hcq/postgresql
1
0
Fork 0
mirror of https://git.postgresql.org/git/postgresql.git synced 2026-02-22 06:17:00 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
1349d2790bf48a4de072931c722f39337e72055e
postgresql/src/include/optimizer/paths.h
David Rowley 1349d2790b Improve performance of ORDER BY / DISTINCT aggregates 
ORDER BY / DISTINCT aggreagtes have, since implemented in Postgres, been
executed by always performing a sort in nodeAgg.c to sort the tuples in
the current group into the correct order before calling the transition
function on the sorted tuples.  This was not great as often there might be
an index that could have provided pre-sorted input and allowed the
transition functions to be called as the rows come in, rather than having
to store them in a tuplestore in order to sort them once all the tuples
for the group have arrived.

Here we change the planner so it requests a path with a sort order which
supports the most amount of ORDER BY / DISTINCT aggregate functions and
add new code to the executor to allow it to support the processing of
ORDER BY / DISTINCT aggregates where the tuples are already sorted in the
correct order.

Since there can be many ORDER BY / DISTINCT aggregates in any given query
level, it's very possible that we can't find an order that suits all of
these aggregates.  The sort order that the planner chooses is simply the
one that suits the most aggregate functions.  We take the most strictly
sorted variation of each order and see how many aggregate functions can
use that, then we try again with the order of the remaining aggregates to
see if another order would suit more aggregate functions.  For example:

SELECT agg(a ORDER BY a),agg2(a ORDER BY a,b) ...

would request the sort order to be {a, b} because {a} is a subset of the
sort order of {a,b}, but;

SELECT agg(a ORDER BY a),agg2(a ORDER BY c) ...

would just pick a plan ordered by {a} (we give precedence to aggregates
which are earlier in the targetlist).

SELECT agg(a ORDER BY a),agg2(a ORDER BY b),agg3(a ORDER BY b) ...

would choose to order by {b} since two aggregates suit that vs just one
that requires input ordered by {a}.

Author: David Rowley
Reviewed-by: Ronan Dunklau, James Coleman, Ranier Vilela, Richard Guo, Tom Lane
Discussion: https://postgr.es/m/CAApHDvpHzfo92%3DR4W0%2BxVua3BUYCKMckWAmo-2t_KiXN-wYH%3Dw%40mail.gmail.com
2022-08-02 23:11:45 +12:00

267 lines
10 KiB
C
Raw Blame History

/*-------------------------------------------------------------------------
*
* paths.h
* prototypes for various files in optimizer/path
*
*
* Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* src/include/optimizer/paths.h
*
*-------------------------------------------------------------------------
*/
#ifndef PATHS_H
#define PATHS_H
#include "nodes/pathnodes.h"
/*
* allpaths.c
*/
extern PGDLLIMPORT bool enable_geqo;
extern PGDLLIMPORT int geqo_threshold;
extern PGDLLIMPORT int min_parallel_table_scan_size;
extern PGDLLIMPORT int min_parallel_index_scan_size;
extern PGDLLIMPORT bool enable_group_by_reordering;
/* Hook for plugins to get control in set_rel_pathlist() */
typedef void (*set_rel_pathlist_hook_type) (PlannerInfo *root,
RelOptInfo *rel,
Index rti,
RangeTblEntry *rte);
extern PGDLLIMPORT set_rel_pathlist_hook_type set_rel_pathlist_hook;
/* Hook for plugins to get control in add_paths_to_joinrel() */
typedef void (*set_join_pathlist_hook_type) (PlannerInfo *root,
RelOptInfo *joinrel,
RelOptInfo *outerrel,
RelOptInfo *innerrel,
JoinType jointype,
JoinPathExtraData *extra);
extern PGDLLIMPORT set_join_pathlist_hook_type set_join_pathlist_hook;
/* Hook for plugins to replace standard_join_search() */
typedef RelOptInfo *(*join_search_hook_type) (PlannerInfo *root,
int levels_needed,
List *initial_rels);
extern PGDLLIMPORT join_search_hook_type join_search_hook;
extern RelOptInfo *make_one_rel(PlannerInfo *root, List *joinlist);
extern RelOptInfo *standard_join_search(PlannerInfo *root, int levels_needed,
List *initial_rels);
extern void generate_gather_paths(PlannerInfo *root, RelOptInfo *rel,
bool override_rows);
extern void generate_useful_gather_paths(PlannerInfo *root, RelOptInfo *rel,
bool override_rows);
extern int compute_parallel_worker(RelOptInfo *rel, double heap_pages,
double index_pages, int max_workers);
extern void create_partial_bitmap_paths(PlannerInfo *root, RelOptInfo *rel,
Path *bitmapqual);
extern void generate_partitionwise_join_paths(PlannerInfo *root,
RelOptInfo *rel);
#ifdef OPTIMIZER_DEBUG
extern void debug_print_rel(PlannerInfo *root, RelOptInfo *rel);
#endif
/*
* indxpath.c
* routines to generate index paths
*/
extern void create_index_paths(PlannerInfo *root, RelOptInfo *rel);
extern bool relation_has_unique_index_for(PlannerInfo *root, RelOptInfo *rel,
List *restrictlist,
List *exprlist, List *oprlist);
extern bool indexcol_is_bool_constant_for_query(PlannerInfo *root,
IndexOptInfo *index,
int indexcol);
extern bool match_index_to_operand(Node *operand, int indexcol,
IndexOptInfo *index);
extern void check_index_predicates(PlannerInfo *root, RelOptInfo *rel);
/*
* tidpath.h
* routines to generate tid paths
*/
extern void create_tidscan_paths(PlannerInfo *root, RelOptInfo *rel);
/*
* joinpath.c
* routines to create join paths
*/
extern void add_paths_to_joinrel(PlannerInfo *root, RelOptInfo *joinrel,
RelOptInfo *outerrel, RelOptInfo *innerrel,
JoinType jointype, SpecialJoinInfo *sjinfo,
List *restrictlist);
/*
* joinrels.c
* routines to determine which relations to join
*/
extern void join_search_one_level(PlannerInfo *root, int level);
extern RelOptInfo *make_join_rel(PlannerInfo *root,
RelOptInfo *rel1, RelOptInfo *rel2);
extern bool have_join_order_restriction(PlannerInfo *root,
RelOptInfo *rel1, RelOptInfo *rel2);
extern bool have_dangerous_phv(PlannerInfo *root,
Relids outer_relids, Relids inner_params);
extern void mark_dummy_rel(RelOptInfo *rel);
/*
* equivclass.c
* routines for managing EquivalenceClasses
*/
typedef bool (*ec_matches_callback_type) (PlannerInfo *root,
RelOptInfo *rel,
EquivalenceClass *ec,
EquivalenceMember *em,
void *arg);
extern bool process_equivalence(PlannerInfo *root,
RestrictInfo **p_restrictinfo,
bool below_outer_join);
extern Expr *canonicalize_ec_expression(Expr *expr,
Oid req_type, Oid req_collation);
extern void reconsider_outer_join_clauses(PlannerInfo *root);
extern EquivalenceClass *get_eclass_for_sort_expr(PlannerInfo *root,
Expr *expr,
Relids nullable_relids,
List *opfamilies,
Oid opcintype,
Oid collation,
Index sortref,
Relids rel,
bool create_it);
extern EquivalenceMember *find_ec_member_matching_expr(EquivalenceClass *ec,
Expr *expr,
Relids relids);
extern EquivalenceMember *find_computable_ec_member(PlannerInfo *root,
EquivalenceClass *ec,
List *exprs,
Relids relids,
bool require_parallel_safe);
extern bool relation_can_be_sorted_early(PlannerInfo *root, RelOptInfo *rel,
EquivalenceClass *ec,
bool require_parallel_safe);
extern void generate_base_implied_equalities(PlannerInfo *root);
extern List *generate_join_implied_equalities(PlannerInfo *root,
Relids join_relids,
Relids outer_relids,
RelOptInfo *inner_rel);
extern List *generate_join_implied_equalities_for_ecs(PlannerInfo *root,
List *eclasses,
Relids join_relids,
Relids outer_relids,
RelOptInfo *inner_rel);
extern bool exprs_known_equal(PlannerInfo *root, Node *item1, Node *item2);
extern EquivalenceClass *match_eclasses_to_foreign_key_col(PlannerInfo *root,
ForeignKeyOptInfo *fkinfo,
int colno);
extern RestrictInfo *find_derived_clause_for_ec_member(EquivalenceClass *ec,
EquivalenceMember *em);
extern void add_child_rel_equivalences(PlannerInfo *root,
AppendRelInfo *appinfo,
RelOptInfo *parent_rel,
RelOptInfo *child_rel);
extern void add_child_join_rel_equivalences(PlannerInfo *root,
int nappinfos,
AppendRelInfo **appinfos,
RelOptInfo *parent_rel,
RelOptInfo *child_rel);
extern List *generate_implied_equalities_for_column(PlannerInfo *root,
RelOptInfo *rel,
ec_matches_callback_type callback,
void *callback_arg,
Relids prohibited_rels);
extern bool have_relevant_eclass_joinclause(PlannerInfo *root,
RelOptInfo *rel1, RelOptInfo *rel2);
extern bool has_relevant_eclass_joinclause(PlannerInfo *root,
RelOptInfo *rel1);
extern bool eclass_useful_for_merging(PlannerInfo *root,
EquivalenceClass *eclass,
RelOptInfo *rel);
extern bool is_redundant_derived_clause(RestrictInfo *rinfo, List *clauselist);
extern bool is_redundant_with_indexclauses(RestrictInfo *rinfo,
List *indexclauses);
/*
* pathkeys.c
* utilities for matching and building path keys
*/
typedef enum
{
PATHKEYS_EQUAL, /* pathkeys are identical */
PATHKEYS_BETTER1, /* pathkey 1 is a superset of pathkey 2 */
PATHKEYS_BETTER2, /* vice versa */
PATHKEYS_DIFFERENT /* neither pathkey includes the other */
} PathKeysComparison;
extern PathKeysComparison compare_pathkeys(List *keys1, List *keys2);
extern bool pathkeys_contained_in(List *keys1, List *keys2);
extern bool pathkeys_count_contained_in(List *keys1, List *keys2, int *n_common);
extern int group_keys_reorder_by_pathkeys(List *pathkeys,
List **group_pathkeys,
List **group_clauses);
extern List *get_useful_group_keys_orderings(PlannerInfo *root, double nrows,
List *path_pathkeys,
List *group_pathkeys, List *group_clauses,
List *aggregate_pathkeys);
extern Path *get_cheapest_path_for_pathkeys(List *paths, List *pathkeys,
Relids required_outer,
CostSelector cost_criterion,
bool require_parallel_safe);
extern Path *get_cheapest_fractional_path_for_pathkeys(List *paths,
List *pathkeys,
Relids required_outer,
double fraction);
extern Path *get_cheapest_parallel_safe_total_inner(List *paths);
extern List *build_index_pathkeys(PlannerInfo *root, IndexOptInfo *index,
ScanDirection scandir);
extern List *build_partition_pathkeys(PlannerInfo *root, RelOptInfo *partrel,
ScanDirection scandir, bool *partialkeys);
extern List *build_expression_pathkey(PlannerInfo *root, Expr *expr,
Relids nullable_relids, Oid opno,
Relids rel, bool create_it);
extern List *convert_subquery_pathkeys(PlannerInfo *root, RelOptInfo *rel,
List *subquery_pathkeys,
List *subquery_tlist);
extern List *build_join_pathkeys(PlannerInfo *root,
RelOptInfo *joinrel,
JoinType jointype,
List *outer_pathkeys);
extern List *make_pathkeys_for_sortclauses(PlannerInfo *root,
List *sortclauses,
List *tlist);
extern void initialize_mergeclause_eclasses(PlannerInfo *root,
RestrictInfo *restrictinfo);
extern void update_mergeclause_eclasses(PlannerInfo *root,
RestrictInfo *restrictinfo);
extern List *find_mergeclauses_for_outer_pathkeys(PlannerInfo *root,
List *pathkeys,
List *restrictinfos);
extern List *select_outer_pathkeys_for_merge(PlannerInfo *root,
List *mergeclauses,
RelOptInfo *joinrel);
extern List *make_inner_pathkeys_for_merge(PlannerInfo *root,
List *mergeclauses,
List *outer_pathkeys);
extern List *trim_mergeclauses_for_inner_pathkeys(PlannerInfo *root,
List *mergeclauses,
List *pathkeys);
extern List *truncate_useless_pathkeys(PlannerInfo *root,
RelOptInfo *rel,
List *pathkeys);
extern bool has_useful_pathkeys(PlannerInfo *root, RelOptInfo *rel);
extern List *append_pathkeys(List *target, List *source);
extern PathKey *make_canonical_pathkey(PlannerInfo *root,
EquivalenceClass *eclass, Oid opfamily,
int strategy, bool nulls_first);
extern void add_paths_to_append_rel(PlannerInfo *root, RelOptInfo *rel,
List *live_childrels);
#endif /* PATHS_H */
Reference in New Issue View Git Blame Copy Permalink