From 0454ee1969ac49ef056e9fc8896332c2cada54ef Mon Sep 17 00:00:00 2001 From: amit Date: Wed, 17 Oct 2018 18:14:13 +0900 Subject: [PATCH 4/6] Lazy creation of RTEs for inheritance children Currently, they're created in the planner's prep's phase, at which point, it's too early to perform partition pruning or constraint exclusion, which results in *all* partitions being opened and range table entries being created for them. With large number of children, that can be pretty inefficient overall if most queries would only access one or few of them. This commit moves the processing that's currently done in expand_inherited_table called from subquery_planner to a new function that's called from set_append_rel_size, which is late enough during query planning that we're able to perform partition pruning (and constraint exclusion). This also enables us to open the relation and initialize planner objects for only the unpruned partitions. For non-partition children, we still need to open them before we could perform constraint exclusion. Although the late initialization approach described above only benefits the partitioning case as far as the number of child relations that need to be opened is concerned, it seems undesirable to make a special case of it. Instead, this moves the inheritance expansion code into a new module named append.c whose functionality is invoked from set_append_rel_size, which contains the new code for inheritance child initialization. The only way partitioning is special in the new module is that it performs pruning before any child relations are initialized and only the unpruned children are initialized. A related new module named appendinfo.c contains the code related to inheritance translation of expressions. For partitioning, although we don't create planner data structures for pruned partitions, partitionwise join code relies on the fact fact that even though partitions may have been pruned, they'd still own a RelOptInfo to handle the outer join case where the pruned partition appears on the nullable side of join. Partitionwise join code deals with that by allocating dummy RelOptInfos for pruned partitions. There are some regression test diffs: 1. Caused by the fact that we no longer allocate a duplicate RT entry for a partitioned table in its role as child and also that the individual partition RT entries are now created in the order in which their parent's are processed, whereas previously they'd be added to the range table in the order of depth-first expansion of inheritance tree. 2. Those in postgres_fdw.out are caused by the fact that junk columns required for row marking are added to reltarget->exprs later than user columns, because the row marking junk columns arent added until after the inheritance is expanded which as of this commit is later than it used to be. --- contrib/postgres_fdw/expected/postgres_fdw.out | 32 +- src/backend/optimizer/path/allpaths.c | 206 +--- src/backend/optimizer/path/equivclass.c | 1 + src/backend/optimizer/path/joinrels.c | 63 ++ src/backend/optimizer/plan/initsplan.c | 58 - src/backend/optimizer/plan/planner.c | 55 +- src/backend/optimizer/plan/setrefs.c | 6 + src/backend/optimizer/prep/preptlist.c | 11 +- src/backend/optimizer/prep/prepunion.c | 1236 --------------------- src/backend/optimizer/util/Makefile | 5 +- src/backend/optimizer/util/append.c | 679 +++++++++++ src/backend/optimizer/util/appendinfo.c | 851 ++++++++++++++ src/backend/optimizer/util/pathnode.c | 1 + src/backend/optimizer/util/plancat.c | 41 +- src/backend/optimizer/util/relnode.c | 81 +- src/backend/partitioning/partprune.c | 44 +- src/include/nodes/relation.h | 8 + src/include/optimizer/append.h | 28 + src/include/optimizer/appendinfo.h | 43 + src/include/optimizer/pathnode.h | 1 + src/include/optimizer/plancat.h | 2 +- src/include/optimizer/prep.h | 20 +- src/include/partitioning/partprune.h | 2 +- src/test/regress/expected/join.out | 22 +- src/test/regress/expected/partition_aggregate.out | 4 +- 25 files changed, 1888 insertions(+), 1612 deletions(-) create mode 100644 src/backend/optimizer/util/append.c create mode 100644 src/backend/optimizer/util/appendinfo.c create mode 100644 src/include/optimizer/append.h create mode 100644 src/include/optimizer/appendinfo.h diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 21a2ef5ad3..c930bf7bab 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -7085,15 +7085,15 @@ select * from bar where f1 in (select f1 from foo) for update; Output: bar2.f1, bar2.f2, bar2.ctid, bar2.*, bar2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE -> Hash - Output: foo.ctid, foo.*, foo.tableoid, foo.f1 + Output: foo.f1, foo.ctid, foo.*, foo.tableoid -> HashAggregate - Output: foo.ctid, foo.*, foo.tableoid, foo.f1 + Output: foo.f1, foo.ctid, foo.*, foo.tableoid Group Key: foo.f1 -> Append -> Seq Scan on public.foo - Output: foo.ctid, foo.*, foo.tableoid, foo.f1 + Output: foo.f1, foo.ctid, foo.*, foo.tableoid -> Foreign Scan on public.foo2 - Output: foo2.ctid, foo2.*, foo2.tableoid, foo2.f1 + Output: foo2.f1, foo2.ctid, foo2.*, foo2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 (23 rows) @@ -7123,15 +7123,15 @@ select * from bar where f1 in (select f1 from foo) for share; Output: bar2.f1, bar2.f2, bar2.ctid, bar2.*, bar2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE -> Hash - Output: foo.ctid, foo.*, foo.tableoid, foo.f1 + Output: foo.f1, foo.ctid, foo.*, foo.tableoid -> HashAggregate - Output: foo.ctid, foo.*, foo.tableoid, foo.f1 + Output: foo.f1, foo.ctid, foo.*, foo.tableoid Group Key: foo.f1 -> Append -> Seq Scan on public.foo - Output: foo.ctid, foo.*, foo.tableoid, foo.f1 + Output: foo.f1, foo.ctid, foo.*, foo.tableoid -> Foreign Scan on public.foo2 - Output: foo2.ctid, foo2.*, foo2.tableoid, foo2.f1 + Output: foo2.f1, foo2.ctid, foo2.*, foo2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 (23 rows) @@ -7160,15 +7160,15 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); -> Seq Scan on public.bar Output: bar.f1, bar.f2, bar.ctid -> Hash - Output: foo.ctid, foo.*, foo.tableoid, foo.f1 + Output: foo.f1, foo.ctid, foo.tableoid, foo.* -> HashAggregate - Output: foo.ctid, foo.*, foo.tableoid, foo.f1 + Output: foo.f1, foo.ctid, foo.tableoid, foo.* Group Key: foo.f1 -> Append -> Seq Scan on public.foo - Output: foo.ctid, foo.*, foo.tableoid, foo.f1 + Output: foo.f1, foo.ctid, foo.tableoid, foo.* -> Foreign Scan on public.foo2 - Output: foo2.ctid, foo2.*, foo2.tableoid, foo2.f1 + Output: foo2.f1, foo2.ctid, foo2.tableoid, foo2.* Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -> Hash Join Output: bar2.f1, (bar2.f2 + 100), bar2.f3, bar2.ctid, foo.ctid, foo.*, foo.tableoid @@ -7178,15 +7178,15 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: bar2.f1, bar2.f2, bar2.f3, bar2.ctid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE -> Hash - Output: foo.ctid, foo.*, foo.tableoid, foo.f1 + Output: foo.f1, foo.ctid, foo.tableoid, foo.* -> HashAggregate - Output: foo.ctid, foo.*, foo.tableoid, foo.f1 + Output: foo.f1, foo.ctid, foo.tableoid, foo.* Group Key: foo.f1 -> Append -> Seq Scan on public.foo - Output: foo.ctid, foo.*, foo.tableoid, foo.f1 + Output: foo.f1, foo.ctid, foo.tableoid, foo.* -> Foreign Scan on public.foo2 - Output: foo2.ctid, foo2.*, foo2.tableoid, foo2.f1 + Output: foo2.f1, foo2.ctid, foo2.tableoid, foo2.* Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 (39 rows) diff --git a/src/backend/optimizer/path/allpaths.c b/src/backend/optimizer/path/allpaths.c index 051e4a8e74..971da18c1d 100644 --- a/src/backend/optimizer/path/allpaths.c +++ b/src/backend/optimizer/path/allpaths.c @@ -30,6 +30,8 @@ #ifdef OPTIMIZER_DEBUG #include "nodes/print.h" #endif +#include "optimizer/append.h" +#include "optimizer/appendinfo.h" #include "optimizer/clauses.h" #include "optimizer/cost.h" #include "optimizer/geqo.h" @@ -44,7 +46,6 @@ #include "optimizer/var.h" #include "parser/parse_clause.h" #include "parser/parsetree.h" -#include "partitioning/partprune.h" #include "rewrite/rewriteManip.h" #include "utils/lsyscache.h" @@ -942,8 +943,6 @@ set_append_rel_size(PlannerInfo *root, RelOptInfo *rel, double *parent_attrsizes; int nattrs; ListCell *l; - Relids live_children = NULL; - bool did_pruning = false; /* Guard against stack overflow due to overly deep inheritance tree. */ check_stack_depth(); @@ -951,29 +950,22 @@ set_append_rel_size(PlannerInfo *root, RelOptInfo *rel, Assert(IS_SIMPLE_REL(rel)); /* - * Initialize partitioned_child_rels to contain this RT index. - * - * Note that during the set_append_rel_pathlist() phase, we will bubble up - * the indexes of partitioned relations that appear down in the tree, so - * that when we've created Paths for all the children, the root - * partitioned table's list will contain all such indexes. + * Add append children to the PlannerInfo. */ - if (rte->relkind == RELKIND_PARTITIONED_TABLE) - rel->partitioned_child_rels = list_make1_int(rti); + expand_append_rel(root, rel, rte, rti); + + /* Did we find out that none of the children produce any output? */ + if (IS_DUMMY_REL(rel)) + return; /* - * If the partitioned relation has any baserestrictinfo quals then we - * attempt to use these quals to prune away partitions that cannot - * possibly contain any tuples matching these quals. In this case we'll - * store the relids of all partitions which could possibly contain a - * matching tuple, and skip anything else in the loop below. + * If we only need to scan the parent because all of the children are + * either pruned or excluded, do so right away and return. */ - if (enable_partition_pruning && - rte->relkind == RELKIND_PARTITIONED_TABLE && - rel->baserestrictinfo != NIL) + if (!rte->inh) { - live_children = prune_append_rel_partitions(rel); - did_pruning = true; + set_rel_size(root, rel, rti, rte); + return; } /* @@ -1013,12 +1005,8 @@ set_append_rel_size(PlannerInfo *root, RelOptInfo *rel, int childRTindex; RangeTblEntry *childRTE; RelOptInfo *childrel; - List *childquals; - Index cq_min_security; - bool have_const_false_cq; ListCell *parentvars; ListCell *childvars; - ListCell *lc; /* append_rel_list contains all append rels; ignore others */ if (appinfo->parent_relid != parentRTindex) @@ -1026,18 +1014,31 @@ set_append_rel_size(PlannerInfo *root, RelOptInfo *rel, childRTindex = appinfo->child_relid; childRTE = root->simple_rte_array[childRTindex]; + Assert(childRTE != NULL); - /* - * The child rel's RelOptInfo was already created during - * add_base_rels_to_query. - */ + /* The child rel's RelOptInfo is created during expand_append_rel */ childrel = find_base_rel(root, childRTindex); Assert(childrel->reloptkind == RELOPT_OTHER_MEMBER_REL); /* - * Copy/Modify targetlist. Even if this child is deemed empty, we need - * its targetlist in case it falls on nullable side in a child-join - * because of partitionwise join. + * Child relation may have be marked dummy if build_append_child_rel + * found self-contradictory quals. + */ + if (IS_DUMMY_REL(childrel)) + continue; + + if (relation_excluded_by_constraints(root, childrel, childRTE)) + { + /* + * This child need not be scanned, so we can omit it from the + * appendrel. + */ + set_dummy_rel_pathlist(childrel); + continue; + } + + /* + * Copy/Modify targetlist. * * NB: the resulting childrel->reltarget->exprs may contain arbitrary * expressions, which otherwise would not occur in a rel's targetlist. @@ -1066,144 +1067,6 @@ set_append_rel_size(PlannerInfo *root, RelOptInfo *rel, add_child_rel_equivalences(root, appinfo, rel, childrel); childrel->has_eclass_joins = rel->has_eclass_joins; - /* - * We have to copy the parent's quals to the child, with appropriate - * substitution of variables. However, only the baserestrictinfo - * quals are needed before we can check for constraint exclusion; so - * do that first and then check to see if we can disregard this child. - * - * The child rel's targetlist might contain non-Var expressions, which - * means that substitution into the quals could produce opportunities - * for const-simplification, and perhaps even pseudoconstant quals. - * Therefore, transform each RestrictInfo separately to see if it - * reduces to a constant or pseudoconstant. (We must process them - * separately to keep track of the security level of each qual.) - */ - childquals = NIL; - cq_min_security = UINT_MAX; - have_const_false_cq = false; - foreach(lc, rel->baserestrictinfo) - { - RestrictInfo *rinfo = (RestrictInfo *) lfirst(lc); - Node *childqual; - ListCell *lc2; - - Assert(IsA(rinfo, RestrictInfo)); - childqual = adjust_appendrel_attrs(root, - (Node *) rinfo->clause, - 1, &appinfo); - childqual = eval_const_expressions(root, childqual); - /* check for flat-out constant */ - if (childqual && IsA(childqual, Const)) - { - if (((Const *) childqual)->constisnull || - !DatumGetBool(((Const *) childqual)->constvalue)) - { - /* Restriction reduces to constant FALSE or NULL */ - have_const_false_cq = true; - break; - } - /* Restriction reduces to constant TRUE, so drop it */ - continue; - } - /* might have gotten an AND clause, if so flatten it */ - foreach(lc2, make_ands_implicit((Expr *) childqual)) - { - Node *onecq = (Node *) lfirst(lc2); - bool pseudoconstant; - - /* check for pseudoconstant (no Vars or volatile functions) */ - pseudoconstant = - !contain_vars_of_level(onecq, 0) && - !contain_volatile_functions(onecq); - if (pseudoconstant) - { - /* tell createplan.c to check for gating quals */ - root->hasPseudoConstantQuals = true; - } - /* reconstitute RestrictInfo with appropriate properties */ - childquals = lappend(childquals, - make_restrictinfo((Expr *) onecq, - rinfo->is_pushed_down, - rinfo->outerjoin_delayed, - pseudoconstant, - rinfo->security_level, - NULL, NULL, NULL)); - /* track minimum security level among child quals */ - cq_min_security = Min(cq_min_security, rinfo->security_level); - } - } - - /* - * In addition to the quals inherited from the parent, we might have - * securityQuals associated with this particular child node. - * (Currently this can only happen in appendrels originating from - * UNION ALL; inheritance child tables don't have their own - * securityQuals, see expand_inherited_rtentry().) Pull any such - * securityQuals up into the baserestrictinfo for the child. This is - * similar to process_security_barrier_quals() for the parent rel, - * except that we can't make any general deductions from such quals, - * since they don't hold for the whole appendrel. - */ - if (childRTE->securityQuals) - { - Index security_level = 0; - - foreach(lc, childRTE->securityQuals) - { - List *qualset = (List *) lfirst(lc); - ListCell *lc2; - - foreach(lc2, qualset) - { - Expr *qual = (Expr *) lfirst(lc2); - - /* not likely that we'd see constants here, so no check */ - childquals = lappend(childquals, - make_restrictinfo(qual, - true, false, false, - security_level, - NULL, NULL, NULL)); - cq_min_security = Min(cq_min_security, security_level); - } - security_level++; - } - Assert(security_level <= root->qual_security_level); - } - - /* - * OK, we've got all the baserestrictinfo quals for this child. - */ - childrel->baserestrictinfo = childquals; - childrel->baserestrict_min_security = cq_min_security; - - if (have_const_false_cq) - { - /* - * Some restriction clause reduced to constant FALSE or NULL after - * substitution, so this child need not be scanned. - */ - set_dummy_rel_pathlist(childrel); - continue; - } - - if (did_pruning && !bms_is_member(appinfo->child_relid, live_children)) - { - /* This partition was pruned; skip it. */ - set_dummy_rel_pathlist(childrel); - continue; - } - - if (relation_excluded_by_constraints(root, childrel, childRTE)) - { - /* - * This child need not be scanned, so we can omit it from the - * appendrel. - */ - set_dummy_rel_pathlist(childrel); - continue; - } - /* CE failed, so finish copying/modifying join quals. */ childrel->joininfo = (List *) adjust_appendrel_attrs(root, @@ -1274,7 +1137,7 @@ set_append_rel_size(PlannerInfo *root, RelOptInfo *rel, child_relids, top_parent_relids); root->parse = parse; - tlist = preprocess_targetlist(root); + tlist = preprocess_targetlist(root, true); build_base_rel_tlists(root, tlist); root->parse = orig_parse; @@ -2738,6 +2601,7 @@ inheritance_make_rel_from_joinlist(PlannerInfo *root, continue; childrel = find_base_rel(root, appinfo->child_relid); + Assert(childrel != NULL); /* Ignore excluded/pruned children. */ if (IS_DUMMY_REL(childrel)) diff --git a/src/backend/optimizer/path/equivclass.c b/src/backend/optimizer/path/equivclass.c index b22b36ec0e..5ace28eab0 100644 --- a/src/backend/optimizer/path/equivclass.c +++ b/src/backend/optimizer/path/equivclass.c @@ -22,6 +22,7 @@ #include "catalog/pg_type.h" #include "nodes/makefuncs.h" #include "nodes/nodeFuncs.h" +#include "optimizer/appendinfo.h" #include "optimizer/clauses.h" #include "optimizer/pathnode.h" #include "optimizer/paths.h" diff --git a/src/backend/optimizer/path/joinrels.c b/src/backend/optimizer/path/joinrels.c index d3d21fed5d..6e321ec9e7 100644 --- a/src/backend/optimizer/path/joinrels.c +++ b/src/backend/optimizer/path/joinrels.c @@ -15,11 +15,13 @@ #include "postgres.h" #include "miscadmin.h" +#include "optimizer/appendinfo.h" #include "optimizer/clauses.h" #include "optimizer/joininfo.h" #include "optimizer/pathnode.h" #include "optimizer/paths.h" #include "optimizer/prep.h" +#include "optimizer/tlist.h" #include "partitioning/partbounds.h" #include "utils/lsyscache.h" #include "utils/memutils.h" @@ -46,6 +48,9 @@ static void try_partitionwise_join(PlannerInfo *root, RelOptInfo *rel1, List *parent_restrictlist); static int match_expr_to_partition_keys(Expr *expr, RelOptInfo *rel, bool strict_op); +static RelOptInfo *build_dummy_partition_rel(PlannerInfo *root, + RelOptInfo *parent, + int partidx); /* @@ -1376,6 +1381,11 @@ try_partitionwise_join(PlannerInfo *root, RelOptInfo *rel1, RelOptInfo *rel2, AppendRelInfo **appinfos; int nappinfos; + if (child_rel1 == NULL) + child_rel1 = build_dummy_partition_rel(root, rel1, cnt_parts); + if (child_rel2 == NULL) + child_rel2 = build_dummy_partition_rel(root, rel2, cnt_parts); + /* We should never try to join two overlapping sets of rels. */ Assert(!bms_overlap(child_rel1->relids, child_rel2->relids)); child_joinrelids = bms_union(child_rel1->relids, child_rel2->relids); @@ -1582,3 +1592,56 @@ match_expr_to_partition_keys(Expr *expr, RelOptInfo *rel, bool strict_op) return -1; } + +/* + * build_dummy_partition_rel + * Build a RelOptInfo and AppendRelInfo for a pruned partition + * + * This does not result in opening the relation or a range table entry being + * created. Also, the RelOptInfo thus created is not stored anywhere else + * beside the parent's part_rels array. + * + * The only reason this exists is because partition-wise join, in some cases, + * needs a RelOptInfo to represent an empty relation that's on the nullable + * side of an outer join, so that a Path representing the outer join can be + * created. + */ +RelOptInfo * +build_dummy_partition_rel(PlannerInfo *root, RelOptInfo *parent, int partidx) +{ + RangeTblEntry *parentrte = root->simple_rte_array[parent->relid]; + RelOptInfo *rel; + + Assert(parent->part_rels[partidx] == NULL); + + /* Create minimally valid-looking RelOptInfo with parent's relid. */ + rel = makeNode(RelOptInfo); + rel->reloptkind = RELOPT_OTHER_MEMBER_REL; + rel->relid = parent->relid; + rel->relids = bms_copy(parent->relids); + if (parent->top_parent_relids) + rel->top_parent_relids = parent->top_parent_relids; + else + rel->top_parent_relids = bms_copy(parent->relids); + rel->reltarget = copy_pathtarget(parent->reltarget); + parent->part_rels[partidx] = rel; + mark_dummy_rel(rel); + + /* + * Now we'll need a (no-op) AppendRelInfo for parent, because we're + * setting the dummy partition's relid to be same as the parent's. + */ + if (root->append_rel_array[parent->relid] == NULL) + { + /* Pass parent's info as for both the parent rel and child rel. */ + AppendRelInfo *appinfo = make_append_rel_info(parent, parentrte, + parent->tupdesc, + parentrte->relid, + parent->reltype, + parent->relid); + + root->append_rel_array[parent->relid] = appinfo; + } + + return rel; +} diff --git a/src/backend/optimizer/plan/initsplan.c b/src/backend/optimizer/plan/initsplan.c index 01335db511..7636aa82c4 100644 --- a/src/backend/optimizer/plan/initsplan.c +++ b/src/backend/optimizer/plan/initsplan.c @@ -616,64 +616,6 @@ create_lateral_join_info(PlannerInfo *root) bms_add_member(brel2->lateral_referencers, rti); } } - - /* - * Lastly, propagate lateral_relids and lateral_referencers from appendrel - * parent rels to their child rels. We intentionally give each child rel - * the same minimum parameterization, even though it's quite possible that - * some don't reference all the lateral rels. This is because any append - * path for the parent will have to have the same parameterization for - * every child anyway, and there's no value in forcing extra - * reparameterize_path() calls. Similarly, a lateral reference to the - * parent prevents use of otherwise-movable join rels for each child. - */ - for (rti = 1; rti < root->simple_rel_array_size; rti++) - { - RelOptInfo *brel = root->simple_rel_array[rti]; - RangeTblEntry *brte = root->simple_rte_array[rti]; - - /* - * Skip empty slots. Also skip non-simple relations i.e. dead - * relations. - */ - if (brel == NULL || !IS_SIMPLE_REL(brel)) - continue; - - /* - * In the case of table inheritance, the parent RTE is directly linked - * to every child table via an AppendRelInfo. In the case of table - * partitioning, the inheritance hierarchy is expanded one level at a - * time rather than flattened. Therefore, an other member rel that is - * a partitioned table may have children of its own, and must - * therefore be marked with the appropriate lateral info so that those - * children eventually get marked also. - */ - Assert(brte); - if (brel->reloptkind == RELOPT_OTHER_MEMBER_REL && - (brte->rtekind != RTE_RELATION || - brte->relkind != RELKIND_PARTITIONED_TABLE)) - continue; - - if (brte->inh) - { - foreach(lc, root->append_rel_list) - { - AppendRelInfo *appinfo = (AppendRelInfo *) lfirst(lc); - RelOptInfo *childrel; - - if (appinfo->parent_relid != rti) - continue; - childrel = root->simple_rel_array[appinfo->child_relid]; - Assert(childrel->reloptkind == RELOPT_OTHER_MEMBER_REL); - Assert(childrel->direct_lateral_relids == NULL); - childrel->direct_lateral_relids = brel->direct_lateral_relids; - Assert(childrel->lateral_relids == NULL); - childrel->lateral_relids = brel->lateral_relids; - Assert(childrel->lateral_referencers == NULL); - childrel->lateral_referencers = brel->lateral_referencers; - } - } - } } diff --git a/src/backend/optimizer/plan/planner.c b/src/backend/optimizer/plan/planner.c index 93b8c761c2..b54dc6c38e 100644 --- a/src/backend/optimizer/plan/planner.c +++ b/src/backend/optimizer/plan/planner.c @@ -23,6 +23,7 @@ #include "access/sysattr.h" #include "access/xact.h" #include "catalog/pg_constraint.h" +#include "catalog/pg_inherits.h" #include "catalog/pg_proc.h" #include "catalog/pg_type.h" #include "executor/executor.h" @@ -38,6 +39,7 @@ #include "nodes/print.h" #endif #include "nodes/relation.h" +#include "optimizer/appendinfo.h" #include "optimizer/clauses.h" #include "optimizer/cost.h" #include "optimizer/pathnode.h" @@ -699,27 +701,24 @@ subquery_planner(PlannerGlobal *glob, Query *parse, } if (rte->lateral) root->hasLateralRTEs = true; + + /* + * While at it, also update the inh status. If the relation doesn't + * or can't have any children, there is no point in letting inh be set + * to true. Note that we do this before processing rowmarks, so that + * the correct information for setting isParent field of PlanRowMarks. + */ + if (rte->rtekind == RTE_RELATION) + rte->inh = rte->inh && has_subclass(rte->relid); } /* * Preprocess RowMark information. We need to do this after subquery - * pullup (so that all non-inherited RTEs are present) and before - * inheritance expansion (so that the info is available for - * expand_inherited_tables to examine and modify). + * pullup (so that all non-inherited RTEs are present). */ preprocess_rowmarks(root); /* - * Expand any rangetable entries that are inheritance sets into "append - * relations". This can add entries to the rangetable, but they must be - * plain base relations not joins, so it's OK (and marginally more - * efficient) to do it after checking for join RTEs. We must do it after - * pulling up subqueries, else we'd fail to handle inherited tables in - * subqueries. - */ - expand_inherited_tables(root); - - /* * Set hasHavingQual to remember if HAVING clause is present. Needed * because preprocess_expression will reduce a constant-true condition to * an empty qual list ... but "HAVING TRUE" is not a semantic no-op. @@ -1215,7 +1214,7 @@ inheritance_planner(PlannerInfo *root) orig_tlist = list_copy(root->parse->targetList); /* Do the scan/join planning. */ - tlist = preprocess_targetlist(root); + tlist = preprocess_targetlist(root, false); qp_extra.tlist = tlist; qp_extra.activeWindows = qp_extra.groupClause = NIL; planned_rel = query_planner(root, tlist, standard_qp_callback, &qp_extra); @@ -1223,9 +1222,10 @@ inheritance_planner(PlannerInfo *root) /* * If it turned out during query planning that all the children are dummy * (pruned or excluded by constraints), no need to do the steps below. - * Let grouping_planner finish up the final path. + * For regular inheritance case, it's possible that we only need to modify + * the parent table. Let grouping_planner finish up the final path. */ - if (IS_DUMMY_REL(planned_rel)) + if (!parent_rte->inh || IS_DUMMY_REL(planned_rel)) { grouping_planner(root, false, planned_rel, 0.0); return; @@ -1580,7 +1580,7 @@ grouping_planner(PlannerInfo *root, bool inheritance_update, } /* Preprocess targetlist */ - tlist = preprocess_targetlist(root); + tlist = preprocess_targetlist(root, inheritance_update); /* * We are now done hacking up the query's targetlist. Most of the @@ -1674,6 +1674,15 @@ grouping_planner(PlannerInfo *root, bool inheritance_update, standard_qp_callback, &qp_extra); /* + * Query planning may have added some columns to the top-level tlist, + * which happens when there row marks applied to inheritance parent + * relations (additional junk columns needed for applying row marks + * are added after expanding inheritance.) + */ + if (list_length(tlist) < list_length(root->processed_tlist)) + tlist = root->processed_tlist; + + /* * Convert the query's result tlist into PathTarget format. * * Note: it's desirable to not do this till after query_planner(), @@ -2360,7 +2369,7 @@ preprocess_rowmarks(PlannerInfo *root) newrc->allMarkTypes = (1 << newrc->markType); newrc->strength = rc->strength; newrc->waitPolicy = rc->waitPolicy; - newrc->isParent = false; + newrc->isParent = rte->inh; prowmarks = lappend(prowmarks, newrc); } @@ -2385,7 +2394,7 @@ preprocess_rowmarks(PlannerInfo *root) newrc->allMarkTypes = (1 << newrc->markType); newrc->strength = LCS_NONE; newrc->waitPolicy = LockWaitBlock; /* doesn't matter */ - newrc->isParent = false; + newrc->isParent = rte->rtekind == RTE_RELATION ? rte->inh : false; prowmarks = lappend(prowmarks, newrc); } @@ -6765,6 +6774,10 @@ apply_scanjoin_target_to_paths(PlannerInfo *root, int nappinfos; List *child_scanjoin_targets = NIL; + /* Skip processing pruned partitions. */ + if (child_rel == NULL) + continue; + /* Translate scan/join targets for this child. */ appinfos = find_appinfos_by_relids(root, child_rel->relids, &nappinfos); @@ -6866,6 +6879,10 @@ create_partitionwise_grouping_paths(PlannerInfo *root, RelOptInfo *child_grouped_rel; RelOptInfo *child_partially_grouped_rel; + /* Skip processing pruned partitions. */ + if (child_input_rel == NULL) + continue; + /* Input child rel must have a path */ Assert(child_input_rel->pathlist != NIL); diff --git a/src/backend/optimizer/plan/setrefs.c b/src/backend/optimizer/plan/setrefs.c index 6d6ef1c376..454870609a 100644 --- a/src/backend/optimizer/plan/setrefs.c +++ b/src/backend/optimizer/plan/setrefs.c @@ -326,6 +326,12 @@ add_rtes_to_flat_rtable(PlannerInfo *root, bool recursing) UPPERREL_FINAL, NULL))) add_rtes_to_flat_rtable(rel->subroot, true); } + /* + * A NULL rel also means an unplanned subquery rte, so apply + * flatten_unplanned_rtes. + */ + else + flatten_unplanned_rtes(glob, rte); } rti++; } diff --git a/src/backend/optimizer/prep/preptlist.c b/src/backend/optimizer/prep/preptlist.c index 8603feef2b..9c0a1c1b1c 100644 --- a/src/backend/optimizer/prep/preptlist.c +++ b/src/backend/optimizer/prep/preptlist.c @@ -67,7 +67,7 @@ static List *expand_targetlist(List *tlist, int command_type, * is also preprocessed (and updated in-place). */ List * -preprocess_targetlist(PlannerInfo *root) +preprocess_targetlist(PlannerInfo *root, bool inheritance_update) { Query *parse = root->parse; int result_relation = parse->resultRelation; @@ -134,6 +134,15 @@ preprocess_targetlist(PlannerInfo *root) if (rc->rti != rc->prti) continue; + /* + * For inheritance parent row marks, we defer adding junk columns + * until we've added child row marks, because some children might + * require different row mark types which affects which junk columns + * are needed in the top-level tlist. + */ + if (rc->isParent && !inheritance_update) + continue; + if (rc->allMarkTypes & ~(1 << ROW_MARK_COPY)) { /* Need to fetch TID */ diff --git a/src/backend/optimizer/prep/prepunion.c b/src/backend/optimizer/prep/prepunion.c index ef1f978889..70f37c593f 100644 --- a/src/backend/optimizer/prep/prepunion.c +++ b/src/backend/optimizer/prep/prepunion.c @@ -12,11 +12,6 @@ * case, but most of the heavy lifting for that is done elsewhere, * notably in prepjointree.c and allpaths.c. * - * There is also some code here to support planning of queries that use - * inheritance (SELECT FROM foo*). Inheritance trees are converted into - * append relations, and thenceforth share code with the UNION ALL case. - * - * * Portions Copyright (c) 1996-2018, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California * @@ -54,13 +49,6 @@ #include "utils/syscache.h" -typedef struct -{ - PlannerInfo *root; - int nappinfos; - AppendRelInfo **appinfos; -} adjust_appendrel_attrs_context; - static RelOptInfo *recurse_set_operations(Node *setOp, PlannerInfo *root, List *colTypes, List *colCollations, bool junkOK, @@ -99,31 +87,6 @@ static List *generate_append_tlist(List *colTypes, List *colCollations, List *input_tlists, List *refnames_tlist); static List *generate_setop_grouplist(SetOperationStmt *op, List *targetlist); -static void expand_inherited_rtentry(PlannerInfo *root, RangeTblEntry *rte, - Index rti); -static void expand_partitioned_rtentry(PlannerInfo *root, - RangeTblEntry *parentrte, - Index parentRTindex, Relation parentrel, - PlanRowMark *top_parentrc, LOCKMODE lockmode, - List **appinfos); -static void expand_single_inheritance_child(PlannerInfo *root, - RangeTblEntry *parentrte, - Index parentRTindex, Relation parentrel, - PlanRowMark *top_parentrc, Relation childrel, - List **appinfos, RangeTblEntry **childrte_p, - Index *childRTindex_p); -static void make_inh_translation_list(Relation oldrelation, - Relation newrelation, - Index newvarno, - List **translated_vars); -static Bitmapset *translate_col_privs(const Bitmapset *parent_privs, - List *translated_vars); -static Node *adjust_appendrel_attrs_mutator(Node *node, - adjust_appendrel_attrs_context *context); -static Relids adjust_child_relids(Relids relids, int nappinfos, - AppendRelInfo **appinfos); -static List *adjust_inherited_tlist(List *tlist, - AppendRelInfo *context); /* @@ -1460,1202 +1423,3 @@ generate_setop_grouplist(SetOperationStmt *op, List *targetlist) Assert(lg == NULL); return grouplist; } - - -/* - * expand_inherited_tables - * Expand each rangetable entry that represents an inheritance set - * into an "append relation". At the conclusion of this process, - * the "inh" flag is set in all and only those RTEs that are append - * relation parents. - */ -void -expand_inherited_tables(PlannerInfo *root) -{ - Index nrtes; - Index rti; - ListCell *rl; - - /* - * expand_inherited_rtentry may add RTEs to parse->rtable. The function is - * expected to recursively handle any RTEs that it creates with inh=true. - * So just scan as far as the original end of the rtable list. - */ - nrtes = list_length(root->parse->rtable); - rl = list_head(root->parse->rtable); - for (rti = 1; rti <= nrtes; rti++) - { - RangeTblEntry *rte = (RangeTblEntry *) lfirst(rl); - - expand_inherited_rtentry(root, rte, rti); - rl = lnext(rl); - } -} - -/* - * expand_inherited_rtentry - * Check whether a rangetable entry represents an inheritance set. - * If so, add entries for all the child tables to the query's - * rangetable, and build AppendRelInfo nodes for all the child tables - * and add them to root->append_rel_list. If not, clear the entry's - * "inh" flag to prevent later code from looking for AppendRelInfos. - * - * Note that the original RTE is considered to represent the whole - * inheritance set. The first of the generated RTEs is an RTE for the same - * table, but with inh = false, to represent the parent table in its role - * as a simple member of the inheritance set. - * - * A childless table is never considered to be an inheritance set. For - * regular inheritance, a parent RTE must always have at least two associated - * AppendRelInfos: one corresponding to the parent table as a simple member of - * inheritance set and one or more corresponding to the actual children. - * Since a partitioned table is not scanned, it might have only one associated - * AppendRelInfo. - */ -static void -expand_inherited_rtentry(PlannerInfo *root, RangeTblEntry *rte, Index rti) -{ - Oid parentOID; - PlanRowMark *oldrc; - Relation oldrelation; - LOCKMODE lockmode; - List *inhOIDs; - ListCell *l; - - /* Does RT entry allow inheritance? */ - if (!rte->inh) - return; - /* Ignore any already-expanded UNION ALL nodes */ - if (rte->rtekind != RTE_RELATION) - { - Assert(rte->rtekind == RTE_SUBQUERY); - return; - } - /* Fast path for common case of childless table */ - parentOID = rte->relid; - if (!has_subclass(parentOID)) - { - /* Clear flag before returning */ - rte->inh = false; - return; - } - - /* - * The rewriter should already have obtained an appropriate lock on each - * relation named in the query. However, for each child relation we add - * to the query, we must obtain an appropriate lock, because this will be - * the first use of those relations in the parse/rewrite/plan pipeline. - * Child rels should use the same lockmode as their parent. - */ - lockmode = rte->rellockmode; - - /* Scan for all members of inheritance set, acquire needed locks */ - inhOIDs = find_all_inheritors(parentOID, lockmode, NULL); - - /* - * Check that there's at least one descendant, else treat as no-child - * case. This could happen despite above has_subclass() check, if table - * once had a child but no longer does. - */ - if (list_length(inhOIDs) < 2) - { - /* Clear flag before returning */ - rte->inh = false; - return; - } - - /* - * If parent relation is selected FOR UPDATE/SHARE, we need to mark its - * PlanRowMark as isParent = true, and generate a new PlanRowMark for each - * child. - */ - oldrc = get_plan_rowmark(root->rowMarks, rti); - if (oldrc) - oldrc->isParent = true; - - /* - * Must open the parent relation to examine its tupdesc. We need not lock - * it; we assume the rewriter already did. - */ - oldrelation = heap_open(parentOID, NoLock); - - /* Scan the inheritance set and expand it */ - if (RelationGetPartitionDesc(oldrelation) != NULL) - { - Assert(rte->relkind == RELKIND_PARTITIONED_TABLE); - - /* - * If this table has partitions, recursively expand them in the order - * in which they appear in the PartitionDesc. While at it, also - * extract the partition key columns of all the partitioned tables. - */ - expand_partitioned_rtentry(root, rte, rti, oldrelation, oldrc, - lockmode, &root->append_rel_list); - } - else - { - List *appinfos = NIL; - RangeTblEntry *childrte; - Index childRTindex; - - /* - * This table has no partitions. Expand any plain inheritance - * children in the order the OIDs were returned by - * find_all_inheritors. - */ - foreach(l, inhOIDs) - { - Oid childOID = lfirst_oid(l); - Relation newrelation; - - /* Open rel if needed; we already have required locks */ - if (childOID != parentOID) - newrelation = heap_open(childOID, NoLock); - else - newrelation = oldrelation; - - /* - * It is possible that the parent table has children that are temp - * tables of other backends. We cannot safely access such tables - * (because of buffering issues), and the best thing to do seems - * to be to silently ignore them. - */ - if (childOID != parentOID && RELATION_IS_OTHER_TEMP(newrelation)) - { - heap_close(newrelation, lockmode); - continue; - } - - expand_single_inheritance_child(root, rte, rti, oldrelation, oldrc, - newrelation, - &appinfos, &childrte, - &childRTindex); - - /* Close child relations, but keep locks */ - if (childOID != parentOID) - heap_close(newrelation, NoLock); - } - - /* - * If all the children were temp tables, pretend it's a - * non-inheritance situation; we don't need Append node in that case. - * The duplicate RTE we added for the parent table is harmless, so we - * don't bother to get rid of it; ditto for the useless PlanRowMark - * node. - */ - if (list_length(appinfos) < 2) - rte->inh = false; - else - root->append_rel_list = list_concat(root->append_rel_list, - appinfos); - - } - - heap_close(oldrelation, NoLock); -} - -/* - * expand_partitioned_rtentry - * Recursively expand an RTE for a partitioned table. - * - * Note that RelationGetPartitionDispatchInfo will expand partitions in the - * same order as this code. - */ -static void -expand_partitioned_rtentry(PlannerInfo *root, RangeTblEntry *parentrte, - Index parentRTindex, Relation parentrel, - PlanRowMark *top_parentrc, LOCKMODE lockmode, - List **appinfos) -{ - int i; - RangeTblEntry *childrte; - Index childRTindex; - PartitionDesc partdesc = RelationGetPartitionDesc(parentrel); - - check_stack_depth(); - - /* A partitioned table should always have a partition descriptor. */ - Assert(partdesc); - - Assert(parentrte->inh); - - /* - * Note down whether any partition key cols are being updated. Though it's - * the root partitioned table's updatedCols we are interested in, we - * instead use parentrte to get the updatedCols. This is convenient - * because parentrte already has the root partrel's updatedCols translated - * to match the attribute ordering of parentrel. - */ - if (!root->partColsUpdated) - root->partColsUpdated = - has_partition_attrs(parentrel, parentrte->updatedCols, NULL); - - /* First expand the partitioned table itself. */ - expand_single_inheritance_child(root, parentrte, parentRTindex, parentrel, - top_parentrc, parentrel, - appinfos, &childrte, &childRTindex); - - /* - * If the partitioned table has no partitions, treat this as the - * non-inheritance case. - */ - if (partdesc->nparts == 0) - { - parentrte->inh = false; - return; - } - - for (i = 0; i < partdesc->nparts; i++) - { - Oid childOID = partdesc->oids[i]; - Relation childrel; - - /* Open rel; we already have required locks */ - childrel = heap_open(childOID, NoLock); - - /* - * Temporary partitions belonging to other sessions should have been - * disallowed at definition, but for paranoia's sake, let's double - * check. - */ - if (RELATION_IS_OTHER_TEMP(childrel)) - elog(ERROR, "temporary relation from another session found as partition"); - - expand_single_inheritance_child(root, parentrte, parentRTindex, - parentrel, top_parentrc, childrel, - appinfos, &childrte, &childRTindex); - - /* If this child is itself partitioned, recurse */ - if (childrel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE) - expand_partitioned_rtentry(root, childrte, childRTindex, - childrel, top_parentrc, lockmode, - appinfos); - - /* Close child relation, but keep locks */ - heap_close(childrel, NoLock); - } -} - -/* - * expand_single_inheritance_child - * Build a RangeTblEntry and an AppendRelInfo, if appropriate, plus - * maybe a PlanRowMark. - * - * We now expand the partition hierarchy level by level, creating a - * corresponding hierarchy of AppendRelInfos and RelOptInfos, where each - * partitioned descendant acts as a parent of its immediate partitions. - * (This is a difference from what older versions of PostgreSQL did and what - * is still done in the case of table inheritance for unpartitioned tables, - * where the hierarchy is flattened during RTE expansion.) - * - * PlanRowMarks still carry the top-parent's RTI, and the top-parent's - * allMarkTypes field still accumulates values from all descendents. - * - * "parentrte" and "parentRTindex" are immediate parent's RTE and - * RTI. "top_parentrc" is top parent's PlanRowMark. - * - * The child RangeTblEntry and its RTI are returned in "childrte_p" and - * "childRTindex_p" resp. - */ -static void -expand_single_inheritance_child(PlannerInfo *root, RangeTblEntry *parentrte, - Index parentRTindex, Relation parentrel, - PlanRowMark *top_parentrc, Relation childrel, - List **appinfos, RangeTblEntry **childrte_p, - Index *childRTindex_p) -{ - Query *parse = root->parse; - Oid parentOID = RelationGetRelid(parentrel); - Oid childOID = RelationGetRelid(childrel); - RangeTblEntry *childrte; - Index childRTindex; - AppendRelInfo *appinfo; - - /* - * Build an RTE for the child, and attach to query's rangetable list. We - * copy most fields of the parent's RTE, but replace relation OID and - * relkind, and set inh = false. Also, set requiredPerms to zero since - * all required permissions checks are done on the original RTE. Likewise, - * set the child's securityQuals to empty, because we only want to apply - * the parent's RLS conditions regardless of what RLS properties - * individual children may have. (This is an intentional choice to make - * inherited RLS work like regular permissions checks.) The parent - * securityQuals will be propagated to children along with other base - * restriction clauses, so we don't need to do it here. - */ - childrte = copyObject(parentrte); - *childrte_p = childrte; - childrte->relid = childOID; - childrte->relkind = childrel->rd_rel->relkind; - /* A partitioned child will need to be expanded further. */ - if (childOID != parentOID && - childrte->relkind == RELKIND_PARTITIONED_TABLE) - childrte->inh = true; - else - childrte->inh = false; - childrte->requiredPerms = 0; - childrte->securityQuals = NIL; - parse->rtable = lappend(parse->rtable, childrte); - childRTindex = list_length(parse->rtable); - *childRTindex_p = childRTindex; - - /* - * We need an AppendRelInfo if paths will be built for the child RTE. If - * childrte->inh is true, then we'll always need to generate append paths - * for it. If childrte->inh is false, we must scan it if it's not a - * partitioned table; but if it is a partitioned table, then it never has - * any data of its own and need not be scanned. - */ - if (childrte->relkind != RELKIND_PARTITIONED_TABLE || childrte->inh) - { - appinfo = makeNode(AppendRelInfo); - appinfo->parent_relid = parentRTindex; - appinfo->child_relid = childRTindex; - appinfo->parent_reltype = parentrel->rd_rel->reltype; - appinfo->child_reltype = childrel->rd_rel->reltype; - make_inh_translation_list(parentrel, childrel, childRTindex, - &appinfo->translated_vars); - appinfo->parent_reloid = parentOID; - *appinfos = lappend(*appinfos, appinfo); - - /* - * Translate the column permissions bitmaps to the child's attnums (we - * have to build the translated_vars list before we can do this). But - * if this is the parent table, leave copyObject's result alone. - * - * Note: we need to do this even though the executor won't run any - * permissions checks on the child RTE. The insertedCols/updatedCols - * bitmaps may be examined for trigger-firing purposes. - */ - if (childOID != parentOID) - { - childrte->selectedCols = translate_col_privs(parentrte->selectedCols, - appinfo->translated_vars); - childrte->insertedCols = translate_col_privs(parentrte->insertedCols, - appinfo->translated_vars); - childrte->updatedCols = translate_col_privs(parentrte->updatedCols, - appinfo->translated_vars); - } - } - - /* - * Build a PlanRowMark if parent is marked FOR UPDATE/SHARE. - */ - if (top_parentrc) - { - PlanRowMark *childrc = makeNode(PlanRowMark); - - childrc->rti = childRTindex; - childrc->prti = top_parentrc->rti; - childrc->rowmarkId = top_parentrc->rowmarkId; - /* Reselect rowmark type, because relkind might not match parent */ - childrc->markType = select_rowmark_type(childrte, - top_parentrc->strength); - childrc->allMarkTypes = (1 << childrc->markType); - childrc->strength = top_parentrc->strength; - childrc->waitPolicy = top_parentrc->waitPolicy; - - /* - * We mark RowMarks for partitioned child tables as parent RowMarks so - * that the executor ignores them (except their existence means that - * the child tables be locked using appropriate mode). - */ - childrc->isParent = (childrte->relkind == RELKIND_PARTITIONED_TABLE); - - /* Include child's rowmark type in top parent's allMarkTypes */ - top_parentrc->allMarkTypes |= childrc->allMarkTypes; - - root->rowMarks = lappend(root->rowMarks, childrc); - } -} - -/* - * make_inh_translation_list - * Build the list of translations from parent Vars to child Vars for - * an inheritance child. - * - * For paranoia's sake, we match type/collation as well as attribute name. - */ -static void -make_inh_translation_list(Relation oldrelation, Relation newrelation, - Index newvarno, - List **translated_vars) -{ - List *vars = NIL; - TupleDesc old_tupdesc = RelationGetDescr(oldrelation); - TupleDesc new_tupdesc = RelationGetDescr(newrelation); - Oid new_relid = RelationGetRelid(newrelation); - int oldnatts = old_tupdesc->natts; - int newnatts = new_tupdesc->natts; - int old_attno; - int new_attno = 0; - - for (old_attno = 0; old_attno < oldnatts; old_attno++) - { - Form_pg_attribute att; - char *attname; - Oid atttypid; - int32 atttypmod; - Oid attcollation; - - att = TupleDescAttr(old_tupdesc, old_attno); - if (att->attisdropped) - { - /* Just put NULL into this list entry */ - vars = lappend(vars, NULL); - continue; - } - attname = NameStr(att->attname); - atttypid = att->atttypid; - atttypmod = att->atttypmod; - attcollation = att->attcollation; - - /* - * When we are generating the "translation list" for the parent table - * of an inheritance set, no need to search for matches. - */ - if (oldrelation == newrelation) - { - vars = lappend(vars, makeVar(newvarno, - (AttrNumber) (old_attno + 1), - atttypid, - atttypmod, - attcollation, - 0)); - continue; - } - - /* - * Otherwise we have to search for the matching column by name. - * There's no guarantee it'll have the same column position, because - * of cases like ALTER TABLE ADD COLUMN and multiple inheritance. - * However, in simple cases, the relative order of columns is mostly - * the same in both relations, so try the column of newrelation that - * follows immediately after the one that we just found, and if that - * fails, let syscache handle it. - */ - if (new_attno >= newnatts || - (att = TupleDescAttr(new_tupdesc, new_attno))->attisdropped || - strcmp(attname, NameStr(att->attname)) != 0) - { - HeapTuple newtup; - - newtup = SearchSysCacheAttName(new_relid, attname); - if (!newtup) - elog(ERROR, "could not find inherited attribute \"%s\" of relation \"%s\"", - attname, RelationGetRelationName(newrelation)); - new_attno = ((Form_pg_attribute) GETSTRUCT(newtup))->attnum - 1; - ReleaseSysCache(newtup); - - att = TupleDescAttr(new_tupdesc, new_attno); - } - - /* Found it, check type and collation match */ - if (atttypid != att->atttypid || atttypmod != att->atttypmod) - elog(ERROR, "attribute \"%s\" of relation \"%s\" does not match parent's type", - attname, RelationGetRelationName(newrelation)); - if (attcollation != att->attcollation) - elog(ERROR, "attribute \"%s\" of relation \"%s\" does not match parent's collation", - attname, RelationGetRelationName(newrelation)); - - vars = lappend(vars, makeVar(newvarno, - (AttrNumber) (new_attno + 1), - atttypid, - atttypmod, - attcollation, - 0)); - new_attno++; - } - - *translated_vars = vars; -} - -/* - * translate_col_privs - * Translate a bitmapset representing per-column privileges from the - * parent rel's attribute numbering to the child's. - * - * The only surprise here is that we don't translate a parent whole-row - * reference into a child whole-row reference. That would mean requiring - * permissions on all child columns, which is overly strict, since the - * query is really only going to reference the inherited columns. Instead - * we set the per-column bits for all inherited columns. - */ -static Bitmapset * -translate_col_privs(const Bitmapset *parent_privs, - List *translated_vars) -{ - Bitmapset *child_privs = NULL; - bool whole_row; - int attno; - ListCell *lc; - - /* System attributes have the same numbers in all tables */ - for (attno = FirstLowInvalidHeapAttributeNumber + 1; attno < 0; attno++) - { - if (bms_is_member(attno - FirstLowInvalidHeapAttributeNumber, - parent_privs)) - child_privs = bms_add_member(child_privs, - attno - FirstLowInvalidHeapAttributeNumber); - } - - /* Check if parent has whole-row reference */ - whole_row = bms_is_member(InvalidAttrNumber - FirstLowInvalidHeapAttributeNumber, - parent_privs); - - /* And now translate the regular user attributes, using the vars list */ - attno = InvalidAttrNumber; - foreach(lc, translated_vars) - { - Var *var = lfirst_node(Var, lc); - - attno++; - if (var == NULL) /* ignore dropped columns */ - continue; - if (whole_row || - bms_is_member(attno - FirstLowInvalidHeapAttributeNumber, - parent_privs)) - child_privs = bms_add_member(child_privs, - var->varattno - FirstLowInvalidHeapAttributeNumber); - } - - return child_privs; -} - -/* - * adjust_appendrel_attrs - * Copy the specified query or expression and translate Vars referring to a - * parent rel to refer to the corresponding child rel instead. We also - * update rtindexes appearing outside Vars, such as resultRelation and - * jointree relids. - * - * Note: this is only applied after conversion of sublinks to subplans, - * so we don't need to cope with recursion into sub-queries. - * - * Note: this is not hugely different from what pullup_replace_vars() does; - * maybe we should try to fold the two routines together. - */ -Node * -adjust_appendrel_attrs(PlannerInfo *root, Node *node, int nappinfos, - AppendRelInfo **appinfos) -{ - Node *result; - adjust_appendrel_attrs_context context; - - context.root = root; - context.nappinfos = nappinfos; - context.appinfos = appinfos; - - /* If there's nothing to adjust, don't call this function. */ - Assert(nappinfos >= 1 && appinfos != NULL); - - /* - * Must be prepared to start with a Query or a bare expression tree. - */ - if (node && IsA(node, Query)) - { - Query *newnode; - int cnt; - - newnode = query_tree_mutator((Query *) node, - adjust_appendrel_attrs_mutator, - (void *) &context, - QTW_IGNORE_RC_SUBQUERIES); - for (cnt = 0; cnt < nappinfos; cnt++) - { - AppendRelInfo *appinfo = appinfos[cnt]; - - if (newnode->resultRelation == appinfo->parent_relid) - { - newnode->resultRelation = appinfo->child_relid; - /* Fix tlist resnos too, if it's inherited UPDATE */ - if (newnode->commandType == CMD_UPDATE) - newnode->targetList = - adjust_inherited_tlist(newnode->targetList, - appinfo); - break; - } - } - - result = (Node *) newnode; - } - else - result = adjust_appendrel_attrs_mutator(node, &context); - - return result; -} - -static Node * -adjust_appendrel_attrs_mutator(Node *node, - adjust_appendrel_attrs_context *context) -{ - AppendRelInfo **appinfos = context->appinfos; - int nappinfos = context->nappinfos; - int cnt; - - if (node == NULL) - return NULL; - if (IsA(node, Var)) - { - Var *var = (Var *) copyObject(node); - AppendRelInfo *appinfo = NULL; - - for (cnt = 0; cnt < nappinfos; cnt++) - { - if (var->varno == appinfos[cnt]->parent_relid) - { - appinfo = appinfos[cnt]; - break; - } - } - - if (var->varlevelsup == 0 && appinfo) - { - var->varno = appinfo->child_relid; - var->varnoold = appinfo->child_relid; - if (var->varattno > 0) - { - Node *newnode; - - if (var->varattno > list_length(appinfo->translated_vars)) - elog(ERROR, "attribute %d of relation \"%s\" does not exist", - var->varattno, get_rel_name(appinfo->parent_reloid)); - newnode = copyObject(list_nth(appinfo->translated_vars, - var->varattno - 1)); - if (newnode == NULL) - elog(ERROR, "attribute %d of relation \"%s\" does not exist", - var->varattno, get_rel_name(appinfo->parent_reloid)); - return newnode; - } - else if (var->varattno == 0) - { - /* - * Whole-row Var: if we are dealing with named rowtypes, we - * can use a whole-row Var for the child table plus a coercion - * step to convert the tuple layout to the parent's rowtype. - * Otherwise we have to generate a RowExpr. - */ - if (OidIsValid(appinfo->child_reltype)) - { - Assert(var->vartype == appinfo->parent_reltype); - if (appinfo->parent_reltype != appinfo->child_reltype) - { - ConvertRowtypeExpr *r = makeNode(ConvertRowtypeExpr); - - r->arg = (Expr *) var; - r->resulttype = appinfo->parent_reltype; - r->convertformat = COERCE_IMPLICIT_CAST; - r->location = -1; - /* Make sure the Var node has the right type ID, too */ - var->vartype = appinfo->child_reltype; - return (Node *) r; - } - } - else - { - /* - * Build a RowExpr containing the translated variables. - * - * In practice var->vartype will always be RECORDOID here, - * so we need to come up with some suitable column names. - * We use the parent RTE's column names. - * - * Note: we can't get here for inheritance cases, so there - * is no need to worry that translated_vars might contain - * some dummy NULLs. - */ - RowExpr *rowexpr; - List *fields; - RangeTblEntry *rte; - - rte = rt_fetch(appinfo->parent_relid, - context->root->parse->rtable); - fields = copyObject(appinfo->translated_vars); - rowexpr = makeNode(RowExpr); - rowexpr->args = fields; - rowexpr->row_typeid = var->vartype; - rowexpr->row_format = COERCE_IMPLICIT_CAST; - rowexpr->colnames = copyObject(rte->eref->colnames); - rowexpr->location = -1; - - return (Node *) rowexpr; - } - } - /* system attributes don't need any other translation */ - } - return (Node *) var; - } - if (IsA(node, CurrentOfExpr)) - { - CurrentOfExpr *cexpr = (CurrentOfExpr *) copyObject(node); - - for (cnt = 0; cnt < nappinfos; cnt++) - { - AppendRelInfo *appinfo = appinfos[cnt]; - - if (cexpr->cvarno == appinfo->parent_relid) - { - cexpr->cvarno = appinfo->child_relid; - break; - } - } - return (Node *) cexpr; - } - if (IsA(node, RangeTblRef)) - { - RangeTblRef *rtr = (RangeTblRef *) copyObject(node); - - for (cnt = 0; cnt < nappinfos; cnt++) - { - AppendRelInfo *appinfo = appinfos[cnt]; - - if (rtr->rtindex == appinfo->parent_relid) - { - rtr->rtindex = appinfo->child_relid; - break; - } - } - return (Node *) rtr; - } - if (IsA(node, JoinExpr)) - { - /* Copy the JoinExpr node with correct mutation of subnodes */ - JoinExpr *j; - AppendRelInfo *appinfo; - - j = (JoinExpr *) expression_tree_mutator(node, - adjust_appendrel_attrs_mutator, - (void *) context); - /* now fix JoinExpr's rtindex (probably never happens) */ - for (cnt = 0; cnt < nappinfos; cnt++) - { - appinfo = appinfos[cnt]; - - if (j->rtindex == appinfo->parent_relid) - { - j->rtindex = appinfo->child_relid; - break; - } - } - return (Node *) j; - } - if (IsA(node, PlaceHolderVar)) - { - /* Copy the PlaceHolderVar node with correct mutation of subnodes */ - PlaceHolderVar *phv; - - phv = (PlaceHolderVar *) expression_tree_mutator(node, - adjust_appendrel_attrs_mutator, - (void *) context); - /* now fix PlaceHolderVar's relid sets */ - if (phv->phlevelsup == 0) - phv->phrels = adjust_child_relids(phv->phrels, context->nappinfos, - context->appinfos); - return (Node *) phv; - } - - /* - * This is needed, because inheritance_make_rel_from_joinlist needs to - * translate root->join_info_list executing make_rel_from_joinlist for a - * given child. - */ - if (IsA(node, SpecialJoinInfo)) - { - SpecialJoinInfo *oldinfo = (SpecialJoinInfo *) node; - SpecialJoinInfo *newinfo = makeNode(SpecialJoinInfo); - - memcpy(newinfo, oldinfo, sizeof(SpecialJoinInfo)); - newinfo->min_lefthand = adjust_child_relids(oldinfo->min_lefthand, - context->nappinfos, - context->appinfos); - newinfo->min_righthand = adjust_child_relids(oldinfo->min_righthand, - context->nappinfos, - context->appinfos); - newinfo->syn_lefthand = adjust_child_relids(oldinfo->syn_lefthand, - context->nappinfos, - context->appinfos); - newinfo->syn_righthand = adjust_child_relids(oldinfo->syn_righthand, - context->nappinfos, - context->appinfos); - newinfo->semi_rhs_exprs = - (List *) expression_tree_mutator((Node *) - oldinfo->semi_rhs_exprs, - adjust_appendrel_attrs_mutator, - (void *) context); - return (Node *) newinfo; - } - - /* Shouldn't need to handle planner auxiliary nodes here */ - Assert(!IsA(node, AppendRelInfo)); - Assert(!IsA(node, PlaceHolderInfo)); - Assert(!IsA(node, MinMaxAggInfo)); - - /* - * We have to process RestrictInfo nodes specially. (Note: although - * set_append_rel_pathlist will hide RestrictInfos in the parent's - * baserestrictinfo list from us, it doesn't hide those in joininfo.) - */ - if (IsA(node, RestrictInfo)) - { - RestrictInfo *oldinfo = (RestrictInfo *) node; - RestrictInfo *newinfo = makeNode(RestrictInfo); - - /* Copy all flat-copiable fields */ - memcpy(newinfo, oldinfo, sizeof(RestrictInfo)); - - /* Recursively fix the clause itself */ - newinfo->clause = (Expr *) - adjust_appendrel_attrs_mutator((Node *) oldinfo->clause, context); - - /* and the modified version, if an OR clause */ - newinfo->orclause = (Expr *) - adjust_appendrel_attrs_mutator((Node *) oldinfo->orclause, context); - - /* adjust relid sets too */ - newinfo->clause_relids = adjust_child_relids(oldinfo->clause_relids, - context->nappinfos, - context->appinfos); - newinfo->required_relids = adjust_child_relids(oldinfo->required_relids, - context->nappinfos, - context->appinfos); - newinfo->outer_relids = adjust_child_relids(oldinfo->outer_relids, - context->nappinfos, - context->appinfos); - newinfo->nullable_relids = adjust_child_relids(oldinfo->nullable_relids, - context->nappinfos, - context->appinfos); - newinfo->left_relids = adjust_child_relids(oldinfo->left_relids, - context->nappinfos, - context->appinfos); - newinfo->right_relids = adjust_child_relids(oldinfo->right_relids, - context->nappinfos, - context->appinfos); - - /* - * Reset cached derivative fields, since these might need to have - * different values when considering the child relation. Note we - * don't reset left_ec/right_ec: each child variable is implicitly - * equivalent to its parent, so still a member of the same EC if any. - */ - newinfo->eval_cost.startup = -1; - newinfo->norm_selec = -1; - newinfo->outer_selec = -1; - newinfo->left_em = NULL; - newinfo->right_em = NULL; - newinfo->scansel_cache = NIL; - newinfo->left_bucketsize = -1; - newinfo->right_bucketsize = -1; - newinfo->left_mcvfreq = -1; - newinfo->right_mcvfreq = -1; - - return (Node *) newinfo; - } - - /* - * NOTE: we do not need to recurse into sublinks, because they should - * already have been converted to subplans before we see them. - */ - Assert(!IsA(node, SubLink)); - Assert(!IsA(node, Query)); - - return expression_tree_mutator(node, adjust_appendrel_attrs_mutator, - (void *) context); -} - -/* - * Substitute child relids for parent relids in a Relid set. The array of - * appinfos specifies the substitutions to be performed. - */ -static Relids -adjust_child_relids(Relids relids, int nappinfos, AppendRelInfo **appinfos) -{ - Bitmapset *result = NULL; - int cnt; - - for (cnt = 0; cnt < nappinfos; cnt++) - { - AppendRelInfo *appinfo = appinfos[cnt]; - - /* Remove parent, add child */ - if (bms_is_member(appinfo->parent_relid, relids)) - { - /* Make a copy if we are changing the set. */ - if (!result) - result = bms_copy(relids); - - result = bms_del_member(result, appinfo->parent_relid); - result = bms_add_member(result, appinfo->child_relid); - } - } - - /* If we made any changes, return the modified copy. */ - if (result) - return result; - - /* Otherwise, return the original set without modification. */ - return relids; -} - -/* - * Replace any relid present in top_parent_relids with its child in - * child_relids. Members of child_relids can be multiple levels below top - * parent in the partition hierarchy. - */ -Relids -adjust_child_relids_multilevel(PlannerInfo *root, Relids relids, - Relids child_relids, Relids top_parent_relids) -{ - AppendRelInfo **appinfos; - int nappinfos; - Relids parent_relids = NULL; - Relids result; - Relids tmp_result = NULL; - int cnt; - - /* - * If the given relids set doesn't contain any of the top parent relids, - * it will remain unchanged. - */ - if (!bms_overlap(relids, top_parent_relids)) - return relids; - - appinfos = find_appinfos_by_relids(root, child_relids, &nappinfos); - - /* Construct relids set for the immediate parent of the given child. */ - for (cnt = 0; cnt < nappinfos; cnt++) - { - AppendRelInfo *appinfo = appinfos[cnt]; - - parent_relids = bms_add_member(parent_relids, appinfo->parent_relid); - } - - /* Recurse if immediate parent is not the top parent. */ - if (!bms_equal(parent_relids, top_parent_relids)) - { - tmp_result = adjust_child_relids_multilevel(root, relids, - parent_relids, - top_parent_relids); - relids = tmp_result; - } - - result = adjust_child_relids(relids, nappinfos, appinfos); - - /* Free memory consumed by any intermediate result. */ - if (tmp_result) - bms_free(tmp_result); - bms_free(parent_relids); - pfree(appinfos); - - return result; -} - -/* - * Adjust the targetlist entries of an inherited UPDATE operation - * - * The expressions have already been fixed, but we have to make sure that - * the target resnos match the child table (they may not, in the case of - * a column that was added after-the-fact by ALTER TABLE). In some cases - * this can force us to re-order the tlist to preserve resno ordering. - * (We do all this work in special cases so that preptlist.c is fast for - * the typical case.) - * - * The given tlist has already been through expression_tree_mutator; - * therefore the TargetEntry nodes are fresh copies that it's okay to - * scribble on. - * - * Note that this is not needed for INSERT because INSERT isn't inheritable. - */ -static List * -adjust_inherited_tlist(List *tlist, AppendRelInfo *context) -{ - bool changed_it = false; - ListCell *tl; - List *new_tlist; - bool more; - int attrno; - - /* This should only happen for an inheritance case, not UNION ALL */ - Assert(OidIsValid(context->parent_reloid)); - - /* Scan tlist and update resnos to match attnums of child rel */ - foreach(tl, tlist) - { - TargetEntry *tle = (TargetEntry *) lfirst(tl); - Var *childvar; - - if (tle->resjunk) - continue; /* ignore junk items */ - - /* Look up the translation of this column: it must be a Var */ - if (tle->resno <= 0 || - tle->resno > list_length(context->translated_vars)) - elog(ERROR, "attribute %d of relation \"%s\" does not exist", - tle->resno, get_rel_name(context->parent_reloid)); - childvar = (Var *) list_nth(context->translated_vars, tle->resno - 1); - if (childvar == NULL || !IsA(childvar, Var)) - elog(ERROR, "attribute %d of relation \"%s\" does not exist", - tle->resno, get_rel_name(context->parent_reloid)); - - if (tle->resno != childvar->varattno) - { - tle->resno = childvar->varattno; - changed_it = true; - } - } - - /* - * If we changed anything, re-sort the tlist by resno, and make sure - * resjunk entries have resnos above the last real resno. The sort - * algorithm is a bit stupid, but for such a seldom-taken path, small is - * probably better than fast. - */ - if (!changed_it) - return tlist; - - new_tlist = NIL; - more = true; - for (attrno = 1; more; attrno++) - { - more = false; - foreach(tl, tlist) - { - TargetEntry *tle = (TargetEntry *) lfirst(tl); - - if (tle->resjunk) - continue; /* ignore junk items */ - - if (tle->resno == attrno) - new_tlist = lappend(new_tlist, tle); - else if (tle->resno > attrno) - more = true; - } - } - - foreach(tl, tlist) - { - TargetEntry *tle = (TargetEntry *) lfirst(tl); - - if (!tle->resjunk) - continue; /* here, ignore non-junk items */ - - tle->resno = attrno; - new_tlist = lappend(new_tlist, tle); - attrno++; - } - - return new_tlist; -} - -/* - * adjust_appendrel_attrs_multilevel - * Apply Var translations from a toplevel appendrel parent down to a child. - * - * In some cases we need to translate expressions referencing a parent relation - * to reference an appendrel child that's multiple levels removed from it. - */ -Node * -adjust_appendrel_attrs_multilevel(PlannerInfo *root, Node *node, - Relids child_relids, - Relids top_parent_relids) -{ - AppendRelInfo **appinfos; - Bitmapset *parent_relids = NULL; - int nappinfos; - int cnt; - - Assert(bms_num_members(child_relids) == bms_num_members(top_parent_relids)); - - appinfos = find_appinfos_by_relids(root, child_relids, &nappinfos); - - /* Construct relids set for the immediate parent of given child. */ - for (cnt = 0; cnt < nappinfos; cnt++) - { - AppendRelInfo *appinfo = appinfos[cnt]; - - parent_relids = bms_add_member(parent_relids, appinfo->parent_relid); - } - - /* Recurse if immediate parent is not the top parent. */ - if (!bms_equal(parent_relids, top_parent_relids)) - node = adjust_appendrel_attrs_multilevel(root, node, parent_relids, - top_parent_relids); - - /* Now translate for this child */ - node = adjust_appendrel_attrs(root, node, nappinfos, appinfos); - - pfree(appinfos); - - return node; -} - -/* - * Construct the SpecialJoinInfo for a child-join by translating - * SpecialJoinInfo for the join between parents. left_relids and right_relids - * are the relids of left and right side of the join respectively. - */ -SpecialJoinInfo * -build_child_join_sjinfo(PlannerInfo *root, SpecialJoinInfo *parent_sjinfo, - Relids left_relids, Relids right_relids) -{ - SpecialJoinInfo *sjinfo = makeNode(SpecialJoinInfo); - AppendRelInfo **left_appinfos; - int left_nappinfos; - AppendRelInfo **right_appinfos; - int right_nappinfos; - - memcpy(sjinfo, parent_sjinfo, sizeof(SpecialJoinInfo)); - left_appinfos = find_appinfos_by_relids(root, left_relids, - &left_nappinfos); - right_appinfos = find_appinfos_by_relids(root, right_relids, - &right_nappinfos); - - sjinfo->min_lefthand = adjust_child_relids(sjinfo->min_lefthand, - left_nappinfos, left_appinfos); - sjinfo->min_righthand = adjust_child_relids(sjinfo->min_righthand, - right_nappinfos, - right_appinfos); - sjinfo->syn_lefthand = adjust_child_relids(sjinfo->syn_lefthand, - left_nappinfos, left_appinfos); - sjinfo->syn_righthand = adjust_child_relids(sjinfo->syn_righthand, - right_nappinfos, - right_appinfos); - sjinfo->semi_rhs_exprs = (List *) adjust_appendrel_attrs(root, - (Node *) sjinfo->semi_rhs_exprs, - right_nappinfos, - right_appinfos); - - pfree(left_appinfos); - pfree(right_appinfos); - - return sjinfo; -} - -/* - * find_appinfos_by_relids - * Find AppendRelInfo structures for all relations specified by relids. - * - * The AppendRelInfos are returned in an array, which can be pfree'd by the - * caller. *nappinfos is set to the number of entries in the array. - */ -AppendRelInfo ** -find_appinfos_by_relids(PlannerInfo *root, Relids relids, int *nappinfos) -{ - AppendRelInfo **appinfos; - int cnt = 0; - int i; - - *nappinfos = bms_num_members(relids); - appinfos = (AppendRelInfo **) palloc(sizeof(AppendRelInfo *) * *nappinfos); - - i = -1; - while ((i = bms_next_member(relids, i)) >= 0) - { - AppendRelInfo *appinfo = root->append_rel_array[i]; - - if (!appinfo) - elog(ERROR, "child rel %d not found in append_rel_array", i); - - appinfos[cnt++] = appinfo; - } - return appinfos; -} diff --git a/src/backend/optimizer/util/Makefile b/src/backend/optimizer/util/Makefile index c54d0a690d..d166030a10 100644 --- a/src/backend/optimizer/util/Makefile +++ b/src/backend/optimizer/util/Makefile @@ -12,7 +12,8 @@ subdir = src/backend/optimizer/util top_builddir = ../../../.. include $(top_builddir)/src/Makefile.global -OBJS = clauses.o joininfo.o orclauses.o pathnode.o placeholder.o \ - plancat.o predtest.o relnode.o restrictinfo.o tlist.o var.o +OBJS = append.o appendinfo.o clauses.o joininfo.o orclauses.o pathnode.o \ + placeholder.o plancat.o predtest.o relnode.o restrictinfo.o tlist.o \ + var.o include $(top_srcdir)/src/backend/common.mk diff --git a/src/backend/optimizer/util/append.c b/src/backend/optimizer/util/append.c new file mode 100644 index 0000000000..76d9246d5f --- /dev/null +++ b/src/backend/optimizer/util/append.c @@ -0,0 +1,679 @@ +/*------------------------------------------------------------------------- + * + * append.c + * Routines to process children of an appendrel parent + * + * Portions Copyright (c) 1996-2018, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/optimizer/path/append.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include + +#include "access/sysattr.h" +#include "catalog/partition.h" +#include "catalog/pg_class.h" +#include "catalog/pg_inherits.h" +#include "catalog/pg_type.h" +#include "nodes/makefuncs.h" +#include "optimizer/append.h" +#include "optimizer/appendinfo.h" +#include "optimizer/clauses.h" +#include "optimizer/pathnode.h" +#include "optimizer/paths.h" +#include "optimizer/plancat.h" +#include "optimizer/planmain.h" +#include "optimizer/planner.h" +#include "optimizer/prep.h" +#include "optimizer/restrictinfo.h" +#include "optimizer/tlist.h" +#include "optimizer/var.h" +#include "partitioning/partprune.h" +#include "utils/rel.h" + +static RelOptInfo *add_inheritance_child_rel(PlannerInfo *root, + RelOptInfo *rel, + RangeTblEntry *rte, + Oid childOID, + LOCKMODE lockmode, + PlanRowMark *top_parentrc); +static RelOptInfo *build_append_child_rel(PlannerInfo *root, + RelOptInfo *parent, + Index childRTindex); +static List *add_rowmark_junk_columns(PlannerInfo *root, PlanRowMark *rc); + +/* + * expand_append_rel + * This initializes RelOptInfos for an appendrel's child relations. + * + * 'rel' is the appendrel parent, whose range table entry ('rte') has been + * marked to require adding children. An appendrel parent could either + * be a subquery (if we flattened UNION ALL query) or a table that's known + * to have inheritance children. The latter consists of both regular + * inheritance parents and partitioned tables. + * + * For a subquery parent, there is not much to be done here because the + * children's RTEs are already present in the query, so we just initialize + * RelOptInfos for them. Also, the AppendRelInfos for child subqueries + * have already been added. + * + * For tables, we need to add the children to the range table and initialize + * AppendRelInfos, RelOptInfos, and PlanRowMarks (if any) for them. For + * a partitioned parent, we only add the children remaining after pruning. + * For regular inheritance parents, we find the children using + * find_all_inheritors and add all of them. + * + * If it turns out that there are no children, then we set rte->inh to false + * to let the caller know that only the parent table needs to be scanned. The + * caller can accordingly switch to a non-Append path. For a partitioned + * parent, that means an empty relation because parents themselves contain no + * data. + * + * For the regular inheritance case, the parent also gets another RTE with + * inh = false to represent it as an appendrel child. The original RTE is + * considered to represent the whole inheritance set. + */ +void +expand_append_rel(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte, + Index rti) +{ + LOCKMODE lockmode; + ListCell *l; + + Assert(rte->inh); + /* Inheritance parent (partitioned or not) or UNION ALL parent subquery. */ + Assert(rte->rtekind == RTE_RELATION || rte->rtekind == RTE_SUBQUERY); + + /* + * The rewriter should already have obtained an appropriate lock on + * each relation named in the query. However, for each child relation + * we add to the query, we must obtain an appropriate lock, because + * this will be the first use of those relations in the + * parse/rewrite/plan pipeline. Child rels should use the same + * lockmode as their parent. + */ + if (rte->rtekind == RTE_RELATION) + { + lockmode = rte->rellockmode; + Assert(has_subclass(rte->relid)); + } + + /* + * UNION ALL children already got RTEs and AppendRelInfos, so just build + * RelOptInfos and return. + * + * It might be a bit odd that this code is in this, because there is + * nothing to expand really. + */ + if (rte->rtekind == RTE_SUBQUERY) + { + /* + * We don't need to use expand_planner_arrays in this case, because + * no new child RTEs are created. setup_simple_rel_arrays() and + * setup_append_rel_array would've considered these child RTEs when + * allocating space for various arrays. + */ + foreach(l, root->append_rel_list) + { + AppendRelInfo *appinfo = lfirst(l); + Index childRTindex = appinfo->child_relid; + + if (appinfo->parent_relid != rti) + continue; + + Assert(childRTindex < root->simple_rel_array_size); + Assert(root->simple_rte_array[childRTindex] != NULL); + + /* + * We set the correct value of baserestricinfo and + * baserestrict_min_security below. + */ + root->simple_rel_array[childRTindex] = + build_append_child_rel(root, rel, appinfo->child_relid); + } + } + else if (rte->relkind == RELKIND_PARTITIONED_TABLE) + { + Index root_parent = rel->inh_root_parent > 0 ? + rel->inh_root_parent : + rel->relid; + PlanRowMark *rootrc = NULL; + int i; + Bitmapset *partindexes; + + Assert(rte->rtekind == RTE_RELATION); + Assert(lockmode != NoLock); + + /* If root partitioned table, lock *all* partitions in the tree. */ + if (rel->relid == root_parent) + (void) find_all_inheritors(rte->relid, lockmode, NULL); + + /* + * Initialize partitioned_child_rels to contain this RT index. + * + * Note that during the set_append_rel_pathlist() phase, we will bubble + * up the indexes of partitioned relations that appear down in the + * tree, so that when we've created Paths for all the children, the + * root partitioned table's list will contain all such indexes. + */ + rel->partitioned_child_rels = list_make1_int(rti); + + /* Perform pruning. */ + partindexes = prune_append_rel_partitions(rel); + + /* Must expand PlannerInfo arrays before we can add children. */ + expand_planner_arrays(root, bms_num_members(partindexes)); + + /* + * For partitioned tables, we also store the partition RelOptInfo + * pointers in the parent's RelOptInfo. + */ + rel->part_rels = (RelOptInfo **) palloc0(sizeof(RelOptInfo *) * + rel->nparts); + + rootrc = get_plan_rowmark(root->rowMarks, root_parent); + Assert(rootrc == NULL || rootrc->isParent); + + i = -1; + while ((i = bms_next_member(partindexes, i)) >= 0) + { + Oid childOID = rel->part_oids[i]; + RelOptInfo *childrel; + + /* Already locked, so pass NoLock. */ + childrel = add_inheritance_child_rel(root, rel, rte, + childOID, + NoLock, + rootrc); + rel->part_rels[i] = childrel; + } + + /* + * Add junk columns needed by the row mark if any and also add the + * relevant expressions to the root parent's reltarget. + */ + if (rootrc) + { + List *tlist = add_rowmark_junk_columns(root, rootrc); + + build_base_rel_tlists(root, tlist); + } + + } + else + { + /* + * Regular inheritance case, where each child must be opened and + * checked if it can be excluded. + */ + PlanRowMark *oldrc; + List *inhOIDs; + int num_children; + int num_children_added = 0; + + Assert(rte->rtekind == RTE_RELATION); + Assert(lockmode != NoLock); + + /* Scan for all members of inheritance set, acquire needed locks */ + inhOIDs = find_all_inheritors(rte->relid, lockmode, NULL); + num_children = list_length(inhOIDs); + + /* + * Check that there's at least one descendant, else treat as no-child + * case. This could happen despite the has_subclass() check passing, + * if table once had a child but no longer does (relhassubclass is + * only opportunistically reset). + */ + if (num_children < 2) + { + /* Clear flag before returning */ + rte->inh = false; + return; + } + + /* + * If parent relation is selected FOR UPDATE/SHARE, we need to mark + * its PlanRowMark as isParent = true, and generate a new PlanRowMark + * for each child. + */ + oldrc = get_plan_rowmark(root->rowMarks, rti); + Assert(oldrc == NULL || oldrc->isParent); + + /* + * Must expand PlannerInfo arrays by num_children before we can add + * children. + */ + expand_planner_arrays(root, num_children); + + foreach(l, inhOIDs) + { + Oid childOID = lfirst_oid(l); + + /* + * We pass NoLock here, because find_all_inheritors already got + * the lock. + */ + if (add_inheritance_child_rel(root, rel, rte, childOID, NoLock, + oldrc) != NULL) + num_children_added++; + } + + /* + * If all children, including the parent (as child rel), were + * excluded, mark the parent rel as empty. + */ + if (num_children_added == 0) + mark_dummy_rel(rel); + /* + * If all the children were temp tables, pretend it's a + * non-inheritance situation; we don't need Append node in that case. + * The duplicate RTE we added for the parent table is harmless, so we + * don't bother to get rid of it; ditto for the useless PlanRowMark + * node. + */ + else if (num_children_added == 1) + rte->inh = false; + + /* + * Add junk columns needed by the row mark if any and also add the + * relevant expressions to the root parent's reltarget. + */ + if (oldrc) + { + List *tlist = add_rowmark_junk_columns(root, oldrc); + + build_base_rel_tlists(root, tlist); + } + } +} + +/* + * add_inheritance_child_rel + * This conditionally adds various objects needed for planning an + * inheritance child table + * + * The added objects include a RangeTblEntry, an AppendRelInfo, a PlanRowMark, + * and finally a RelOptInfo. Return value is the RelOptInfo if one is added, + * NULL otherwise. + * + * If the child is a partitioned table with 0 partitions or if it's a + * temporary table from another session, we cannot get any data from it, + * so we don't add anything in that case. + */ +static RelOptInfo * +add_inheritance_child_rel(PlannerInfo *root, + RelOptInfo *parent, + RangeTblEntry *rte, + Oid childOID, + LOCKMODE lockmode, + PlanRowMark *top_parentrc) +{ + Query *parse = root->parse; + Relation childrel; + Index childRTindex; + RangeTblEntry *childrte; + AppendRelInfo *appinfo; + RelOptInfo *childrelopt; + + childrel = heap_open(childOID, lockmode); + + /* + * A partitioned child table with 0 children is a dummy rel, so don't + * bother creating planner objects for it. + */ + if (childrel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE) + { + PartitionDesc partdesc = RelationGetPartitionDesc(childrel); + + Assert(!RELATION_IS_OTHER_TEMP(childrel)); + if (partdesc->nparts == 0) + { + heap_close(childrel, NoLock); + return NULL; + } + } + + /* + * If childrel doesn't belong to this session, skip it, also relinquishing + * the lock. + */ + if (RELATION_IS_OTHER_TEMP(childrel)) + { + heap_close(childrel, lockmode); + return NULL; + } + + /* + * Build an RTE for the child, and attach to query's rangetable list. We + * copy most fields of the parent's RTE, but replace relation OID and + * relkind, and set inh appropriately. Also, set requiredPerms to zero + * since all required permissions checks are done on the original RTE. + * Likewise, set the child's securityQuals to empty, because we only want + * to apply the parent's RLS conditions regardless of what RLS properties + * individual children may have. (This is an intentional choice to make + * inherited RLS work like regular permissions checks.) The parent + * securityQuals will be propagated to children along with other base + * restriction clauses, so we don't need to do it here. + */ + childrte = copyObject(rte); + childrte->relid = RelationGetRelid(childrel); + childrte->relkind = RelationGetForm(childrel)->relkind; + /* + * A partitioned child will need to be expanded as an append parent + * itself, so set its inh to true. + */ + childrte->inh = (childrte->relkind == RELKIND_PARTITIONED_TABLE); + childrte->requiredPerms = 0; + childrte->securityQuals = NIL; + parse->rtable = lappend(parse->rtable, childrte); + childRTindex = list_length(parse->rtable); + + /* Create an AppendRelInfo and add it to planner's global list. */ + appinfo = make_append_rel_info(parent, rte, + RelationGetDescr(childrel), + RelationGetRelid(childrel), + RelationGetForm(childrel)->reltype, + childRTindex); + root->append_rel_list = lappend(root->append_rel_list, appinfo); + + /* Close the child relation, but keep the lock. */ + heap_close(childrel, NoLock); + + /* + * Translate the column permissions bitmaps to the child's attnums (we + * have to build the translated_vars list before we can do this). But + * if this is the parent table, leave copyObject's result alone. + * + * Note: we need to do this even though the executor won't run any + * permissions checks on the child RTE. The insertedCols/updatedCols + * bitmaps may be examined for trigger-firing purposes. + */ + if (childrte->relid != rte->relid) + { + childrte->selectedCols = translate_col_privs(rte->selectedCols, + appinfo->translated_vars); + childrte->insertedCols = translate_col_privs(rte->insertedCols, + appinfo->translated_vars); + childrte->updatedCols = translate_col_privs(rte->updatedCols, + appinfo->translated_vars); + } + + /* Add child PlanRowMark. */ + if (top_parentrc) + { + PlanRowMark *childrc = makeNode(PlanRowMark); + + childrc->rti = list_length(parse->rtable); + childrc->prti = top_parentrc->rti; + childrc->rowmarkId = top_parentrc->rowmarkId; + /* Reselect rowmark type, because relkind might not match parent */ + childrc->markType = select_rowmark_type(childrte, top_parentrc->strength); + childrc->allMarkTypes = (1 << childrc->markType); + childrc->strength = top_parentrc->strength; + childrc->waitPolicy = top_parentrc->waitPolicy; + + /* + * We mark RowMarks for partitioned child tables as parent RowMarks so + * that the executor ignores them (except their existence means that + * the child tables be locked using appropriate mode). + */ + childrc->isParent = (childrte->relkind == RELKIND_PARTITIONED_TABLE); + + /* Include child's rowmark type in top parent's allMarkTypes */ + top_parentrc->allMarkTypes |= childrc->allMarkTypes; + root->rowMarks = lappend(root->rowMarks, childrc); + } + + /* + * Add the RelOptInfo. Even though we may not really scan this relation + * for reasons such as contradictory quals, we still need need to create + * one, because for every RTE in the query's range table, there must be an + * accompanying RelOptInfo. + */ + + /* First, store the RTE and appinfos into planner arrays. */ + Assert(root->simple_rte_array[childRTindex] == NULL); + root->simple_rte_array[childRTindex] = childrte; + Assert(root->append_rel_array[childRTindex] == NULL); + root->append_rel_array[childRTindex] = appinfo; + + childrelopt = build_append_child_rel(root, parent, childRTindex); + Assert(childrelopt != NULL); + + return childrelopt; +} + +/* + * build_append_child_rel + * Build a RelOptInfo for child relation of an append rel + * + * After creating the RelOptInfo for the given child RT index, it goes on to + * initialize some of its fields base on the parent RelOptInfo. + * + * If the quals in baserestrictinfo turns out to be self-contradictory, the + * RelOptInfo is marked dummy before returning. + */ +static RelOptInfo * +build_append_child_rel(PlannerInfo *root, + RelOptInfo *parent, + Index childRTindex) +{ + RelOptInfo *childrel; + RangeTblEntry *childRTE = root->simple_rte_array[childRTindex]; + AppendRelInfo *appinfo = root->append_rel_array[childRTindex]; + List *childquals; + ListCell *lc; + bool have_const_false_cq; + Index cq_min_security; + + /* Build the RelOptInfo. */ + childrel = build_simple_rel(root, childRTindex, parent); + + /* + * Propagate lateral_relids and lateral_referencers from appendrel + * parent rels to their child rels. We intentionally give each child rel + * the same minimum parameterization, even though it's quite possible that + * some don't reference all the lateral rels. This is because any append + * path for the parent will have to have the same parameterization for + * every child anyway, and there's no value in forcing extra + * reparameterize_path() calls. Similarly, a lateral reference to the + * parent prevents use of otherwise-movable join rels for each child. + */ + childrel->direct_lateral_relids = parent->direct_lateral_relids; + childrel->lateral_relids = parent->lateral_relids; + childrel->lateral_referencers = parent->lateral_referencers; + + /* + * We have to copy the parent's quals to the child, with appropriate + * substitution of variables. However, only the baserestrictinfo + * quals are needed before we can check for constraint exclusion; so + * do that first and then check to see if we can disregard this child. + * + * The child rel's targetlist might contain non-Var expressions, which + * means that substitution into the quals could produce opportunities + * for const-simplification, and perhaps even pseudoconstant quals. + * Therefore, transform each RestrictInfo separately to see if it + * reduces to a constant or pseudoconstant. (We must process them + * separately to keep track of the security level of each qual.) + */ + childquals = false; + cq_min_security = UINT_MAX; + have_const_false_cq = false; + foreach(lc, parent->baserestrictinfo) + { + RestrictInfo *rinfo = (RestrictInfo *) lfirst(lc); + Node *childqual = (Node *) rinfo->clause; + ListCell *lc2; + + Assert(IsA(rinfo, RestrictInfo)); + childqual = adjust_appendrel_attrs(root, childqual, + 1, &appinfo); + childqual = eval_const_expressions(root, childqual); + /* check for flat-out constant */ + if (childqual && IsA(childqual, Const)) + { + if (((Const *) childqual)->constisnull || + !DatumGetBool(((Const *) childqual)->constvalue)) + { + /* Restriction reduces to constant FALSE or NULL */ + have_const_false_cq = true; + break; + } + /* Restriction reduces to constant TRUE, so drop it */ + continue; + } + /* might have gotten an AND clause, if so flatten it */ + foreach(lc2, make_ands_implicit((Expr *) childqual)) + { + Node *onecq = (Node *) lfirst(lc2); + bool pseudoconstant; + + /* check for pseudoconstant (no Vars or volatile functions) */ + pseudoconstant = + !contain_vars_of_level(onecq, 0) && + !contain_volatile_functions(onecq); + if (pseudoconstant) + { + /* tell createplan.c to check for gating quals */ + root->hasPseudoConstantQuals = true; + } + /* reconstitute RestrictInfo with appropriate properties */ + childquals = lappend(childquals, + make_restrictinfo((Expr *) onecq, + rinfo->is_pushed_down, + rinfo->outerjoin_delayed, + pseudoconstant, + rinfo->security_level, + NULL, NULL, NULL)); + cq_min_security = Min(cq_min_security, rinfo->security_level); + } + } + + /* + * In addition to the quals inherited from the parent, we might + * have securityQuals associated with this particular child node. + * (Currently this can only happen in appendrels originating from + * UNION ALL; inheritance child tables don't have their own + * securityQuals.) Pull any such securityQuals up into the + * baserestrictinfo for the child. This is similar to + * process_security_barrier_quals() for the parent rel, except + * that we can't make any general deductions from such quals, + * since they don't hold for the whole appendrel. + */ + if (childRTE->securityQuals) + { + Index security_level = 0; + + foreach(lc, childRTE->securityQuals) + { + List *qualset = (List *) lfirst(lc); + ListCell *lc2; + + foreach(lc2, qualset) + { + Expr *qual = (Expr *) lfirst(lc2); + + /* + * not likely that we'd see constants here, so no + * check + */ + childquals = lappend(childquals, + make_restrictinfo(qual, + true, + false, + false, + security_level, + NULL, NULL, + NULL)); + cq_min_security = Min(cq_min_security, security_level); + } + security_level++; + } + Assert(security_level <= root->qual_security_level); + } + + /* Set child's version of baserestrictinfo. */ + childrel->baserestrictinfo = childquals; + childrel->baserestrict_min_security = cq_min_security; + + if (have_const_false_cq) + { + /* + * Some restriction clause reduced to constant FALSE or NULL after + * substitution, so this child need not be scanned. + */ + set_dummy_rel_pathlist(childrel); + } + + return childrel; +} + +/* + * add_rowmark_junk_columns + * Add necessary junk columns for rowmarked inheritance parent rel. + * + * These values are needed for locking of rels selected FOR UPDATE/SHARE, and + * to do EvalPlanQual rechecking. See comments for PlanRowMark in + * plannodes.h. + */ +static List * +add_rowmark_junk_columns(PlannerInfo *root, PlanRowMark *rc) +{ + List *tlist = root->processed_tlist; + Var *var; + char resname[32]; + TargetEntry *tle; + + if (rc->allMarkTypes & ~(1 << ROW_MARK_COPY)) + { + /* Need to fetch TID */ + var = makeVar(rc->rti, + SelfItemPointerAttributeNumber, + TIDOID, + -1, + InvalidOid, + 0); + snprintf(resname, sizeof(resname), "ctid%u", rc->rowmarkId); + tle = makeTargetEntry((Expr *) var, + list_length(tlist) + 1, + pstrdup(resname), + true); + tlist = lappend(tlist, tle); + } + if (rc->allMarkTypes & (1 << ROW_MARK_COPY)) + { + /* Need the whole row as a junk var */ + var = makeWholeRowVar(root->simple_rte_array[rc->rti], + rc->rti, + 0, + false); + snprintf(resname, sizeof(resname), "wholerow%u", rc->rowmarkId); + tle = makeTargetEntry((Expr *) var, + list_length(tlist) + 1, + pstrdup(resname), + true); + tlist = lappend(tlist, tle); + } + + /* For inheritance cases, always fetch the tableoid too. */ + var = makeVar(rc->rti, + TableOidAttributeNumber, + OIDOID, + -1, + InvalidOid, + 0); + snprintf(resname, sizeof(resname), "tableoid%u", rc->rowmarkId); + tle = makeTargetEntry((Expr *) var, + list_length(tlist) + 1, + pstrdup(resname), + true); + tlist = lappend(tlist, tle); + + return tlist; +} diff --git a/src/backend/optimizer/util/appendinfo.c b/src/backend/optimizer/util/appendinfo.c new file mode 100644 index 0000000000..24d1e15cf9 --- /dev/null +++ b/src/backend/optimizer/util/appendinfo.c @@ -0,0 +1,851 @@ +/*------------------------------------------------------------------------- + * + * appendinfo.c + * Routines for mapping between append parent(s) and children + * + * Portions Copyright (c) 1996-2018, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/optimizer/path/appendinfo.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "access/htup_details.h" +#include "access/sysattr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "optimizer/appendinfo.h" +#include "parser/parsetree.h" +#include "utils/rel.h" +#include "utils/lsyscache.h" +#include "utils/syscache.h" + +typedef struct +{ + PlannerInfo *root; + int nappinfos; + AppendRelInfo **appinfos; +} adjust_appendrel_attrs_context; + +static void make_inh_translation_list(TupleDesc old_tupdesc, + TupleDesc new_tupdesc, + Oid from_rel, Oid to_rel, + Index newvarno, List **translated_vars); +static Node *adjust_appendrel_attrs_mutator(Node *node, + adjust_appendrel_attrs_context *context); +static Relids adjust_child_relids(Relids relids, int nappinfos, + AppendRelInfo **appinfos); +static List *adjust_inherited_tlist(List *tlist, + AppendRelInfo *context); + +AppendRelInfo * +make_append_rel_info(RelOptInfo *parentrel, RangeTblEntry *parentrte, + TupleDesc childdesc, Oid childoid, Oid childreltype, + Index childRTindex) +{ + AppendRelInfo *appinfo = makeNode(AppendRelInfo); + + appinfo->parent_relid = parentrel->relid; + appinfo->child_relid = childRTindex; + appinfo->parent_reltype = parentrel->reltype; + appinfo->child_reltype = childreltype; + make_inh_translation_list(parentrel->tupdesc, childdesc, + parentrte->relid, childoid, + childRTindex, + &appinfo->translated_vars); + appinfo->parent_reloid = parentrte->relid; + + return appinfo; +} + +/* + * translate_col_privs + * Translate a bitmapset representing per-column privileges from the + * parent rel's attribute numbering to the child's. + * + * The only surprise here is that we don't translate a parent whole-row + * reference into a child whole-row reference. That would mean requiring + * permissions on all child columns, which is overly strict, since the + * query is really only going to reference the inherited columns. Instead + * we set the per-column bits for all inherited columns. + */ +Bitmapset * +translate_col_privs(const Bitmapset *parent_privs, + List *translated_vars) +{ + Bitmapset *child_privs = NULL; + bool whole_row; + int attno; + ListCell *lc; + + /* System attributes have the same numbers in all tables */ + for (attno = FirstLowInvalidHeapAttributeNumber + 1; attno < 0; attno++) + { + if (bms_is_member(attno - FirstLowInvalidHeapAttributeNumber, + parent_privs)) + child_privs = bms_add_member(child_privs, + attno - FirstLowInvalidHeapAttributeNumber); + } + + /* Check if parent has whole-row reference */ + whole_row = bms_is_member(InvalidAttrNumber - FirstLowInvalidHeapAttributeNumber, + parent_privs); + + /* And now translate the regular user attributes, using the vars list */ + attno = InvalidAttrNumber; + foreach(lc, translated_vars) + { + Var *var = lfirst_node(Var, lc); + + attno++; + if (var == NULL) /* ignore dropped columns */ + continue; + if (whole_row || + bms_is_member(attno - FirstLowInvalidHeapAttributeNumber, + parent_privs)) + child_privs = bms_add_member(child_privs, + var->varattno - FirstLowInvalidHeapAttributeNumber); + } + + return child_privs; +} + +/* + * adjust_appendrel_attrs + * Copy the specified query or expression and translate Vars referring to a + * parent rel to refer to the corresponding child rel instead. We also + * update rtindexes appearing outside Vars, such as resultRelation and + * jointree relids. + * + * Note: this is only applied after conversion of sublinks to subplans, + * so we don't need to cope with recursion into sub-queries. + * + * Note: this is not hugely different from what pullup_replace_vars() does; + * maybe we should try to fold the two routines together. + */ +Node * +adjust_appendrel_attrs(PlannerInfo *root, Node *node, int nappinfos, + AppendRelInfo **appinfos) +{ + Node *result; + adjust_appendrel_attrs_context context; + + context.root = root; + context.nappinfos = nappinfos; + context.appinfos = appinfos; + + /* If there's nothing to adjust, don't call this function. */ + Assert(nappinfos >= 1 && appinfos != NULL); + + /* + * Must be prepared to start with a Query or a bare expression tree. + */ + if (node && IsA(node, Query)) + { + Query *newnode; + int cnt; + + newnode = query_tree_mutator((Query *) node, + adjust_appendrel_attrs_mutator, + (void *) &context, + QTW_IGNORE_RC_SUBQUERIES); + for (cnt = 0; cnt < nappinfos; cnt++) + { + AppendRelInfo *appinfo = appinfos[cnt]; + + if (newnode->resultRelation == appinfo->parent_relid) + { + newnode->resultRelation = appinfo->child_relid; + /* Fix tlist resnos too, if it's inherited UPDATE */ + if (newnode->commandType == CMD_UPDATE) + newnode->targetList = + adjust_inherited_tlist(newnode->targetList, + appinfo); + break; + } + } + + result = (Node *) newnode; + } + else + result = adjust_appendrel_attrs_mutator(node, &context); + + return result; +} + +static Node * +adjust_appendrel_attrs_mutator(Node *node, + adjust_appendrel_attrs_context *context) +{ + AppendRelInfo **appinfos = context->appinfos; + int nappinfos = context->nappinfos; + int cnt; + + if (node == NULL) + return NULL; + if (IsA(node, Var)) + { + Var *var = (Var *) copyObject(node); + AppendRelInfo *appinfo = NULL; + + for (cnt = 0; cnt < nappinfos; cnt++) + { + if (var->varno == appinfos[cnt]->parent_relid) + { + appinfo = appinfos[cnt]; + break; + } + } + + if (var->varlevelsup == 0 && appinfo) + { + var->varno = appinfo->child_relid; + var->varnoold = appinfo->child_relid; + if (var->varattno > 0) + { + Node *newnode; + + if (var->varattno > list_length(appinfo->translated_vars)) + elog(ERROR, "attribute %d of relation \"%s\" does not exist", + var->varattno, get_rel_name(appinfo->parent_reloid)); + newnode = copyObject(list_nth(appinfo->translated_vars, + var->varattno - 1)); + if (newnode == NULL) + elog(ERROR, "attribute %d of relation \"%s\" does not exist", + var->varattno, get_rel_name(appinfo->parent_reloid)); + return newnode; + } + else if (var->varattno == 0) + { + /* + * Whole-row Var: if we are dealing with named rowtypes, we + * can use a whole-row Var for the child table plus a coercion + * step to convert the tuple layout to the parent's rowtype. + * Otherwise we have to generate a RowExpr. + */ + if (OidIsValid(appinfo->child_reltype)) + { + Assert(var->vartype == appinfo->parent_reltype); + if (appinfo->parent_reltype != appinfo->child_reltype) + { + ConvertRowtypeExpr *r = makeNode(ConvertRowtypeExpr); + + r->arg = (Expr *) var; + r->resulttype = appinfo->parent_reltype; + r->convertformat = COERCE_IMPLICIT_CAST; + r->location = -1; + /* Make sure the Var node has the right type ID, too */ + var->vartype = appinfo->child_reltype; + return (Node *) r; + } + } + else + { + /* + * Build a RowExpr containing the translated variables. + * + * In practice var->vartype will always be RECORDOID here, + * so we need to come up with some suitable column names. + * We use the parent RTE's column names. + * + * Note: we can't get here for inheritance cases, so there + * is no need to worry that translated_vars might contain + * some dummy NULLs. + */ + RowExpr *rowexpr; + List *fields; + RangeTblEntry *rte; + + rte = rt_fetch(appinfo->parent_relid, + context->root->parse->rtable); + fields = copyObject(appinfo->translated_vars); + rowexpr = makeNode(RowExpr); + rowexpr->args = fields; + rowexpr->row_typeid = var->vartype; + rowexpr->row_format = COERCE_IMPLICIT_CAST; + rowexpr->colnames = copyObject(rte->eref->colnames); + rowexpr->location = -1; + + return (Node *) rowexpr; + } + } + /* system attributes don't need any other translation */ + } + return (Node *) var; + } + if (IsA(node, CurrentOfExpr)) + { + CurrentOfExpr *cexpr = (CurrentOfExpr *) copyObject(node); + + for (cnt = 0; cnt < nappinfos; cnt++) + { + AppendRelInfo *appinfo = appinfos[cnt]; + + if (cexpr->cvarno == appinfo->parent_relid) + { + cexpr->cvarno = appinfo->child_relid; + break; + } + } + return (Node *) cexpr; + } + if (IsA(node, RangeTblRef)) + { + RangeTblRef *rtr = (RangeTblRef *) copyObject(node); + + for (cnt = 0; cnt < nappinfos; cnt++) + { + AppendRelInfo *appinfo = appinfos[cnt]; + + if (rtr->rtindex == appinfo->parent_relid) + { + rtr->rtindex = appinfo->child_relid; + break; + } + } + return (Node *) rtr; + } + if (IsA(node, JoinExpr)) + { + /* Copy the JoinExpr node with correct mutation of subnodes */ + JoinExpr *j; + AppendRelInfo *appinfo; + + j = (JoinExpr *) expression_tree_mutator(node, + adjust_appendrel_attrs_mutator, + (void *) context); + /* now fix JoinExpr's rtindex (probably never happens) */ + for (cnt = 0; cnt < nappinfos; cnt++) + { + appinfo = appinfos[cnt]; + + if (j->rtindex == appinfo->parent_relid) + { + j->rtindex = appinfo->child_relid; + break; + } + } + return (Node *) j; + } + if (IsA(node, PlaceHolderVar)) + { + /* Copy the PlaceHolderVar node with correct mutation of subnodes */ + PlaceHolderVar *phv; + + phv = (PlaceHolderVar *) expression_tree_mutator(node, + adjust_appendrel_attrs_mutator, + (void *) context); + /* now fix PlaceHolderVar's relid sets */ + if (phv->phlevelsup == 0) + phv->phrels = adjust_child_relids(phv->phrels, context->nappinfos, + context->appinfos); + return (Node *) phv; + } + + /* + * This is needed, because inheritance_make_rel_from_joinlist needs to + * translate root->join_info_list executing make_rel_from_joinlist for a + * given child. + */ + if (IsA(node, SpecialJoinInfo)) + { + SpecialJoinInfo *oldinfo = (SpecialJoinInfo *) node; + SpecialJoinInfo *newinfo = makeNode(SpecialJoinInfo); + + memcpy(newinfo, oldinfo, sizeof(SpecialJoinInfo)); + newinfo->min_lefthand = adjust_child_relids(oldinfo->min_lefthand, + context->nappinfos, + context->appinfos); + newinfo->min_righthand = adjust_child_relids(oldinfo->min_righthand, + context->nappinfos, + context->appinfos); + newinfo->syn_lefthand = adjust_child_relids(oldinfo->syn_lefthand, + context->nappinfos, + context->appinfos); + newinfo->syn_righthand = adjust_child_relids(oldinfo->syn_righthand, + context->nappinfos, + context->appinfos); + newinfo->semi_rhs_exprs = + (List *) expression_tree_mutator((Node *) + oldinfo->semi_rhs_exprs, + adjust_appendrel_attrs_mutator, + (void *) context); + return (Node *) newinfo; + } + + /* Shouldn't need to handle planner auxiliary nodes here */ + Assert(!IsA(node, AppendRelInfo)); + Assert(!IsA(node, PlaceHolderInfo)); + Assert(!IsA(node, MinMaxAggInfo)); + + /* + * We have to process RestrictInfo nodes specially. (Note: although + * set_append_rel_pathlist will hide RestrictInfos in the parent's + * baserestrictinfo list from us, it doesn't hide those in joininfo.) + */ + if (IsA(node, RestrictInfo)) + { + RestrictInfo *oldinfo = (RestrictInfo *) node; + RestrictInfo *newinfo = makeNode(RestrictInfo); + + /* Copy all flat-copiable fields */ + memcpy(newinfo, oldinfo, sizeof(RestrictInfo)); + + /* Recursively fix the clause itself */ + newinfo->clause = (Expr *) + adjust_appendrel_attrs_mutator((Node *) oldinfo->clause, context); + + /* and the modified version, if an OR clause */ + newinfo->orclause = (Expr *) + adjust_appendrel_attrs_mutator((Node *) oldinfo->orclause, context); + + /* adjust relid sets too */ + newinfo->clause_relids = adjust_child_relids(oldinfo->clause_relids, + context->nappinfos, + context->appinfos); + newinfo->required_relids = adjust_child_relids(oldinfo->required_relids, + context->nappinfos, + context->appinfos); + newinfo->outer_relids = adjust_child_relids(oldinfo->outer_relids, + context->nappinfos, + context->appinfos); + newinfo->nullable_relids = adjust_child_relids(oldinfo->nullable_relids, + context->nappinfos, + context->appinfos); + newinfo->left_relids = adjust_child_relids(oldinfo->left_relids, + context->nappinfos, + context->appinfos); + newinfo->right_relids = adjust_child_relids(oldinfo->right_relids, + context->nappinfos, + context->appinfos); + + /* + * Reset cached derivative fields, since these might need to have + * different values when considering the child relation. Note we + * don't reset left_ec/right_ec: each child variable is implicitly + * equivalent to its parent, so still a member of the same EC if any. + */ + newinfo->eval_cost.startup = -1; + newinfo->norm_selec = -1; + newinfo->outer_selec = -1; + newinfo->left_em = NULL; + newinfo->right_em = NULL; + newinfo->scansel_cache = NIL; + newinfo->left_bucketsize = -1; + newinfo->right_bucketsize = -1; + newinfo->left_mcvfreq = -1; + newinfo->right_mcvfreq = -1; + + return (Node *) newinfo; + } + + /* + * NOTE: we do not need to recurse into sublinks, because they should + * already have been converted to subplans before we see them. + */ + Assert(!IsA(node, SubLink)); + Assert(!IsA(node, Query)); + + return expression_tree_mutator(node, adjust_appendrel_attrs_mutator, + (void *) context); +} + +/* + * Substitute child relids for parent relids in a Relid set. The array of + * appinfos specifies the substitutions to be performed. + */ +static Relids +adjust_child_relids(Relids relids, int nappinfos, AppendRelInfo **appinfos) +{ + Bitmapset *result = NULL; + int cnt; + + for (cnt = 0; cnt < nappinfos; cnt++) + { + AppendRelInfo *appinfo = appinfos[cnt]; + + /* Remove parent, add child */ + if (bms_is_member(appinfo->parent_relid, relids)) + { + /* Make a copy if we are changing the set. */ + if (!result) + result = bms_copy(relids); + + result = bms_del_member(result, appinfo->parent_relid); + result = bms_add_member(result, appinfo->child_relid); + } + } + + /* If we made any changes, return the modified copy. */ + if (result) + return result; + + /* Otherwise, return the original set without modification. */ + return relids; +} + +/* + * Replace any relid present in top_parent_relids with its child in + * child_relids. Members of child_relids can be multiple levels below top + * parent in the partition hierarchy. + */ +Relids +adjust_child_relids_multilevel(PlannerInfo *root, Relids relids, + Relids child_relids, Relids top_parent_relids) +{ + AppendRelInfo **appinfos; + int nappinfos; + Relids parent_relids = NULL; + Relids result; + Relids tmp_result = NULL; + int cnt; + + /* + * If the given relids set doesn't contain any of the top parent relids, + * it will remain unchanged. + */ + if (!bms_overlap(relids, top_parent_relids)) + return relids; + + appinfos = find_appinfos_by_relids(root, child_relids, &nappinfos); + + /* Construct relids set for the immediate parent of the given child. */ + for (cnt = 0; cnt < nappinfos; cnt++) + { + AppendRelInfo *appinfo = appinfos[cnt]; + + parent_relids = bms_add_member(parent_relids, appinfo->parent_relid); + } + + /* Recurse if immediate parent is not the top parent. */ + if (!bms_equal(parent_relids, top_parent_relids)) + { + tmp_result = adjust_child_relids_multilevel(root, relids, + parent_relids, + top_parent_relids); + relids = tmp_result; + } + + result = adjust_child_relids(relids, nappinfos, appinfos); + + /* Free memory consumed by any intermediate result. */ + if (tmp_result) + bms_free(tmp_result); + bms_free(parent_relids); + pfree(appinfos); + + return result; +} + +/* + * adjust_appendrel_attrs_multilevel + * Apply Var translations from a toplevel appendrel parent down to a child. + * + * In some cases we need to translate expressions referencing a parent relation + * to reference an appendrel child that's multiple levels removed from it. + */ +Node * +adjust_appendrel_attrs_multilevel(PlannerInfo *root, Node *node, + Relids child_relids, + Relids top_parent_relids) +{ + AppendRelInfo **appinfos; + Bitmapset *parent_relids = NULL; + int nappinfos; + int cnt; + + Assert(bms_num_members(child_relids) == bms_num_members(top_parent_relids)); + + appinfos = find_appinfos_by_relids(root, child_relids, &nappinfos); + + /* Construct relids set for the immediate parent of given child. */ + for (cnt = 0; cnt < nappinfos; cnt++) + { + AppendRelInfo *appinfo = appinfos[cnt]; + + parent_relids = bms_add_member(parent_relids, appinfo->parent_relid); + } + + /* Recurse if immediate parent is not the top parent. */ + if (!bms_equal(parent_relids, top_parent_relids)) + node = adjust_appendrel_attrs_multilevel(root, node, parent_relids, + top_parent_relids); + + /* Now translate for this child */ + node = adjust_appendrel_attrs(root, node, nappinfos, appinfos); + + pfree(appinfos); + + return node; +} + +/* + * Construct the SpecialJoinInfo for a child-join by translating + * SpecialJoinInfo for the join between parents. left_relids and right_relids + * are the relids of left and right side of the join respectively. + */ +SpecialJoinInfo * +build_child_join_sjinfo(PlannerInfo *root, SpecialJoinInfo *parent_sjinfo, + Relids left_relids, Relids right_relids) +{ + SpecialJoinInfo *sjinfo = makeNode(SpecialJoinInfo); + AppendRelInfo **left_appinfos; + int left_nappinfos; + AppendRelInfo **right_appinfos; + int right_nappinfos; + + memcpy(sjinfo, parent_sjinfo, sizeof(SpecialJoinInfo)); + left_appinfos = find_appinfos_by_relids(root, left_relids, + &left_nappinfos); + right_appinfos = find_appinfos_by_relids(root, right_relids, + &right_nappinfos); + + sjinfo->min_lefthand = adjust_child_relids(sjinfo->min_lefthand, + left_nappinfos, left_appinfos); + sjinfo->min_righthand = adjust_child_relids(sjinfo->min_righthand, + right_nappinfos, + right_appinfos); + sjinfo->syn_lefthand = adjust_child_relids(sjinfo->syn_lefthand, + left_nappinfos, left_appinfos); + sjinfo->syn_righthand = adjust_child_relids(sjinfo->syn_righthand, + right_nappinfos, + right_appinfos); + sjinfo->semi_rhs_exprs = (List *) adjust_appendrel_attrs(root, + (Node *) sjinfo->semi_rhs_exprs, + right_nappinfos, + right_appinfos); + + pfree(left_appinfos); + pfree(right_appinfos); + + return sjinfo; +} + +/* + * find_appinfos_by_relids + * Find AppendRelInfo structures for all relations specified by relids. + * + * The AppendRelInfos are returned in an array, which can be pfree'd by the + * caller. *nappinfos is set to the number of entries in the array. + */ +AppendRelInfo ** +find_appinfos_by_relids(PlannerInfo *root, Relids relids, int *nappinfos) +{ + AppendRelInfo **appinfos; + int cnt = 0; + int i; + + *nappinfos = bms_num_members(relids); + appinfos = (AppendRelInfo **) palloc(sizeof(AppendRelInfo *) * *nappinfos); + + i = -1; + while ((i = bms_next_member(relids, i)) >= 0) + { + AppendRelInfo *appinfo = root->append_rel_array[i]; + + if (!appinfo) + elog(ERROR, "child rel %d not found in append_rel_array", i); + + appinfos[cnt++] = appinfo; + } + return appinfos; +} + +/* + * make_inh_translation_list + * Build the list of translations from parent Vars to child Vars for + * an inheritance child. + * + * For paranoia's sake, we match type/collation as well as attribute name. + */ +static void +make_inh_translation_list(TupleDesc old_tupdesc, TupleDesc new_tupdesc, + Oid from_rel, Oid to_rel, + Index newvarno, List **translated_vars) +{ + List *vars = NIL; + int oldnatts = old_tupdesc->natts; + int newnatts = new_tupdesc->natts; + int old_attno; + int new_attno = 0; + + for (old_attno = 0; old_attno < oldnatts; old_attno++) + { + Form_pg_attribute att; + char *attname; + Oid atttypid; + int32 atttypmod; + Oid attcollation; + + att = TupleDescAttr(old_tupdesc, old_attno); + if (att->attisdropped) + { + /* Just put NULL into this list entry */ + vars = lappend(vars, NULL); + continue; + } + attname = NameStr(att->attname); + atttypid = att->atttypid; + atttypmod = att->atttypmod; + attcollation = att->attcollation; + + /* + * When we are generating the "translation list" for the parent table + * of an inheritance set, no need to search for matches. + */ + if (from_rel == to_rel) + { + vars = lappend(vars, makeVar(newvarno, + (AttrNumber) (old_attno + 1), + atttypid, + atttypmod, + attcollation, + 0)); + continue; + } + + /* + * Otherwise we have to search for the matching column by name. + * There's no guarantee it'll have the same column position, because + * of cases like ALTER TABLE ADD COLUMN and multiple inheritance. + * However, in simple cases, the relative order of columns is mostly + * the same in both relations, so try the column of newrelation that + * follows immediately after the one that we just found, and if that + * fails, let syscache handle it. + */ + if (new_attno >= newnatts || + (att = TupleDescAttr(new_tupdesc, new_attno))->attisdropped || + strcmp(attname, NameStr(att->attname)) != 0) + { + HeapTuple newtup; + + newtup = SearchSysCacheAttName(to_rel, attname); + if (!newtup) + elog(ERROR, "could not find inherited attribute \"%s\" of relation \"%s\"", + attname, get_rel_name(to_rel)); + new_attno = ((Form_pg_attribute) GETSTRUCT(newtup))->attnum - 1; + ReleaseSysCache(newtup); + + att = TupleDescAttr(new_tupdesc, new_attno); + } + + /* Found it, check type and collation match */ + if (atttypid != att->atttypid || atttypmod != att->atttypmod) + elog(ERROR, "attribute \"%s\" of relation \"%s\" does not match parent's type", + attname, get_rel_name(to_rel)); + if (attcollation != att->attcollation) + elog(ERROR, "attribute \"%s\" of relation \"%s\" does not match parent's collation", + attname, get_rel_name(to_rel)); + + vars = lappend(vars, makeVar(newvarno, + (AttrNumber) (new_attno + 1), + atttypid, + atttypmod, + attcollation, + 0)); + new_attno++; + } + + *translated_vars = vars; +} + +/* + * Adjust the targetlist entries of an inherited UPDATE operation + * + * The expressions have already been fixed, but we have to make sure that + * the target resnos match the child table (they may not, in the case of + * a column that was added after-the-fact by ALTER TABLE). In some cases + * this can force us to re-order the tlist to preserve resno ordering. + * (We do all this work in special cases so that preptlist.c is fast for + * the typical case.) + * + * The given tlist has already been through expression_tree_mutator; + * therefore the TargetEntry nodes are fresh copies that it's okay to + * scribble on. + * + * Note that this is not needed for INSERT because INSERT isn't inheritable. + */ +static List * +adjust_inherited_tlist(List *tlist, AppendRelInfo *context) +{ + bool changed_it = false; + ListCell *tl; + List *new_tlist; + bool more; + int attrno; + + /* This should only happen for an inheritance case, not UNION ALL */ + Assert(OidIsValid(context->parent_reloid)); + + /* Scan tlist and update resnos to match attnums of child rel */ + foreach(tl, tlist) + { + TargetEntry *tle = (TargetEntry *) lfirst(tl); + Var *childvar; + + if (tle->resjunk) + continue; /* ignore junk items */ + + /* Look up the translation of this column: it must be a Var */ + if (tle->resno <= 0 || + tle->resno > list_length(context->translated_vars)) + elog(ERROR, "attribute %d of relation \"%s\" does not exist", + tle->resno, get_rel_name(context->parent_reloid)); + childvar = (Var *) list_nth(context->translated_vars, tle->resno - 1); + if (childvar == NULL || !IsA(childvar, Var)) + elog(ERROR, "attribute %d of relation \"%s\" does not exist", + tle->resno, get_rel_name(context->parent_reloid)); + + if (tle->resno != childvar->varattno) + { + tle->resno = childvar->varattno; + changed_it = true; + } + } + + /* + * If we changed anything, re-sort the tlist by resno, and make sure + * resjunk entries have resnos above the last real resno. The sort + * algorithm is a bit stupid, but for such a seldom-taken path, small is + * probably better than fast. + */ + if (!changed_it) + return tlist; + + new_tlist = NIL; + more = true; + for (attrno = 1; more; attrno++) + { + more = false; + foreach(tl, tlist) + { + TargetEntry *tle = (TargetEntry *) lfirst(tl); + + if (tle->resjunk) + continue; /* ignore junk items */ + + if (tle->resno == attrno) + new_tlist = lappend(new_tlist, tle); + else if (tle->resno > attrno) + more = true; + } + } + + foreach(tl, tlist) + { + TargetEntry *tle = (TargetEntry *) lfirst(tl); + + if (!tle->resjunk) + continue; /* here, ignore non-junk items */ + + tle->resno = attrno; + new_tlist = lappend(new_tlist, tle); + attrno++; + } + + return new_tlist; +} diff --git a/src/backend/optimizer/util/pathnode.c b/src/backend/optimizer/util/pathnode.c index d50d86b252..8ce88876c4 100644 --- a/src/backend/optimizer/util/pathnode.c +++ b/src/backend/optimizer/util/pathnode.c @@ -20,6 +20,7 @@ #include "foreign/fdwapi.h" #include "nodes/extensible.h" #include "nodes/nodeFuncs.h" +#include "optimizer/appendinfo.h" #include "optimizer/clauses.h" #include "optimizer/cost.h" #include "optimizer/pathnode.h" diff --git a/src/backend/optimizer/util/plancat.c b/src/backend/optimizer/util/plancat.c index e7b4965337..12d8feb409 100644 --- a/src/backend/optimizer/util/plancat.c +++ b/src/backend/optimizer/util/plancat.c @@ -106,7 +106,7 @@ static void set_baserel_partition_key_exprs(Relation relation, */ void get_relation_info(PlannerInfo *root, Oid relationObjectId, bool inhparent, - RelOptInfo *rel) + Bitmapset *updatedCols, RelOptInfo *rel) { Index varno = rel->relid; Relation relation; @@ -445,11 +445,32 @@ get_relation_info(PlannerInfo *root, Oid relationObjectId, bool inhparent, get_relation_foreign_keys(root, rel, relation, inhparent); /* - * Collect info about relation's partitioning scheme, if any. Only - * inheritance parents may be partitioned. + * Collect some additional information for inheritance parents. */ - if (inhparent && relation->rd_rel->relkind == RELKIND_PARTITIONED_TABLE) - set_relation_partition_info(root, rel, relation); + if (inhparent) + { + /* + * We'll need the TupleDesc when initializing the child relation. + * A copy is being made because concurrent changes might drop + * the relcache entry. That's possible because ALTER TABLE + * child_table NO INHERIT parent_table only requires an + * AccessShareLock on parent_table. + */ + rel->tupdesc = CreateTupleDescCopy(RelationGetDescr(relation)); + rel->reltype = RelationGetForm(relation)->reltype; + + /* + * If partitioned, also save the information of partitioning scheme, + * and whether the query updates any of the partition key columns. + */ + if (relation->rd_rel->relkind == RELKIND_PARTITIONED_TABLE) + { + set_relation_partition_info(root, rel, relation); + if (!root->partColsUpdated) + root->partColsUpdated = + has_partition_attrs(relation, updatedCols, NULL); + } + } heap_close(relation, NoLock); @@ -1855,16 +1876,20 @@ set_relation_partition_info(PlannerInfo *root, RelOptInfo *rel, Relation relation) { PartitionDesc partdesc; - PartitionKey partkey; Assert(relation->rd_rel->relkind == RELKIND_PARTITIONED_TABLE); partdesc = RelationGetPartitionDesc(relation); - partkey = RelationGetPartitionKey(relation); rel->part_scheme = find_partition_scheme(root, relation); Assert(partdesc != NULL && rel->part_scheme != NULL); - rel->boundinfo = partition_bounds_copy(partdesc->boundinfo, partkey); rel->nparts = partdesc->nparts; + + /* + * Since we must've taken a lock on the table, it's okay to simply copy + * the pointers to relcache data here. + */ + rel->part_oids = partdesc->oids; + rel->boundinfo = partdesc->boundinfo; set_baserel_partition_key_exprs(relation, rel); rel->partition_qual = RelationGetPartitionQual(relation); } diff --git a/src/backend/optimizer/util/relnode.c b/src/backend/optimizer/util/relnode.c index 29ba19349f..52a11f434f 100644 --- a/src/backend/optimizer/util/relnode.c +++ b/src/backend/optimizer/util/relnode.c @@ -17,6 +17,7 @@ #include #include "miscadmin.h" +#include "optimizer/appendinfo.h" #include "optimizer/clauses.h" #include "optimizer/cost.h" #include "optimizer/pathnode.h" @@ -130,6 +131,37 @@ setup_append_rel_array(PlannerInfo *root) } } +/* Expand the PlannerInfo arrays by add_size members and zero-init it. */ +void +expand_planner_arrays(PlannerInfo *root, int add_size) +{ + int new_size = root->simple_rel_array_size + add_size; + + root->simple_rte_array = (RangeTblEntry **) + repalloc(root->simple_rte_array, + sizeof(RangeTblEntry *) * new_size); + root->simple_rel_array = (RelOptInfo **) + repalloc(root->simple_rel_array, + sizeof(RelOptInfo *) * new_size); + if (root->append_rel_array) + root->append_rel_array = (AppendRelInfo **) + repalloc(root->append_rel_array, + sizeof(AppendRelInfo *) * new_size); + else + root->append_rel_array = (AppendRelInfo **) + palloc0(sizeof(AppendRelInfo *) * + new_size); + + /* Set the contents of just allocated memory to 0. */ + MemSet(root->simple_rte_array + root->simple_rel_array_size, + 0, sizeof(RangeTblEntry *) * add_size); + MemSet(root->simple_rel_array + root->simple_rel_array_size, + 0, sizeof(RelOptInfo *) * add_size); + MemSet(root->append_rel_array + root->simple_rel_array_size, + 0, sizeof(AppendRelInfo *) * add_size); + root->simple_rel_array_size = new_size; +} + /* * build_simple_rel * Construct a new RelOptInfo for a base relation or 'other' relation. @@ -238,7 +270,8 @@ build_simple_rel(PlannerInfo *root, int relid, RelOptInfo *parent) { case RTE_RELATION: /* Table --- retrieve statistics from the system catalogs */ - get_relation_info(root, rte->relid, rte->inh, rel); + get_relation_info(root, rte->relid, rte->inh, rte->updatedCols, + rel); break; case RTE_SUBQUERY: case RTE_FUNCTION: @@ -279,52 +312,6 @@ build_simple_rel(PlannerInfo *root, int relid, RelOptInfo *parent) root->qual_security_level = Max(root->qual_security_level, list_length(rte->securityQuals)); - /* - * If this rel is an appendrel parent, recurse to build "other rel" - * RelOptInfos for its children. They are "other rels" because they are - * not in the main join tree, but we will need RelOptInfos to plan access - * to them. - */ - if (rte->inh) - { - ListCell *l; - int nparts = rel->nparts; - int cnt_parts = 0; - - if (nparts > 0) - rel->part_rels = (RelOptInfo **) - palloc(sizeof(RelOptInfo *) * nparts); - - foreach(l, root->append_rel_list) - { - AppendRelInfo *appinfo = (AppendRelInfo *) lfirst(l); - RelOptInfo *childrel; - - /* append_rel_list contains all append rels; ignore others */ - if (appinfo->parent_relid != relid) - continue; - - childrel = build_simple_rel(root, appinfo->child_relid, - rel); - - /* Nothing more to do for an unpartitioned table. */ - if (!rel->part_scheme) - continue; - - /* - * The order of partition OIDs in append_rel_list is the same as - * the order in the PartitionDesc, so the order of part_rels will - * also match the PartitionDesc. See expand_partitioned_rtentry. - */ - Assert(cnt_parts < nparts); - rel->part_rels[cnt_parts] = childrel; - cnt_parts++; - } - - /* We should have seen all the child partitions. */ - Assert(cnt_parts == nparts); - } - return rel; } diff --git a/src/backend/partitioning/partprune.c b/src/backend/partitioning/partprune.c index d6ca03de4a..9120fcb0d3 100644 --- a/src/backend/partitioning/partprune.c +++ b/src/backend/partitioning/partprune.c @@ -44,7 +44,9 @@ #include "miscadmin.h" #include "nodes/makefuncs.h" #include "nodes/nodeFuncs.h" +#include "optimizer/appendinfo.h" #include "optimizer/clauses.h" +#include "optimizer/cost.h" #include "optimizer/pathnode.h" #include "optimizer/planner.h" #include "optimizer/predtest.h" @@ -436,17 +438,23 @@ make_partitionedrel_pruneinfo(PlannerInfo *root, RelOptInfo *parentrel, * is, not pruned already). */ subplan_map = (int *) palloc(nparts * sizeof(int)); + memset(subplan_map, -1, nparts * sizeof(int)); subpart_map = (int *) palloc(nparts * sizeof(int)); + memset(subpart_map, -1, nparts * sizeof(int)); present_parts = NULL; for (i = 0; i < nparts; i++) { RelOptInfo *partrel = subpart->part_rels[i]; - int subplanidx = relid_subplan_map[partrel->relid] - 1; - int subpartidx = relid_subpart_map[partrel->relid] - 1; + int subplanidx; + int subpartidx; - subplan_map[i] = subplanidx; - subpart_map[i] = subpartidx; + /* Skip processing pruned partitions. */ + if (partrel == NULL) + continue; + + subplan_map[i] = subplanidx = relid_subplan_map[partrel->relid] - 1; + subpart_map[i] = subpartidx = relid_subpart_map[partrel->relid] - 1; if (subplanidx >= 0) { present_parts = bms_add_member(present_parts, i); @@ -540,23 +548,20 @@ gen_partprune_steps(RelOptInfo *rel, List *clauses, bool *contradictory) /* * prune_append_rel_partitions - * Returns RT indexes of the minimum set of child partitions which must - * be scanned to satisfy rel's baserestrictinfo quals. + * Returns indexes into rel->part_rels of the minimum set of child + * partitions which must be scanned to satisfy rel's baserestrictinfo + * quals. * * Callers must ensure that 'rel' is a partitioned table. */ -Relids +Bitmapset * prune_append_rel_partitions(RelOptInfo *rel) { - Relids result; List *clauses = rel->baserestrictinfo; List *pruning_steps; bool contradictory; PartitionPruneContext context; - Bitmapset *partindexes; - int i; - Assert(clauses != NIL); Assert(rel->part_scheme != NULL); /* If there are no partitions, return the empty set */ @@ -564,6 +569,13 @@ prune_append_rel_partitions(RelOptInfo *rel) return NULL; /* + * If pruning is disabled or if there are no clauses to prune with, + * return all partitions. + */ + if (!enable_partition_pruning || clauses == NIL) + return bms_add_range(NULL, 0, rel->nparts - 1); + + /* * Process clauses. If the clauses are found to be contradictory, we can * return the empty set. */ @@ -590,15 +602,7 @@ prune_append_rel_partitions(RelOptInfo *rel) context.evalexecparams = false; /* Actual pruning happens here. */ - partindexes = get_matching_partitions(&context, pruning_steps); - - /* Add selected partitions' RT indexes to result. */ - i = -1; - result = NULL; - while ((i = bms_next_member(partindexes, i)) >= 0) - result = bms_add_member(result, rel->part_rels[i]->relid); - - return result; + return get_matching_partitions(&context, pruning_steps); } /* diff --git a/src/include/nodes/relation.h b/src/include/nodes/relation.h index 06212ce382..572efff742 100644 --- a/src/include/nodes/relation.h +++ b/src/include/nodes/relation.h @@ -15,6 +15,7 @@ #define RELATION_H #include "access/sdir.h" +#include "access/tupdesc.h" #include "fmgr.h" #include "lib/stringinfo.h" #include "nodes/params.h" @@ -711,6 +712,7 @@ typedef struct RelOptInfo int nparts; /* number of partitions */ struct PartitionBoundInfoData *boundinfo; /* Partition bounds */ List *partition_qual; /* partition constraint */ + Oid *part_oids; /* partition OIDs */ struct RelOptInfo **part_rels; /* Array of RelOptInfos of partitions, * stored in the same order of bounds */ List **partexprs; /* Non-nullable partition key expressions. */ @@ -720,6 +722,12 @@ typedef struct RelOptInfo Index inh_root_parent; /* For otherrels, this is the RT index of * inheritance table mentioned in the query * from which this relation originated */ + /* + * Set only if this is an inheritance parent relation. This information + * is needed when initializing the planning info for children. + */ + TupleDesc tupdesc; /* A "copy" of the table's tuple desriptor */ + Oid reltype; /* Table's reltype */ } RelOptInfo; /* diff --git a/src/include/optimizer/append.h b/src/include/optimizer/append.h new file mode 100644 index 0000000000..5b44530279 --- /dev/null +++ b/src/include/optimizer/append.h @@ -0,0 +1,28 @@ +/*------------------------------------------------------------------------- + * + * append.h + * prototypes for append.c. + * + * + * Portions Copyright (c) 1996-2018, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/optimizer/append.h + * + *------------------------------------------------------------------------- + */ +#ifndef APPEND_H +#define APPEND_H + +#include "nodes/relation.h" + +/* + * append.c + * utilities for dealing with append relations + */ +extern void expand_append_rel(PlannerInfo *root, + RelOptInfo *rel, + RangeTblEntry *rte, + Index rti); + +#endif /* APPEND_H */ diff --git a/src/include/optimizer/appendinfo.h b/src/include/optimizer/appendinfo.h new file mode 100644 index 0000000000..e205e78e6d --- /dev/null +++ b/src/include/optimizer/appendinfo.h @@ -0,0 +1,43 @@ +/*------------------------------------------------------------------------- + * + * appendinfo.h + * Routines for mapping expressions between append rel parent(s) and + * children + * + * Portions Copyright (c) 1996-2018, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/optimizer/appendinfo.h + * + *------------------------------------------------------------------------- + */ +#ifndef APPENDINFO_H +#define APPENDINFO_H + +#include "nodes/plannodes.h" +#include "nodes/relation.h" +#include "utils/relcache.h" + +extern AppendRelInfo *make_append_rel_info(RelOptInfo *parentrel, + RangeTblEntry *parentrte, + TupleDesc childdesc, Oid childoid, Oid childreltype, + Index childRTindex); +extern Bitmapset *translate_col_privs(const Bitmapset *parent_privs, + List *translated_vars); +extern Node *adjust_appendrel_attrs(PlannerInfo *root, Node *node, + int nappinfos, AppendRelInfo **appinfos); + +extern Node *adjust_appendrel_attrs_multilevel(PlannerInfo *root, Node *node, + Relids child_relids, + Relids top_parent_relids); + +extern AppendRelInfo **find_appinfos_by_relids(PlannerInfo *root, + Relids relids, int *nappinfos); + +extern SpecialJoinInfo *build_child_join_sjinfo(PlannerInfo *root, + SpecialJoinInfo *parent_sjinfo, + Relids left_relids, Relids right_relids); +extern Relids adjust_child_relids_multilevel(PlannerInfo *root, Relids relids, + Relids child_relids, Relids top_parent_relids); + +#endif /* APPENDINFO_H */ diff --git a/src/include/optimizer/pathnode.h b/src/include/optimizer/pathnode.h index 81abcf53a8..b1baa3117a 100644 --- a/src/include/optimizer/pathnode.h +++ b/src/include/optimizer/pathnode.h @@ -261,6 +261,7 @@ extern Path *reparameterize_path_by_child(PlannerInfo *root, Path *path, */ extern void setup_simple_rel_arrays(PlannerInfo *root); extern void setup_append_rel_array(PlannerInfo *root); +extern void expand_planner_arrays(PlannerInfo *root, int add_size); extern RelOptInfo *build_simple_rel(PlannerInfo *root, int relid, RelOptInfo *parent); extern RelOptInfo *find_base_rel(PlannerInfo *root, int relid); diff --git a/src/include/optimizer/plancat.h b/src/include/optimizer/plancat.h index 7d53cbbb87..edaf2a3b4f 100644 --- a/src/include/optimizer/plancat.h +++ b/src/include/optimizer/plancat.h @@ -26,7 +26,7 @@ extern PGDLLIMPORT get_relation_info_hook_type get_relation_info_hook; extern void get_relation_info(PlannerInfo *root, Oid relationObjectId, - bool inhparent, RelOptInfo *rel); + bool inhparent, Bitmapset *updatedCols, RelOptInfo *rel); extern List *infer_arbiter_indexes(PlannerInfo *root); diff --git a/src/include/optimizer/prep.h b/src/include/optimizer/prep.h index 38608770a2..0e2cdbc539 100644 --- a/src/include/optimizer/prep.h +++ b/src/include/optimizer/prep.h @@ -38,7 +38,7 @@ extern Expr *canonicalize_qual(Expr *qual, bool is_check); /* * prototypes for preptlist.c */ -extern List *preprocess_targetlist(PlannerInfo *root); +extern List *preprocess_targetlist(PlannerInfo *root, bool inheritance_update); extern PlanRowMark *get_plan_rowmark(List *rowmarks, Index rtindex); @@ -47,22 +47,4 @@ extern PlanRowMark *get_plan_rowmark(List *rowmarks, Index rtindex); */ extern RelOptInfo *plan_set_operations(PlannerInfo *root); -extern void expand_inherited_tables(PlannerInfo *root); - -extern Node *adjust_appendrel_attrs(PlannerInfo *root, Node *node, - int nappinfos, AppendRelInfo **appinfos); - -extern Node *adjust_appendrel_attrs_multilevel(PlannerInfo *root, Node *node, - Relids child_relids, - Relids top_parent_relids); - -extern AppendRelInfo **find_appinfos_by_relids(PlannerInfo *root, - Relids relids, int *nappinfos); - -extern SpecialJoinInfo *build_child_join_sjinfo(PlannerInfo *root, - SpecialJoinInfo *parent_sjinfo, - Relids left_relids, Relids right_relids); -extern Relids adjust_child_relids_multilevel(PlannerInfo *root, Relids relids, - Relids child_relids, Relids top_parent_relids); - #endif /* PREP_H */ diff --git a/src/include/partitioning/partprune.h b/src/include/partitioning/partprune.h index e07aaaf798..ac0a979010 100644 --- a/src/include/partitioning/partprune.h +++ b/src/include/partitioning/partprune.h @@ -76,7 +76,7 @@ extern PartitionPruneInfo *make_partition_pruneinfo(PlannerInfo *root, List *subpaths, List *partitioned_rels, List *prunequal); -extern Relids prune_append_rel_partitions(RelOptInfo *rel); +extern Bitmapset *prune_append_rel_partitions(RelOptInfo *rel); extern Bitmapset *get_matching_partitions(PartitionPruneContext *context, List *pruning_steps); diff --git a/src/test/regress/expected/join.out b/src/test/regress/expected/join.out index 1f5378080d..73f684f992 100644 --- a/src/test/regress/expected/join.out +++ b/src/test/regress/expected/join.out @@ -5547,29 +5547,29 @@ select t1.b, ss.phv from join_ut1 t1 left join lateral (select t2.a as t2a, t3.a t3a, least(t1.a, t2.a, t3.a) phv from join_pt1 t2 join join_ut1 t3 on t2.a = t3.b) ss on t1.a = ss.t2a order by t1.a; - QUERY PLAN ------------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- Sort - Output: t1.b, (LEAST(t1.a, t2.a, t3.a)), t1.a + Output: t1.b, (LEAST(t1.a, t2_1.a, t3.a)), t1.a Sort Key: t1.a -> Nested Loop Left Join - Output: t1.b, (LEAST(t1.a, t2.a, t3.a)), t1.a + Output: t1.b, (LEAST(t1.a, t2_1.a, t3.a)), t1.a -> Seq Scan on public.join_ut1 t1 Output: t1.a, t1.b, t1.c -> Hash Join - Output: t2.a, LEAST(t1.a, t2.a, t3.a) - Hash Cond: (t3.b = t2.a) + Output: t2_1.a, LEAST(t1.a, t2_1.a, t3.a) + Hash Cond: (t3.b = t2_1.a) -> Seq Scan on public.join_ut1 t3 Output: t3.a, t3.b, t3.c -> Hash - Output: t2.a + Output: t2_1.a -> Append - -> Seq Scan on public.join_pt1p1p1 t2 - Output: t2.a - Filter: (t1.a = t2.a) - -> Seq Scan on public.join_pt1p2 t2_1 + -> Seq Scan on public.join_pt1p1p1 t2_1 Output: t2_1.a Filter: (t1.a = t2_1.a) + -> Seq Scan on public.join_pt1p2 t2 + Output: t2.a + Filter: (t1.a = t2.a) (21 rows) select t1.b, ss.phv from join_ut1 t1 left join lateral diff --git a/src/test/regress/expected/partition_aggregate.out b/src/test/regress/expected/partition_aggregate.out index 6bc106831e..1450cef057 100644 --- a/src/test/regress/expected/partition_aggregate.out +++ b/src/test/regress/expected/partition_aggregate.out @@ -144,7 +144,7 @@ SELECT c, sum(a) FROM pagg_tab WHERE 1 = 2 GROUP BY c; QUERY PLAN -------------------------------- HashAggregate - Group Key: pagg_tab.c + Group Key: c -> Result One-Time Filter: false (4 rows) @@ -159,7 +159,7 @@ SELECT c, sum(a) FROM pagg_tab WHERE c = 'x' GROUP BY c; QUERY PLAN -------------------------------- GroupAggregate - Group Key: pagg_tab.c + Group Key: c -> Result One-Time Filter: false (4 rows) -- 2.11.0