From ab5de2813dbbf9fcf3d7c80e168c2ae3092371eb Mon Sep 17 00:00:00 2001 From: Richard Guo Date: Wed, 23 Apr 2025 10:29:15 +0900 Subject: [PATCH 1/3] Expand virtual generated columns before sublink pull-up Currently, we expand virtual generated columns after we have pulled up any SubLinks within the query's quals. This ensures that the virtual generated column references within SubLinks that should be transformed into joins are correctly expanded. This approach works well and has posed no issues. In an upcoming patch, we plan to centralize the collection of catalog information needed early in the planner. This will help avoid repeated table_open/table_close calls for relations in the rangetable. Since this information is required during sublink pull-up, we are moving the expansion of virtual generated columns to occur beforehand. To achieve this, if any EXISTS SubLinks can be pulled up, their rangetables are processed just before pulling them up. --- src/backend/optimizer/plan/planner.c | 17 +++++++------- src/backend/optimizer/plan/subselect.c | 16 ++++++++++++++ src/backend/optimizer/prep/prepjointree.c | 20 +++++++---------- src/include/optimizer/prep.h | 2 +- .../regress/expected/generated_virtual.out | 22 +++++++++++++++++++ src/test/regress/sql/generated_virtual.sql | 9 ++++++++ 6 files changed, 65 insertions(+), 21 deletions(-) diff --git a/src/backend/optimizer/plan/planner.c b/src/backend/optimizer/plan/planner.c index ff65867eebee..d9c2ac374cfb 100644 --- a/src/backend/optimizer/plan/planner.c +++ b/src/backend/optimizer/plan/planner.c @@ -720,6 +720,15 @@ subquery_planner(PlannerGlobal *glob, Query *parse, PlannerInfo *parent_root, */ transform_MERGE_to_join(parse); + /* + * Scan the rangetable for relations with virtual generated columns, and + * replace all Var nodes in the query that reference these columns with + * the generation expressions. Note that this step does not descend into + * sublinks and subqueries; if we pull up any sublinks or subqueries + * below, their rangetables are processed just before pulling them up. + */ + parse = root->parse = expand_virtual_generated_columns(root); + /* * If the FROM clause is empty, replace it with a dummy RTE_RESULT RTE, so * that we don't need so many special cases to deal with that situation. @@ -743,14 +752,6 @@ subquery_planner(PlannerGlobal *glob, Query *parse, PlannerInfo *parent_root, */ preprocess_function_rtes(root); - /* - * Scan the rangetable for relations with virtual generated columns, and - * replace all Var nodes in the query that reference these columns with - * the generation expressions. Recursion issues here are handled in the - * same way as for SubLinks. - */ - parse = root->parse = expand_virtual_generated_columns(root); - /* * Check to see if any subqueries in the jointree can be merged into this * query. diff --git a/src/backend/optimizer/plan/subselect.c b/src/backend/optimizer/plan/subselect.c index e7cb3fede665..89e6873da08f 100644 --- a/src/backend/optimizer/plan/subselect.c +++ b/src/backend/optimizer/plan/subselect.c @@ -1458,6 +1458,7 @@ convert_EXISTS_sublink_to_join(PlannerInfo *root, SubLink *sublink, int varno; Relids clause_varnos; Relids upper_varnos; + PlannerInfo subroot; Assert(sublink->subLinkType == EXISTS_SUBLINK); @@ -1487,6 +1488,21 @@ convert_EXISTS_sublink_to_join(PlannerInfo *root, SubLink *sublink, if (!simplify_EXISTS_query(root, subselect)) return NULL; + /* + * Scan the rangetable for relations with virtual generated columns, and + * replace all Var nodes in the subquery that reference these columns with + * the generation expressions. + * + * Note: we construct up an entirely dummy PlannerInfo for use here. This + * is fine because only the "glob" and "parse" links will be used in this + * case. + */ + MemSet(&subroot, 0, sizeof(subroot)); + subroot.type = T_PlannerInfo; + subroot.glob = root->glob; + subroot.parse = subselect; + subselect = expand_virtual_generated_columns(&subroot); + /* * Separate out the WHERE clause. (We could theoretically also remove * top-level plain JOIN/ON clauses, but it's probably not worth the diff --git a/src/backend/optimizer/prep/prepjointree.c b/src/backend/optimizer/prep/prepjointree.c index 87dc6f56b576..8140d22de703 100644 --- a/src/backend/optimizer/prep/prepjointree.c +++ b/src/backend/optimizer/prep/prepjointree.c @@ -4,10 +4,10 @@ * Planner preprocessing for subqueries and join tree manipulation. * * NOTE: the intended sequence for invoking these operations is + * expand_virtual_generated_columns * replace_empty_jointree * pull_up_sublinks * preprocess_function_rtes - * expand_virtual_generated_columns * pull_up_subqueries * flatten_simple_union_all * do expression preprocessing (including flattening JOIN alias vars) @@ -958,10 +958,6 @@ preprocess_function_rtes(PlannerInfo *root) * generation expressions. Note that we do not descend into subqueries; that * is taken care of when the subqueries are planned. * - * This has to be done after we have pulled up any SubLinks within the query's - * quals; otherwise any virtual generated column references within the SubLinks - * that should be transformed into joins wouldn't get expanded. - * * Returns a modified copy of the query tree, if any relations with virtual * generated columns are present. */ @@ -1333,6 +1329,13 @@ pull_up_simple_subquery(PlannerInfo *root, Node *jtnode, RangeTblEntry *rte, /* No CTEs to worry about */ Assert(subquery->cteList == NIL); + /* + * Scan the rangetable for relations with virtual generated columns, and + * replace all Var nodes in the subquery that reference these columns with + * the generation expressions. + */ + subquery = subroot->parse = expand_virtual_generated_columns(subroot); + /* * If the FROM clause is empty, replace it with a dummy RTE_RESULT RTE, so * that we don't need so many special cases to deal with that situation. @@ -1352,13 +1355,6 @@ pull_up_simple_subquery(PlannerInfo *root, Node *jtnode, RangeTblEntry *rte, */ preprocess_function_rtes(subroot); - /* - * Scan the rangetable for relations with virtual generated columns, and - * replace all Var nodes in the query that reference these columns with - * the generation expressions. - */ - subquery = subroot->parse = expand_virtual_generated_columns(subroot); - /* * Recursively pull up the subquery's subqueries, so that * pull_up_subqueries' processing is complete for its jointree and diff --git a/src/include/optimizer/prep.h b/src/include/optimizer/prep.h index df56202777c7..ceb731bcf5ef 100644 --- a/src/include/optimizer/prep.h +++ b/src/include/optimizer/prep.h @@ -22,10 +22,10 @@ * prototypes for prepjointree.c */ extern void transform_MERGE_to_join(Query *parse); +extern Query *expand_virtual_generated_columns(PlannerInfo *root); extern void replace_empty_jointree(Query *parse); extern void pull_up_sublinks(PlannerInfo *root); extern void preprocess_function_rtes(PlannerInfo *root); -extern Query *expand_virtual_generated_columns(PlannerInfo *root); extern void pull_up_subqueries(PlannerInfo *root); extern void flatten_simple_union_all(PlannerInfo *root); extern void reduce_outer_joins(PlannerInfo *root); diff --git a/src/test/regress/expected/generated_virtual.out b/src/test/regress/expected/generated_virtual.out index 6300e7c1d96e..b766ccb1dc2e 100644 --- a/src/test/regress/expected/generated_virtual.out +++ b/src/test/regress/expected/generated_virtual.out @@ -1591,4 +1591,26 @@ select * from gtest32 t group by grouping sets (a, b, c, d) having c = 20; | | 20 | (1 row) +-- Ensure that virtual generated column references within SubLinks that should +-- be transformed into joins can get expanded +explain (costs off) +select 1 from gtest32 t1 where exists + (select 1 from gtest32 t2 where t1.a > t2.a and t2.b = 2); + QUERY PLAN +------------------------------------- + Nested Loop Semi Join + Join Filter: (t1.a > t2.a) + -> Seq Scan on gtest32 t1 + -> Materialize + -> Seq Scan on gtest32 t2 + Filter: ((a * 2) = 2) +(6 rows) + +select 1 from gtest32 t1 where exists + (select 1 from gtest32 t2 where t1.a > t2.a and t2.b = 2); + ?column? +---------- + 1 +(1 row) + drop table gtest32; diff --git a/src/test/regress/sql/generated_virtual.sql b/src/test/regress/sql/generated_virtual.sql index b4eedeee2fb2..5dd68381e1c5 100644 --- a/src/test/regress/sql/generated_virtual.sql +++ b/src/test/regress/sql/generated_virtual.sql @@ -832,4 +832,13 @@ explain (verbose, costs off) select * from gtest32 t group by grouping sets (a, b, c, d) having c = 20; select * from gtest32 t group by grouping sets (a, b, c, d) having c = 20; +-- Ensure that virtual generated column references within SubLinks that should +-- be transformed into joins can get expanded +explain (costs off) +select 1 from gtest32 t1 where exists + (select 1 from gtest32 t2 where t1.a > t2.a and t2.b = 2); + +select 1 from gtest32 t1 where exists + (select 1 from gtest32 t2 where t1.a > t2.a and t2.b = 2); + drop table gtest32; From 3f1a350bd9b65b45eea5677556232d96772abebd Mon Sep 17 00:00:00 2001 From: Richard Guo Date: Thu, 24 Apr 2025 14:58:03 +0900 Subject: [PATCH 2/3] Centralize collection of catalog info needed early in the planner There are several pieces of catalog information that need to be retrieved for a relation during the early stage of planning. These include relhassubclass, which is used to clear the inh flag if the relation has no children, as well as a column's attgenerated and default value, which are needed to expand virtual generated columns. More such information may be required in the future. Currently, these pieces of catalog data are collected in multiple places, resulting in repeated table_open/table_close calls for each relation in the rangetable. This patch centralizes the collection of all required early-stage catalog information into a single loop over the rangetable, allowing each relation to be opened and closed only once. --- src/backend/optimizer/plan/planner.c | 31 +-- src/backend/optimizer/plan/subselect.c | 9 +- src/backend/optimizer/prep/prepjointree.c | 299 +++++++++++++--------- src/include/optimizer/prep.h | 2 +- 4 files changed, 190 insertions(+), 151 deletions(-) diff --git a/src/backend/optimizer/plan/planner.c b/src/backend/optimizer/plan/planner.c index d9c2ac374cfb..e6d16b799b56 100644 --- a/src/backend/optimizer/plan/planner.c +++ b/src/backend/optimizer/plan/planner.c @@ -721,13 +721,15 @@ subquery_planner(PlannerGlobal *glob, Query *parse, PlannerInfo *parent_root, transform_MERGE_to_join(parse); /* - * Scan the rangetable for relations with virtual generated columns, and - * replace all Var nodes in the query that reference these columns with - * the generation expressions. Note that this step does not descend into - * sublinks and subqueries; if we pull up any sublinks or subqueries - * below, their rangetables are processed just before pulling them up. + * Scan the rangetable for relation RTEs and retrieve the necessary + * catalog information for each relation. Using this information, clear + * the inh flag for any relation that has no children, and expand virtual + * generated columns for any relation that contains them. Note that this + * step does not descend into sublinks and subqueries; if we pull up any + * sublinks or subqueries below, their relation RTEs are processed just + * before pulling them up. */ - parse = root->parse = expand_virtual_generated_columns(root); + parse = root->parse = preprocess_relation_rtes(root); /* * If the FROM clause is empty, replace it with a dummy RTE_RESULT RTE, so @@ -788,23 +790,6 @@ subquery_planner(PlannerGlobal *glob, Query *parse, PlannerInfo *parent_root, switch (rte->rtekind) { - case RTE_RELATION: - if (rte->inh) - { - /* - * Check to see if the relation actually has any children; - * if not, clear the inh flag so we can treat it as a - * plain base relation. - * - * Note: this could give a false-positive result, if the - * rel once had children but no longer does. We used to - * be able to clear rte->inh later on when we discovered - * that, but no more; we have to handle such cases as - * full-fledged inheritance. - */ - rte->inh = has_subclass(rte->relid); - } - break; case RTE_JOIN: root->hasJoinRTEs = true; if (IS_OUTER_JOIN(rte->jointype)) diff --git a/src/backend/optimizer/plan/subselect.c b/src/backend/optimizer/plan/subselect.c index 89e6873da08f..65fc3f49d39e 100644 --- a/src/backend/optimizer/plan/subselect.c +++ b/src/backend/optimizer/plan/subselect.c @@ -1489,9 +1489,10 @@ convert_EXISTS_sublink_to_join(PlannerInfo *root, SubLink *sublink, return NULL; /* - * Scan the rangetable for relations with virtual generated columns, and - * replace all Var nodes in the subquery that reference these columns with - * the generation expressions. + * Scan the rangetable for relation RTEs and retrieve the necessary + * catalog information for each relation. Using this information, clear + * the inh flag for any relation that has no children, and expand virtual + * generated columns for any relation that contains them. * * Note: we construct up an entirely dummy PlannerInfo for use here. This * is fine because only the "glob" and "parse" links will be used in this @@ -1501,7 +1502,7 @@ convert_EXISTS_sublink_to_join(PlannerInfo *root, SubLink *sublink, subroot.type = T_PlannerInfo; subroot.glob = root->glob; subroot.parse = subselect; - subselect = expand_virtual_generated_columns(&subroot); + subselect = preprocess_relation_rtes(&subroot); /* * Separate out the WHERE clause. (We could theoretically also remove diff --git a/src/backend/optimizer/prep/prepjointree.c b/src/backend/optimizer/prep/prepjointree.c index 8140d22de703..4b38851bd42b 100644 --- a/src/backend/optimizer/prep/prepjointree.c +++ b/src/backend/optimizer/prep/prepjointree.c @@ -4,7 +4,7 @@ * Planner preprocessing for subqueries and join tree manipulation. * * NOTE: the intended sequence for invoking these operations is - * expand_virtual_generated_columns + * preprocess_relation_rtes * replace_empty_jointree * pull_up_sublinks * preprocess_function_rtes @@ -102,6 +102,9 @@ typedef struct reduce_outer_joins_partial_state Relids unreduced_side; /* relids in its still-nullable side */ } reduce_outer_joins_partial_state; +static Query *expand_virtual_generated_columns(PlannerInfo *root, Query *parse, + RangeTblEntry *rte, int rt_index, + Relation relation); static Node *pull_up_sublinks_jointree_recurse(PlannerInfo *root, Node *jtnode, Relids *relids); static Node *pull_up_sublinks_qual_recurse(PlannerInfo *root, Node *node, @@ -392,6 +395,173 @@ transform_MERGE_to_join(Query *parse) parse->mergeJoinCondition = NULL; /* join condition not needed */ } +/* + * preprocess_relation_rtes + * Do the preprocessing work for any relation RTEs in the FROM clause. + * + * This scans the rangetable for relation RTEs and retrieves the necessary + * catalog information for each relation. Using this information, it clears + * the inh flag for any relation that has no children, and expands virtual + * generated columns for any relation that contains them. + * + * Note that expanding virtual generated columns may cause the query tree to + * have new copies of rangetable entries. Therefore, we have to use list_nth + * instead of foreach when iterating over the query's rangetable. + * + * Returns a modified copy of the query tree, if any relations with virtual + * generated columns are present. + */ +Query * +preprocess_relation_rtes(PlannerInfo *root) +{ + Query *parse = root->parse; + int rtable_size; + int rt_index; + + rtable_size = list_length(parse->rtable); + + for (rt_index = 0; rt_index < rtable_size; rt_index++) + { + RangeTblEntry *rte = rt_fetch(rt_index + 1, parse->rtable); + Relation relation; + + /* We only care about relation RTEs. */ + if (rte->rtekind != RTE_RELATION) + continue; + + /* + * We need not lock the relation since it was already locked by the + * rewriter. + */ + relation = table_open(rte->relid, NoLock); + + /* + * Check to see if the relation actually has any children; if not, + * clear the inh flag so we can treat it as a plain base relation. + * + * Note: this could give a false-positive result, if the rel once had + * children but no longer does. We used to be able to clear rte->inh + * later on when we discovered that, but no more; we have to handle + * such cases as full-fledged inheritance. + */ + if (rte->inh) + rte->inh = relation->rd_rel->relhassubclass; + + /* + * Check to see if the relation has any virtual generated columns; if + * so, replace all Var nodes in the query that reference these columns + * with the generation expressions. + */ + parse = expand_virtual_generated_columns(root, parse, + rte, rt_index + 1, + relation); + + table_close(relation, NoLock); + } + + return parse; +} + +/* + * expand_virtual_generated_columns + * Expand virtual generated columns for the given relation. + * + * This checks whether the given relation has any virtual generated columns, + * and if so, replaces all Var nodes in the query that reference those columns + * with their generation expressions. + * + * Returns a modified copy of the query tree if the relation contains virtual + * generated columns. + */ +static Query * +expand_virtual_generated_columns(PlannerInfo *root, Query *parse, + RangeTblEntry *rte, int rt_index, + Relation relation) +{ + TupleDesc tupdesc; + + /* Only normal relations can have virtual generated columns */ + Assert(rte->rtekind == RTE_RELATION); + + tupdesc = RelationGetDescr(relation); + if (tupdesc->constr && tupdesc->constr->has_generated_virtual) + { + List *tlist = NIL; + pullup_replace_vars_context rvcontext; + + for (int i = 0; i < tupdesc->natts; i++) + { + Form_pg_attribute attr = TupleDescAttr(tupdesc, i); + TargetEntry *tle; + + if (attr->attgenerated == ATTRIBUTE_GENERATED_VIRTUAL) + { + Node *defexpr; + + defexpr = build_generation_expression(relation, i + 1); + ChangeVarNodes(defexpr, 1, rt_index, 0); + + tle = makeTargetEntry((Expr *) defexpr, i + 1, 0, false); + tlist = lappend(tlist, tle); + } + else + { + Var *var; + + var = makeVar(rt_index, + i + 1, + attr->atttypid, + attr->atttypmod, + attr->attcollation, + 0); + + tle = makeTargetEntry((Expr *) var, i + 1, 0, false); + tlist = lappend(tlist, tle); + } + } + + Assert(list_length(tlist) > 0); + Assert(!rte->lateral); + + /* + * The relation's targetlist items are now in the appropriate form to + * insert into the query, except that we may need to wrap them in + * PlaceHolderVars. Set up required context data for + * pullup_replace_vars. + */ + rvcontext.root = root; + rvcontext.targetlist = tlist; + rvcontext.target_rte = rte; + rvcontext.result_relation = parse->resultRelation; + /* won't need these values */ + rvcontext.relids = NULL; + rvcontext.nullinfo = NULL; + /* pass NULL for outer_hasSubLinks */ + rvcontext.outer_hasSubLinks = NULL; + rvcontext.varno = rt_index; + /* this flag will be set below, if needed */ + rvcontext.wrap_option = REPLACE_WRAP_NONE; + /* initialize cache array with indexes 0 .. length(tlist) */ + rvcontext.rv_cache = palloc0((list_length(tlist) + 1) * + sizeof(Node *)); + + /* + * If the query uses grouping sets, we need a PlaceHolderVar for each + * expression of the relation's targetlist items. (See comments in + * pull_up_simple_subquery().) + */ + if (parse->groupingSets) + rvcontext.wrap_option = REPLACE_WRAP_ALL; + + /* + * Apply pullup variable replacement throughout the query tree. + */ + parse = (Query *) pullup_replace_vars((Node *) parse, &rvcontext); + } + + return parse; +} + /* * replace_empty_jointree * If the Query's jointree is empty, replace it with a dummy RTE_RESULT @@ -949,124 +1119,6 @@ preprocess_function_rtes(PlannerInfo *root) } } -/* - * expand_virtual_generated_columns - * Expand all virtual generated column references in a query. - * - * This scans the rangetable for relations with virtual generated columns, and - * replaces all Var nodes in the query that reference these columns with the - * generation expressions. Note that we do not descend into subqueries; that - * is taken care of when the subqueries are planned. - * - * Returns a modified copy of the query tree, if any relations with virtual - * generated columns are present. - */ -Query * -expand_virtual_generated_columns(PlannerInfo *root) -{ - Query *parse = root->parse; - int rt_index; - ListCell *lc; - - rt_index = 0; - foreach(lc, parse->rtable) - { - RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc); - Relation rel; - TupleDesc tupdesc; - - ++rt_index; - - /* - * Only normal relations can have virtual generated columns. - */ - if (rte->rtekind != RTE_RELATION) - continue; - - rel = table_open(rte->relid, NoLock); - - tupdesc = RelationGetDescr(rel); - if (tupdesc->constr && tupdesc->constr->has_generated_virtual) - { - List *tlist = NIL; - pullup_replace_vars_context rvcontext; - - for (int i = 0; i < tupdesc->natts; i++) - { - Form_pg_attribute attr = TupleDescAttr(tupdesc, i); - TargetEntry *tle; - - if (attr->attgenerated == ATTRIBUTE_GENERATED_VIRTUAL) - { - Node *defexpr; - - defexpr = build_generation_expression(rel, i + 1); - ChangeVarNodes(defexpr, 1, rt_index, 0); - - tle = makeTargetEntry((Expr *) defexpr, i + 1, 0, false); - tlist = lappend(tlist, tle); - } - else - { - Var *var; - - var = makeVar(rt_index, - i + 1, - attr->atttypid, - attr->atttypmod, - attr->attcollation, - 0); - - tle = makeTargetEntry((Expr *) var, i + 1, 0, false); - tlist = lappend(tlist, tle); - } - } - - Assert(list_length(tlist) > 0); - Assert(!rte->lateral); - - /* - * The relation's targetlist items are now in the appropriate form - * to insert into the query, except that we may need to wrap them - * in PlaceHolderVars. Set up required context data for - * pullup_replace_vars. - */ - rvcontext.root = root; - rvcontext.targetlist = tlist; - rvcontext.target_rte = rte; - rvcontext.result_relation = parse->resultRelation; - /* won't need these values */ - rvcontext.relids = NULL; - rvcontext.nullinfo = NULL; - /* pass NULL for outer_hasSubLinks */ - rvcontext.outer_hasSubLinks = NULL; - rvcontext.varno = rt_index; - /* this flag will be set below, if needed */ - rvcontext.wrap_option = REPLACE_WRAP_NONE; - /* initialize cache array with indexes 0 .. length(tlist) */ - rvcontext.rv_cache = palloc0((list_length(tlist) + 1) * - sizeof(Node *)); - - /* - * If the query uses grouping sets, we need a PlaceHolderVar for - * each expression of the relation's targetlist items. (See - * comments in pull_up_simple_subquery().) - */ - if (parse->groupingSets) - rvcontext.wrap_option = REPLACE_WRAP_ALL; - - /* - * Apply pullup variable replacement throughout the query tree. - */ - parse = (Query *) pullup_replace_vars((Node *) parse, &rvcontext); - } - - table_close(rel, NoLock); - } - - return parse; -} - /* * pull_up_subqueries * Look for subqueries in the rangetable that can be pulled up into @@ -1330,11 +1382,12 @@ pull_up_simple_subquery(PlannerInfo *root, Node *jtnode, RangeTblEntry *rte, Assert(subquery->cteList == NIL); /* - * Scan the rangetable for relations with virtual generated columns, and - * replace all Var nodes in the subquery that reference these columns with - * the generation expressions. + * Scan the rangetable for relation RTEs and retrieve the necessary + * catalog information for each relation. Using this information, clear + * the inh flag for any relation that has no children, and expand virtual + * generated columns for any relation that contains them. */ - subquery = subroot->parse = expand_virtual_generated_columns(subroot); + subquery = subroot->parse = preprocess_relation_rtes(subroot); /* * If the FROM clause is empty, replace it with a dummy RTE_RESULT RTE, so diff --git a/src/include/optimizer/prep.h b/src/include/optimizer/prep.h index ceb731bcf5ef..4fbecdb44627 100644 --- a/src/include/optimizer/prep.h +++ b/src/include/optimizer/prep.h @@ -22,7 +22,7 @@ * prototypes for prepjointree.c */ extern void transform_MERGE_to_join(Query *parse); -extern Query *expand_virtual_generated_columns(PlannerInfo *root); +extern Query *preprocess_relation_rtes(PlannerInfo *root); extern void replace_empty_jointree(Query *parse); extern void pull_up_sublinks(PlannerInfo *root); extern void preprocess_function_rtes(PlannerInfo *root); From abc04769ff9bc7ea35d555f8c97a3e3691bfd96b Mon Sep 17 00:00:00 2001 From: Richard Guo Date: Wed, 30 Apr 2025 18:50:37 +0900 Subject: [PATCH 3/3] Reduce "Var IS [NOT] NULL" quals during constant folding In commit b262ad440, we introduced an optimization that reduces an IS [NOT] NULL qual on a NOT NULL column to constant true or constant false, provided we can prove that the input expression of the NullTest is not nullable by any outer joins or grouping sets. This deduction happens quite late in the planner, during the distribution of quals to rels in query_planner. However, this approach has some drawbacks: we can't perform any further folding with the constant, and it turns out to be prone to bugs. Ideally, this deduction should happen during constant folding. However, the per-relation information about which columns are defined as NOT NULL is not available at that point. This information is currently collected from catalogs when building RelOptInfos for base or "other" relations. This patch moves the collection of NOT NULL attribute information for relations before pull_up_sublinks, storing it in a hash table keyed by relation OID. It then uses this information to perform the NullTest deduction for Vars during constant folding. This also makes it possible to leverage this information to pull up NOT IN subqueries. Note that this patch does not get rid of restriction_is_always_true and restriction_is_always_false. Removing them would prevent us from reducing some IS [NOT] NULL quals that we were previously able to reduce, because (a) the self-join elimination may introduce new IS NOT NULL quals after constant folding, and (b) if some outer joins are converted to inner joins, previously irreducible NullTest quals may become reducible. --- .../postgres_fdw/expected/postgres_fdw.out | 8 +- contrib/postgres_fdw/sql/postgres_fdw.sql | 2 +- src/backend/optimizer/plan/initsplan.c | 24 +--- src/backend/optimizer/plan/planner.c | 12 +- src/backend/optimizer/plan/subselect.c | 20 ++- src/backend/optimizer/prep/prepjointree.c | 19 ++- src/backend/optimizer/util/clauses.c | 92 ++++++++++++- src/backend/optimizer/util/inherit.c | 10 +- src/backend/optimizer/util/plancat.c | 127 +++++++++++++++--- src/include/nodes/pathnodes.h | 12 +- src/include/optimizer/optimizer.h | 2 + src/include/optimizer/plancat.h | 4 + .../regress/expected/generated_virtual.out | 6 +- src/test/regress/expected/join.out | 6 +- src/test/regress/expected/predicate.out | 54 +++++++- src/test/regress/sql/predicate.sql | 18 +++ src/tools/pgindent/typedefs.list | 1 + 17 files changed, 336 insertions(+), 81 deletions(-) diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 2185b42bb4f7..e3621a47bf1b 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -710,12 +710,12 @@ EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE c1 = -c1; -- Op Remote SQL: SELECT "C 1", c2, c3, c4, c5, c6, c7, c8 FROM "S 1"."T 1" WHERE (("C 1" = (- "C 1"))) (3 rows) -EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE (c1 IS NOT NULL) IS DISTINCT FROM (c1 IS NOT NULL); -- DistinctExpr - QUERY PLAN --------------------------------------------------------------------------------------------------------------------------------------------- +EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE (c3 IS NOT NULL) IS DISTINCT FROM (c3 IS NOT NULL); -- DistinctExpr + QUERY PLAN +-------------------------------------------------------------------------------------------------------------------------------------- Foreign Scan on public.ft1 t1 Output: c1, c2, c3, c4, c5, c6, c7, c8 - Remote SQL: SELECT "C 1", c2, c3, c4, c5, c6, c7, c8 FROM "S 1"."T 1" WHERE ((("C 1" IS NOT NULL) IS DISTINCT FROM ("C 1" IS NOT NULL))) + Remote SQL: SELECT "C 1", c2, c3, c4, c5, c6, c7, c8 FROM "S 1"."T 1" WHERE (((c3 IS NOT NULL) IS DISTINCT FROM (c3 IS NOT NULL))) (3 rows) EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE c1 = ANY(ARRAY[c2, 1, c1 + 0]); -- ScalarArrayOpExpr diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index e534b40de3c7..036c8749914d 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -352,7 +352,7 @@ EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE c3 IS NULL; -- Nu EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE c3 IS NOT NULL; -- NullTest EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE round(abs(c1), 0) = 1; -- FuncExpr EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE c1 = -c1; -- OpExpr(l) -EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE (c1 IS NOT NULL) IS DISTINCT FROM (c1 IS NOT NULL); -- DistinctExpr +EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE (c3 IS NOT NULL) IS DISTINCT FROM (c3 IS NOT NULL); -- DistinctExpr EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE c1 = ANY(ARRAY[c2, 1, c1 + 0]); -- ScalarArrayOpExpr EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE c1 = (ARRAY[c1,c2,3])[1]; -- SubscriptingRef EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE c6 = E'foo''s\\bar'; -- check special chars diff --git a/src/backend/optimizer/plan/initsplan.c b/src/backend/optimizer/plan/initsplan.c index 01804b085b3b..3e3fec892529 100644 --- a/src/backend/optimizer/plan/initsplan.c +++ b/src/backend/optimizer/plan/initsplan.c @@ -3048,36 +3048,16 @@ add_base_clause_to_rel(PlannerInfo *root, Index relid, * expr_is_nonnullable * Check to see if the Expr cannot be NULL * - * If the Expr is a simple Var that is defined NOT NULL and meanwhile is not - * nulled by any outer joins, then we can know that it cannot be NULL. + * Currently we only support simple Vars. */ static bool expr_is_nonnullable(PlannerInfo *root, Expr *expr) { - RelOptInfo *rel; - Var *var; - /* For now only check simple Vars */ if (!IsA(expr, Var)) return false; - var = (Var *) expr; - - /* could the Var be nulled by any outer joins? */ - if (!bms_is_empty(var->varnullingrels)) - return false; - - /* system columns cannot be NULL */ - if (var->varattno < 0) - return true; - - /* is the column defined NOT NULL? */ - rel = find_base_rel(root, var->varno); - if (var->varattno > 0 && - bms_is_member(var->varattno, rel->notnullattnums)) - return true; - - return false; + return var_is_nonnullable(root, (Var *) expr, true); } /* diff --git a/src/backend/optimizer/plan/planner.c b/src/backend/optimizer/plan/planner.c index e6d16b799b56..66f1f416364c 100644 --- a/src/backend/optimizer/plan/planner.c +++ b/src/backend/optimizer/plan/planner.c @@ -342,6 +342,7 @@ standard_planner(Query *parse, const char *query_string, int cursorOptions, glob->transientPlan = false; glob->dependsOnRole = false; glob->partition_directory = NULL; + glob->rel_notnullatts_hash = NULL; /* * Assess whether it's feasible to use parallel mode for this query. We @@ -723,11 +724,12 @@ subquery_planner(PlannerGlobal *glob, Query *parse, PlannerInfo *parent_root, /* * Scan the rangetable for relation RTEs and retrieve the necessary * catalog information for each relation. Using this information, clear - * the inh flag for any relation that has no children, and expand virtual - * generated columns for any relation that contains them. Note that this - * step does not descend into sublinks and subqueries; if we pull up any - * sublinks or subqueries below, their relation RTEs are processed just - * before pulling them up. + * the inh flag for any relation that has no children, collect not-null + * attribute numbers for any relation that has column not-null + * constraints, and expand virtual generated columns for any relation that + * contains them. Note that this step does not descend into sublinks and + * subqueries; if we pull up any sublinks or subqueries below, their + * relation RTEs are processed just before pulling them up. */ parse = root->parse = preprocess_relation_rtes(root); diff --git a/src/backend/optimizer/plan/subselect.c b/src/backend/optimizer/plan/subselect.c index 65fc3f49d39e..8ea200615946 100644 --- a/src/backend/optimizer/plan/subselect.c +++ b/src/backend/optimizer/plan/subselect.c @@ -1491,8 +1491,10 @@ convert_EXISTS_sublink_to_join(PlannerInfo *root, SubLink *sublink, /* * Scan the rangetable for relation RTEs and retrieve the necessary * catalog information for each relation. Using this information, clear - * the inh flag for any relation that has no children, and expand virtual - * generated columns for any relation that contains them. + * the inh flag for any relation that has no children, collect not-null + * attribute numbers for any relation that has column not-null + * constraints, and expand virtual generated columns for any relation that + * contains them. * * Note: we construct up an entirely dummy PlannerInfo for use here. This * is fine because only the "glob" and "parse" links will be used in this @@ -1749,6 +1751,7 @@ convert_EXISTS_to_ANY(PlannerInfo *root, Query *subselect, Node **testexpr, List **paramIds) { Node *whereClause; + PlannerInfo subroot; List *leftargs, *rightargs, *opids, @@ -1808,12 +1811,15 @@ convert_EXISTS_to_ANY(PlannerInfo *root, Query *subselect, * parent aliases were flattened already, and we're not going to pull any * child Vars (of any description) into the parent. * - * Note: passing the parent's root to eval_const_expressions is - * technically wrong, but we can get away with it since only the - * boundParams (if any) are used, and those would be the same in a - * subroot. + * Note: we construct up an entirely dummy PlannerInfo to pass to + * eval_const_expressions. This is fine because only the "glob" and + * "parse" links are used by eval_const_expressions. */ - whereClause = eval_const_expressions(root, whereClause); + MemSet(&subroot, 0, sizeof(subroot)); + subroot.type = T_PlannerInfo; + subroot.glob = root->glob; + subroot.parse = subselect; + whereClause = eval_const_expressions(&subroot, whereClause); whereClause = (Node *) canonicalize_qual((Expr *) whereClause, false); whereClause = (Node *) make_ands_implicit((Expr *) whereClause); diff --git a/src/backend/optimizer/prep/prepjointree.c b/src/backend/optimizer/prep/prepjointree.c index 4b38851bd42b..35e8d3c183b4 100644 --- a/src/backend/optimizer/prep/prepjointree.c +++ b/src/backend/optimizer/prep/prepjointree.c @@ -36,6 +36,7 @@ #include "optimizer/clauses.h" #include "optimizer/optimizer.h" #include "optimizer/placeholder.h" +#include "optimizer/plancat.h" #include "optimizer/prep.h" #include "optimizer/subselect.h" #include "optimizer/tlist.h" @@ -401,8 +402,9 @@ transform_MERGE_to_join(Query *parse) * * This scans the rangetable for relation RTEs and retrieves the necessary * catalog information for each relation. Using this information, it clears - * the inh flag for any relation that has no children, and expands virtual - * generated columns for any relation that contains them. + * the inh flag for any relation that has no children, collects not-null + * attribute numbers for any relation that has column not-null constraints, and + * expands virtual generated columns for any relation that contains them. * * Note that expanding virtual generated columns may cause the query tree to * have new copies of rangetable entries. Therefore, we have to use list_nth @@ -447,6 +449,13 @@ preprocess_relation_rtes(PlannerInfo *root) if (rte->inh) rte->inh = relation->rd_rel->relhassubclass; + /* + * Check to see if the relation has any column not-null constraints; + * if so, retrieve the constraint information and store it in a + * relation OID based hash table. + */ + get_relation_notnullatts(root, relation); + /* * Check to see if the relation has any virtual generated columns; if * so, replace all Var nodes in the query that reference these columns @@ -1384,8 +1393,10 @@ pull_up_simple_subquery(PlannerInfo *root, Node *jtnode, RangeTblEntry *rte, /* * Scan the rangetable for relation RTEs and retrieve the necessary * catalog information for each relation. Using this information, clear - * the inh flag for any relation that has no children, and expand virtual - * generated columns for any relation that contains them. + * the inh flag for any relation that has no children, collect not-null + * attribute numbers for any relation that has column not-null + * constraints, and expand virtual generated columns for any relation that + * contains them. */ subquery = subroot->parse = preprocess_relation_rtes(subroot); diff --git a/src/backend/optimizer/util/clauses.c b/src/backend/optimizer/util/clauses.c index 26a3e0500866..e83f4b061d71 100644 --- a/src/backend/optimizer/util/clauses.c +++ b/src/backend/optimizer/util/clauses.c @@ -20,6 +20,7 @@ #include "postgres.h" #include "access/htup_details.h" +#include "catalog/pg_class.h" #include "catalog/pg_language.h" #include "catalog/pg_operator.h" #include "catalog/pg_proc.h" @@ -36,6 +37,7 @@ #include "optimizer/clauses.h" #include "optimizer/cost.h" #include "optimizer/optimizer.h" +#include "optimizer/pathnode.h" #include "optimizer/plancat.h" #include "optimizer/planmain.h" #include "parser/analyze.h" @@ -43,6 +45,7 @@ #include "parser/parse_collate.h" #include "parser/parse_func.h" #include "parser/parse_oper.h" +#include "parser/parsetree.h" #include "rewrite/rewriteHandler.h" #include "rewrite/rewriteManip.h" #include "tcop/tcopprot.h" @@ -2242,7 +2245,8 @@ rowtype_field_matches(Oid rowtypeid, int fieldnum, * only operators and functions that are reasonable to try to execute. * * NOTE: "root" can be passed as NULL if the caller never wants to do any - * Param substitutions nor receive info about inlined functions. + * Param substitutions nor receive info about inlined functions nor reduce + * NullTest for Vars to constant true or constant false. * * NOTE: the planner assumes that this will always flatten nested AND and * OR clauses into N-argument form. See comments in prepqual.c. @@ -3537,6 +3541,31 @@ eval_const_expressions_mutator(Node *node, return makeBoolConst(result, false); } + if (!ntest->argisrow && arg && IsA(arg, Var) && context->root) + { + Var *varg = (Var *) arg; + bool result; + + if (var_is_nonnullable(context->root, varg, false)) + { + switch (ntest->nulltesttype) + { + case IS_NULL: + result = false; + break; + case IS_NOT_NULL: + result = true; + break; + default: + elog(ERROR, "unrecognized nulltesttype: %d", + (int) ntest->nulltesttype); + result = false; /* keep compiler quiet */ + break; + } + + return makeBoolConst(result, false); + } + } newntest = makeNode(NullTest); newntest->arg = (Expr *) arg; @@ -4155,6 +4184,67 @@ simplify_function(Oid funcid, Oid result_type, int32 result_typmod, return newexpr; } +/* + * var_is_nonnullable: check to see if the Var cannot be NULL + * + * If the Var is defined NOT NULL and meanwhile is not nulled by any outer + * joins or grouping sets, then we can know that it cannot be NULL. + * + * use_rel_info indicates whether the corresponding RelOptInfo is available for + * use. + */ +bool +var_is_nonnullable(PlannerInfo *root, Var *var, bool use_rel_info) +{ + Relids notnullattnums = NULL; + + Assert(IsA(var, Var)); + + /* skip upper-level Vars */ + if (var->varlevelsup != 0) + return false; + + /* could the Var be nulled by any outer joins or grouping sets? */ + if (!bms_is_empty(var->varnullingrels)) + return false; + + /* system columns cannot be NULL */ + if (var->varattno < 0) + return true; + + /* + * Check if the Var is defined as NOT NULL. We retrieve the column NOT + * NULL constraint information from the corresponding RelOptInfo if it is + * available; otherwise, we search the hash table for this information. + */ + if (use_rel_info) + { + RelOptInfo *rel = find_base_rel(root, var->varno); + + notnullattnums = rel->notnullattnums; + } + else + { + RangeTblEntry *rte = planner_rt_fetch(var->varno, root); + + /* + * We must skip inheritance parent tables, as some child tables may + * have a NOT NULL constraint for a column while others may not. This + * cannot happen with partitioned tables, though. + */ + if (rte->inh && rte->relkind != RELKIND_PARTITIONED_TABLE) + return false; + + notnullattnums = find_relation_notnullatts(root, rte->relid); + } + + if (var->varattno > 0 && + bms_is_member(var->varattno, notnullattnums)) + return true; + + return false; +} + /* * expand_function_arguments: convert named-notation args to positional args * and/or insert default args, as needed diff --git a/src/backend/optimizer/util/inherit.c b/src/backend/optimizer/util/inherit.c index 17e51cd75d74..30d158069e33 100644 --- a/src/backend/optimizer/util/inherit.c +++ b/src/backend/optimizer/util/inherit.c @@ -466,8 +466,7 @@ expand_single_inheritance_child(PlannerInfo *root, RangeTblEntry *parentrte, Index *childRTindex_p) { Query *parse = root->parse; - Oid parentOID PG_USED_FOR_ASSERTS_ONLY = - RelationGetRelid(parentrel); + Oid parentOID = RelationGetRelid(parentrel); Oid childOID = RelationGetRelid(childrel); RangeTblEntry *childrte; Index childRTindex; @@ -513,6 +512,13 @@ expand_single_inheritance_child(PlannerInfo *root, RangeTblEntry *parentrte, *childrte_p = childrte; *childRTindex_p = childRTindex; + /* + * Retrieve column not-null constraint information for the child relation + * if its relation OID is different from the parent's. + */ + if (childOID != parentOID) + get_relation_notnullatts(root, childrel); + /* * Build an AppendRelInfo struct for each parent/child pair. */ diff --git a/src/backend/optimizer/util/plancat.c b/src/backend/optimizer/util/plancat.c index 59233b647302..c6a58afc5e50 100644 --- a/src/backend/optimizer/util/plancat.c +++ b/src/backend/optimizer/util/plancat.c @@ -59,6 +59,12 @@ int constraint_exclusion = CONSTRAINT_EXCLUSION_PARTITION; /* Hook for plugins to get control in get_relation_info() */ get_relation_info_hook_type get_relation_info_hook = NULL; +typedef struct NotnullHashEntry +{ + Oid relid; /* OID of the relation */ + Relids notnullattnums; /* attnums of NOT NULL columns */ +} NotnullHashEntry; + static void get_relation_foreign_keys(PlannerInfo *root, RelOptInfo *rel, Relation relation, bool inhparent); @@ -172,27 +178,7 @@ get_relation_info(PlannerInfo *root, Oid relationObjectId, bool inhparent, * RangeTblEntry does get populated. */ if (!inhparent || relation->rd_rel->relkind == RELKIND_PARTITIONED_TABLE) - { - for (int i = 0; i < relation->rd_att->natts; i++) - { - CompactAttribute *attr = TupleDescCompactAttr(relation->rd_att, i); - - Assert(attr->attnullability != ATTNULLABLE_UNKNOWN); - - if (attr->attnullability == ATTNULLABLE_VALID) - { - rel->notnullattnums = bms_add_member(rel->notnullattnums, - i + 1); - - /* - * Per RemoveAttributeById(), dropped columns will have their - * attnotnull unset, so we needn't check for dropped columns - * in the above condition. - */ - Assert(!attr->attisdropped); - } - } - } + rel->notnullattnums = find_relation_notnullatts(root, relationObjectId); /* * Estimate relation size --- unless it's an inheritance parent, in which @@ -683,6 +669,105 @@ get_relation_foreign_keys(PlannerInfo *root, RelOptInfo *rel, } } +/* + * get_relation_notnullatts - + * Retrieves column not-null constraint information for a given relation. + * + * We do this while we have the relcache entry open, and store the column + * not-null constraint information in a hash table based on the relation OID. + */ +void +get_relation_notnullatts(PlannerInfo *root, Relation relation) +{ + Oid relid = RelationGetRelid(relation); + NotnullHashEntry *hentry; + bool found; + Relids notnullattnums = NULL; + + /* bail out if the relation has no not-null constraints */ + if (relation->rd_att->constr == NULL || + !relation->rd_att->constr->has_not_null) + return; + + /* create the hash table if it hasn't been created yet */ + if (root->glob->rel_notnullatts_hash == NULL) + { + HTAB *hashtab; + HASHCTL hash_ctl; + + hash_ctl.keysize = sizeof(Oid); + hash_ctl.entrysize = sizeof(NotnullHashEntry); + hash_ctl.hcxt = CurrentMemoryContext; + + hashtab = hash_create("Relation NOT NULL attnums", + 64L, /* arbitrary initial size */ + &hash_ctl, + HASH_ELEM | HASH_BLOBS | HASH_CONTEXT); + + root->glob->rel_notnullatts_hash = hashtab; + } + + /* + * Create a hash entry for this relation OID, if we don't have one + * already. + */ + hentry = (NotnullHashEntry *) hash_search(root->glob->rel_notnullatts_hash, + &relid, + HASH_ENTER, + &found); + + /* bail out if a hash entry already exists for this relation OID */ + if (found) + return; + + /* collect the column not-null constraint information for this relation */ + for (int i = 0; i < relation->rd_att->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(relation->rd_att, i); + + Assert(attr->attnullability != ATTNULLABLE_UNKNOWN); + + if (attr->attnullability == ATTNULLABLE_VALID) + { + notnullattnums = bms_add_member(notnullattnums, i + 1); + + /* + * Per RemoveAttributeById(), dropped columns will have their + * attnotnull unset, so we needn't check for dropped columns in + * the above condition. + */ + Assert(!attr->attisdropped); + } + } + + /* ... and initialize the new hash entry */ + hentry->notnullattnums = notnullattnums; +} + +/* + * find_relation_notnullatts - + * Searches the hash table and returns the column not-null constraint + * information for a given relation. + */ +Relids +find_relation_notnullatts(PlannerInfo *root, Oid relid) +{ + NotnullHashEntry *hentry; + bool found; + + if (root->glob->rel_notnullatts_hash == NULL) + return NULL; + + hentry = (NotnullHashEntry *) hash_search(root->glob->rel_notnullatts_hash, + &relid, + HASH_FIND, + &found); + if (!found) + return NULL; + + return hentry->notnullattnums; +} + /* * infer_arbiter_indexes - * Determine the unique indexes used to arbitrate speculative insertion. diff --git a/src/include/nodes/pathnodes.h b/src/include/nodes/pathnodes.h index 6567759595da..e5dd15098f63 100644 --- a/src/include/nodes/pathnodes.h +++ b/src/include/nodes/pathnodes.h @@ -179,6 +179,9 @@ typedef struct PlannerGlobal /* partition descriptors */ PartitionDirectory partition_directory pg_node_attr(read_write_ignore); + + /* hash table for NOT NULL attnums of relations */ + struct HTAB *rel_notnullatts_hash pg_node_attr(read_write_ignore); } PlannerGlobal; /* macro for fetching the Plan associated with a SubPlan node */ @@ -719,6 +722,9 @@ typedef struct PartitionSchemeData *PartitionScheme; * the attribute is needed as part of final targetlist * attr_widths - cache space for per-attribute width estimates; * zero means not computed yet + * notnullattnums - zero-based set containing attnums of NOT NULL + * columns (not populated for rels corresponding to + * non-partitioned inh==true RTEs) * nulling_relids - relids of outer joins that can null this rel * lateral_vars - lateral cross-references of rel, if any (list of * Vars and PlaceHolderVars) @@ -952,11 +958,7 @@ typedef struct RelOptInfo Relids *attr_needed pg_node_attr(read_write_ignore); /* array indexed [min_attr .. max_attr] */ int32 *attr_widths pg_node_attr(read_write_ignore); - - /* - * Zero-based set containing attnums of NOT NULL columns. Not populated - * for rels corresponding to non-partitioned inh==true RTEs. - */ + /* zero-based set containing attnums of NOT NULL columns */ Bitmapset *notnullattnums; /* relids of outer joins that can null this baserel */ Relids nulling_relids; diff --git a/src/include/optimizer/optimizer.h b/src/include/optimizer/optimizer.h index 546828b54bd2..37bc13c2cbde 100644 --- a/src/include/optimizer/optimizer.h +++ b/src/include/optimizer/optimizer.h @@ -154,6 +154,8 @@ extern Node *estimate_expression_value(PlannerInfo *root, Node *node); extern Expr *evaluate_expr(Expr *expr, Oid result_type, int32 result_typmod, Oid result_collation); +extern bool var_is_nonnullable(PlannerInfo *root, Var *var, bool use_rel_info); + extern List *expand_function_arguments(List *args, bool include_out_arguments, Oid result_type, struct HeapTupleData *func_tuple); diff --git a/src/include/optimizer/plancat.h b/src/include/optimizer/plancat.h index cd74e4b1e8b3..d6f6f4ad2d78 100644 --- a/src/include/optimizer/plancat.h +++ b/src/include/optimizer/plancat.h @@ -28,6 +28,10 @@ extern PGDLLIMPORT get_relation_info_hook_type get_relation_info_hook; extern void get_relation_info(PlannerInfo *root, Oid relationObjectId, bool inhparent, RelOptInfo *rel); +extern void get_relation_notnullatts(PlannerInfo *root, Relation relation); + +extern Relids find_relation_notnullatts(PlannerInfo *root, Oid relid); + extern List *infer_arbiter_indexes(PlannerInfo *root); extern void estimate_rel_size(Relation rel, int32 *attr_widths, diff --git a/src/test/regress/expected/generated_virtual.out b/src/test/regress/expected/generated_virtual.out index b766ccb1dc2e..47c049998cd4 100644 --- a/src/test/regress/expected/generated_virtual.out +++ b/src/test/regress/expected/generated_virtual.out @@ -1531,11 +1531,11 @@ where coalesce(t2.b, 1) = 2; explain (costs off) select t1.a from gtest32 t1 left join gtest32 t2 on t1.a = t2.a where coalesce(t2.b, 1) = 2 or t1.a is null; - QUERY PLAN -------------------------------------------------------------- + QUERY PLAN +----------------------------------------- Hash Left Join Hash Cond: (t1.a = t2.a) - Filter: ((COALESCE((t2.a * 2), 1) = 2) OR (t1.a IS NULL)) + Filter: (COALESCE((t2.a * 2), 1) = 2) -> Seq Scan on gtest32 t1 -> Hash -> Seq Scan on gtest32 t2 diff --git a/src/test/regress/expected/join.out b/src/test/regress/expected/join.out index f35a0b18c37c..632ae2afe7cb 100644 --- a/src/test/regress/expected/join.out +++ b/src/test/regress/expected/join.out @@ -3639,8 +3639,8 @@ from nt3 as nt3 ) as ss2 on ss2.id = nt3.nt2_id where nt3.id = 1 and ss2.b3; - QUERY PLAN ------------------------------------------------ + QUERY PLAN +---------------------------------------------- Nested Loop -> Nested Loop -> Index Scan using nt3_pkey on nt3 @@ -3649,7 +3649,7 @@ where nt3.id = 1 and ss2.b3; Index Cond: (id = nt3.nt2_id) -> Index Only Scan using nt1_pkey on nt1 Index Cond: (id = nt2.nt1_id) - Filter: (nt2.b1 AND (id IS NOT NULL)) + Filter: (nt2.b1 AND true) (9 rows) select nt3.id diff --git a/src/test/regress/expected/predicate.out b/src/test/regress/expected/predicate.out index b79037748b7e..59bfe33bb1ce 100644 --- a/src/test/regress/expected/predicate.out +++ b/src/test/regress/expected/predicate.out @@ -84,10 +84,10 @@ SELECT * FROM pred_tab t WHERE t.a IS NULL OR t.c IS NULL; -- are provably false EXPLAIN (COSTS OFF) SELECT * FROM pred_tab t WHERE t.b IS NULL OR t.c IS NULL; - QUERY PLAN ----------------------------------------- + QUERY PLAN +------------------------ Seq Scan on pred_tab t - Filter: ((b IS NULL) OR (c IS NULL)) + Filter: (b IS NULL) (2 rows) -- @@ -231,6 +231,54 @@ SELECT * FROM pred_tab t1 -> Seq Scan on pred_tab t3 (9 rows) +-- +-- Tests for NullTest reduction in EXISTS sublink +-- +-- Ensure the IS_NOT_NULL qual is ignored +EXPLAIN (COSTS OFF) +SELECT * FROM pred_tab t1 + LEFT JOIN pred_tab t2 ON EXISTS + (SELECT 1 FROM pred_tab t3, pred_tab t4, pred_tab t5, pred_tab t6 + WHERE t1.a = t3.a AND t6.a IS NOT NULL); + QUERY PLAN +--------------------------------------------------------- + Nested Loop Left Join + Join Filter: EXISTS(SubPlan 1) + -> Seq Scan on pred_tab t1 + -> Materialize + -> Seq Scan on pred_tab t2 + SubPlan 1 + -> Nested Loop + -> Nested Loop + -> Nested Loop + -> Seq Scan on pred_tab t4 + -> Materialize + -> Seq Scan on pred_tab t3 + Filter: (t1.a = a) + -> Materialize + -> Seq Scan on pred_tab t5 + -> Materialize + -> Seq Scan on pred_tab t6 +(17 rows) + +-- Ensure the IS_NULL qual is reduced to constant-FALSE +EXPLAIN (COSTS OFF) +SELECT * FROM pred_tab t1 + LEFT JOIN pred_tab t2 ON EXISTS + (SELECT 1 FROM pred_tab t3, pred_tab t4, pred_tab t5, pred_tab t6 + WHERE t1.a = t3.a AND t6.a IS NULL); + QUERY PLAN +------------------------------------- + Nested Loop Left Join + Join Filter: (InitPlan 1).col1 + InitPlan 1 + -> Result + One-Time Filter: false + -> Seq Scan on pred_tab t1 + -> Materialize + -> Seq Scan on pred_tab t2 +(8 rows) + DROP TABLE pred_tab; -- Validate we handle IS NULL and IS NOT NULL quals correctly with inheritance -- parents. diff --git a/src/test/regress/sql/predicate.sql b/src/test/regress/sql/predicate.sql index 9dcb81b1bc52..d92277353a01 100644 --- a/src/test/regress/sql/predicate.sql +++ b/src/test/regress/sql/predicate.sql @@ -115,6 +115,24 @@ SELECT * FROM pred_tab t1 LEFT JOIN pred_tab t2 ON t1.a = 1 LEFT JOIN pred_tab t3 ON t2.a IS NULL OR t2.c IS NULL; +-- +-- Tests for NullTest reduction in EXISTS sublink +-- + +-- Ensure the IS_NOT_NULL qual is ignored +EXPLAIN (COSTS OFF) +SELECT * FROM pred_tab t1 + LEFT JOIN pred_tab t2 ON EXISTS + (SELECT 1 FROM pred_tab t3, pred_tab t4, pred_tab t5, pred_tab t6 + WHERE t1.a = t3.a AND t6.a IS NOT NULL); + +-- Ensure the IS_NULL qual is reduced to constant-FALSE +EXPLAIN (COSTS OFF) +SELECT * FROM pred_tab t1 + LEFT JOIN pred_tab t2 ON EXISTS + (SELECT 1 FROM pred_tab t3, pred_tab t4, pred_tab t5, pred_tab t6 + WHERE t1.a = t3.a AND t6.a IS NULL); + DROP TABLE pred_tab; -- Validate we handle IS NULL and IS NOT NULL quals correctly with inheritance diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index a8346cda633a..ac36a8888a33 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1750,6 +1750,7 @@ NonEmptyRange Notification NotificationList NotifyStmt +NotnullHashEntry Nsrt NtDllRoutine NtFlushBuffersFileEx_t