* allpaths.c
* Routines to find possible search paths for processing a query
*
- * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2011, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* IDENTIFICATION
- * $PostgreSQL: pgsql/src/backend/optimizer/path/allpaths.c,v 1.178 2008/12/28 18:53:56 tgl Exp $
+ * src/backend/optimizer/path/allpaths.c
*
*-------------------------------------------------------------------------
*/
#include <math.h>
+#include "catalog/pg_class.h"
#include "nodes/nodeFuncs.h"
#ifdef OPTIMIZER_DEBUG
#include "nodes/print.h"
#include "optimizer/plancat.h"
#include "optimizer/planner.h"
#include "optimizer/prep.h"
+#include "optimizer/restrictinfo.h"
#include "optimizer/var.h"
#include "parser/parse_clause.h"
#include "parser/parsetree.h"
#include "rewrite/rewriteManip.h"
+#include "utils/lsyscache.h"
/* These parameters are set by GUC */
RangeTblEntry *rte);
static void set_append_rel_pathlist(PlannerInfo *root, RelOptInfo *rel,
Index rti, RangeTblEntry *rte);
+static List *accumulate_append_subpath(List *subpaths, Path *path);
static void set_dummy_rel_pathlist(RelOptInfo *rel);
static void set_subquery_pathlist(PlannerInfo *root, RelOptInfo *rel,
Index rti, RangeTblEntry *rte);
static void set_values_pathlist(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte);
static void set_cte_pathlist(PlannerInfo *root, RelOptInfo *rel,
- RangeTblEntry *rte);
+ RangeTblEntry *rte);
static void set_worktable_pathlist(PlannerInfo *root, RelOptInfo *rel,
- RangeTblEntry *rte);
+ RangeTblEntry *rte);
+static void set_foreign_pathlist(PlannerInfo *root, RelOptInfo *rel,
+ RangeTblEntry *rte);
static RelOptInfo *make_rel_from_joinlist(PlannerInfo *root, List *joinlist);
static bool subquery_is_pushdown_safe(Query *subquery, Query *topquery,
bool *differentTypes);
}
else
{
- /* Plain relation */
Assert(rel->rtekind == RTE_RELATION);
- set_plain_rel_pathlist(root, rel, rte);
+ if (get_rel_relkind(rte->relid) == RELKIND_FOREIGN_TABLE)
+ {
+ /* Foreign table */
+ set_foreign_pathlist(root, rel, rte);
+ }
+ else
+ {
+ /* Plain relation */
+ set_plain_rel_pathlist(root, rel, rte);
+ }
}
#ifdef OPTIMIZER_DEBUG
return;
}
+ /*
+ * Test any partial indexes of rel for applicability. We must do this
+ * first since partial unique indexes can affect size estimates.
+ */
+ check_partial_indexes(root, rel);
+
/* Mark rel with estimated output rows, width, etc */
set_baserel_size_estimates(root, rel);
- /* Test any partial indexes of rel for applicability */
- check_partial_indexes(root, rel);
-
/*
* Check to see if we can extract any restriction conditions from join
* quals that are OR-of-AND structures. If so, add them to the rel's
- * restriction list, and recompute the size estimates.
+ * restriction list, and redo the above steps.
*/
if (create_or_index_quals(root, rel))
+ {
+ check_partial_indexes(root, rel);
set_baserel_size_estimates(root, rel);
+ }
/*
* Generate paths and add them to the rel's pathlist.
Index rti, RangeTblEntry *rte)
{
int parentRTindex = rti;
+ List *live_childrels = NIL;
List *subpaths = NIL;
+ List *all_child_pathkeys = NIL;
double parent_rows;
double parent_size;
double *parent_attrsizes;
/*
* Initialize to compute size estimates for whole append relation.
*
- * We handle width estimates by weighting the widths of different
- * child rels proportionally to their number of rows. This is sensible
- * because the use of width estimates is mainly to compute the total
- * relation "footprint" if we have to sort or hash it. To do this,
- * we sum the total equivalent size (in "double" arithmetic) and then
- * divide by the total rowcount estimate. This is done separately for
- * the total rel width and each attribute.
+ * We handle width estimates by weighting the widths of different child
+ * rels proportionally to their number of rows. This is sensible because
+ * the use of width estimates is mainly to compute the total relation
+ * "footprint" if we have to sort or hash it. To do this, we sum the
+ * total equivalent size (in "double" arithmetic) and then divide by the
+ * total rowcount estimate. This is done separately for the total rel
+ * width and each attribute.
*
* Note: if you consider changing this logic, beware that child rels could
* have zero rows and/or width, if they were excluded by constraints.
int childRTindex;
RangeTblEntry *childRTE;
RelOptInfo *childrel;
- Path *childpath;
+ List *childquals;
+ Node *childqual;
+ ListCell *lcp;
ListCell *parentvars;
ListCell *childvars;
* 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.
+ *
+ * As of 8.4, 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. To deal with this, we strip the RestrictInfo
+ * nodes, do the substitution, do const-simplification, and then
+ * reconstitute the RestrictInfo layer.
*/
- childrel->baserestrictinfo = (List *)
- adjust_appendrel_attrs((Node *) rel->baserestrictinfo,
- appinfo);
+ childquals = get_all_actual_clauses(rel->baserestrictinfo);
+ childquals = (List *) adjust_appendrel_attrs((Node *) childquals,
+ appinfo);
+ childqual = eval_const_expressions(root, (Node *)
+ make_ands_explicit(childquals));
+ if (childqual && IsA(childqual, Const) &&
+ (((Const *) childqual)->constisnull ||
+ !DatumGetBool(((Const *) childqual)->constvalue)))
+ {
+ /*
+ * Restriction reduces to constant FALSE or constant NULL after
+ * substitution, so this child need not be scanned.
+ */
+ set_dummy_rel_pathlist(childrel);
+ continue;
+ }
+ childquals = make_ands_implicit((Expr *) childqual);
+ childquals = make_restrictinfos_from_actual_clauses(root,
+ childquals);
+ childrel->baserestrictinfo = childquals;
if (relation_excluded_by_constraints(root, childrel, childRTE))
{
/*
* We have to make child entries in the EquivalenceClass data
- * structures as well.
+ * structures as well. This is needed either if the parent
+ * participates in some eclass joins (because we will want to
+ * consider inner-indexscan joins on the individual children)
+ * or if the parent has useful pathkeys (because we should try
+ * to build MergeAppend paths that produce those sort orderings).
*/
- if (rel->has_eclass_joins)
- {
+ if (rel->has_eclass_joins || has_useful_pathkeys(root, rel))
add_child_rel_equivalences(root, appinfo, rel, childrel);
- childrel->has_eclass_joins = true;
- }
+ childrel->has_eclass_joins = rel->has_eclass_joins;
/*
- * Note: we could compute appropriate attr_needed data for the
- * child's variables, by transforming the parent's attr_needed
- * through the translated_vars mapping. However, currently there's
- * no need because attr_needed is only examined for base relations
- * not otherrels. So we just leave the child's attr_needed empty.
+ * Note: we could compute appropriate attr_needed data for the child's
+ * variables, by transforming the parent's attr_needed through the
+ * translated_vars mapping. However, currently there's no need
+ * because attr_needed is only examined for base relations not
+ * otherrels. So we just leave the child's attr_needed empty.
*/
+ /* Remember which childrels are live, for MergeAppend logic below */
+ live_childrels = lappend(live_childrels, childrel);
+
/*
* Compute the child's access paths, and add the cheapest one to the
* Append path we are constructing for the parent.
- *
- * It's possible that the child is itself an appendrel, in which case
- * we can "cut out the middleman" and just add its child paths to our
- * own list. (We don't try to do this earlier because we need to
- * apply both levels of transformation to the quals.)
*/
set_rel_pathlist(root, childrel, childRTindex, childRTE);
- childpath = childrel->cheapest_total_path;
- if (IsA(childpath, AppendPath))
- subpaths = list_concat(subpaths,
- ((AppendPath *) childpath)->subpaths);
- else
- subpaths = lappend(subpaths, childpath);
+ subpaths = accumulate_append_subpath(subpaths,
+ childrel->cheapest_total_path);
+
+ /*
+ * Collect a list of all the available path orderings for all the
+ * children. We use this as a heuristic to indicate which sort
+ * orderings we should build MergeAppend paths for.
+ */
+ foreach(lcp, childrel->pathlist)
+ {
+ Path *childpath = (Path *) lfirst(lcp);
+ List *childkeys = childpath->pathkeys;
+ ListCell *lpk;
+ bool found = false;
+
+ /* Ignore unsorted paths */
+ if (childkeys == NIL)
+ continue;
+
+ /* Have we already seen this ordering? */
+ foreach(lpk, all_child_pathkeys)
+ {
+ List *existing_pathkeys = (List *) lfirst(lpk);
+
+ if (compare_pathkeys(existing_pathkeys,
+ childkeys) == PATHKEYS_EQUAL)
+ {
+ found = true;
+ break;
+ }
+ }
+ if (!found)
+ {
+ /* No, so add it to all_child_pathkeys */
+ all_child_pathkeys = lappend(all_child_pathkeys, childkeys);
+ }
+ }
/*
* Accumulate size information from each child.
rel->rows = parent_rows;
if (parent_rows > 0)
{
- int i;
+ int i;
rel->width = rint(parent_size / parent_rows);
for (i = 0; i < nattrs; i++)
pfree(parent_attrsizes);
/*
- * Finally, build Append path and install it as the only access path for
- * the parent rel. (Note: this is correct even if we have zero or one
- * live subpath due to constraint exclusion.)
+ * Next, build an unordered Append path for the rel. (Note: this is
+ * correct even if we have zero or one live subpath due to constraint
+ * exclusion.)
*/
add_path(rel, (Path *) create_append_path(rel, subpaths));
- /* Select cheapest path (pretty easy in this case...) */
+ /*
+ * Next, build MergeAppend paths based on the collected list of child
+ * pathkeys. We consider both cheapest-startup and cheapest-total
+ * cases, ie, for each interesting ordering, collect all the cheapest
+ * startup subpaths and all the cheapest total paths, and build a
+ * MergeAppend path for each list.
+ */
+ foreach(l, all_child_pathkeys)
+ {
+ List *pathkeys = (List *) lfirst(l);
+ List *startup_subpaths = NIL;
+ List *total_subpaths = NIL;
+ bool startup_neq_total = false;
+ ListCell *lcr;
+
+ /* Select the child paths for this ordering... */
+ foreach(lcr, live_childrels)
+ {
+ RelOptInfo *childrel = (RelOptInfo *) lfirst(lcr);
+ Path *cheapest_startup,
+ *cheapest_total;
+
+ /* Locate the right paths, if they are available. */
+ cheapest_startup =
+ get_cheapest_path_for_pathkeys(childrel->pathlist,
+ pathkeys,
+ STARTUP_COST);
+ cheapest_total =
+ get_cheapest_path_for_pathkeys(childrel->pathlist,
+ pathkeys,
+ TOTAL_COST);
+
+ /*
+ * If we can't find any paths with the right order just add the
+ * cheapest-total path; we'll have to sort it.
+ */
+ if (cheapest_startup == NULL)
+ cheapest_startup = childrel->cheapest_total_path;
+ if (cheapest_total == NULL)
+ cheapest_total = childrel->cheapest_total_path;
+
+ /*
+ * Notice whether we actually have different paths for the
+ * "cheapest" and "total" cases; frequently there will be no
+ * point in two create_merge_append_path() calls.
+ */
+ if (cheapest_startup != cheapest_total)
+ startup_neq_total = true;
+
+ startup_subpaths =
+ accumulate_append_subpath(startup_subpaths, cheapest_startup);
+ total_subpaths =
+ accumulate_append_subpath(total_subpaths, cheapest_total);
+ }
+
+ /* ... and build the MergeAppend paths */
+ add_path(rel, (Path *) create_merge_append_path(root,
+ rel,
+ startup_subpaths,
+ pathkeys));
+ if (startup_neq_total)
+ add_path(rel, (Path *) create_merge_append_path(root,
+ rel,
+ total_subpaths,
+ pathkeys));
+ }
+
+ /* Select cheapest path */
set_cheapest(rel);
}
+/*
+ * accumulate_append_subpath
+ * Add a subpath to the list being built for an Append or MergeAppend
+ *
+ * It's possible that the child is itself an Append path, in which case
+ * we can "cut out the middleman" and just add its child paths to our
+ * own list. (We don't try to do this earlier because we need to
+ * apply both levels of transformation to the quals.)
+ */
+static List *
+accumulate_append_subpath(List *subpaths, Path *path)
+{
+ if (IsA(path, AppendPath))
+ {
+ AppendPath *apath = (AppendPath *) path;
+
+ /* list_copy is important here to avoid sharing list substructure */
+ return list_concat(subpaths, list_copy(apath->subpaths));
+ }
+ else
+ return lappend(subpaths, path);
+}
+
/*
* set_dummy_rel_pathlist
* Build a dummy path for a relation that's been excluded by constraints
PlannerInfo *subroot;
List *pathkeys;
+ /*
+ * Must copy the Query so that planning doesn't mess up the RTE contents
+ * (really really need to fix the planner to not scribble on its input,
+ * someday).
+ */
+ subquery = copyObject(subquery);
+
/* We need a workspace for keeping track of set-op type coercions */
differentTypes = (bool *)
palloc0((list_length(subquery->targetList) + 1) * sizeof(bool));
false, tuple_fraction,
&subroot);
rel->subrtable = subroot->parse->rtable;
-
- /* Copy number of output rows from subplan */
- rel->tuples = rel->subplan->plan_rows;
+ rel->subrowmark = subroot->rowMarks;
/* Mark rel with estimated output rows, width, etc */
- set_baserel_size_estimates(root, rel);
+ set_subquery_size_estimates(root, rel, subroot);
/* Convert subquery pathkeys to outer representation */
pathkeys = convert_subquery_pathkeys(root, rel, subroot->query_pathkeys);
if (!cteroot) /* shouldn't happen */
elog(ERROR, "bad levelsup for CTE \"%s\"", rte->ctename);
}
+
/*
* Note: cte_plan_ids can be shorter than cteList, if we are still working
* on planning the CTEs (ie, this is a side-reference from another CTE).
/*
* We need to find the non-recursive term's plan, which is in the plan
- * level that's processing the recursive UNION, which is one level
- * *below* where the CTE comes from.
+ * level that's processing the recursive UNION, which is one level *below*
+ * where the CTE comes from.
*/
levelsup = rte->ctelevelsup;
if (levelsup == 0) /* shouldn't happen */
set_cheapest(rel);
}
+/*
+ * set_foreign_pathlist
+ * Build the (single) access path for a foreign table RTE
+ */
+static void
+set_foreign_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
+{
+ /* Mark rel with estimated output rows, width, etc */
+ set_foreign_size_estimates(root, rel);
+
+ /* Generate appropriate path */
+ add_path(rel, (Path *) create_foreignscan_path(root, rel));
+
+ /* Select cheapest path (pretty easy in this case...) */
+ set_cheapest(rel);
+}
+
/*
* make_rel_from_joinlist
* Build access paths using a "joinlist" to guide the join path search.
RelOptInfo *
standard_join_search(PlannerInfo *root, int levels_needed, List *initial_rels)
{
- List **joinitems;
int lev;
RelOptInfo *rel;
+ /*
+ * This function cannot be invoked recursively within any one planning
+ * problem, so join_rel_level[] can't be in use already.
+ */
+ Assert(root->join_rel_level == NULL);
+
/*
* We employ a simple "dynamic programming" algorithm: we first find all
* ways to build joins of two jointree items, then all ways to build joins
* joins, and so on until we have considered all ways to join all the
* items into one rel.
*
- * joinitems[j] is a list of all the j-item rels. Initially we set
- * joinitems[1] to represent all the single-jointree-item relations.
+ * root->join_rel_level[j] is a list of all the j-item rels. Initially we
+ * set root->join_rel_level[1] to represent all the single-jointree-item
+ * relations.
*/
- joinitems = (List **) palloc0((levels_needed + 1) * sizeof(List *));
+ root->join_rel_level = (List **) palloc0((levels_needed + 1) * sizeof(List *));
- joinitems[1] = initial_rels;
+ root->join_rel_level[1] = initial_rels;
for (lev = 2; lev <= levels_needed; lev++)
{
- ListCell *x;
+ ListCell *lc;
/*
* Determine all possible pairs of relations to be joined at this
* level, and build paths for making each one from every available
* pair of lower-level relations.
*/
- joinitems[lev] = join_search_one_level(root, lev, joinitems);
+ join_search_one_level(root, lev);
/*
* Do cleanup work on each just-processed rel.
*/
- foreach(x, joinitems[lev])
+ foreach(lc, root->join_rel_level[lev])
{
- rel = (RelOptInfo *) lfirst(x);
+ rel = (RelOptInfo *) lfirst(lc);
/* Find and save the cheapest paths for this rel */
set_cheapest(rel);
/*
* We should have a single rel at the final level.
*/
- if (joinitems[levels_needed] == NIL)
+ if (root->join_rel_level[levels_needed] == NIL)
elog(ERROR, "failed to build any %d-way joins", levels_needed);
- Assert(list_length(joinitems[levels_needed]) == 1);
+ Assert(list_length(root->join_rel_level[levels_needed]) == 1);
- rel = (RelOptInfo *) linitial(joinitems[levels_needed]);
+ rel = (RelOptInfo *) linitial(root->join_rel_level[levels_needed]);
+
+ root->join_rel_level = NULL;
return rel;
}
* since that could change the set of rows returned.
*
* 2. If the subquery contains any window functions, we can't push quals
- * into it, because that would change the results.
+ * into it, because that could change the results.
*
* 3. If the subquery contains EXCEPT or EXCEPT ALL set ops we cannot push
- * quals into it, because that would change the results.
+ * quals into it, because that could change the results.
*
* 4. For subqueries using UNION/UNION ALL/INTERSECT/INTERSECT ALL, we can
* push quals into each component query, but the quals can only reference
* of rows returned. (This condition is vacuous for DISTINCT, because then
* there are no non-DISTINCT output columns, so we needn't check. But note
* we are assuming that the qual can't distinguish values that the DISTINCT
- * operator sees as equal. This is a bit shaky but we have no way to test
+ * operator sees as equal. This is a bit shaky but we have no way to test
* for the case, and it's unlikely enough that we shouldn't refuse the
* optimization just because it could theoretically happen.)
*
return false;
/*
- * It would be unsafe to push down window function calls, but at least
- * for the moment we could never see any in a qual anyhow.
+ * It would be unsafe to push down window function calls, but at least for
+ * the moment we could never see any in a qual anyhow.
*/
Assert(!contain_window_function(qual));
* Examine all Vars used in clause; since it's a restriction clause, all
* such Vars must refer to subselect output columns.
*/
- vars = pull_var_clause(qual, true);
+ vars = pull_var_clause(qual, PVC_INCLUDE_PLACEHOLDERS);
foreach(vl, vars)
{
Var *var = (Var *) lfirst(vl);
*/
qual = ResolveNew(qual, rti, 0, rte,
subquery->targetList,
- CMD_SELECT, 0);
+ CMD_SELECT, 0,
+ &subquery->hasSubLinks);
/*
* Now attach the qual to the proper place: normally WHERE, but if the
case T_TidPath:
ptype = "TidScan";
break;
+ case T_ForeignPath:
+ ptype = "ForeignScan";
+ break;
case T_AppendPath:
ptype = "Append";
break;
+ case T_MergeAppendPath:
+ ptype = "MergeAppend";
+ break;
case T_ResultPath:
ptype = "Result";
break;
{
MergePath *mp = (MergePath *) path;
- if (mp->outersortkeys || mp->innersortkeys)
- {
- for (i = 0; i < indent; i++)
- printf("\t");
- printf(" sortouter=%d sortinner=%d\n",
- ((mp->outersortkeys) ? 1 : 0),
- ((mp->innersortkeys) ? 1 : 0));
- }
+ for (i = 0; i < indent; i++)
+ printf("\t");
+ printf(" sortouter=%d sortinner=%d materializeinner=%d\n",
+ ((mp->outersortkeys) ? 1 : 0),
+ ((mp->innersortkeys) ? 1 : 0),
+ ((mp->materialize_inner) ? 1 : 0));
}
print_path(root, jp->outerjoinpath, indent + 1);
projects / postgresql / blobdiff