diff options
Diffstat (limited to 'src/backend/optimizer/util')
-rw-r--r-- | src/backend/optimizer/util/clauses.c | 99 | ||||
-rw-r--r-- | src/backend/optimizer/util/inherit.c | 10 | ||||
-rw-r--r-- | src/backend/optimizer/util/paramassign.c | 109 | ||||
-rw-r--r-- | src/backend/optimizer/util/pathnode.c | 84 | ||||
-rw-r--r-- | src/backend/optimizer/util/placeholder.c | 40 | ||||
-rw-r--r-- | src/backend/optimizer/util/plancat.c | 127 |
6 files changed, 384 insertions, 85 deletions
diff --git a/src/backend/optimizer/util/clauses.c b/src/backend/optimizer/util/clauses.c index 26a3e050086..6f0b338d2cd 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. @@ -3333,6 +3337,13 @@ eval_const_expressions_mutator(Node *node, -1, coalesceexpr->coalescecollid); + /* + * If there's exactly one surviving argument, we no longer + * need COALESCE at all: the result is that argument + */ + if (list_length(newargs) == 1) + return (Node *) linitial(newargs); + newcoalesce = makeNode(CoalesceExpr); newcoalesce->coalescetype = coalesceexpr->coalescetype; newcoalesce->coalescecollid = coalesceexpr->coalescecollid; @@ -3537,6 +3548,31 @@ 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; @@ -4156,6 +4192,67 @@ simplify_function(Oid funcid, Oid result_type, int32 result_typmod, } /* + * 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 17e51cd75d7..30d158069e3 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; @@ -514,6 +513,13 @@ expand_single_inheritance_child(PlannerInfo *root, RangeTblEntry *parentrte, *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. */ appinfo = make_append_rel_info(parentrel, childrel, diff --git a/src/backend/optimizer/util/paramassign.c b/src/backend/optimizer/util/paramassign.c index 3bd3ce37c8f..4c13c5931b4 100644 --- a/src/backend/optimizer/util/paramassign.c +++ b/src/backend/optimizer/util/paramassign.c @@ -599,38 +599,46 @@ process_subquery_nestloop_params(PlannerInfo *root, List *subplan_params) } /* - * Identify any NestLoopParams that should be supplied by a NestLoop plan - * node with the specified lefthand rels. Remove them from the active - * root->curOuterParams list and return them as the result list. + * Identify any NestLoopParams that should be supplied by a NestLoop + * plan node with the specified lefthand rels and required-outer rels. + * Remove them from the active root->curOuterParams list and return + * them as the result list. * - * XXX Here we also hack up the returned Vars and PHVs so that they do not - * contain nullingrel sets exceeding what is available from the outer side. - * This is needed if we have applied outer join identity 3, - * (A leftjoin B on (Pab)) leftjoin C on (Pb*c) - * = A leftjoin (B leftjoin C on (Pbc)) on (Pab) - * and C contains lateral references to B. It's still safe to apply the - * identity, but the parser will have created those references in the form - * "b*" (i.e., with varnullingrels listing the A/B join), while what we will - * have available from the nestloop's outer side is just "b". We deal with - * that here by stripping the nullingrels down to what is available from the - * outer side according to leftrelids. - * - * That fixes matters for the case of forward application of identity 3. - * If the identity was applied in the reverse direction, we will have - * parameter Vars containing too few nullingrel bits rather than too many. - * Currently, that causes no problems because setrefs.c applies only a - * subset check to nullingrels in NestLoopParams, but we'd have to work - * harder if we ever want to tighten that check. This is all pretty annoying - * because it greatly weakens setrefs.c's cross-check, but the alternative + * Vars and PHVs appearing in the result list must have nullingrel sets + * that could validly appear in the lefthand rel's output. Ordinarily that + * would be true already, but if we have applied outer join identity 3, + * there could be more or fewer nullingrel bits in the nodes appearing in + * curOuterParams than are in the nominal leftrelids. We deal with that by + * forcing their nullingrel sets to include exactly the outer-join relids + * that appear in leftrelids and can null the respective Var or PHV. + * This fix is a bit ad-hoc and intellectually unsatisfactory, because it's + * essentially jumping to the conclusion that we've placed evaluation of + * the nestloop parameters correctly, and thus it defeats the intent of the + * subsequent nullingrel cross-checks in setrefs.c. But the alternative * seems to be to generate multiple versions of each laterally-parameterized * subquery, which'd be unduly expensive. */ List * -identify_current_nestloop_params(PlannerInfo *root, Relids leftrelids) +identify_current_nestloop_params(PlannerInfo *root, + Relids leftrelids, + Relids outerrelids) { List *result; + Relids allleftrelids; ListCell *cell; + /* + * We'll be able to evaluate a PHV in the lefthand path if it uses the + * lefthand rels plus any available required-outer rels. But don't do so + * if it uses *only* required-outer rels; in that case it should be + * evaluated higher in the tree. For Vars, no such hair-splitting is + * necessary since they depend on only one relid. + */ + if (outerrelids) + allleftrelids = bms_union(leftrelids, outerrelids); + else + allleftrelids = leftrelids; + result = NIL; foreach(cell, root->curOuterParams) { @@ -646,25 +654,60 @@ identify_current_nestloop_params(PlannerInfo *root, Relids leftrelids) bms_is_member(nlp->paramval->varno, leftrelids)) { Var *var = (Var *) nlp->paramval; + RelOptInfo *rel = root->simple_rel_array[var->varno]; root->curOuterParams = foreach_delete_current(root->curOuterParams, cell); - var->varnullingrels = bms_intersect(var->varnullingrels, + var->varnullingrels = bms_intersect(rel->nulling_relids, leftrelids); result = lappend(result, nlp); } - else if (IsA(nlp->paramval, PlaceHolderVar) && - bms_is_subset(find_placeholder_info(root, - (PlaceHolderVar *) nlp->paramval)->ph_eval_at, - leftrelids)) + else if (IsA(nlp->paramval, PlaceHolderVar)) { PlaceHolderVar *phv = (PlaceHolderVar *) nlp->paramval; + PlaceHolderInfo *phinfo = find_placeholder_info(root, phv); + Relids eval_at = phinfo->ph_eval_at; - root->curOuterParams = foreach_delete_current(root->curOuterParams, - cell); - phv->phnullingrels = bms_intersect(phv->phnullingrels, - leftrelids); - result = lappend(result, nlp); + if (bms_is_subset(eval_at, allleftrelids) && + bms_overlap(eval_at, leftrelids)) + { + root->curOuterParams = foreach_delete_current(root->curOuterParams, + cell); + + /* + * Deal with an edge case: if the PHV was pulled up out of a + * subquery and it contains a subquery that was originally + * pushed down from this query level, then that will still be + * represented as a SubLink, because SS_process_sublinks won't + * recurse into outer PHVs, so it didn't get transformed + * during expression preprocessing in the subquery. We need a + * version of the PHV that has a SubPlan, which we can get + * from the current query level's placeholder_list. This is + * quite grotty of course, but dealing with it earlier in the + * handling of subplan params would be just as grotty, and it + * might end up being a waste of cycles if we don't decide to + * treat the PHV as a NestLoopParam. (Perhaps that whole + * mechanism should be redesigned someday, but today is not + * that day.) + */ + if (root->parse->hasSubLinks) + { + phv = copyObject(phinfo->ph_var); + + /* + * The ph_var will have empty nullingrels, but that + * doesn't matter since we're about to overwrite + * phv->phnullingrels. Other fields should be OK already. + */ + nlp->paramval = (Var *) phv; + } + + phv->phnullingrels = + bms_intersect(get_placeholder_nulling_relids(root, phinfo), + leftrelids); + + result = lappend(result, nlp); + } } } return result; diff --git a/src/backend/optimizer/util/pathnode.c b/src/backend/optimizer/util/pathnode.c index e0192d4a491..a4c5867cdcb 100644 --- a/src/backend/optimizer/util/pathnode.c +++ b/src/backend/optimizer/util/pathnode.c @@ -1404,12 +1404,12 @@ create_append_path(PlannerInfo *root, pathnode->path.total_cost = child->total_cost; } else - cost_append(pathnode); + cost_append(pathnode, root); /* Must do this last, else cost_append complains */ pathnode->path.pathkeys = child->pathkeys; } else - cost_append(pathnode); + cost_append(pathnode, root); /* If the caller provided a row estimate, override the computed value. */ if (rows >= 0) @@ -1515,6 +1515,9 @@ create_merge_append_path(PlannerInfo *root, foreach(l, subpaths) { Path *subpath = (Path *) lfirst(l); + int presorted_keys; + Path sort_path; /* dummy for result of + * cost_sort/cost_incremental_sort */ /* All child paths should be unparameterized */ Assert(bms_is_empty(PATH_REQ_OUTER(subpath))); @@ -1523,32 +1526,52 @@ create_merge_append_path(PlannerInfo *root, pathnode->path.parallel_safe = pathnode->path.parallel_safe && subpath->parallel_safe; - if (pathkeys_contained_in(pathkeys, subpath->pathkeys)) + if (!pathkeys_count_contained_in(pathkeys, subpath->pathkeys, + &presorted_keys)) { - /* Subpath is adequately ordered, we won't need to sort it */ - input_disabled_nodes += subpath->disabled_nodes; - input_startup_cost += subpath->startup_cost; - input_total_cost += subpath->total_cost; - } - else - { - /* We'll need to insert a Sort node, so include cost for that */ - Path sort_path; /* dummy for result of cost_sort */ + /* + * We'll need to insert a Sort node, so include costs for that. We + * choose to use incremental sort if it is enabled and there are + * presorted keys; otherwise we use full sort. + * + * We can use the parent's LIMIT if any, since we certainly won't + * pull more than that many tuples from any child. + */ + if (enable_incremental_sort && presorted_keys > 0) + { + cost_incremental_sort(&sort_path, + root, + pathkeys, + presorted_keys, + subpath->disabled_nodes, + subpath->startup_cost, + subpath->total_cost, + subpath->rows, + subpath->pathtarget->width, + 0.0, + work_mem, + pathnode->limit_tuples); + } + else + { + cost_sort(&sort_path, + root, + pathkeys, + subpath->disabled_nodes, + subpath->total_cost, + subpath->rows, + subpath->pathtarget->width, + 0.0, + work_mem, + pathnode->limit_tuples); + } - cost_sort(&sort_path, - root, - pathkeys, - subpath->disabled_nodes, - subpath->total_cost, - subpath->rows, - subpath->pathtarget->width, - 0.0, - work_mem, - pathnode->limit_tuples); - input_disabled_nodes += sort_path.disabled_nodes; - input_startup_cost += sort_path.startup_cost; - input_total_cost += sort_path.total_cost; + subpath = &sort_path; } + + input_disabled_nodes += subpath->disabled_nodes; + input_startup_cost += subpath->startup_cost; + input_total_cost += subpath->total_cost; } /* @@ -1666,7 +1689,7 @@ create_material_path(RelOptInfo *rel, Path *subpath) MemoizePath * create_memoize_path(PlannerInfo *root, RelOptInfo *rel, Path *subpath, List *param_exprs, List *hash_operators, - bool singlerow, bool binary_mode, double calls) + bool singlerow, bool binary_mode, Cardinality est_calls) { MemoizePath *pathnode = makeNode(MemoizePath); @@ -1687,7 +1710,6 @@ create_memoize_path(PlannerInfo *root, RelOptInfo *rel, Path *subpath, pathnode->param_exprs = param_exprs; pathnode->singlerow = singlerow; pathnode->binary_mode = binary_mode; - pathnode->calls = clamp_row_est(calls); /* * For now we set est_entries to 0. cost_memoize_rescan() does all the @@ -1697,6 +1719,12 @@ create_memoize_path(PlannerInfo *root, RelOptInfo *rel, Path *subpath, */ pathnode->est_entries = 0; + pathnode->est_calls = clamp_row_est(est_calls); + + /* These will also be set later in cost_memoize_rescan() */ + pathnode->est_unique_keys = 0.0; + pathnode->est_hit_ratio = 0.0; + /* we should not generate this path type when enable_memoize=false */ Assert(enable_memoize); pathnode->path.disabled_nodes = subpath->disabled_nodes; @@ -4236,7 +4264,7 @@ reparameterize_path(PlannerInfo *root, Path *path, mpath->hash_operators, mpath->singlerow, mpath->binary_mode, - mpath->calls); + mpath->est_calls); } default: break; diff --git a/src/backend/optimizer/util/placeholder.c b/src/backend/optimizer/util/placeholder.c index 41a4c81e94a..e1cd00a72fb 100644 --- a/src/backend/optimizer/util/placeholder.c +++ b/src/backend/optimizer/util/placeholder.c @@ -545,3 +545,43 @@ contain_placeholder_references_walker(Node *node, return expression_tree_walker(node, contain_placeholder_references_walker, context); } + +/* + * Compute the set of outer-join relids that can null a placeholder. + * + * This is analogous to RelOptInfo.nulling_relids for Vars, but we compute it + * on-the-fly rather than saving it somewhere. Currently the value is needed + * at most once per query, so there's little value in doing otherwise. If it + * ever gains more widespread use, perhaps we should cache the result in + * PlaceHolderInfo. + */ +Relids +get_placeholder_nulling_relids(PlannerInfo *root, PlaceHolderInfo *phinfo) +{ + Relids result = NULL; + int relid = -1; + + /* + * Form the union of all potential nulling OJs for each baserel included + * in ph_eval_at. + */ + while ((relid = bms_next_member(phinfo->ph_eval_at, relid)) > 0) + { + RelOptInfo *rel = root->simple_rel_array[relid]; + + /* ignore the RTE_GROUP RTE */ + if (relid == root->group_rtindex) + continue; + + if (rel == NULL) /* must be an outer join */ + { + Assert(bms_is_member(relid, root->outer_join_rels)); + continue; + } + result = bms_add_members(result, rel->nulling_relids); + } + + /* Now remove any OJs already included in ph_eval_at, and we're done. */ + result = bms_del_members(result, phinfo->ph_eval_at); + return result; +} diff --git a/src/backend/optimizer/util/plancat.c b/src/backend/optimizer/util/plancat.c index 59233b64730..c6a58afc5e5 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 @@ -684,6 +670,105 @@ 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. * |