* shorn of features like subselects, inheritance, aggregates, grouping,
* and so on. (Those are the things planner.c deals with.)
*
- * Portions Copyright (c) 1996-2000, PostgreSQL, Inc
+ * Portions Copyright (c) 1996-2002, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/optimizer/plan/planmain.c,v 1.53 2000/03/21 05:11:58 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/optimizer/plan/planmain.c,v 1.75 2003/03/10 03:53:50 tgl Exp $
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
-#include <sys/types.h>
-
#include "optimizer/clauses.h"
#include "optimizer/cost.h"
#include "optimizer/pathnode.h"
#include "optimizer/paths.h"
#include "optimizer/planmain.h"
-#include "optimizer/tlist.h"
-
-
-static Plan *subplanner(Query *root, List *flat_tlist, List *qual,
- double tuple_fraction);
/*--------------------
* query_planner
- * Generate a plan for a basic query, which may involve joins but
- * not any fancier features.
+ * Generate a path (that is, a simplified plan) for a basic query,
+ * which may involve joins but not any fancier features.
*
+ * Since query_planner does not handle the toplevel processing (grouping,
+ * sorting, etc) it cannot select the best path by itself. It selects
+ * two paths: the cheapest path that produces all the required tuples,
+ * independent of any ordering considerations, and the cheapest path that
+ * produces the expected fraction of the required tuples in the required
+ * ordering, if there is a path that is cheaper for this than just sorting
+ * the output of the cheapest overall path. The caller (grouping_planner)
+ * will make the final decision about which to use.
+ *
+ * Input parameters:
+ * root is the query to plan
* tlist is the target list the query should produce (NOT root->targetList!)
- * qual is the qualification of the query (likewise!)
* tuple_fraction is the fraction of tuples we expect will be retrieved
*
- * qual must already have been converted to implicit-AND form.
+ * Output parameters:
+ * *cheapest_path receives the overall-cheapest path for the query
+ * *sorted_path receives the cheapest presorted path for the query,
+ * if any (NULL if there is no useful presorted path)
*
- * Note: the Query node now also includes a query_pathkeys field, which
- * is both an input and an output of query_planner(). The input value
- * signals query_planner that the indicated sort order is wanted in the
- * final output plan. The output value is the actual pathkeys of the
- * selected path. This might not be the same as what the caller requested;
- * the caller must do pathkeys_contained_in() to decide whether an
- * explicit sort is still needed. (The main reason query_pathkeys is a
- * Query field and not a passed parameter is that the low-level routines
- * in indxpath.c need to see it.) The pathkeys value passed to query_planner
- * has not yet been "canonicalized", since the necessary info does not get
- * computed until subplanner() scans the qual clauses. We canonicalize it
- * inside subplanner() as soon as that task is done. The output value
- * will be in canonical form as well.
+ * Note: the Query node also includes a query_pathkeys field, which is both
+ * an input and an output of query_planner(). The input value signals
+ * query_planner that the indicated sort order is wanted in the final output
+ * plan. But this value has not yet been "canonicalized", since the needed
+ * info does not get computed until we scan the qual clauses. We canonicalize
+ * it as soon as that task is done. (The main reason query_pathkeys is a
+ * Query field and not a passed parameter is that the low-level routines in
+ * indxpath.c need to see it.)
*
* tuple_fraction is interpreted as follows:
- * 0 (or less): expect all tuples to be retrieved (normal case)
+ * 0: expect all tuples to be retrieved (normal case)
* 0 < tuple_fraction < 1: expect the given fraction of tuples available
* from the plan to be retrieved
* tuple_fraction >= 1: tuple_fraction is the absolute number of tuples
* expected to be retrieved (ie, a LIMIT specification)
- * Note that while this routine and its subroutines treat a negative
- * tuple_fraction the same as 0, union_planner has a different interpretation.
- *
- * Returns a query plan.
*--------------------
*/
-Plan *
-query_planner(Query *root,
- List *tlist,
- List *qual,
- double tuple_fraction)
+void
+query_planner(Query *root, List *tlist, double tuple_fraction,
+ Path **cheapest_path, Path **sorted_path)
{
- List *constant_qual = NIL;
- List *var_only_tlist;
- Plan *subplan;
+ List *constant_quals;
+ RelOptInfo *final_rel;
+ Path *cheapestpath;
+ Path *sortedpath;
/*
- * If the query contains no relation references at all, it must be
- * something like "SELECT 2+2;". Build a trivial "Result" plan.
+ * If the query has an empty join tree, then it's something easy like
+ * "SELECT 2+2;" or "INSERT ... VALUES()". Fall through quickly.
*/
- if (root->rtable == NIL)
+ if (root->jointree->fromlist == NIL)
{
- /* If it's not a select, it should have had a target relation... */
- if (root->commandType != CMD_SELECT)
- elog(ERROR, "Empty range table for non-SELECT query");
-
- root->query_pathkeys = NIL; /* signal unordered result */
-
- /* Make childless Result node to evaluate given tlist. */
- return (Plan *) make_result(tlist, (Node *) qual, (Plan *) NULL);
+ *cheapest_path = (Path *) create_result_path(NULL, NULL,
+ (List *) root->jointree->quals);
+ *sorted_path = NULL;
+ return;
}
/*
- * Pull out any non-variable qual clauses so these can be put in a
+ * Pull out any non-variable WHERE clauses so these can be put in a
* toplevel "Result" node, where they will gate execution of the whole
* plan (the Result will not invoke its descendant plan unless the
* quals are true). Note that any *really* non-variable quals will
* vars, although if the qual reduces to "WHERE FALSE" this path will
* also be taken.
*/
- qual = pull_constant_clauses(qual, &constant_qual);
+ root->jointree->quals = (Node *)
+ pull_constant_clauses((List *) root->jointree->quals,
+ &constant_quals);
/*
- * Create a target list that consists solely of (resdom var) target
- * list entries, i.e., contains no arbitrary expressions.
+ * init planner lists to empty
*
- * All subplan nodes will have "flat" (var-only) tlists.
- *
- * This implies that all expression evaluations are done at the root
- * of the plan tree. Once upon a time there was code to try to push
- * expensive function calls down to lower plan nodes, but that's dead
- * code and has been for a long time...
+ * NOTE: in_info_list was set up by subquery_planner, do not touch here
*/
- var_only_tlist = flatten_tlist(tlist);
+ root->base_rel_list = NIL;
+ root->other_rel_list = NIL;
+ root->join_rel_list = NIL;
+ root->equi_key_list = NIL;
/*
- * Choose the best access path and build a plan for it.
+ * Construct RelOptInfo nodes for all base relations in query.
*/
- subplan = subplanner(root, var_only_tlist, qual, tuple_fraction);
+ add_base_rels_to_query(root, (Node *) root->jointree);
/*
- * Build a result node to control the plan if we have constant quals.
+ * Examine the targetlist and qualifications, adding entries to
+ * baserel targetlists for all referenced Vars. Restrict and join
+ * clauses are added to appropriate lists belonging to the mentioned
+ * relations. We also build lists of equijoined keys for pathkey
+ * construction.
+ *
+ * Note: all subplan nodes will have "flat" (var-only) tlists.
+ * This implies that all expression evaluations are done at the root of
+ * the plan tree. Once upon a time there was code to try to push
+ * expensive function calls down to lower plan nodes, but that's dead
+ * code and has been for a long time...
*/
- if (constant_qual)
- {
- /*
- * The result node will also be responsible for evaluating
- * the originally requested tlist.
- */
- subplan = (Plan *) make_result(tlist,
- (Node *) constant_qual,
- subplan);
- }
- else
- {
- /*
- * Replace the toplevel plan node's flattened target list with the
- * targetlist given by my caller, so that expressions are evaluated.
- */
- subplan->targetlist = tlist;
- }
+ build_base_rel_tlists(root, tlist);
- return subplan;
-}
-
-/*
- * subplanner
- *
- * Subplanner creates an entire plan consisting of joins and scans
- * for processing a single level of attributes.
- *
- * flat_tlist is the flattened target list
- * qual is the qualification to be satisfied
- * tuple_fraction is the fraction of tuples we expect will be retrieved
- *
- * See query_planner() comments about the interpretation of tuple_fraction.
- *
- * Returns a subplan.
- */
-static Plan *
-subplanner(Query *root,
- List *flat_tlist,
- List *qual,
- double tuple_fraction)
-{
- RelOptInfo *final_rel;
- Path *cheapestpath;
- Path sort_path; /* dummy for result of cost_sort */
- Path *presortedpath;
+ (void) distribute_quals_to_rels(root, (Node *) root->jointree);
/*
- * Initialize the targetlist and qualification, adding entries to
- * base_rel_list as relation references are found (e.g., in the
- * qualification, the targetlist, etc.). Restrict and join clauses
- * are added to appropriate lists belonging to the mentioned relations,
- * and we also build lists of equijoined keys for pathkey construction.
+ * Use the completed lists of equijoined keys to deduce any implied
+ * but unstated equalities (for example, A=B and B=C imply A=C).
*/
- root->base_rel_list = NIL;
- root->join_rel_list = NIL;
- root->equi_key_list = NIL;
-
- make_var_only_tlist(root, flat_tlist);
- add_restrict_and_join_to_rels(root, qual);
- add_missing_rels_to_query(root);
+ generate_implied_equalities(root);
/*
- * We should now have all the pathkey equivalence sets built,
- * so it's now possible to convert the requested query_pathkeys
- * to canonical form.
+ * We should now have all the pathkey equivalence sets built, so it's
+ * now possible to convert the requested query_pathkeys to canonical
+ * form.
*/
root->query_pathkeys = canonicalize_pathkeys(root, root->query_pathkeys);
*/
final_rel = make_one_rel(root);
- if (! final_rel)
- {
- /*
- * We expect to end up here for a trivial INSERT ... VALUES query
- * (which will have a target relation, so it gets past query_planner's
- * check for empty range table; but the target rel is unreferenced
- * and not marked inJoinSet, so we find there is nothing to join).
- *
- * It's also possible to get here if the query was rewritten by the
- * rule processor (creating rangetable entries not marked inJoinSet)
- * but the rules either did nothing or were simplified to nothing
- * by constant-expression folding. So, don't complain.
- */
- root->query_pathkeys = NIL; /* signal unordered result */
-
- /* Make childless Result node to evaluate given tlist. */
- return (Plan *) make_result(flat_tlist, (Node *) qual, (Plan *) NULL);
- }
-
-#ifdef NOT_USED /* fix xfunc */
-
- /*
- * Perform Predicate Migration on each path, to optimize and correctly
- * assess the cost of each before choosing the cheapest one. -- JMH,
- * 11/16/92
- *
- * Needn't do so if the top rel is pruneable: that means there's no
- * expensive functions left to pull up. -- JMH, 11/22/92
- */
- if (XfuncMode != XFUNC_OFF && XfuncMode != XFUNC_NOPM &&
- XfuncMode != XFUNC_NOPULL && !final_rel->pruneable)
- {
- List *pathnode;
-
- foreach(pathnode, final_rel->pathlist)
- {
- if (xfunc_do_predmig((Path *) lfirst(pathnode)))
- set_cheapest(final_rel);
- }
- }
-#endif
+ if (!final_rel || !final_rel->cheapest_total_path)
+ elog(ERROR, "query_planner: failed to construct a relation");
/*
- * Now that we have an estimate of the final rel's size, we can convert
- * a tuple_fraction specified as an absolute count (ie, a LIMIT option)
- * into a fraction of the total tuples.
+ * Now that we have an estimate of the final rel's size, we can
+ * convert a tuple_fraction specified as an absolute count (ie, a
+ * LIMIT option) into a fraction of the total tuples.
*/
if (tuple_fraction >= 1.0)
tuple_fraction /= final_rel->rows;
/*
- * Determine the cheapest path, independently of any ordering
- * considerations. We do, however, take into account whether the
- * whole plan is expected to be evaluated or not.
- */
- if (tuple_fraction <= 0.0 || tuple_fraction >= 1.0)
- cheapestpath = final_rel->cheapest_total_path;
- else
- cheapestpath =
- get_cheapest_fractional_path_for_pathkeys(final_rel->pathlist,
- NIL,
- tuple_fraction);
-
- Assert(cheapestpath != NULL);
-
- /*
- * Select the best path and create a subplan to execute it.
+ * Pick out the cheapest-total path and the cheapest presorted path
+ * for the requested pathkeys (if there is one). We should take the
+ * tuple fraction into account when selecting the cheapest presorted
+ * path, but not when selecting the cheapest-total path, since if we
+ * have to sort then we'll have to fetch all the tuples. (But there's
+ * a special case: if query_pathkeys is NIL, meaning order doesn't
+ * matter, then the "cheapest presorted" path will be the cheapest
+ * overall for the tuple fraction.)
*
- * If no special sort order is wanted, or if the cheapest path is
- * already appropriately ordered, we use the cheapest path found above.
- */
- if (root->query_pathkeys == NIL ||
- pathkeys_contained_in(root->query_pathkeys,
- cheapestpath->pathkeys))
- {
- root->query_pathkeys = cheapestpath->pathkeys;
- return create_plan(root, cheapestpath);
- }
-
- /*
- * Otherwise, look to see if we have an already-ordered path that is
- * cheaper than doing an explicit sort on the cheapest-total-cost path.
+ * The cheapest-total path is also the one to use if grouping_planner
+ * decides to use hashed aggregation, so we return it separately even
+ * if this routine thinks the presorted path is the winner.
*/
cheapestpath = final_rel->cheapest_total_path;
- cost_sort(&sort_path, root->query_pathkeys,
- final_rel->rows, final_rel->width);
- sort_path.startup_cost += cheapestpath->total_cost;
- sort_path.total_cost += cheapestpath->total_cost;
- presortedpath =
+ sortedpath =
get_cheapest_fractional_path_for_pathkeys(final_rel->pathlist,
root->query_pathkeys,
tuple_fraction);
- if (presortedpath)
+
+ /* Don't return same path in both guises; just wastes effort */
+ if (sortedpath == cheapestpath)
+ sortedpath = NULL;
+
+ /*
+ * Forget about the presorted path if it would be cheaper to sort the
+ * cheapest-total path. Here we need consider only the behavior at
+ * the tuple fraction point.
+ */
+ if (sortedpath)
{
- if (compare_fractional_path_costs(presortedpath, &sort_path,
- tuple_fraction) <= 0)
+ Path sort_path; /* dummy for result of cost_sort */
+
+ if (root->query_pathkeys == NIL ||
+ pathkeys_contained_in(root->query_pathkeys,
+ cheapestpath->pathkeys))
+ {
+ /* No sort needed for cheapest path */
+ sort_path.startup_cost = cheapestpath->startup_cost;
+ sort_path.total_cost = cheapestpath->total_cost;
+ }
+ else
{
- /* Found a better presorted path, use it */
- root->query_pathkeys = presortedpath->pathkeys;
- return create_plan(root, presortedpath);
+ /* Figure cost for sorting */
+ cost_sort(&sort_path, root, root->query_pathkeys,
+ cheapestpath->total_cost,
+ final_rel->rows, final_rel->width);
+ }
+
+ if (compare_fractional_path_costs(sortedpath, &sort_path,
+ tuple_fraction) > 0)
+ {
+ /* Presorted path is a loser */
+ sortedpath = NULL;
}
- /* otherwise, doing it the hard way is still cheaper */
}
/*
- * Nothing for it but to sort the cheapest-total-cost path --- but we let
- * the caller do that. union_planner has to be able to add a sort node
- * anyway, so no need for extra code here. (Furthermore, the given
- * pathkeys might involve something we can't compute here, such as an
- * aggregate function...)
+ * If we have constant quals, add a toplevel Result step to process them.
*/
- root->query_pathkeys = cheapestpath->pathkeys;
- return create_plan(root, cheapestpath);
+ if (constant_quals)
+ {
+ cheapestpath = (Path *) create_result_path(final_rel,
+ cheapestpath,
+ constant_quals);
+ if (sortedpath)
+ sortedpath = (Path *) create_result_path(final_rel,
+ sortedpath,
+ constant_quals);
+ }
+
+ *cheapest_path = cheapestpath;
+ *sorted_path = sortedpath;
}