 +6416,8 @@ prepare_sort_from_pathkeys(Plan *lefttree, List *pathkeys, * 'relids' is the set of relations required by prepare_sort_from_pathkeys() */ static Sort * -make_sort_from_pathkeys(Plan *lefttree, List *pathkeys, Relids relids) +make_sort_from_pathkeys(PlannerInfo *root, Plan *lefttree, List *pathkeys, + Relids relids) { int numsortkeys; AttrNumber *sortColIdx; @@ -6419,7 +6426,7 @@ make_sort_from_pathkeys(Plan *lefttree, List *pathkeys, Relids relids) bool *nullsFirst; /* Compute sort column info, and adjust lefttree as needed */ - lefttree = prepare_sort_from_pathkeys(lefttree, pathkeys, + lefttree = prepare_sort_from_pathkeys(root, lefttree, pathkeys, relids, NULL, false, @@ -6445,8 +6452,9 @@ make_sort_from_pathkeys(Plan *lefttree, List *pathkeys, Relids relids) * 'nPresortedCols' is the number of presorted columns in input tuples */ static IncrementalSort * -make_incrementalsort_from_pathkeys(Plan *lefttree, List *pathkeys, - Relids relids, int nPresortedCols) +make_incrementalsort_from_pathkeys(PlannerInfo *root, Plan *lefttree, + List *pathkeys, Relids relids, + int nPresortedCols) { int numsortkeys; AttrNumber *sortColIdx; @@ -6455,7 +6463,7 @@ make_incrementalsort_from_pathkeys(Plan *lefttree, List *pathkeys, bool *nullsFirst; /* Compute sort column info, and adjust lefttree as needed */ - lefttree = prepare_sort_from_pathkeys(lefttree, pathkeys, + lefttree = prepare_sort_from_pathkeys(root, lefttree, pathkeys, relids, NULL, false, @@ -6812,7 +6820,8 @@ make_unique_from_sortclauses(Plan *lefttree, List *distinctList) * as above, but use pathkeys to identify the sort columns and semantics */ static Unique * -make_unique_from_pathkeys(Plan *lefttree, List *pathkeys, int numCols) +make_unique_from_pathkeys(PlannerInfo *root, Plan *lefttree, List *pathkeys, + int numCols) { Unique *node = makeNode(Unique); Plan *plan = &node->plan; @@ -6875,7 +6884,7 @@ make_unique_from_pathkeys(Plan *lefttree, List *pathkeys, int numCols) foreach(j, plan->targetlist) { tle = (TargetEntry *) lfirst(j); - em = find_ec_member_matching_expr(ec, tle->expr, NULL); + em = find_ec_member_matching_expr(root, ec, tle->expr, NULL); if (em) { /* found expr already in tlist */ diff --git a/src/backend/optimizer/util/relnode.c b/src/backend/optimizer/util/relnode.c index ff507331a06..8dc51353791 100644 --- a/src/backend/optimizer/util/relnode.c +++ b/src/backend/optimizer/util/relnode.c @@ -119,6 +119,9 @@ setup_simple_rel_arrays(PlannerInfo *root) root->simple_rte_array[rti++] = rte; } + root->eclass_indexes_array = (EquivalenceClassIndexes *) + palloc0(size * sizeof(EquivalenceClassIndexes)); + /* append_rel_array is not needed if there are no AppendRelInfos */ if (root->append_rel_list == NIL) { @@ -181,6 +184,9 @@ expand_planner_arrays(PlannerInfo *root, int add_size) root->append_rel_array = palloc0_array(AppendRelInfo *, new_size); + root->eclass_indexes_array = + repalloc0_array(root->eclass_indexes_array, EquivalenceClassIndexes, root->simple_rel_array_size, new_size); + root->simple_rel_array_size = new_size; } @@ -234,6 +240,7 @@ build_simple_rel(PlannerInfo *root, int relid, RelOptInfo *parent) rel->subplan_params = NIL; rel->rel_parallel_workers = -1; /* set up in get_relation_info */ rel->amflags = 0; + rel->eclass_child_members = NIL; rel->serverid = InvalidOid; if (rte->rtekind == RTE_RELATION) { @@ -629,6 +636,12 @@ add_join_rel(PlannerInfo *root, RelOptInfo *joinrel) /* GEQO requires us to append the new joinrel to the end of the list! */ root->join_rel_list = lappend(root->join_rel_list, joinrel); + /* + * Store the index of this joinrel to use in + * add_child_join_rel_equivalences(). + */ + joinrel->join_rel_list_index = list_length(root->join_rel_list) - 1; + /* store it into the auxiliary hashtable if there is one. */ if (root->join_rel_hash) { @@ -741,6 +754,7 @@ build_join_rel(PlannerInfo *root, joinrel->subplan_params = NIL; joinrel->rel_parallel_workers = -1; joinrel->amflags = 0; + joinrel->eclass_child_members = NIL; joinrel->serverid = InvalidOid; joinrel->userid = InvalidOid; joinrel->useridiscurrent = false; @@ -928,6 +942,7 @@ build_child_join_rel(PlannerInfo *root, RelOptInfo *outer_rel, joinrel->subroot = NULL; joinrel->subplan_params = NIL; joinrel->amflags = 0; + joinrel->eclass_child_members = NIL; joinrel->serverid = InvalidOid; joinrel->userid = InvalidOid; joinrel->useridiscurrent = false; @@ -1490,6 +1505,7 @@ fetch_upper_rel(PlannerInfo *root, UpperRelationKind kind, Relids relids) upperrel->cheapest_total_path = NULL; upperrel->cheapest_unique_path = NULL; upperrel->cheapest_parameterized_paths = NIL; + upperrel->eclass_child_members = NIL; /* XXX Is this required? */ root->upper_rels[kind] = lappend(root->upper_rels[kind], upperrel); diff --git a/src/include/nodes/pathnodes.h b/src/include/nodes/pathnodes.h index fbf05322c75..9651f52d405 100644 --- a/src/include/nodes/pathnodes.h +++ b/src/include/nodes/pathnodes.h @@ -213,6 +213,8 @@ typedef struct PlannerInfo PlannerInfo; #define HAVE_PLANNERINFO_TYPEDEF 1 #endif +struct EquivalenceClassIndexes; + struct PlannerInfo { pg_node_attr(no_copy_equal, no_read, no_query_jumble) @@ -269,6 +271,13 @@ struct PlannerInfo */ struct AppendRelInfo **append_rel_array pg_node_attr(read_write_ignore); + /* + * eclass_indexes_array is the same length as simple_rel_array and holds + * the indexes of the corresponding rels for faster lookups of + * RestrictInfo. See the EquivalenceClass comment for more details. + */ + struct EquivalenceClassIndexes *eclass_indexes_array pg_node_attr(read_write_ignore); + /* * all_baserels is a Relids set of all base relids (but not joins or * "other" rels) in the query. This is computed in deconstruct_jointree. @@ -981,6 +990,17 @@ typedef struct RelOptInfo /* Bitmask of optional features supported by the table AM */ uint32 amflags; + /* + * information about a join rel + */ + /* index in root->join_rel_list of this rel */ + Index join_rel_list_index; + + /* + * EquivalenceMembers referencing this rel + */ + List *eclass_child_members; + /* * Information about foreign tables and foreign joins */ @@ -1400,6 +1420,12 @@ typedef struct JoinDomain * entry: consider SELECT random() AS a, random() AS b ... ORDER BY b,a. * So we record the SortGroupRef of the originating sort clause. * + * EquivalenceClass->ec_members can only have parent members, and child members + * are stored in RelOptInfos, from which those child members are translated. To + * lookup child EquivalenceMembers, we use EquivalenceAllMemberIterator. See + * its comment for usage. The approach to lookup child members quickly is + * described as setup_eclass_all_member_iterator_for_relids() comment. + * * NB: if ec_merged isn't NULL, this class has been merged into another, and * should be ignored in favor of using the pointed-to class. * @@ -1474,8 +1500,61 @@ typedef struct EquivalenceMember JoinDomain *em_jdomain; /* join domain containing the source clause */ /* if em_is_child is true, this links to corresponding EM for top parent */ struct EquivalenceMember *em_parent pg_node_attr(read_write_ignore); + EquivalenceClass *em_ec; /* EquivalenceClass which has this member */ } EquivalenceMember; +/* + * EquivalenceAllMemberIterator + * + * EquivalenceAllMemberIterator is designed to iterate over all parent + * EquivalenceMembers and child members associated with the given 'ec' that + * are relevant to the specified 'relids'. In particular, it iterates over: + * - All parent members stored directly in ec->ec_members. + * - The child members whose em_relids is a subset of the given 'relids'. + * + * Note: + * - The iterator may return false positives, i.e., child members whose + * em_relids is not a subset. So the caller must check that they satisfy + * the desired condition. + * + * The most common way to use this iterator is as follows: + * ----- + * PlannerInfo *root = given; + * EquivalenceClass *ec = given; + * Relids rel = given; + * EquivalenceAllMemberIterator it; + * EquivalenceMember *em; + * + * setup_eclass_all_member_iterator_for_relids(&it, root, ec, rel); + * while ((em = eclass_all_member_iterator_for_relids_next(&it)) != NULL) + * { + * use em ...; + * } + * dispose_eclass_all_member_iterator_for_relids(&it); + * ----- + */ +typedef struct +{ + int index; /* current index within 'ec_members'. */ + bool modified; /* is 'ec_members' a newly allocated one? */ + List *ec_members; /* parent and child members */ +} EquivalenceAllMemberIterator; + +/* + * EquivalenceClassIndexes + * + * As mentioned in the EquivalenceClass comment, we introduce a + * bitmapset-based indexing mechanism for faster lookups of child + * EquivalenceMembers. This struct exists for each relation and holds the + * corresponding indexes. + */ +typedef struct EquivalenceClassIndexes +{ + Bitmapset *joinrel_indexes; /* Indexes in PlannerInfo's join_rel_list + * list for RelOptInfos that mention this + * relation */ +} EquivalenceClassIndexes; + /* * PathKeys * diff --git a/src/include/optimizer/paths.h b/src/include/optimizer/paths.h index bc5dfd7db41..954ab6e1955 100644 --- a/src/include/optimizer/paths.h +++ b/src/include/optimizer/paths.h @@ -140,7 +140,8 @@ extern EquivalenceClass *get_eclass_for_sort_expr(PlannerInfo *root, Index sortref, Relids rel, bool create_it); -extern EquivalenceMember *find_ec_member_matching_expr(EquivalenceClass *ec, +extern EquivalenceMember *find_ec_member_matching_expr(PlannerInfo *root, + EquivalenceClass *ec, Expr *expr, Relids relids); extern EquivalenceMember *find_computable_ec_member(PlannerInfo *root, @@ -182,6 +183,12 @@ extern void add_setop_child_rel_equivalences(PlannerInfo *root, RelOptInfo *child_rel, List *child_tlist, List *setop_pathkeys); +extern void setup_eclass_all_member_iterator_for_relids(EquivalenceAllMemberIterator *it, + PlannerInfo *root, + EquivalenceClass *ec, + Relids relids); +extern EquivalenceMember *eclass_all_member_iterator_for_relids_next(EquivalenceAllMemberIterator *it); +extern void dispose_eclass_all_member_iterator_for_relids(EquivalenceAllMemberIterator *it); extern List *generate_implied_equalities_for_column(PlannerInfo *root, RelOptInfo *rel, ec_matches_callback_type callback, diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 93339ef3c58..31ffc643916 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -696,7 +696,9 @@ EphemeralNamedRelation EphemeralNamedRelationData EphemeralNamedRelationMetadata EphemeralNamedRelationMetadataData +EquivalenceAllMemberIterator EquivalenceClass +EquivalenceClassIndexes EquivalenceMember ErrorContextCallback ErrorData -- 2.45.2.windows.1