costsize.c File Reference

#include "postgres.h"
#include <limits.h>
#include <math.h>
#include "access/amapi.h"
#include "access/htup_details.h"
#include "access/tsmapi.h"
#include "executor/executor.h"
#include "executor/nodeAgg.h"
#include "executor/nodeHash.h"
#include "executor/nodeMemoize.h"
#include "miscadmin.h"
#include "nodes/makefuncs.h"
#include "nodes/nodeFuncs.h"
#include "optimizer/clauses.h"
#include "optimizer/cost.h"
#include "optimizer/optimizer.h"
#include "optimizer/pathnode.h"
#include "optimizer/paths.h"
#include "optimizer/placeholder.h"
#include "optimizer/plancat.h"
#include "optimizer/planmain.h"
#include "optimizer/restrictinfo.h"
#include "parser/parsetree.h"
#include "utils/lsyscache.h"
#include "utils/selfuncs.h"
#include "utils/spccache.h"
#include "utils/tuplesort.h"

Include dependency graph for costsize.c:

Go to the source code of this file.

Data Structures
struct	cost_qual_eval_context

Macros
#define	LOG2(x)   (log(x) / 0.693147180559945)
#define	APPEND_CPU_COST_MULTIPLIER   0.5
#define	MAXIMUM_ROWCOUNT   1e100

Functions
static List *	extract_nonindex_conditions (List *qual_clauses, List *indexclauses)
static MergeScanSelCache *	cached_scansel (PlannerInfo *root, RestrictInfo *rinfo, PathKey *pathkey)
static void	cost_rescan (PlannerInfo *root, Path *path, Cost *rescan_startup_cost, Cost *rescan_total_cost)
static bool	cost_qual_eval_walker (Node *node, cost_qual_eval_context *context)
static void	get_restriction_qual_cost (PlannerInfo *root, RelOptInfo *baserel, ParamPathInfo *param_info, QualCost *qpqual_cost)
static bool	has_indexed_join_quals (NestPath *path)
static double	approx_tuple_count (PlannerInfo *root, JoinPath *path, List *quals)
static double	calc_joinrel_size_estimate (PlannerInfo *root, RelOptInfo *joinrel, RelOptInfo *outer_rel, RelOptInfo *inner_rel, double outer_rows, double inner_rows, SpecialJoinInfo *sjinfo, List *restrictlist)
static Selectivity	get_foreign_key_join_selectivity (PlannerInfo *root, Relids outer_relids, Relids inner_relids, SpecialJoinInfo *sjinfo, List **restrictlist)
static Cost	append_nonpartial_cost (List *subpaths, int numpaths, int parallel_workers)
static void	set_rel_width (PlannerInfo *root, RelOptInfo *rel)
static int32	get_expr_width (PlannerInfo *root, const Node *expr)
static double	relation_byte_size (double tuples, int width)
static double	page_size (double tuples, int width)
static double	get_parallel_divisor (Path *path)
double	clamp_row_est (double nrows)
long	clamp_cardinality_to_long (Cardinality x)
void	cost_seqscan (Path *path, PlannerInfo *root, RelOptInfo *baserel, ParamPathInfo *param_info)
void	cost_samplescan (Path *path, PlannerInfo *root, RelOptInfo *baserel, ParamPathInfo *param_info)
void	cost_gather (GatherPath *path, PlannerInfo *root, RelOptInfo *rel, ParamPathInfo *param_info, double *rows)
void	cost_gather_merge (GatherMergePath *path, PlannerInfo *root, RelOptInfo *rel, ParamPathInfo *param_info, Cost input_startup_cost, Cost input_total_cost, double *rows)
void	cost_index (IndexPath *path, PlannerInfo *root, double loop_count, bool partial_path)
double	index_pages_fetched (double tuples_fetched, BlockNumber pages, double index_pages, PlannerInfo *root)
static double	get_indexpath_pages (Path *bitmapqual)
void	cost_bitmap_heap_scan (Path *path, PlannerInfo *root, RelOptInfo *baserel, ParamPathInfo *param_info, Path *bitmapqual, double loop_count)
void	cost_bitmap_tree_node (Path *path, Cost *cost, Selectivity *selec)
void	cost_bitmap_and_node (BitmapAndPath *path, PlannerInfo *root)
void	cost_bitmap_or_node (BitmapOrPath *path, PlannerInfo *root)
void	cost_tidscan (Path *path, PlannerInfo *root, RelOptInfo *baserel, List *tidquals, ParamPathInfo *param_info)
void	cost_tidrangescan (Path *path, PlannerInfo *root, RelOptInfo *baserel, List *tidrangequals, ParamPathInfo *param_info)
void	cost_subqueryscan (SubqueryScanPath *path, PlannerInfo *root, RelOptInfo *baserel, ParamPathInfo *param_info, bool trivial_pathtarget)
void	cost_functionscan (Path *path, PlannerInfo *root, RelOptInfo *baserel, ParamPathInfo *param_info)
void	cost_tablefuncscan (Path *path, PlannerInfo *root, RelOptInfo *baserel, ParamPathInfo *param_info)
void	cost_valuesscan (Path *path, PlannerInfo *root, RelOptInfo *baserel, ParamPathInfo *param_info)
void	cost_ctescan (Path *path, PlannerInfo *root, RelOptInfo *baserel, ParamPathInfo *param_info)
void	cost_namedtuplestorescan (Path *path, PlannerInfo *root, RelOptInfo *baserel, ParamPathInfo *param_info)
void	cost_resultscan (Path *path, PlannerInfo *root, RelOptInfo *baserel, ParamPathInfo *param_info)
void	cost_recursive_union (Path *runion, Path *nrterm, Path *rterm)
static void	cost_tuplesort (Cost *startup_cost, Cost *run_cost, double tuples, int width, Cost comparison_cost, int sort_mem, double limit_tuples)
void	cost_incremental_sort (Path *path, PlannerInfo *root, List *pathkeys, int presorted_keys, Cost input_startup_cost, Cost input_total_cost, double input_tuples, int width, Cost comparison_cost, int sort_mem, double limit_tuples)
void	cost_sort (Path *path, PlannerInfo *root, List *pathkeys, Cost input_cost, double tuples, int width, Cost comparison_cost, int sort_mem, double limit_tuples)
void	cost_append (AppendPath *apath)
void	cost_merge_append (Path *path, PlannerInfo *root, List *pathkeys, int n_streams, Cost input_startup_cost, Cost input_total_cost, double tuples)
void	cost_material (Path *path, Cost input_startup_cost, Cost input_total_cost, double tuples, int width)
static void	cost_memoize_rescan (PlannerInfo *root, MemoizePath *mpath, Cost *rescan_startup_cost, Cost *rescan_total_cost)
void	cost_agg (Path *path, PlannerInfo *root, AggStrategy aggstrategy, const AggClauseCosts *aggcosts, int numGroupCols, double numGroups, List *quals, Cost input_startup_cost, Cost input_total_cost, double input_tuples, double input_width)
void	cost_windowagg (Path *path, PlannerInfo *root, List *windowFuncs, int numPartCols, int numOrderCols, Cost input_startup_cost, Cost input_total_cost, double input_tuples)
void	cost_group (Path *path, PlannerInfo *root, int numGroupCols, double numGroups, List *quals, Cost input_startup_cost, Cost input_total_cost, double input_tuples)
void	initial_cost_nestloop (PlannerInfo *root, JoinCostWorkspace *workspace, JoinType jointype, Path *outer_path, Path *inner_path, JoinPathExtraData *extra)
void	final_cost_nestloop (PlannerInfo *root, NestPath *path, JoinCostWorkspace *workspace, JoinPathExtraData *extra)
void	initial_cost_mergejoin (PlannerInfo *root, JoinCostWorkspace *workspace, JoinType jointype, List *mergeclauses, Path *outer_path, Path *inner_path, List *outersortkeys, List *innersortkeys, JoinPathExtraData *extra)
void	final_cost_mergejoin (PlannerInfo *root, MergePath *path, JoinCostWorkspace *workspace, JoinPathExtraData *extra)
void	initial_cost_hashjoin (PlannerInfo *root, JoinCostWorkspace *workspace, JoinType jointype, List *hashclauses, Path *outer_path, Path *inner_path, JoinPathExtraData *extra, bool parallel_hash)
void	final_cost_hashjoin (PlannerInfo *root, HashPath *path, JoinCostWorkspace *workspace, JoinPathExtraData *extra)
void	cost_subplan (PlannerInfo *root, SubPlan *subplan, Plan *plan)
void	cost_qual_eval (QualCost *cost, List *quals, PlannerInfo *root)
void	cost_qual_eval_node (QualCost *cost, Node *qual, PlannerInfo *root)
void	compute_semi_anti_join_factors (PlannerInfo *root, RelOptInfo *joinrel, RelOptInfo *outerrel, RelOptInfo *innerrel, JoinType jointype, SpecialJoinInfo *sjinfo, List *restrictlist, SemiAntiJoinFactors *semifactors)
void	set_baserel_size_estimates (PlannerInfo *root, RelOptInfo *rel)
double	get_parameterized_baserel_size (PlannerInfo *root, RelOptInfo *rel, List *param_clauses)
void	set_joinrel_size_estimates (PlannerInfo *root, RelOptInfo *rel, RelOptInfo *outer_rel, RelOptInfo *inner_rel, SpecialJoinInfo *sjinfo, List *restrictlist)
double	get_parameterized_joinrel_size (PlannerInfo *root, RelOptInfo *rel, Path *outer_path, Path *inner_path, SpecialJoinInfo *sjinfo, List *restrict_clauses)
void	set_subquery_size_estimates (PlannerInfo *root, RelOptInfo *rel)
void	set_function_size_estimates (PlannerInfo *root, RelOptInfo *rel)
void	set_tablefunc_size_estimates (PlannerInfo *root, RelOptInfo *rel)
void	set_values_size_estimates (PlannerInfo *root, RelOptInfo *rel)
void	set_cte_size_estimates (PlannerInfo *root, RelOptInfo *rel, double cte_rows)
void	set_namedtuplestore_size_estimates (PlannerInfo *root, RelOptInfo *rel)
void	set_result_size_estimates (PlannerInfo *root, RelOptInfo *rel)
void	set_foreign_size_estimates (PlannerInfo *root, RelOptInfo *rel)
PathTarget *	set_pathtarget_cost_width (PlannerInfo *root, PathTarget *target)
double	compute_bitmap_pages (PlannerInfo *root, RelOptInfo *baserel, Path *bitmapqual, int loop_count, Cost *cost, double *tuple)

Variables
double	seq_page_cost = DEFAULT_SEQ_PAGE_COST
double	random_page_cost = DEFAULT_RANDOM_PAGE_COST
double	cpu_tuple_cost = DEFAULT_CPU_TUPLE_COST
double	cpu_index_tuple_cost = DEFAULT_CPU_INDEX_TUPLE_COST
double	cpu_operator_cost = DEFAULT_CPU_OPERATOR_COST
double	parallel_tuple_cost = DEFAULT_PARALLEL_TUPLE_COST
double	parallel_setup_cost = DEFAULT_PARALLEL_SETUP_COST
double	recursive_worktable_factor = DEFAULT_RECURSIVE_WORKTABLE_FACTOR
int	effective_cache_size = DEFAULT_EFFECTIVE_CACHE_SIZE
Cost	disable_cost = 1.0e10
int	max_parallel_workers_per_gather = 2
bool	enable_seqscan = true
bool	enable_indexscan = true
bool	enable_indexonlyscan = true
bool	enable_bitmapscan = true
bool	enable_tidscan = true
bool	enable_sort = true
bool	enable_incremental_sort = true
bool	enable_hashagg = true
bool	enable_nestloop = true
bool	enable_material = true
bool	enable_memoize = true
bool	enable_mergejoin = true
bool	enable_hashjoin = true
bool	enable_gathermerge = true
bool	enable_partitionwise_join = false
bool	enable_partitionwise_aggregate = false
bool	enable_parallel_append = true
bool	enable_parallel_hash = true
bool	enable_partition_pruning = true
bool	enable_presorted_aggregate = true
bool	enable_async_append = true

Macro Definition Documentation

APPEND_CPU_COST_MULTIPLIER

#define APPEND_CPU_COST_MULTIPLIER   0.5

Definition at line 110 of file costsize.c.

LOG2

#define LOG2

(

x

)

(log(x) / 0.693147180559945)

Definition at line 103 of file costsize.c.

MAXIMUM_ROWCOUNT

#define MAXIMUM_ROWCOUNT   1e100

Definition at line 118 of file costsize.c.

Function Documentation

append_nonpartial_cost()

static Cost append_nonpartial_cost ( List *  subpaths, int  numpaths, int  parallel_workers  )

static

Definition at line 2127 of file costsize.c.

{
    Cost       *costarr;
    int         arrlen;
    ListCell   *l;
    ListCell   *cell;
    int         path_index;
    int         min_index;
    int         max_index;
 
    if (numpaths == 0)
        return 0;
 
    /*
     * Array length is number of workers or number of relevant paths,
     * whichever is less.
     */
    arrlen = Min(parallel_workers, numpaths);
    costarr = (Cost *) palloc(sizeof(Cost) * arrlen);
 
    /* The first few paths will each be claimed by a different worker. */
    path_index = 0;
    foreach(cell, subpaths)
    {
        Path       *subpath = (Path *) lfirst(cell);
 
        if (path_index == arrlen)
            break;
        costarr[path_index++] = subpath->total_cost;
    }
 
    /*
     * Since subpaths are sorted by decreasing cost, the last one will have
     * the minimum cost.
     */
    min_index = arrlen - 1;
 
    /*
     * For each of the remaining subpaths, add its cost to the array element
     * with minimum cost.
     */
    for_each_cell(l, subpaths, cell)
    {
        Path       *subpath = (Path *) lfirst(l);
 
        /* Consider only the non-partial paths */
        if (path_index++ == numpaths)
            break;
 
        costarr[min_index] += subpath->total_cost;
 
        /* Update the new min cost array index */
        min_index = 0;
        for (int i = 0; i < arrlen; i++)
        {
            if (costarr[i] < costarr[min_index])
                min_index = i;
        }
    }
 
    /* Return the highest cost from the array */
    max_index = 0;
    for (int i = 0; i < arrlen; i++)
    {
        if (costarr[i] > costarr[max_index])
            max_index = i;
    }
 
    return costarr[max_index];
}

References for_each_cell, i, lfirst, Min, palloc(), and subpath().

Referenced by cost_append().

approx_tuple_count()

static double approx_tuple_count ( PlannerInfo *  root, JoinPath *  path, List *  quals  )

static

Definition at line 4937 of file costsize.c.

{
    double      tuples;
    double      outer_tuples = path->outerjoinpath->rows;
    double      inner_tuples = path->innerjoinpath->rows;
    SpecialJoinInfo sjinfo;
    Selectivity selec = 1.0;
    ListCell   *l;
 
    /*
     * Make up a SpecialJoinInfo for JOIN_INNER semantics.
     */
    sjinfo.type = T_SpecialJoinInfo;
    sjinfo.min_lefthand = path->outerjoinpath->parent->relids;
    sjinfo.min_righthand = path->innerjoinpath->parent->relids;
    sjinfo.syn_lefthand = path->outerjoinpath->parent->relids;
    sjinfo.syn_righthand = path->innerjoinpath->parent->relids;
    sjinfo.jointype = JOIN_INNER;
    sjinfo.ojrelid = 0;
    sjinfo.commute_above_l = NULL;
    sjinfo.commute_above_r = NULL;
    sjinfo.commute_below = NULL;
    /* we don't bother trying to make the remaining fields valid */
    sjinfo.lhs_strict = false;
    sjinfo.semi_can_btree = false;
    sjinfo.semi_can_hash = false;
    sjinfo.semi_operators = NIL;
    sjinfo.semi_rhs_exprs = NIL;
 
    /* Get the approximate selectivity */
    foreach(l, quals)
    {
        Node       *qual = (Node *) lfirst(l);
 
        /* Note that clause_selectivity will be able to cache its result */
        selec *= clause_selectivity(root, qual, 0, JOIN_INNER, &sjinfo);
    }
 
    /* Apply it to the input relation sizes */
    tuples = selec * outer_tuples * inner_tuples;
 
    return clamp_row_est(tuples);
}

References clamp_row_est(), clause_selectivity(), SpecialJoinInfo::commute_above_l, SpecialJoinInfo::commute_above_r, SpecialJoinInfo::commute_below, JoinPath::innerjoinpath, JOIN_INNER, SpecialJoinInfo::jointype, lfirst, SpecialJoinInfo::lhs_strict, SpecialJoinInfo::min_lefthand, SpecialJoinInfo::min_righthand, NIL, SpecialJoinInfo::ojrelid, JoinPath::outerjoinpath, Path::rows, SpecialJoinInfo::semi_can_btree, SpecialJoinInfo::semi_can_hash, SpecialJoinInfo::semi_operators, SpecialJoinInfo::semi_rhs_exprs, SpecialJoinInfo::syn_lefthand, and SpecialJoinInfo::syn_righthand.

Referenced by final_cost_hashjoin(), and final_cost_mergejoin().

cached_scansel()

static MergeScanSelCache * cached_scansel ( PlannerInfo *  root, RestrictInfo *  rinfo, PathKey *  pathkey  )

static

Definition at line 3724 of file costsize.c.

{
    MergeScanSelCache *cache;
    ListCell   *lc;
    Selectivity leftstartsel,
                leftendsel,
                rightstartsel,
                rightendsel;
    MemoryContext oldcontext;
 
    /* Do we have this result already? */
    foreach(lc, rinfo->scansel_cache)
    {
        cache = (MergeScanSelCache *) lfirst(lc);
        if (cache->opfamily == pathkey->pk_opfamily &&
            cache->collation == pathkey->pk_eclass->ec_collation &&
            cache->strategy == pathkey->pk_strategy &&
            cache->nulls_first == pathkey->pk_nulls_first)
            return cache;
    }
 
    /* Nope, do the computation */
    mergejoinscansel(root,
                     (Node *) rinfo->clause,
                     pathkey->pk_opfamily,
                     pathkey->pk_strategy,
                     pathkey->pk_nulls_first,
                     &leftstartsel,
                     &leftendsel,
                     &rightstartsel,
                     &rightendsel);
 
    /* Cache the result in suitably long-lived workspace */
    oldcontext = MemoryContextSwitchTo(root->planner_cxt);
 
    cache = (MergeScanSelCache *) palloc(sizeof(MergeScanSelCache));
    cache->opfamily = pathkey->pk_opfamily;
    cache->collation = pathkey->pk_eclass->ec_collation;
    cache->strategy = pathkey->pk_strategy;
    cache->nulls_first = pathkey->pk_nulls_first;
    cache->leftstartsel = leftstartsel;
    cache->leftendsel = leftendsel;
    cache->rightstartsel = rightstartsel;
    cache->rightendsel = rightendsel;
 
    rinfo->scansel_cache = lappend(rinfo->scansel_cache, cache);
 
    MemoryContextSwitchTo(oldcontext);
 
    return cache;
}

References RestrictInfo::clause, MergeScanSelCache::collation, lappend(), MergeScanSelCache::leftendsel, MergeScanSelCache::leftstartsel, lfirst, MemoryContextSwitchTo(), mergejoinscansel(), MergeScanSelCache::nulls_first, MergeScanSelCache::opfamily, palloc(), PathKey::pk_nulls_first, PathKey::pk_opfamily, PathKey::pk_strategy, MergeScanSelCache::rightendsel, MergeScanSelCache::rightstartsel, and MergeScanSelCache::strategy.

Referenced by initial_cost_mergejoin().

calc_joinrel_size_estimate()

static double calc_joinrel_size_estimate ( PlannerInfo *  root, RelOptInfo *  joinrel, RelOptInfo *  outer_rel, RelOptInfo *  inner_rel, double  outer_rows, double  inner_rows, SpecialJoinInfo *  sjinfo, List *  restrictlist  )

static

Definition at line 5148 of file costsize.c.

{
    JoinType    jointype = sjinfo->jointype;
    Selectivity fkselec;
    Selectivity jselec;
    Selectivity pselec;
    double      nrows;
 
    /*
     * Compute joinclause selectivity.  Note that we are only considering
     * clauses that become restriction clauses at this join level; we are not
     * double-counting them because they were not considered in estimating the
     * sizes of the component rels.
     *
     * First, see whether any of the joinclauses can be matched to known FK
     * constraints.  If so, drop those clauses from the restrictlist, and
     * instead estimate their selectivity using FK semantics.  (We do this
     * without regard to whether said clauses are local or "pushed down".
     * Probably, an FK-matching clause could never be seen as pushed down at
     * an outer join, since it would be strict and hence would be grounds for
     * join strength reduction.)  fkselec gets the net selectivity for
     * FK-matching clauses, or 1.0 if there are none.
     */
    fkselec = get_foreign_key_join_selectivity(root,
                                               outer_rel->relids,
                                               inner_rel->relids,
                                               sjinfo,
                                               &restrictlist);
 
    /*
     * For an outer join, we have to distinguish the selectivity of the join's
     * own clauses (JOIN/ON conditions) from any clauses that were "pushed
     * down".  For inner joins we just count them all as joinclauses.
     */
    if (IS_OUTER_JOIN(jointype))
    {
        List       *joinquals = NIL;
        List       *pushedquals = NIL;
        ListCell   *l;
 
        /* Grovel through the clauses to separate into two lists */
        foreach(l, restrictlist)
        {
            RestrictInfo *rinfo = lfirst_node(RestrictInfo, l);
 
            if (RINFO_IS_PUSHED_DOWN(rinfo, joinrel->relids))
                pushedquals = lappend(pushedquals, rinfo);
            else
                joinquals = lappend(joinquals, rinfo);
        }
 
        /* Get the separate selectivities */
        jselec = clauselist_selectivity(root,
                                        joinquals,
                                        0,
                                        jointype,
                                        sjinfo);
        pselec = clauselist_selectivity(root,
                                        pushedquals,
                                        0,
                                        jointype,
                                        sjinfo);
 
        /* Avoid leaking a lot of ListCells */
        list_free(joinquals);
        list_free(pushedquals);
    }
    else
    {
        jselec = clauselist_selectivity(root,
                                        restrictlist,
                                        0,
                                        jointype,
                                        sjinfo);
        pselec = 0.0;           /* not used, keep compiler quiet */
    }
 
    /*
     * Basically, we multiply size of Cartesian product by selectivity.
     *
     * If we are doing an outer join, take that into account: the joinqual
     * selectivity has to be clamped using the knowledge that the output must
     * be at least as large as the non-nullable input.  However, any
     * pushed-down quals are applied after the outer join, so their
     * selectivity applies fully.
     *
     * For JOIN_SEMI and JOIN_ANTI, the selectivity is defined as the fraction
     * of LHS rows that have matches, and we apply that straightforwardly.
     */
    switch (jointype)
    {
        case JOIN_INNER:
            nrows = outer_rows * inner_rows * fkselec * jselec;
            /* pselec not used */
            break;
        case JOIN_LEFT:
            nrows = outer_rows * inner_rows * fkselec * jselec;
            if (nrows < outer_rows)
                nrows = outer_rows;
            nrows *= pselec;
            break;
        case JOIN_FULL:
            nrows = outer_rows * inner_rows * fkselec * jselec;
            if (nrows < outer_rows)
                nrows = outer_rows;
            if (nrows < inner_rows)
                nrows = inner_rows;
            nrows *= pselec;
            break;
        case JOIN_SEMI:
            nrows = outer_rows * fkselec * jselec;
            /* pselec not used */
            break;
        case JOIN_ANTI:
            nrows = outer_rows * (1.0 - fkselec * jselec);
            nrows *= pselec;
            break;
        default:
            /* other values not expected here */
            elog(ERROR, "unrecognized join type: %d", (int) jointype);
            nrows = 0;          /* keep compiler quiet */
            break;
    }
 
    return clamp_row_est(nrows);
}

References clamp_row_est(), clauselist_selectivity(), elog(), ERROR, get_foreign_key_join_selectivity(), IS_OUTER_JOIN, JOIN_ANTI, JOIN_FULL, JOIN_INNER, JOIN_LEFT, JOIN_SEMI, SpecialJoinInfo::jointype, lappend(), lfirst_node, list_free(), NIL, RelOptInfo::relids, and RINFO_IS_PUSHED_DOWN.

Referenced by get_parameterized_joinrel_size(), and set_joinrel_size_estimates().

clamp_cardinality_to_long()

long clamp_cardinality_to_long

(

Cardinality

x

)

Definition at line 226 of file costsize.c.

{
    /*
     * Just for paranoia's sake, ensure we do something sane with negative or
     * NaN values.
     */
    if (isnan(x))
        return LONG_MAX;
    if (x <= 0)
        return 0;
 
    /*
     * If "long" is 64 bits, then LONG_MAX cannot be represented exactly as a
     * double.  Casting it to double and back may well result in overflow due
     * to rounding, so avoid doing that.  We trust that any double value that
     * compares strictly less than "(double) LONG_MAX" will cast to a
     * representable "long" value.
     */
    return (x < (double) LONG_MAX) ? (long) x : LONG_MAX;
}

References x.

Referenced by buildSubPlanHash(), create_recursiveunion_plan(), create_setop_plan(), and make_agg().

clamp_row_est()

double clamp_row_est

(

double

nrows

)

Definition at line 203 of file costsize.c.

{
    /*
     * Avoid infinite and NaN row estimates.  Costs derived from such values
     * are going to be useless.  Also force the estimate to be at least one
     * row, to make explain output look better and to avoid possible
     * divide-by-zero when interpolating costs.  Make it an integer, too.
     */
    if (nrows > MAXIMUM_ROWCOUNT || isnan(nrows))
        nrows = MAXIMUM_ROWCOUNT;
    else if (nrows <= 1.0)
        nrows = 1.0;
    else
        nrows = rint(nrows);
 
    return nrows;
}

References MAXIMUM_ROWCOUNT.

Referenced by adjust_limit_rows_costs(), approx_tuple_count(), bernoulli_samplescangetsamplesize(), calc_joinrel_size_estimate(), compute_bitmap_pages(), cost_agg(), cost_append(), cost_bitmap_heap_scan(), cost_group(), cost_index(), cost_seqscan(), cost_subplan(), cost_subqueryscan(), create_bitmap_subplan(), estimate_hash_bucket_stats(), estimate_num_groups(), estimate_path_cost_size(), estimate_size(), expression_returns_set_rows(), final_cost_hashjoin(), final_cost_mergejoin(), final_cost_nestloop(), get_parameterized_baserel_size(), get_variable_numdistinct(), initial_cost_mergejoin(), set_baserel_size_estimates(), set_cte_size_estimates(), set_foreign_size(), system_rows_samplescangetsamplesize(), system_samplescangetsamplesize(), and system_time_samplescangetsamplesize().

compute_bitmap_pages()

double compute_bitmap_pages	(	PlannerInfo *	root,
		RelOptInfo *	baserel,
		Path *	bitmapqual,
		int	loop_count,
		Cost *	cost,
		double *	tuple
	)

Definition at line 6155 of file costsize.c.

{
    Cost        indexTotalCost;
    Selectivity indexSelectivity;
    double      T;
    double      pages_fetched;
    double      tuples_fetched;
    double      heap_pages;
    long        maxentries;
 
    /*
     * Fetch total cost of obtaining the bitmap, as well as its total
     * selectivity.
     */
    cost_bitmap_tree_node(bitmapqual, &indexTotalCost, &indexSelectivity);
 
    /*
     * Estimate number of main-table pages fetched.
     */
    tuples_fetched = clamp_row_est(indexSelectivity * baserel->tuples);
 
    T = (baserel->pages > 1) ? (double) baserel->pages : 1.0;
 
    /*
     * For a single scan, the number of heap pages that need to be fetched is
     * the same as the Mackert and Lohman formula for the case T <= b (ie, no
     * re-reads needed).
     */
    pages_fetched = (2.0 * T * tuples_fetched) / (2.0 * T + tuples_fetched);
 
    /*
     * Calculate the number of pages fetched from the heap.  Then based on
     * current work_mem estimate get the estimated maxentries in the bitmap.
     * (Note that we always do this calculation based on the number of pages
     * that would be fetched in a single iteration, even if loop_count > 1.
     * That's correct, because only that number of entries will be stored in
     * the bitmap at one time.)
     */
    heap_pages = Min(pages_fetched, baserel->pages);
    maxentries = tbm_calculate_entries(work_mem * 1024L);
 
    if (loop_count > 1)
    {
        /*
         * For repeated bitmap scans, scale up the number of tuples fetched in
         * the Mackert and Lohman formula by the number of scans, so that we
         * estimate the number of pages fetched by all the scans. Then
         * pro-rate for one scan.
         */
        pages_fetched = index_pages_fetched(tuples_fetched * loop_count,
                                            baserel->pages,
                                            get_indexpath_pages(bitmapqual),
                                            root);
        pages_fetched /= loop_count;
    }
 
    if (pages_fetched >= T)
        pages_fetched = T;
    else
        pages_fetched = ceil(pages_fetched);
 
    if (maxentries < heap_pages)
    {
        double      exact_pages;
        double      lossy_pages;
 
        /*
         * Crude approximation of the number of lossy pages.  Because of the
         * way tbm_lossify() is coded, the number of lossy pages increases
         * very sharply as soon as we run short of memory; this formula has
         * that property and seems to perform adequately in testing, but it's
         * possible we could do better somehow.
         */
        lossy_pages = Max(0, heap_pages - maxentries / 2);
        exact_pages = heap_pages - lossy_pages;
 
        /*
         * If there are lossy pages then recompute the number of tuples
         * processed by the bitmap heap node.  We assume here that the chance
         * of a given tuple coming from an exact page is the same as the
         * chance that a given page is exact.  This might not be true, but
         * it's not clear how we can do any better.
         */
        if (lossy_pages > 0)
            tuples_fetched =
                clamp_row_est(indexSelectivity *
                              (exact_pages / heap_pages) * baserel->tuples +
                              (lossy_pages / heap_pages) * baserel->tuples);
    }
 
    if (cost)
        *cost = indexTotalCost;
    if (tuple)
        *tuple = tuples_fetched;
 
    return pages_fetched;
}

References clamp_row_est(), cost_bitmap_tree_node(), get_indexpath_pages(), index_pages_fetched(), Max, Min, RelOptInfo::pages, T, tbm_calculate_entries(), RelOptInfo::tuples, and work_mem.

Referenced by cost_bitmap_heap_scan(), and create_partial_bitmap_paths().

compute_semi_anti_join_factors()

void compute_semi_anti_join_factors	(	PlannerInfo *	root,
		RelOptInfo *	joinrel,
		RelOptInfo *	outerrel,
		RelOptInfo *	innerrel,
		JoinType	jointype,
		SpecialJoinInfo *	sjinfo,
		List *	restrictlist,
		SemiAntiJoinFactors *	semifactors
	)

Definition at line 4732 of file costsize.c.

{
    Selectivity jselec;
    Selectivity nselec;
    Selectivity avgmatch;
    SpecialJoinInfo norm_sjinfo;
    List       *joinquals;
    ListCell   *l;
 
    /*
     * In an ANTI join, we must ignore clauses that are "pushed down", since
     * those won't affect the match logic.  In a SEMI join, we do not
     * distinguish joinquals from "pushed down" quals, so just use the whole
     * restrictinfo list.  For other outer join types, we should consider only
     * non-pushed-down quals, so that this devolves to an IS_OUTER_JOIN check.
     */
    if (IS_OUTER_JOIN(jointype))
    {
        joinquals = NIL;
        foreach(l, restrictlist)
        {
            RestrictInfo *rinfo = lfirst_node(RestrictInfo, l);
 
            if (!RINFO_IS_PUSHED_DOWN(rinfo, joinrel->relids))
                joinquals = lappend(joinquals, rinfo);
        }
    }
    else
        joinquals = restrictlist;
 
    /*
     * Get the JOIN_SEMI or JOIN_ANTI selectivity of the join clauses.
     */
    jselec = clauselist_selectivity(root,
                                    joinquals,
                                    0,
                                    (jointype == JOIN_ANTI) ? JOIN_ANTI : JOIN_SEMI,
                                    sjinfo);
 
    /*
     * Also get the normal inner-join selectivity of the join clauses.
     */
    norm_sjinfo.type = T_SpecialJoinInfo;
    norm_sjinfo.min_lefthand = outerrel->relids;
    norm_sjinfo.min_righthand = innerrel->relids;
    norm_sjinfo.syn_lefthand = outerrel->relids;
    norm_sjinfo.syn_righthand = innerrel->relids;
    norm_sjinfo.jointype = JOIN_INNER;
    norm_sjinfo.ojrelid = 0;
    norm_sjinfo.commute_above_l = NULL;
    norm_sjinfo.commute_above_r = NULL;
    norm_sjinfo.commute_below = NULL;
    /* we don't bother trying to make the remaining fields valid */
    norm_sjinfo.lhs_strict = false;
    norm_sjinfo.semi_can_btree = false;
    norm_sjinfo.semi_can_hash = false;
    norm_sjinfo.semi_operators = NIL;
    norm_sjinfo.semi_rhs_exprs = NIL;
 
    nselec = clauselist_selectivity(root,
                                    joinquals,
                                    0,
                                    JOIN_INNER,
                                    &norm_sjinfo);
 
    /* Avoid leaking a lot of ListCells */
    if (IS_OUTER_JOIN(jointype))
        list_free(joinquals);
 
    /*
     * jselec can be interpreted as the fraction of outer-rel rows that have
     * any matches (this is true for both SEMI and ANTI cases).  And nselec is
     * the fraction of the Cartesian product that matches.  So, the average
     * number of matches for each outer-rel row that has at least one match is
     * nselec * inner_rows / jselec.
     *
     * Note: it is correct to use the inner rel's "rows" count here, even
     * though we might later be considering a parameterized inner path with
     * fewer rows.  This is because we have included all the join clauses in
     * the selectivity estimate.
     */
    if (jselec > 0)             /* protect against zero divide */
    {
        avgmatch = nselec * innerrel->rows / jselec;
        /* Clamp to sane range */
        avgmatch = Max(1.0, avgmatch);
    }
    else
        avgmatch = 1.0;
 
    semifactors->outer_match_frac = jselec;
    semifactors->match_count = avgmatch;
}

References clauselist_selectivity(), SpecialJoinInfo::commute_above_l, SpecialJoinInfo::commute_above_r, SpecialJoinInfo::commute_below, IS_OUTER_JOIN, JOIN_ANTI, JOIN_INNER, JOIN_SEMI, SpecialJoinInfo::jointype, lappend(), lfirst_node, SpecialJoinInfo::lhs_strict, list_free(), SemiAntiJoinFactors::match_count, Max, SpecialJoinInfo::min_lefthand, SpecialJoinInfo::min_righthand, NIL, SpecialJoinInfo::ojrelid, SemiAntiJoinFactors::outer_match_frac, RelOptInfo::relids, RINFO_IS_PUSHED_DOWN, RelOptInfo::rows, SpecialJoinInfo::semi_can_btree, SpecialJoinInfo::semi_can_hash, SpecialJoinInfo::semi_operators, SpecialJoinInfo::semi_rhs_exprs, SpecialJoinInfo::syn_lefthand, and SpecialJoinInfo::syn_righthand.

Referenced by add_paths_to_joinrel().

cost_agg()

void cost_agg	(	Path *	path,
		PlannerInfo *	root,
		AggStrategy	aggstrategy,
		const AggClauseCosts *	aggcosts,
		int	numGroupCols,
		double	numGroups,
		List *	quals,
		Cost	input_startup_cost,
		Cost	input_total_cost,
		double	input_tuples,
		double	input_width
	)

Definition at line 2622 of file costsize.c.

{
    double      output_tuples;
    Cost        startup_cost;
    Cost        total_cost;
    AggClauseCosts dummy_aggcosts;
 
    /* Use all-zero per-aggregate costs if NULL is passed */
    if (aggcosts == NULL)
    {
        Assert(aggstrategy == AGG_HASHED);
        MemSet(&dummy_aggcosts, 0, sizeof(AggClauseCosts));
        aggcosts = &dummy_aggcosts;
    }
 
    /*
     * The transCost.per_tuple component of aggcosts should be charged once
     * per input tuple, corresponding to the costs of evaluating the aggregate
     * transfns and their input expressions. The finalCost.per_tuple component
     * is charged once per output tuple, corresponding to the costs of
     * evaluating the finalfns.  Startup costs are of course charged but once.
     *
     * If we are grouping, we charge an additional cpu_operator_cost per
     * grouping column per input tuple for grouping comparisons.
     *
     * We will produce a single output tuple if not grouping, and a tuple per
     * group otherwise.  We charge cpu_tuple_cost for each output tuple.
     *
     * Note: in this cost model, AGG_SORTED and AGG_HASHED have exactly the
     * same total CPU cost, but AGG_SORTED has lower startup cost.  If the
     * input path is already sorted appropriately, AGG_SORTED should be
     * preferred (since it has no risk of memory overflow).  This will happen
     * as long as the computed total costs are indeed exactly equal --- but if
     * there's roundoff error we might do the wrong thing.  So be sure that
     * the computations below form the same intermediate values in the same
     * order.
     */
    if (aggstrategy == AGG_PLAIN)
    {
        startup_cost = input_total_cost;
        startup_cost += aggcosts->transCost.startup;
        startup_cost += aggcosts->transCost.per_tuple * input_tuples;
        startup_cost += aggcosts->finalCost.startup;
        startup_cost += aggcosts->finalCost.per_tuple;
        /* we aren't grouping */
        total_cost = startup_cost + cpu_tuple_cost;
        output_tuples = 1;
    }
    else if (aggstrategy == AGG_SORTED || aggstrategy == AGG_MIXED)
    {
        /* Here we are able to deliver output on-the-fly */
        startup_cost = input_startup_cost;
        total_cost = input_total_cost;
        if (aggstrategy == AGG_MIXED && !enable_hashagg)
        {
            startup_cost += disable_cost;
            total_cost += disable_cost;
        }
        /* calcs phrased this way to match HASHED case, see note above */
        total_cost += aggcosts->transCost.startup;
        total_cost += aggcosts->transCost.per_tuple * input_tuples;
        total_cost += (cpu_operator_cost * numGroupCols) * input_tuples;
        total_cost += aggcosts->finalCost.startup;
        total_cost += aggcosts->finalCost.per_tuple * numGroups;
        total_cost += cpu_tuple_cost * numGroups;
        output_tuples = numGroups;
    }
    else
    {
        /* must be AGG_HASHED */
        startup_cost = input_total_cost;
        if (!enable_hashagg)
            startup_cost += disable_cost;
        startup_cost += aggcosts->transCost.startup;
        startup_cost += aggcosts->transCost.per_tuple * input_tuples;
        /* cost of computing hash value */
        startup_cost += (cpu_operator_cost * numGroupCols) * input_tuples;
        startup_cost += aggcosts->finalCost.startup;
 
        total_cost = startup_cost;
        total_cost += aggcosts->finalCost.per_tuple * numGroups;
        /* cost of retrieving from hash table */
        total_cost += cpu_tuple_cost * numGroups;
        output_tuples = numGroups;
    }
 
    /*
     * Add the disk costs of hash aggregation that spills to disk.
     *
     * Groups that go into the hash table stay in memory until finalized, so
     * spilling and reprocessing tuples doesn't incur additional invocations
     * of transCost or finalCost. Furthermore, the computed hash value is
     * stored with the spilled tuples, so we don't incur extra invocations of
     * the hash function.
     *
     * Hash Agg begins returning tuples after the first batch is complete.
     * Accrue writes (spilled tuples) to startup_cost and to total_cost;
     * accrue reads only to total_cost.
     */
    if (aggstrategy == AGG_HASHED || aggstrategy == AGG_MIXED)
    {
        double      pages;
        double      pages_written = 0.0;
        double      pages_read = 0.0;
        double      spill_cost;
        double      hashentrysize;
        double      nbatches;
        Size        mem_limit;
        uint64      ngroups_limit;
        int         num_partitions;
        int         depth;
 
        /*
         * Estimate number of batches based on the computed limits. If less
         * than or equal to one, all groups are expected to fit in memory;
         * otherwise we expect to spill.
         */
        hashentrysize = hash_agg_entry_size(list_length(root->aggtransinfos),
                                            input_width,
                                            aggcosts->transitionSpace);
        hash_agg_set_limits(hashentrysize, numGroups, 0, &mem_limit,
                            &ngroups_limit, &num_partitions);
 
        nbatches = Max((numGroups * hashentrysize) / mem_limit,
                       numGroups / ngroups_limit);
 
        nbatches = Max(ceil(nbatches), 1.0);
        num_partitions = Max(num_partitions, 2);
 
        /*
         * The number of partitions can change at different levels of
         * recursion; but for the purposes of this calculation assume it stays
         * constant.
         */
        depth = ceil(log(nbatches) / log(num_partitions));
 
        /*
         * Estimate number of pages read and written. For each level of
         * recursion, a tuple must be written and then later read.
         */
        pages = relation_byte_size(input_tuples, input_width) / BLCKSZ;
        pages_written = pages_read = pages * depth;
 
        /*
         * HashAgg has somewhat worse IO behavior than Sort on typical
         * hardware/OS combinations. Account for this with a generic penalty.
         */
        pages_read *= 2.0;
        pages_written *= 2.0;
 
        startup_cost += pages_written * random_page_cost;
        total_cost += pages_written * random_page_cost;
        total_cost += pages_read * seq_page_cost;
 
        /* account for CPU cost of spilling a tuple and reading it back */
        spill_cost = depth * input_tuples * 2.0 * cpu_tuple_cost;
        startup_cost += spill_cost;
        total_cost += spill_cost;
    }
 
    /*
     * If there are quals (HAVING quals), account for their cost and
     * selectivity.
     */
    if (quals)
    {
        QualCost    qual_cost;
 
        cost_qual_eval(&qual_cost, quals, root);
        startup_cost += qual_cost.startup;
        total_cost += qual_cost.startup + output_tuples * qual_cost.per_tuple;
 
        output_tuples = clamp_row_est(output_tuples *
                                      clauselist_selectivity(root,
                                                             quals,
                                                             0,
                                                             JOIN_INNER,
                                                             NULL));
    }
 
    path->rows = output_tuples;
    path->startup_cost = startup_cost;
    path->total_cost = total_cost;
}

References AGG_HASHED, AGG_MIXED, AGG_PLAIN, AGG_SORTED, PlannerInfo::aggtransinfos, Assert(), clamp_row_est(), clauselist_selectivity(), cost_qual_eval(), cpu_operator_cost, cpu_tuple_cost, disable_cost, enable_hashagg, AggClauseCosts::finalCost, hash_agg_entry_size(), hash_agg_set_limits(), JOIN_INNER, list_length(), Max, MemSet, QualCost::per_tuple, random_page_cost, relation_byte_size(), Path::rows, seq_page_cost, QualCost::startup, Path::startup_cost, Path::total_cost, AggClauseCosts::transCost, and AggClauseCosts::transitionSpace.

Referenced by choose_hashed_setop(), create_agg_path(), create_groupingsets_path(), and create_unique_path().

cost_append()

void cost_append

(

AppendPath *

apath

)

Definition at line 2203 of file costsize.c.

{
    ListCell   *l;
 
    apath->path.startup_cost = 0;
    apath->path.total_cost = 0;
    apath->path.rows = 0;
 
    if (apath->subpaths == NIL)
        return;
 
    if (!apath->path.parallel_aware)
    {
        List       *pathkeys = apath->path.pathkeys;
 
        if (pathkeys == NIL)
        {
            Path       *firstsubpath = (Path *) linitial(apath->subpaths);
 
            /*
             * For an unordered, non-parallel-aware Append we take the startup
             * cost as the startup cost of the first subpath.
             */
            apath->path.startup_cost = firstsubpath->startup_cost;
 
            /* Compute rows and costs as sums of subplan rows and costs. */
            foreach(l, apath->subpaths)
            {
                Path       *subpath = (Path *) lfirst(l);
 
                apath->path.rows += subpath->rows;
                apath->path.total_cost += subpath->total_cost;
            }
        }
        else
        {
            /*
             * For an ordered, non-parallel-aware Append we take the startup
             * cost as the sum of the subpath startup costs.  This ensures
             * that we don't underestimate the startup cost when a query's
             * LIMIT is such that several of the children have to be run to
             * satisfy it.  This might be overkill --- another plausible hack
             * would be to take the Append's startup cost as the maximum of
             * the child startup costs.  But we don't want to risk believing
             * that an ORDER BY LIMIT query can be satisfied at small cost
             * when the first child has small startup cost but later ones
             * don't.  (If we had the ability to deal with nonlinear cost
             * interpolation for partial retrievals, we would not need to be
             * so conservative about this.)
             *
             * This case is also different from the above in that we have to
             * account for possibly injecting sorts into subpaths that aren't
             * natively ordered.
             */
            foreach(l, apath->subpaths)
            {
                Path       *subpath = (Path *) lfirst(l);
                Path        sort_path;  /* dummy for result of cost_sort */
 
                if (!pathkeys_contained_in(pathkeys, subpath->pathkeys))
                {
                    /*
                     * We'll need to insert a Sort node, so include costs for
                     * that.  We can use the parent's LIMIT if any, since we
                     * certainly won't pull more than that many tuples from
                     * any child.
                     */
                    cost_sort(&sort_path,
                              NULL, /* doesn't currently need root */
                              pathkeys,
                              subpath->total_cost,
                              subpath->rows,
                              subpath->pathtarget->width,
                              0.0,
                              work_mem,
                              apath->limit_tuples);
                    subpath = &sort_path;
                }
 
                apath->path.rows += subpath->rows;
                apath->path.startup_cost += subpath->startup_cost;
                apath->path.total_cost += subpath->total_cost;
            }
        }
    }
    else                        /* parallel-aware */
    {
        int         i = 0;
        double      parallel_divisor = get_parallel_divisor(&apath->path);
 
        /* Parallel-aware Append never produces ordered output. */
        Assert(apath->path.pathkeys == NIL);
 
        /* Calculate startup cost. */
        foreach(l, apath->subpaths)
        {
            Path       *subpath = (Path *) lfirst(l);
 
            /*
             * Append will start returning tuples when the child node having
             * lowest startup cost is done setting up. We consider only the
             * first few subplans that immediately get a worker assigned.
             */
            if (i == 0)
                apath->path.startup_cost = subpath->startup_cost;
            else if (i < apath->path.parallel_workers)
                apath->path.startup_cost = Min(apath->path.startup_cost,
                                               subpath->startup_cost);
 
            /*
             * Apply parallel divisor to subpaths.  Scale the number of rows
             * for each partial subpath based on the ratio of the parallel
             * divisor originally used for the subpath to the one we adopted.
             * Also add the cost of partial paths to the total cost, but
             * ignore non-partial paths for now.
             */
            if (i < apath->first_partial_path)
                apath->path.rows += subpath->rows / parallel_divisor;
            else
            {
                double      subpath_parallel_divisor;
 
                subpath_parallel_divisor = get_parallel_divisor(subpath);
                apath->path.rows += subpath->rows * (subpath_parallel_divisor /
                                                     parallel_divisor);
                apath->path.total_cost += subpath->total_cost;
            }
 
            apath->path.rows = clamp_row_est(apath->path.rows);
 
            i++;
        }
 
        /* Add cost for non-partial subpaths. */
        apath->path.total_cost +=
            append_nonpartial_cost(apath->subpaths,
                                   apath->first_partial_path,
                                   apath->path.parallel_workers);
    }
 
    /*
     * Although Append does not do any selection or projection, it's not free;
     * add a small per-tuple overhead.
     */
    apath->path.total_cost +=
        cpu_tuple_cost * APPEND_CPU_COST_MULTIPLIER * apath->path.rows;
}

References APPEND_CPU_COST_MULTIPLIER, append_nonpartial_cost(), Assert(), clamp_row_est(), cost_sort(), cpu_tuple_cost, AppendPath::first_partial_path, get_parallel_divisor(), i, lfirst, AppendPath::limit_tuples, linitial, Min, NIL, Path::parallel_aware, Path::parallel_workers, AppendPath::path, Path::pathkeys, pathkeys_contained_in(), Path::rows, Path::startup_cost, subpath(), AppendPath::subpaths, Path::total_cost, and work_mem.

Referenced by create_append_path().

cost_bitmap_and_node()

void cost_bitmap_and_node	(	BitmapAndPath *	path,
		PlannerInfo *	root
	)

Definition at line 1129 of file costsize.c.

{
    Cost        totalCost;
    Selectivity selec;
    ListCell   *l;
 
    /*
     * We estimate AND selectivity on the assumption that the inputs are
     * independent.  This is probably often wrong, but we don't have the info
     * to do better.
     *
     * The runtime cost of the BitmapAnd itself is estimated at 100x
     * cpu_operator_cost for each tbm_intersect needed.  Probably too small,
     * definitely too simplistic?
     */
    totalCost = 0.0;
    selec = 1.0;
    foreach(l, path->bitmapquals)
    {
        Path       *subpath = (Path *) lfirst(l);
        Cost        subCost;
        Selectivity subselec;
 
        cost_bitmap_tree_node(subpath, &subCost, &subselec);
 
        selec *= subselec;
 
        totalCost += subCost;
        if (l != list_head(path->bitmapquals))
            totalCost += 100.0 * cpu_operator_cost;
    }
    path->bitmapselectivity = selec;
    path->path.rows = 0;        /* per above, not used */
    path->path.startup_cost = totalCost;
    path->path.total_cost = totalCost;
}

References BitmapAndPath::bitmapquals, BitmapAndPath::bitmapselectivity, cost_bitmap_tree_node(), cpu_operator_cost, lfirst, list_head(), BitmapAndPath::path, Path::rows, Path::startup_cost, subpath(), and Path::total_cost.

Referenced by create_bitmap_and_path().

cost_bitmap_heap_scan()

void cost_bitmap_heap_scan	(	Path *	path,
		PlannerInfo *	root,
		RelOptInfo *	baserel,
		ParamPathInfo *	param_info,
		Path *	bitmapqual,
		double	loop_count
	)

Definition at line 985 of file costsize.c.

{
    Cost        startup_cost = 0;
    Cost        run_cost = 0;
    Cost        indexTotalCost;
    QualCost    qpqual_cost;
    Cost        cpu_per_tuple;
    Cost        cost_per_page;
    Cost        cpu_run_cost;
    double      tuples_fetched;
    double      pages_fetched;
    double      spc_seq_page_cost,
                spc_random_page_cost;
    double      T;
 
    /* Should only be applied to base relations */
    Assert(IsA(baserel, RelOptInfo));
    Assert(baserel->relid > 0);
    Assert(baserel->rtekind == RTE_RELATION);
 
    /* Mark the path with the correct row estimate */
    if (param_info)
        path->rows = param_info->ppi_rows;
    else
        path->rows = baserel->rows;
 
    if (!enable_bitmapscan)
        startup_cost += disable_cost;
 
    pages_fetched = compute_bitmap_pages(root, baserel, bitmapqual,
                                         loop_count, &indexTotalCost,
                                         &tuples_fetched);
 
    startup_cost += indexTotalCost;
    T = (baserel->pages > 1) ? (double) baserel->pages : 1.0;
 
    /* Fetch estimated page costs for tablespace containing table. */
    get_tablespace_page_costs(baserel->reltablespace,
                              &spc_random_page_cost,
                              &spc_seq_page_cost);
 
    /*
     * For small numbers of pages we should charge spc_random_page_cost
     * apiece, while if nearly all the table's pages are being read, it's more
     * appropriate to charge spc_seq_page_cost apiece.  The effect is
     * nonlinear, too. For lack of a better idea, interpolate like this to
     * determine the cost per page.
     */
    if (pages_fetched >= 2.0)
        cost_per_page = spc_random_page_cost -
            (spc_random_page_cost - spc_seq_page_cost)
            * sqrt(pages_fetched / T);
    else
        cost_per_page = spc_random_page_cost;
 
    run_cost += pages_fetched * cost_per_page;
 
    /*
     * Estimate CPU costs per tuple.
     *
     * Often the indexquals don't need to be rechecked at each tuple ... but
     * not always, especially not if there are enough tuples involved that the
     * bitmaps become lossy.  For the moment, just assume they will be
     * rechecked always.  This means we charge the full freight for all the
     * scan clauses.
     */
    get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
 
    startup_cost += qpqual_cost.startup;
    cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple;
    cpu_run_cost = cpu_per_tuple * tuples_fetched;
 
    /* Adjust costing for parallelism, if used. */
    if (path->parallel_workers > 0)
    {
        double      parallel_divisor = get_parallel_divisor(path);
 
        /* The CPU cost is divided among all the workers. */
        cpu_run_cost /= parallel_divisor;
 
        path->rows = clamp_row_est(path->rows / parallel_divisor);
    }
 
 
    run_cost += cpu_run_cost;
 
    /* tlist eval costs are paid per output row, not per tuple scanned */
    startup_cost += path->pathtarget->cost.startup;
    run_cost += path->pathtarget->cost.per_tuple * path->rows;
 
    path->startup_cost = startup_cost;
    path->total_cost = startup_cost + run_cost;
}

References Assert(), clamp_row_est(), compute_bitmap_pages(), cpu_tuple_cost, disable_cost, enable_bitmapscan, get_parallel_divisor(), get_restriction_qual_cost(), get_tablespace_page_costs(), IsA, RelOptInfo::pages, Path::parallel_workers, QualCost::per_tuple, ParamPathInfo::ppi_rows, RelOptInfo::relid, RelOptInfo::reltablespace, RelOptInfo::rows, Path::rows, RTE_RELATION, RelOptInfo::rtekind, QualCost::startup, Path::startup_cost, T, and Path::total_cost.

Referenced by bitmap_scan_cost_est(), and create_bitmap_heap_path().

cost_bitmap_or_node()

void cost_bitmap_or_node	(	BitmapOrPath *	path,
		PlannerInfo *	root
	)

Definition at line 1173 of file costsize.c.

{
    Cost        totalCost;
    Selectivity selec;
    ListCell   *l;
 
    /*
     * We estimate OR selectivity on the assumption that the inputs are
     * non-overlapping, since that's often the case in "x IN (list)" type
     * situations.  Of course, we clamp to 1.0 at the end.
     *
     * The runtime cost of the BitmapOr itself is estimated at 100x
     * cpu_operator_cost for each tbm_union needed.  Probably too small,
     * definitely too simplistic?  We are aware that the tbm_unions are
     * optimized out when the inputs are BitmapIndexScans.
     */
    totalCost = 0.0;
    selec = 0.0;
    foreach(l, path->bitmapquals)
    {
        Path       *subpath = (Path *) lfirst(l);
        Cost        subCost;
        Selectivity subselec;
 
        cost_bitmap_tree_node(subpath, &subCost, &subselec);
 
        selec += subselec;
 
        totalCost += subCost;
        if (l != list_head(path->bitmapquals) &&
            !IsA(subpath, IndexPath))
            totalCost += 100.0 * cpu_operator_cost;
    }
    path->bitmapselectivity = Min(selec, 1.0);
    path->path.rows = 0;        /* per above, not used */
    path->path.startup_cost = totalCost;
    path->path.total_cost = totalCost;
}

References BitmapOrPath::bitmapquals, BitmapOrPath::bitmapselectivity, cost_bitmap_tree_node(), cpu_operator_cost, IsA, lfirst, list_head(), Min, BitmapOrPath::path, Path::rows, Path::startup_cost, subpath(), and Path::total_cost.

Referenced by create_bitmap_or_path().

cost_bitmap_tree_node()

void cost_bitmap_tree_node	(	Path *	path,
		Cost *	cost,
		Selectivity *	selec
	)

Definition at line 1086 of file costsize.c.

{
    if (IsA(path, IndexPath))
    {
        *cost = ((IndexPath *) path)->indextotalcost;
        *selec = ((IndexPath *) path)->indexselectivity;
 
        /*
         * Charge a small amount per retrieved tuple to reflect the costs of
         * manipulating the bitmap.  This is mostly to make sure that a bitmap
         * scan doesn't look to be the same cost as an indexscan to retrieve a
         * single tuple.
         */
        *cost += 0.1 * cpu_operator_cost * path->rows;
    }
    else if (IsA(path, BitmapAndPath))
    {
        *cost = path->total_cost;
        *selec = ((BitmapAndPath *) path)->bitmapselectivity;
    }
    else if (IsA(path, BitmapOrPath))
    {
        *cost = path->total_cost;
        *selec = ((BitmapOrPath *) path)->bitmapselectivity;
    }
    else
    {
        elog(ERROR, "unrecognized node type: %d", nodeTag(path));
        *cost = *selec = 0;     /* keep compiler quiet */
    }
}

References cpu_operator_cost, elog(), ERROR, IsA, nodeTag, Path::rows, and Path::total_cost.

Referenced by choose_bitmap_and(), compute_bitmap_pages(), cost_bitmap_and_node(), cost_bitmap_or_node(), and path_usage_comparator().

cost_ctescan()

void cost_ctescan	(	Path *	path,
		PlannerInfo *	root,
		RelOptInfo *	baserel,
		ParamPathInfo *	param_info
	)

Definition at line 1670 of file costsize.c.

{
    Cost        startup_cost = 0;
    Cost        run_cost = 0;
    QualCost    qpqual_cost;
    Cost        cpu_per_tuple;
 
    /* Should only be applied to base relations that are CTEs */
    Assert(baserel->relid > 0);
    Assert(baserel->rtekind == RTE_CTE);
 
    /* Mark the path with the correct row estimate */
    if (param_info)
        path->rows = param_info->ppi_rows;
    else
        path->rows = baserel->rows;
 
    /* Charge one CPU tuple cost per row for tuplestore manipulation */
    cpu_per_tuple = cpu_tuple_cost;
 
    /* Add scanning CPU costs */
    get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
 
    startup_cost += qpqual_cost.startup;
    cpu_per_tuple += cpu_tuple_cost + qpqual_cost.per_tuple;
    run_cost += cpu_per_tuple * baserel->tuples;
 
    /* tlist eval costs are paid per output row, not per tuple scanned */
    startup_cost += path->pathtarget->cost.startup;
    run_cost += path->pathtarget->cost.per_tuple * path->rows;
 
    path->startup_cost = startup_cost;
    path->total_cost = startup_cost + run_cost;
}

References Assert(), cpu_tuple_cost, get_restriction_qual_cost(), QualCost::per_tuple, ParamPathInfo::ppi_rows, RelOptInfo::relid, RelOptInfo::rows, Path::rows, RTE_CTE, RelOptInfo::rtekind, QualCost::startup, Path::startup_cost, Path::total_cost, and RelOptInfo::tuples.

Referenced by create_ctescan_path(), and create_worktablescan_path().

cost_functionscan()

void cost_functionscan	(	Path *	path,
		PlannerInfo *	root,
		RelOptInfo *	baserel,
		ParamPathInfo *	param_info
	)

Definition at line 1503 of file costsize.c.

{
    Cost        startup_cost = 0;
    Cost        run_cost = 0;
    QualCost    qpqual_cost;
    Cost        cpu_per_tuple;
    RangeTblEntry *rte;
    QualCost    exprcost;
 
    /* Should only be applied to base relations that are functions */
    Assert(baserel->relid > 0);
    rte = planner_rt_fetch(baserel->relid, root);
    Assert(rte->rtekind == RTE_FUNCTION);
 
    /* Mark the path with the correct row estimate */
    if (param_info)
        path->rows = param_info->ppi_rows;
    else
        path->rows = baserel->rows;
 
    /*
     * Estimate costs of executing the function expression(s).
     *
     * Currently, nodeFunctionscan.c always executes the functions to
     * completion before returning any rows, and caches the results in a
     * tuplestore.  So the function eval cost is all startup cost, and per-row
     * costs are minimal.
     *
     * XXX in principle we ought to charge tuplestore spill costs if the
     * number of rows is large.  However, given how phony our rowcount
     * estimates for functions tend to be, there's not a lot of point in that
     * refinement right now.
     */
    cost_qual_eval_node(&exprcost, (Node *) rte->functions, root);
 
    startup_cost += exprcost.startup + exprcost.per_tuple;
 
    /* Add scanning CPU costs */
    get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
 
    startup_cost += qpqual_cost.startup;
    cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple;
    run_cost += cpu_per_tuple * baserel->tuples;
 
    /* tlist eval costs are paid per output row, not per tuple scanned */
    startup_cost += path->pathtarget->cost.startup;
    run_cost += path->pathtarget->cost.per_tuple * path->rows;
 
    path->startup_cost = startup_cost;
    path->total_cost = startup_cost + run_cost;
}

References Assert(), cost_qual_eval_node(), cpu_tuple_cost, RangeTblEntry::functions, get_restriction_qual_cost(), QualCost::per_tuple, planner_rt_fetch, ParamPathInfo::ppi_rows, RelOptInfo::relid, RelOptInfo::rows, Path::rows, RTE_FUNCTION, RangeTblEntry::rtekind, QualCost::startup, Path::startup_cost, Path::total_cost, and RelOptInfo::tuples.

Referenced by create_functionscan_path().

cost_gather()

void cost_gather	(	GatherPath *	path,
		PlannerInfo *	root,
		RelOptInfo *	rel,
		ParamPathInfo *	param_info,
		double *	rows
	)

Definition at line 408 of file costsize.c.

{
    Cost        startup_cost = 0;
    Cost        run_cost = 0;
 
    /* Mark the path with the correct row estimate */
    if (rows)
        path->path.rows = *rows;
    else if (param_info)
        path->path.rows = param_info->ppi_rows;
    else
        path->path.rows = rel->rows;
 
    startup_cost = path->subpath->startup_cost;
 
    run_cost = path->subpath->total_cost - path->subpath->startup_cost;
 
    /* Parallel setup and communication cost. */
    startup_cost += parallel_setup_cost;
    run_cost += parallel_tuple_cost * path->path.rows;
 
    path->path.startup_cost = startup_cost;
    path->path.total_cost = (startup_cost + run_cost);
}

References parallel_setup_cost, parallel_tuple_cost, GatherPath::path, ParamPathInfo::ppi_rows, RelOptInfo::rows, Path::rows, Path::startup_cost, GatherPath::subpath, and Path::total_cost.

Referenced by create_gather_path().

cost_gather_merge()

void cost_gather_merge	(	GatherMergePath *	path,
		PlannerInfo *	root,
		RelOptInfo *	rel,
		ParamPathInfo *	param_info,
		Cost	input_startup_cost,
		Cost	input_total_cost,
		double *	rows
	)

Definition at line 446 of file costsize.c.

{
    Cost        startup_cost = 0;
    Cost        run_cost = 0;
    Cost        comparison_cost;
    double      N;
    double      logN;
 
    /* Mark the path with the correct row estimate */
    if (rows)
        path->path.rows = *rows;
    else if (param_info)
        path->path.rows = param_info->ppi_rows;
    else
        path->path.rows = rel->rows;
 
    if (!enable_gathermerge)
        startup_cost += disable_cost;
 
    /*
     * Add one to the number of workers to account for the leader.  This might
     * be overgenerous since the leader will do less work than other workers
     * in typical cases, but we'll go with it for now.
     */
    Assert(path->num_workers > 0);
    N = (double) path->num_workers + 1;
    logN = LOG2(N);
 
    /* Assumed cost per tuple comparison */
    comparison_cost = 2.0 * cpu_operator_cost;
 
    /* Heap creation cost */
    startup_cost += comparison_cost * N * logN;
 
    /* Per-tuple heap maintenance cost */
    run_cost += path->path.rows * comparison_cost * logN;
 
    /* small cost for heap management, like cost_merge_append */
    run_cost += cpu_operator_cost * path->path.rows;
 
    /*
     * Parallel setup and communication cost.  Since Gather Merge, unlike
     * Gather, requires us to block until a tuple is available from every
     * worker, we bump the IPC cost up a little bit as compared with Gather.
     * For lack of a better idea, charge an extra 5%.
     */
    startup_cost += parallel_setup_cost;
    run_cost += parallel_tuple_cost * path->path.rows * 1.05;
 
    path->path.startup_cost = startup_cost + input_startup_cost;
    path->path.total_cost = (startup_cost + run_cost + input_total_cost);
}

References Assert(), cpu_operator_cost, disable_cost, enable_gathermerge, LOG2, GatherMergePath::num_workers, parallel_setup_cost, parallel_tuple_cost, GatherMergePath::path, ParamPathInfo::ppi_rows, RelOptInfo::rows, Path::rows, Path::startup_cost, and Path::total_cost.

Referenced by create_gather_merge_path().

cost_group()

void cost_group	(	Path *	path,
		PlannerInfo *	root,
		int	numGroupCols,
		double	numGroups,
		List *	quals,
		Cost	input_startup_cost,
		Cost	input_total_cost,
		double	input_tuples
	)

Definition at line 2894 of file costsize.c.

{
    double      output_tuples;
    Cost        startup_cost;
    Cost        total_cost;
 
    output_tuples = numGroups;
    startup_cost = input_startup_cost;
    total_cost = input_total_cost;
 
    /*
     * Charge one cpu_operator_cost per comparison per input tuple. We assume
     * all columns get compared at most of the tuples.
     */
    total_cost += cpu_operator_cost * input_tuples * numGroupCols;
 
    /*
     * If there are quals (HAVING quals), account for their cost and
     * selectivity.
     */
    if (quals)
    {
        QualCost    qual_cost;
 
        cost_qual_eval(&qual_cost, quals, root);
        startup_cost += qual_cost.startup;
        total_cost += qual_cost.startup + output_tuples * qual_cost.per_tuple;
 
        output_tuples = clamp_row_est(output_tuples *
                                      clauselist_selectivity(root,
                                                             quals,
                                                             0,
                                                             JOIN_INNER,
                                                             NULL));
    }
 
    path->rows = output_tuples;
    path->startup_cost = startup_cost;
    path->total_cost = total_cost;
}

References clamp_row_est(), clauselist_selectivity(), cost_qual_eval(), cpu_operator_cost, JOIN_INNER, QualCost::per_tuple, Path::rows, QualCost::startup, Path::startup_cost, and Path::total_cost.

Referenced by choose_hashed_setop(), and create_group_path().

cost_incremental_sort()

void cost_incremental_sort	(	Path *	path,
		PlannerInfo *	root,
		List *	pathkeys,
		int	presorted_keys,
		Cost	input_startup_cost,
		Cost	input_total_cost,
		double	input_tuples,
		int	width,
		Cost	comparison_cost,
		int	sort_mem,
		double	limit_tuples
	)

Definition at line 1958 of file costsize.c.

{
    Cost        startup_cost,
                run_cost,
                input_run_cost = input_total_cost - input_startup_cost;
    double      group_tuples,
                input_groups;
    Cost        group_startup_cost,
                group_run_cost,
                group_input_run_cost;
    List       *presortedExprs = NIL;
    ListCell   *l;
    bool        unknown_varno = false;
 
    Assert(presorted_keys > 0 && presorted_keys < list_length(pathkeys));
 
    /*
     * We want to be sure the cost of a sort is never estimated as zero, even
     * if passed-in tuple count is zero.  Besides, mustn't do log(0)...
     */
    if (input_tuples < 2.0)
        input_tuples = 2.0;
 
    /* Default estimate of number of groups, capped to one group per row. */
    input_groups = Min(input_tuples, DEFAULT_NUM_DISTINCT);
 
    /*
     * Extract presorted keys as list of expressions.
     *
     * We need to be careful about Vars containing "varno 0" which might have
     * been introduced by generate_append_tlist, which would confuse
     * estimate_num_groups (in fact it'd fail for such expressions). See
     * recurse_set_operations which has to deal with the same issue.
     *
     * Unlike recurse_set_operations we can't access the original target list
     * here, and even if we could it's not very clear how useful would that be
     * for a set operation combining multiple tables. So we simply detect if
     * there are any expressions with "varno 0" and use the default
     * DEFAULT_NUM_DISTINCT in that case.
     *
     * We might also use either 1.0 (a single group) or input_tuples (each row
     * being a separate group), pretty much the worst and best case for
     * incremental sort. But those are extreme cases and using something in
     * between seems reasonable. Furthermore, generate_append_tlist is used
     * for set operations, which are likely to produce mostly unique output
     * anyway - from that standpoint the DEFAULT_NUM_DISTINCT is defensive
     * while maintaining lower startup cost.
     */
    foreach(l, pathkeys)
    {
        PathKey    *key = (PathKey *) lfirst(l);
        EquivalenceMember *member = (EquivalenceMember *)
        linitial(key->pk_eclass->ec_members);
 
        /*
         * Check if the expression contains Var with "varno 0" so that we
         * don't call estimate_num_groups in that case.
         */
        if (bms_is_member(0, pull_varnos(root, (Node *) member->em_expr)))
        {
            unknown_varno = true;
            break;
        }
 
        /* expression not containing any Vars with "varno 0" */
        presortedExprs = lappend(presortedExprs, member->em_expr);
 
        if (foreach_current_index(l) + 1 >= presorted_keys)
            break;
    }
 
    /* Estimate the number of groups with equal presorted keys. */
    if (!unknown_varno)
        input_groups = estimate_num_groups(root, presortedExprs, input_tuples,
                                           NULL, NULL);
 
    group_tuples = input_tuples / input_groups;
    group_input_run_cost = input_run_cost / input_groups;
 
    /*
     * Estimate the average cost of sorting of one group where presorted keys
     * are equal.
     */
    cost_tuplesort(&group_startup_cost, &group_run_cost,
                   group_tuples, width, comparison_cost, sort_mem,
                   limit_tuples);
 
    /*
     * Startup cost of incremental sort is the startup cost of its first group
     * plus the cost of its input.
     */
    startup_cost = group_startup_cost + input_startup_cost +
        group_input_run_cost;
 
    /*
     * After we started producing tuples from the first group, the cost of
     * producing all the tuples is given by the cost to finish processing this
     * group, plus the total cost to process the remaining groups, plus the
     * remaining cost of input.
     */
    run_cost = group_run_cost + (group_run_cost + group_startup_cost) *
        (input_groups - 1) + group_input_run_cost * (input_groups - 1);
 
    /*
     * Incremental sort adds some overhead by itself. Firstly, it has to
     * detect the sort groups. This is roughly equal to one extra copy and
     * comparison per tuple.
     */
    run_cost += (cpu_tuple_cost + comparison_cost) * input_tuples;
 
    /*
     * Additionally, we charge double cpu_tuple_cost for each input group to
     * account for the tuplesort_reset that's performed after each group.
     */
    run_cost += 2.0 * cpu_tuple_cost * input_groups;
 
    path->rows = input_tuples;
    path->startup_cost = startup_cost;
    path->total_cost = startup_cost + run_cost;
}

References Assert(), bms_is_member(), cost_tuplesort(), cpu_tuple_cost, DEFAULT_NUM_DISTINCT, EquivalenceMember::em_expr, estimate_num_groups(), foreach_current_index, sort-test::key, lappend(), lfirst, linitial, list_length(), Min, NIL, pull_varnos(), Path::rows, Path::startup_cost, and Path::total_cost.

Referenced by create_incremental_sort_path().

cost_index()

void cost_index	(	IndexPath *	path,
		PlannerInfo *	root,
		double	loop_count,
		bool	partial_path
	)

Definition at line 521 of file costsize.c.

{
    IndexOptInfo *index = path->indexinfo;
    RelOptInfo *baserel = index->rel;
    bool        indexonly = (path->path.pathtype == T_IndexOnlyScan);
    amcostestimate_function amcostestimate;
    List       *qpquals;
    Cost        startup_cost = 0;
    Cost        run_cost = 0;
    Cost        cpu_run_cost = 0;
    Cost        indexStartupCost;
    Cost        indexTotalCost;
    Selectivity indexSelectivity;
    double      indexCorrelation,
                csquared;
    double      spc_seq_page_cost,
                spc_random_page_cost;
    Cost        min_IO_cost,
                max_IO_cost;
    QualCost    qpqual_cost;
    Cost        cpu_per_tuple;
    double      tuples_fetched;
    double      pages_fetched;
    double      rand_heap_pages;
    double      index_pages;
 
    /* Should only be applied to base relations */
    Assert(IsA(baserel, RelOptInfo) &&
           IsA(index, IndexOptInfo));
    Assert(baserel->relid > 0);
    Assert(baserel->rtekind == RTE_RELATION);
 
    /*
     * Mark the path with the correct row estimate, and identify which quals
     * will need to be enforced as qpquals.  We need not check any quals that
     * are implied by the index's predicate, so we can use indrestrictinfo not
     * baserestrictinfo as the list of relevant restriction clauses for the
     * rel.
     */
    if (path->path.param_info)
    {
        path->path.rows = path->path.param_info->ppi_rows;
        /* qpquals come from the rel's restriction clauses and ppi_clauses */
        qpquals = list_concat(extract_nonindex_conditions(path->indexinfo->indrestrictinfo,
                                                          path->indexclauses),
                              extract_nonindex_conditions(path->path.param_info->ppi_clauses,
                                                          path->indexclauses));
    }
    else
    {
        path->path.rows = baserel->rows;
        /* qpquals come from just the rel's restriction clauses */
        qpquals = extract_nonindex_conditions(path->indexinfo->indrestrictinfo,
                                              path->indexclauses);
    }
 
    if (!enable_indexscan)
        startup_cost += disable_cost;
    /* we don't need to check enable_indexonlyscan; indxpath.c does that */
 
    /*
     * Call index-access-method-specific code to estimate the processing cost
     * for scanning the index, as well as the selectivity of the index (ie,
     * the fraction of main-table tuples we will have to retrieve) and its
     * correlation to the main-table tuple order.  We need a cast here because
     * pathnodes.h uses a weak function type to avoid including amapi.h.
     */
    amcostestimate = (amcostestimate_function) index->amcostestimate;
    amcostestimate(root, path, loop_count,
                   &indexStartupCost, &indexTotalCost,
                   &indexSelectivity, &indexCorrelation,
                   &index_pages);
 
    /*
     * Save amcostestimate's results for possible use in bitmap scan planning.
     * We don't bother to save indexStartupCost or indexCorrelation, because a
     * bitmap scan doesn't care about either.
     */
    path->indextotalcost = indexTotalCost;
    path->indexselectivity = indexSelectivity;
 
    /* all costs for touching index itself included here */
    startup_cost += indexStartupCost;
    run_cost += indexTotalCost - indexStartupCost;
 
    /* estimate number of main-table tuples fetched */
    tuples_fetched = clamp_row_est(indexSelectivity * baserel->tuples);
 
    /* fetch estimated page costs for tablespace containing table */
    get_tablespace_page_costs(baserel->reltablespace,
                              &spc_random_page_cost,
                              &spc_seq_page_cost);
 
    /*----------
     * Estimate number of main-table pages fetched, and compute I/O cost.
     *
     * When the index ordering is uncorrelated with the table ordering,
     * we use an approximation proposed by Mackert and Lohman (see
     * index_pages_fetched() for details) to compute the number of pages
     * fetched, and then charge spc_random_page_cost per page fetched.
     *
     * When the index ordering is exactly correlated with the table ordering
     * (just after a CLUSTER, for example), the number of pages fetched should
     * be exactly selectivity * table_size.  What's more, all but the first
     * will be sequential fetches, not the random fetches that occur in the
     * uncorrelated case.  So if the number of pages is more than 1, we
     * ought to charge
     *      spc_random_page_cost + (pages_fetched - 1) * spc_seq_page_cost
     * For partially-correlated indexes, we ought to charge somewhere between
     * these two estimates.  We currently interpolate linearly between the
     * estimates based on the correlation squared (XXX is that appropriate?).
     *
     * If it's an index-only scan, then we will not need to fetch any heap
     * pages for which the visibility map shows all tuples are visible.
     * Hence, reduce the estimated number of heap fetches accordingly.
     * We use the measured fraction of the entire heap that is all-visible,
     * which might not be particularly relevant to the subset of the heap
     * that this query will fetch; but it's not clear how to do better.
     *----------
     */
    if (loop_count > 1)
    {
        /*
         * For repeated indexscans, the appropriate estimate for the
         * uncorrelated case is to scale up the number of tuples fetched in
         * the Mackert and Lohman formula by the number of scans, so that we
         * estimate the number of pages fetched by all the scans; then
         * pro-rate the costs for one scan.  In this case we assume all the
         * fetches are random accesses.
         */
        pages_fetched = index_pages_fetched(tuples_fetched * loop_count,
                                            baserel->pages,
                                            (double) index->pages,
                                            root);
 
        if (indexonly)
            pages_fetched = ceil(pages_fetched * (1.0 - baserel->allvisfrac));
 
        rand_heap_pages = pages_fetched;
 
        max_IO_cost = (pages_fetched * spc_random_page_cost) / loop_count;
 
        /*
         * In the perfectly correlated case, the number of pages touched by
         * each scan is selectivity * table_size, and we can use the Mackert
         * and Lohman formula at the page level to estimate how much work is
         * saved by caching across scans.  We still assume all the fetches are
         * random, though, which is an overestimate that's hard to correct for
         * without double-counting the cache effects.  (But in most cases
         * where such a plan is actually interesting, only one page would get
         * fetched per scan anyway, so it shouldn't matter much.)
         */
        pages_fetched = ceil(indexSelectivity * (double) baserel->pages);
 
        pages_fetched = index_pages_fetched(pages_fetched * loop_count,
                                            baserel->pages,
                                            (double) index->pages,
                                            root);
 
        if (indexonly)
            pages_fetched = ceil(pages_fetched * (1.0 - baserel->allvisfrac));
 
        min_IO_cost = (pages_fetched * spc_random_page_cost) / loop_count;
    }
    else
    {
        /*
         * Normal case: apply the Mackert and Lohman formula, and then
         * interpolate between that and the correlation-derived result.
         */
        pages_fetched = index_pages_fetched(tuples_fetched,
                                            baserel->pages,
                                            (double) index->pages,
                                            root);
 
        if (indexonly)
            pages_fetched = ceil(pages_fetched * (1.0 - baserel->allvisfrac));
 
        rand_heap_pages = pages_fetched;
 
        /* max_IO_cost is for the perfectly uncorrelated case (csquared=0) */
        max_IO_cost = pages_fetched * spc_random_page_cost;
 
        /* min_IO_cost is for the perfectly correlated case (csquared=1) */
        pages_fetched = ceil(indexSelectivity * (double) baserel->pages);
 
        if (indexonly)
            pages_fetched = ceil(pages_fetched * (1.0 - baserel->allvisfrac));
 
        if (pages_fetched > 0)
        {
            min_IO_cost = spc_random_page_cost;
            if (pages_fetched > 1)
                min_IO_cost += (pages_fetched - 1) * spc_seq_page_cost;
        }
        else
            min_IO_cost = 0;
    }
 
    if (partial_path)
    {
        /*
         * For index only scans compute workers based on number of index pages
         * fetched; the number of heap pages we fetch might be so small as to
         * effectively rule out parallelism, which we don't want to do.
         */
        if (indexonly)
            rand_heap_pages = -1;
 
        /*
         * Estimate the number of parallel workers required to scan index. Use
         * the number of heap pages computed considering heap fetches won't be
         * sequential as for parallel scans the pages are accessed in random
         * order.
         */
        path->path.parallel_workers = compute_parallel_worker(baserel,
                                                              rand_heap_pages,
                                                              index_pages,
                                                              max_parallel_workers_per_gather);
 
        /*
         * Fall out if workers can't be assigned for parallel scan, because in
         * such a case this path will be rejected.  So there is no benefit in
         * doing extra computation.
         */
        if (path->path.parallel_workers <= 0)
            return;
 
        path->path.parallel_aware = true;
    }
 
    /*
     * Now interpolate based on estimated index order correlation to get total
     * disk I/O cost for main table accesses.
     */
    csquared = indexCorrelation * indexCorrelation;
 
    run_cost += max_IO_cost + csquared * (min_IO_cost - max_IO_cost);
 
    /*
     * Estimate CPU costs per tuple.
     *
     * What we want here is cpu_tuple_cost plus the evaluation costs of any
     * qual clauses that we have to evaluate as qpquals.
     */
    cost_qual_eval(&qpqual_cost, qpquals, root);
 
    startup_cost += qpqual_cost.startup;
    cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple;
 
    cpu_run_cost += cpu_per_tuple * tuples_fetched;
 
    /* tlist eval costs are paid per output row, not per tuple scanned */
    startup_cost += path->path.pathtarget->cost.startup;
    cpu_run_cost += path->path.pathtarget->cost.per_tuple * path->path.rows;
 
    /* Adjust costing for parallelism, if used. */
    if (path->path.parallel_workers > 0)
    {
        double      parallel_divisor = get_parallel_divisor(&path->path);
 
        path->path.rows = clamp_row_est(path->path.rows / parallel_divisor);
 
        /* The CPU cost is divided among all the workers. */
        cpu_run_cost /= parallel_divisor;
    }
 
    run_cost += cpu_run_cost;
 
    path->path.startup_cost = startup_cost;
    path->path.total_cost = startup_cost + run_cost;
}

References RelOptInfo::allvisfrac, Assert(), clamp_row_est(), compute_parallel_worker(), cost_qual_eval(), cpu_tuple_cost, disable_cost, enable_indexscan, extract_nonindex_conditions(), get_parallel_divisor(), get_tablespace_page_costs(), index_pages_fetched(), IndexPath::indexclauses, IndexPath::indexinfo, IndexPath::indexselectivity, IndexPath::indextotalcost, IndexOptInfo::indrestrictinfo, IsA, list_concat(), max_parallel_workers_per_gather, RelOptInfo::pages, Path::parallel_aware, Path::parallel_workers, IndexPath::path, Path::pathtype, QualCost::per_tuple, RelOptInfo::relid, RelOptInfo::reltablespace, RelOptInfo::rows, Path::rows, RTE_RELATION, RelOptInfo::rtekind, QualCost::startup, Path::startup_cost, Path::total_cost, and RelOptInfo::tuples.

Referenced by create_index_path(), and reparameterize_path().

cost_material()

void cost_material	(	Path *	path,
		Cost	input_startup_cost,
		Cost	input_total_cost,
		double	tuples,
		int	width
	)

Definition at line 2425 of file costsize.c.

{
    Cost        startup_cost = input_startup_cost;
    Cost        run_cost = input_total_cost - input_startup_cost;
    double      nbytes = relation_byte_size(tuples, width);
    long        work_mem_bytes = work_mem * 1024L;
 
    path->rows = tuples;
 
    /*
     * Whether spilling or not, charge 2x cpu_operator_cost per tuple to
     * reflect bookkeeping overhead.  (This rate must be more than what
     * cost_rescan charges for materialize, ie, cpu_operator_cost per tuple;
     * if it is exactly the same then there will be a cost tie between
     * nestloop with A outer, materialized B inner and nestloop with B outer,
     * materialized A inner.  The extra cost ensures we'll prefer
     * materializing the smaller rel.)  Note that this is normally a good deal
     * less than cpu_tuple_cost; which is OK because a Material plan node
     * doesn't do qual-checking or projection, so it's got less overhead than
     * most plan nodes.
     */
    run_cost += 2 * cpu_operator_cost * tuples;
 
    /*
     * If we will spill to disk, charge at the rate of seq_page_cost per page.
     * This cost is assumed to be evenly spread through the plan run phase,
     * which isn't exactly accurate but our cost model doesn't allow for
     * nonuniform costs within the run phase.
     */
    if (nbytes > work_mem_bytes)
    {
        double      npages = ceil(nbytes / BLCKSZ);
 
        run_cost += seq_page_cost * npages;
    }
 
    path->startup_cost = startup_cost;
    path->total_cost = startup_cost + run_cost;
}

References cpu_operator_cost, relation_byte_size(), Path::rows, seq_page_cost, Path::startup_cost, Path::total_cost, and work_mem.

Referenced by create_material_path(), and materialize_finished_plan().

cost_memoize_rescan()

static void cost_memoize_rescan ( PlannerInfo *  root, MemoizePath *  mpath, Cost *  rescan_startup_cost, Cost *  rescan_total_cost  )

static

Definition at line 2481 of file costsize.c.

{
    EstimationInfo estinfo;
    ListCell   *lc;
    Cost        input_startup_cost = mpath->subpath->startup_cost;
    Cost        input_total_cost = mpath->subpath->total_cost;
    double      tuples = mpath->subpath->rows;
    double      calls = mpath->calls;
    int         width = mpath->subpath->pathtarget->width;
 
    double      hash_mem_bytes;
    double      est_entry_bytes;
    double      est_cache_entries;
    double      ndistinct;
    double      evict_ratio;
    double      hit_ratio;
    Cost        startup_cost;
    Cost        total_cost;
 
    /* available cache space */
    hash_mem_bytes = get_hash_memory_limit();
 
    /*
     * Set the number of bytes each cache entry should consume in the cache.
     * To provide us with better estimations on how many cache entries we can
     * store at once, we make a call to the executor here to ask it what
     * memory overheads there are for a single cache entry.
     */
    est_entry_bytes = relation_byte_size(tuples, width) +
        ExecEstimateCacheEntryOverheadBytes(tuples);
 
    /* include the estimated width for the cache keys */
    foreach(lc, mpath->param_exprs)
        est_entry_bytes += get_expr_width(root, (Node *) lfirst(lc));
 
    /* estimate on the upper limit of cache entries we can hold at once */
    est_cache_entries = floor(hash_mem_bytes / est_entry_bytes);
 
    /* estimate on the distinct number of parameter values */
    ndistinct = estimate_num_groups(root, mpath->param_exprs, calls, NULL,
                                    &estinfo);
 
    /*
     * When the estimation fell back on using a default value, it's a bit too
     * risky to assume that it's ok to use a Memoize node.  The use of a
     * default could cause us to use a Memoize node when it's really
     * inappropriate to do so.  If we see that this has been done, then we'll
     * assume that every call will have unique parameters, which will almost
     * certainly mean a MemoizePath will never survive add_path().
     */
    if ((estinfo.flags & SELFLAG_USED_DEFAULT) != 0)
        ndistinct = calls;
 
    /*
     * Since we've already estimated the maximum number of entries we can
     * store at once and know the estimated number of distinct values we'll be
     * called with, we'll take this opportunity to set the path's est_entries.
     * This will ultimately determine the hash table size that the executor
     * will use.  If we leave this at zero, the executor will just choose the
     * size itself.  Really this is not the right place to do this, but it's
     * convenient since everything is already calculated.
     */
    mpath->est_entries = Min(Min(ndistinct, est_cache_entries),
                             PG_UINT32_MAX);
 
    /*
     * When the number of distinct parameter values is above the amount we can
     * store in the cache, then we'll have to evict some entries from the
     * cache.  This is not free. Here we estimate how often we'll incur the
     * cost of that eviction.
     */
    evict_ratio = 1.0 - Min(est_cache_entries, ndistinct) / ndistinct;
 
    /*
     * In order to estimate how costly a single scan will be, we need to
     * attempt to estimate what the cache hit ratio will be.  To do that we
     * must look at how many scans are estimated in total for this node and
     * how many of those scans we expect to get a cache hit.
     */
    hit_ratio = ((calls - ndistinct) / calls) *
        (est_cache_entries / Max(ndistinct, est_cache_entries));
 
    Assert(hit_ratio >= 0 && hit_ratio <= 1.0);
 
    /*
     * Set the total_cost accounting for the expected cache hit ratio.  We
     * also add on a cpu_operator_cost to account for a cache lookup. This
     * will happen regardless of whether it's a cache hit or not.
     */
    total_cost = input_total_cost * (1.0 - hit_ratio) + cpu_operator_cost;
 
    /* Now adjust the total cost to account for cache evictions */
 
    /* Charge a cpu_tuple_cost for evicting the actual cache entry */
    total_cost += cpu_tuple_cost * evict_ratio;
 
    /*
     * Charge a 10th of cpu_operator_cost to evict every tuple in that entry.
     * The per-tuple eviction is really just a pfree, so charging a whole
     * cpu_operator_cost seems a little excessive.
     */
    total_cost += cpu_operator_cost / 10.0 * evict_ratio * tuples;
 
    /*
     * Now adjust for storing things in the cache, since that's not free
     * either.  Everything must go in the cache.  We don't proportion this
     * over any ratio, just apply it once for the scan.  We charge a
     * cpu_tuple_cost for the creation of the cache entry and also a
     * cpu_operator_cost for each tuple we expect to cache.
     */
    total_cost += cpu_tuple_cost + cpu_operator_cost * tuples;
 
    /*
     * Getting the first row must be also be proportioned according to the
     * expected cache hit ratio.
     */
    startup_cost = input_startup_cost * (1.0 - hit_ratio);
 
    /*
     * Additionally we charge a cpu_tuple_cost to account for cache lookups,
     * which we'll do regardless of whether it was a cache hit or not.
     */
    startup_cost += cpu_tuple_cost;
 
    *rescan_startup_cost = startup_cost;
    *rescan_total_cost = total_cost;
}

References Assert(), MemoizePath::calls, cpu_operator_cost, cpu_tuple_cost, MemoizePath::est_entries, estimate_num_groups(), ExecEstimateCacheEntryOverheadBytes(), EstimationInfo::flags, get_expr_width(), get_hash_memory_limit(), lfirst, Max, Min, MemoizePath::param_exprs, PG_UINT32_MAX, relation_byte_size(), Path::rows, SELFLAG_USED_DEFAULT, Path::startup_cost, MemoizePath::subpath, and Path::total_cost.

Referenced by cost_rescan().

cost_merge_append()

void cost_merge_append	(	Path *	path,
		PlannerInfo *	root,
		List *	pathkeys,
		int	n_streams,
		Cost	input_startup_cost,
		Cost	input_total_cost,
		double	tuples
	)

Definition at line 2376 of file costsize.c.

{
    Cost        startup_cost = 0;
    Cost        run_cost = 0;
    Cost        comparison_cost;
    double      N;
    double      logN;
 
    /*
     * Avoid log(0)...
     */
    N = (n_streams < 2) ? 2.0 : (double) n_streams;
    logN = LOG2(N);
 
    /* Assumed cost per tuple comparison */
    comparison_cost = 2.0 * cpu_operator_cost;
 
    /* Heap creation cost */
    startup_cost += comparison_cost * N * logN;
 
    /* Per-tuple heap maintenance cost */
    run_cost += tuples * comparison_cost * logN;
 
    /*
     * Although MergeAppend does not do any selection or projection, it's not
     * free; add a small per-tuple overhead.
     */
    run_cost += cpu_tuple_cost * APPEND_CPU_COST_MULTIPLIER * tuples;
 
    path->startup_cost = startup_cost + input_startup_cost;
    path->total_cost = startup_cost + run_cost + input_total_cost;
}

References APPEND_CPU_COST_MULTIPLIER, cpu_operator_cost, cpu_tuple_cost, LOG2, Path::startup_cost, and Path::total_cost.

Referenced by create_merge_append_path().

cost_namedtuplestorescan()

void cost_namedtuplestorescan	(	Path *	path,
		PlannerInfo *	root,
		RelOptInfo *	baserel,
		ParamPathInfo *	param_info
	)

Definition at line 1711 of file costsize.c.

{
    Cost        startup_cost = 0;
    Cost        run_cost = 0;
    QualCost    qpqual_cost;
    Cost        cpu_per_tuple;
 
    /* Should only be applied to base relations that are Tuplestores */
    Assert(baserel->relid > 0);
    Assert(baserel->rtekind == RTE_NAMEDTUPLESTORE);
 
    /* Mark the path with the correct row estimate */
    if (param_info)
        path->rows = param_info->ppi_rows;
    else
        path->rows = baserel->rows;
 
    /* Charge one CPU tuple cost per row for tuplestore manipulation */
    cpu_per_tuple = cpu_tuple_cost;
 
    /* Add scanning CPU costs */
    get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
 
    startup_cost += qpqual_cost.startup;
    cpu_per_tuple += cpu_tuple_cost + qpqual_cost.per_tuple;
    run_cost += cpu_per_tuple * baserel->tuples;
 
    path->startup_cost = startup_cost;
    path->total_cost = startup_cost + run_cost;
}

References Assert(), cpu_tuple_cost, get_restriction_qual_cost(), QualCost::per_tuple, ParamPathInfo::ppi_rows, RelOptInfo::relid, RelOptInfo::rows, Path::rows, RTE_NAMEDTUPLESTORE, RelOptInfo::rtekind, QualCost::startup, Path::startup_cost, Path::total_cost, and RelOptInfo::tuples.

Referenced by create_namedtuplestorescan_path().

cost_qual_eval()

void cost_qual_eval	(	QualCost *	cost,
		List *	quals,
		PlannerInfo *	root
	)

Definition at line 4370 of file costsize.c.

{
    cost_qual_eval_context context;
    ListCell   *l;
 
    context.root = root;
    context.total.startup = 0;
    context.total.per_tuple = 0;
 
    /* We don't charge any cost for the implicit ANDing at top level ... */
 
    foreach(l, quals)
    {
        Node       *qual = (Node *) lfirst(l);
 
        cost_qual_eval_walker(qual, &context);
    }
 
    *cost = context.total;
}

References cost_qual_eval_walker(), lfirst, QualCost::per_tuple, cost_qual_eval_context::root, QualCost::startup, and cost_qual_eval_context::total.

Referenced by add_foreign_grouping_paths(), cost_agg(), cost_group(), cost_index(), cost_subplan(), cost_tidrangescan(), cost_tidscan(), create_group_result_path(), create_minmaxagg_path(), estimate_path_cost_size(), final_cost_hashjoin(), final_cost_mergejoin(), final_cost_nestloop(), get_restriction_qual_cost(), inline_function(), plan_cluster_use_sort(), postgresGetForeignJoinPaths(), postgresGetForeignRelSize(), set_baserel_size_estimates(), and set_foreign_size_estimates().

cost_qual_eval_node()

void cost_qual_eval_node	(	QualCost *	cost,
		Node *	qual,
		PlannerInfo *	root
	)

Definition at line 4396 of file costsize.c.

{
    cost_qual_eval_context context;
 
    context.root = root;
    context.total.startup = 0;
    context.total.per_tuple = 0;
 
    cost_qual_eval_walker(qual, &context);
 
    *cost = context.total;
}

References cost_qual_eval_walker(), QualCost::per_tuple, cost_qual_eval_context::root, QualCost::startup, and cost_qual_eval_context::total.

Referenced by add_placeholders_to_joinrel(), cost_functionscan(), cost_qual_eval_walker(), cost_tablefuncscan(), cost_windowagg(), get_agg_clause_costs(), index_other_operands_eval_cost(), make_sort_input_target(), order_qual_clauses(), set_pathtarget_cost_width(), and set_rel_width().

cost_qual_eval_walker()

static bool cost_qual_eval_walker ( Node *  node, cost_qual_eval_context *  context  )

static

Definition at line 4410 of file costsize.c.

{
    if (node == NULL)
        return false;
 
    /*
     * RestrictInfo nodes contain an eval_cost field reserved for this
     * routine's use, so that it's not necessary to evaluate the qual clause's
     * cost more than once.  If the clause's cost hasn't been computed yet,
     * the field's startup value will contain -1.
     */
    if (IsA(node, RestrictInfo))
    {
        RestrictInfo *rinfo = (RestrictInfo *) node;
 
        if (rinfo->eval_cost.startup < 0)
        {
            cost_qual_eval_context locContext;
 
            locContext.root = context->root;
            locContext.total.startup = 0;
            locContext.total.per_tuple = 0;
 
            /*
             * For an OR clause, recurse into the marked-up tree so that we
             * set the eval_cost for contained RestrictInfos too.
             */
            if (rinfo->orclause)
                cost_qual_eval_walker((Node *) rinfo->orclause, &locContext);
            else
                cost_qual_eval_walker((Node *) rinfo->clause, &locContext);
 
            /*
             * If the RestrictInfo is marked pseudoconstant, it will be tested
             * only once, so treat its cost as all startup cost.
             */
            if (rinfo->pseudoconstant)
            {
                /* count one execution during startup */
                locContext.total.startup += locContext.total.per_tuple;
                locContext.total.per_tuple = 0;
            }
            rinfo->eval_cost = locContext.total;
        }
        context->total.startup += rinfo->eval_cost.startup;
        context->total.per_tuple += rinfo->eval_cost.per_tuple;
        /* do NOT recurse into children */
        return false;
    }
 
    /*
     * For each operator or function node in the given tree, we charge the
     * estimated execution cost given by pg_proc.procost (remember to multiply
     * this by cpu_operator_cost).
     *
     * Vars and Consts are charged zero, and so are boolean operators (AND,
     * OR, NOT). Simplistic, but a lot better than no model at all.
     *
     * Should we try to account for the possibility of short-circuit
     * evaluation of AND/OR?  Probably *not*, because that would make the
     * results depend on the clause ordering, and we are not in any position
     * to expect that the current ordering of the clauses is the one that's
     * going to end up being used.  The above per-RestrictInfo caching would
     * not mix well with trying to re-order clauses anyway.
     *
     * Another issue that is entirely ignored here is that if a set-returning
     * function is below top level in the tree, the functions/operators above
     * it will need to be evaluated multiple times.  In practical use, such
     * cases arise so seldom as to not be worth the added complexity needed;
     * moreover, since our rowcount estimates for functions tend to be pretty
     * phony, the results would also be pretty phony.
     */
    if (IsA(node, FuncExpr))
    {
        add_function_cost(context->root, ((FuncExpr *) node)->funcid, node,
                          &context->total);
    }
    else if (IsA(node, OpExpr) ||
             IsA(node, DistinctExpr) ||
             IsA(node, NullIfExpr))
    {
        /* rely on struct equivalence to treat these all alike */
        set_opfuncid((OpExpr *) node);
        add_function_cost(context->root, ((OpExpr *) node)->opfuncid, node,
                          &context->total);
    }
    else if (IsA(node, ScalarArrayOpExpr))
    {
        ScalarArrayOpExpr *saop = (ScalarArrayOpExpr *) node;
        Node       *arraynode = (Node *) lsecond(saop->args);
        QualCost    sacosts;
        QualCost    hcosts;
        int         estarraylen = estimate_array_length(arraynode);
 
        set_sa_opfuncid(saop);
        sacosts.startup = sacosts.per_tuple = 0;
        add_function_cost(context->root, saop->opfuncid, NULL,
                          &sacosts);
 
        if (OidIsValid(saop->hashfuncid))
        {
            /* Handle costs for hashed ScalarArrayOpExpr */
            hcosts.startup = hcosts.per_tuple = 0;
 
            add_function_cost(context->root, saop->hashfuncid, NULL, &hcosts);
            context->total.startup += sacosts.startup + hcosts.startup;
 
            /* Estimate the cost of building the hashtable. */
            context->total.startup += estarraylen * hcosts.per_tuple;
 
            /*
             * XXX should we charge a little bit for sacosts.per_tuple when
             * building the table, or is it ok to assume there will be zero
             * hash collision?
             */
 
            /*
             * Charge for hashtable lookups.  Charge a single hash and a
             * single comparison.
             */
            context->total.per_tuple += hcosts.per_tuple + sacosts.per_tuple;
        }
        else
        {
            /*
             * Estimate that the operator will be applied to about half of the
             * array elements before the answer is determined.
             */
            context->total.startup += sacosts.startup;
            context->total.per_tuple += sacosts.per_tuple *
                estimate_array_length(arraynode) * 0.5;
        }
    }
    else if (IsA(node, Aggref) ||
             IsA(node, WindowFunc))
    {
        /*
         * Aggref and WindowFunc nodes are (and should be) treated like Vars,
         * ie, zero execution cost in the current model, because they behave
         * essentially like Vars at execution.  We disregard the costs of
         * their input expressions for the same reason.  The actual execution
         * costs of the aggregate/window functions and their arguments have to
         * be factored into plan-node-specific costing of the Agg or WindowAgg
         * plan node.
         */
        return false;           /* don't recurse into children */
    }
    else if (IsA(node, GroupingFunc))
    {
        /* Treat this as having cost 1 */
        context->total.per_tuple += cpu_operator_cost;
        return false;           /* don't recurse into children */
    }
    else if (IsA(node, CoerceViaIO))
    {
        CoerceViaIO *iocoerce = (CoerceViaIO *) node;
        Oid         iofunc;
        Oid         typioparam;
        bool        typisvarlena;
 
        /* check the result type's input function */
        getTypeInputInfo(iocoerce->resulttype,
                         &iofunc, &typioparam);
        add_function_cost(context->root, iofunc, NULL,
                          &context->total);
        /* check the input type's output function */
        getTypeOutputInfo(exprType((Node *) iocoerce->arg),
                          &iofunc, &typisvarlena);
        add_function_cost(context->root, iofunc, NULL,
                          &context->total);
    }
    else if (IsA(node, ArrayCoerceExpr))
    {
        ArrayCoerceExpr *acoerce = (ArrayCoerceExpr *) node;
        QualCost    perelemcost;
 
        cost_qual_eval_node(&perelemcost, (Node *) acoerce->elemexpr,
                            context->root);
        context->total.startup += perelemcost.startup;
        if (perelemcost.per_tuple > 0)
            context->total.per_tuple += perelemcost.per_tuple *
                estimate_array_length((Node *) acoerce->arg);
    }
    else if (IsA(node, RowCompareExpr))
    {
        /* Conservatively assume we will check all the columns */
        RowCompareExpr *rcexpr = (RowCompareExpr *) node;
        ListCell   *lc;
 
        foreach(lc, rcexpr->opnos)
        {
            Oid         opid = lfirst_oid(lc);
 
            add_function_cost(context->root, get_opcode(opid), NULL,
                              &context->total);
        }
    }
    else if (IsA(node, MinMaxExpr) ||
             IsA(node, XmlExpr) ||
             IsA(node, CoerceToDomain) ||
             IsA(node, NextValueExpr))
    {
        /* Treat all these as having cost 1 */
        context->total.per_tuple += cpu_operator_cost;
    }
    else if (IsA(node, CurrentOfExpr))
    {
        /* Report high cost to prevent selection of anything but TID scan */
        context->total.startup += disable_cost;
    }
    else if (IsA(node, SubLink))
    {
        /* This routine should not be applied to un-planned expressions */
        elog(ERROR, "cannot handle unplanned sub-select");
    }
    else if (IsA(node, SubPlan))
    {
        /*
         * A subplan node in an expression typically indicates that the
         * subplan will be executed on each evaluation, so charge accordingly.
         * (Sub-selects that can be executed as InitPlans have already been
         * removed from the expression.)
         */
        SubPlan    *subplan = (SubPlan *) node;
 
        context->total.startup += subplan->startup_cost;
        context->total.per_tuple += subplan->per_call_cost;
 
        /*
         * We don't want to recurse into the testexpr, because it was already
         * counted in the SubPlan node's costs.  So we're done.
         */
        return false;
    }
    else if (IsA(node, AlternativeSubPlan))
    {
        /*
         * Arbitrarily use the first alternative plan for costing.  (We should
         * certainly only include one alternative, and we don't yet have
         * enough information to know which one the executor is most likely to
         * use.)
         */
        AlternativeSubPlan *asplan = (AlternativeSubPlan *) node;
 
        return cost_qual_eval_walker((Node *) linitial(asplan->subplans),
                                     context);
    }
    else if (IsA(node, PlaceHolderVar))
    {
        /*
         * A PlaceHolderVar should be given cost zero when considering general
         * expression evaluation costs.  The expense of doing the contained
         * expression is charged as part of the tlist eval costs of the scan
         * or join where the PHV is first computed (see set_rel_width and
         * add_placeholders_to_joinrel).  If we charged it again here, we'd be
         * double-counting the cost for each level of plan that the PHV
         * bubbles up through.  Hence, return without recursing into the
         * phexpr.
         */
        return false;
    }
 
    /* recurse into children */
    return expression_tree_walker(node, cost_qual_eval_walker,
                                  (void *) context);
}

References add_function_cost(), CoerceViaIO::arg, ArrayCoerceExpr::arg, ScalarArrayOpExpr::args, RestrictInfo::clause, cost_qual_eval_node(), cpu_operator_cost, disable_cost, ArrayCoerceExpr::elemexpr, elog(), ERROR, estimate_array_length(), expression_tree_walker, exprType(), get_opcode(), getTypeInputInfo(), getTypeOutputInfo(), IsA, lfirst_oid, linitial, lsecond, OidIsValid, SubPlan::per_call_cost, QualCost::per_tuple, CoerceViaIO::resulttype, cost_qual_eval_context::root, set_opfuncid(), set_sa_opfuncid(), QualCost::startup, SubPlan::startup_cost, AlternativeSubPlan::subplans, and cost_qual_eval_context::total.

Referenced by cost_qual_eval(), and cost_qual_eval_node().

cost_recursive_union()

void cost_recursive_union	(	Path *	runion,
		Path *	nrterm,
		Path *	rterm
	)

Definition at line 1785 of file costsize.c.

{
    Cost        startup_cost;
    Cost        total_cost;
    double      total_rows;
 
    /* We probably have decent estimates for the non-recursive term */
    startup_cost = nrterm->startup_cost;
    total_cost = nrterm->total_cost;
    total_rows = nrterm->rows;
 
    /*
     * We arbitrarily assume that about 10 recursive iterations will be
     * needed, and that we've managed to get a good fix on the cost and output
     * size of each one of them.  These are mighty shaky assumptions but it's
     * hard to see how to do better.
     */
    total_cost += 10 * rterm->total_cost;
    total_rows += 10 * rterm->rows;
 
    /*
     * Also charge cpu_tuple_cost per row to account for the costs of
     * manipulating the tuplestores.  (We don't worry about possible
     * spill-to-disk costs.)
     */
    total_cost += cpu_tuple_cost * total_rows;
 
    runion->startup_cost = startup_cost;
    runion->total_cost = total_cost;
    runion->rows = total_rows;
    runion->pathtarget->width = Max(nrterm->pathtarget->width,
                                    rterm->pathtarget->width);
}

References cpu_tuple_cost, Max, Path::rows, Path::startup_cost, and Path::total_cost.

Referenced by create_recursiveunion_path().

cost_rescan()

static void cost_rescan ( PlannerInfo *  root, Path *  path, Cost *  rescan_startup_cost, Cost *  rescan_total_cost  )

static

Definition at line 4258 of file costsize.c.

{
    switch (path->pathtype)
    {
        case T_FunctionScan:
 
            /*
             * Currently, nodeFunctionscan.c always executes the function to
             * completion before returning any rows, and caches the results in
             * a tuplestore.  So the function eval cost is all startup cost
             * and isn't paid over again on rescans. However, all run costs
             * will be paid over again.
             */
            *rescan_startup_cost = 0;
            *rescan_total_cost = path->total_cost - path->startup_cost;
            break;
        case T_HashJoin:
 
            /*
             * If it's a single-batch join, we don't need to rebuild the hash
             * table during a rescan.
             */
            if (((HashPath *) path)->num_batches == 1)
            {
                /* Startup cost is exactly the cost of hash table building */
                *rescan_startup_cost = 0;
                *rescan_total_cost = path->total_cost - path->startup_cost;
            }
            else
            {
                /* Otherwise, no special treatment */
                *rescan_startup_cost = path->startup_cost;
                *rescan_total_cost = path->total_cost;
            }
            break;
        case T_CteScan:
        case T_WorkTableScan:
            {
                /*
                 * These plan types materialize their final result in a
                 * tuplestore or tuplesort object.  So the rescan cost is only
                 * cpu_tuple_cost per tuple, unless the result is large enough
                 * to spill to disk.
                 */
                Cost        run_cost = cpu_tuple_cost * path->rows;
                double      nbytes = relation_byte_size(path->rows,
                                                        path->pathtarget->width);
                long        work_mem_bytes = work_mem * 1024L;
 
                if (nbytes > work_mem_bytes)
                {
                    /* It will spill, so account for re-read cost */
                    double      npages = ceil(nbytes / BLCKSZ);
 
                    run_cost += seq_page_cost * npages;
                }
                *rescan_startup_cost = 0;
                *rescan_total_cost = run_cost;
            }
            break;
        case T_Material:
        case T_Sort:
            {
                /*
                 * These plan types not only materialize their results, but do
                 * not implement qual filtering or projection.  So they are
                 * even cheaper to rescan than the ones above.  We charge only
                 * cpu_operator_cost per tuple.  (Note: keep that in sync with
                 * the run_cost charge in cost_sort, and also see comments in
                 * cost_material before you change it.)
                 */
                Cost        run_cost = cpu_operator_cost * path->rows;
                double      nbytes = relation_byte_size(path->rows,
                                                        path->pathtarget->width);
                long        work_mem_bytes = work_mem * 1024L;
 
                if (nbytes > work_mem_bytes)
                {
                    /* It will spill, so account for re-read cost */
                    double      npages = ceil(nbytes / BLCKSZ);
 
                    run_cost += seq_page_cost * npages;
                }
                *rescan_startup_cost = 0;
                *rescan_total_cost = run_cost;
            }
            break;
        case T_Memoize:
            /* All the hard work is done by cost_memoize_rescan */
            cost_memoize_rescan(root, (MemoizePath *) path,
                                rescan_startup_cost, rescan_total_cost);
            break;
        default:
            *rescan_startup_cost = path->startup_cost;
            *rescan_total_cost = path->total_cost;
            break;
    }
}

References cost_memoize_rescan(), cpu_operator_cost, cpu_tuple_cost, Path::pathtype, relation_byte_size(), seq_page_cost, Path::startup_cost, Path::total_cost, and work_mem.

Referenced by initial_cost_nestloop().

cost_resultscan()

void cost_resultscan	(	Path *	path,
		PlannerInfo *	root,
		RelOptInfo *	baserel,
		ParamPathInfo *	param_info
	)

Definition at line 1748 of file costsize.c.

{
    Cost        startup_cost = 0;
    Cost        run_cost = 0;
    QualCost    qpqual_cost;
    Cost        cpu_per_tuple;
 
    /* Should only be applied to RTE_RESULT base relations */
    Assert(baserel->relid > 0);
    Assert(baserel->rtekind == RTE_RESULT);
 
    /* Mark the path with the correct row estimate */
    if (param_info)
        path->rows = param_info->ppi_rows;
    else
        path->rows = baserel->rows;
 
    /* We charge qual cost plus cpu_tuple_cost */
    get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
 
    startup_cost += qpqual_cost.startup;
    cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple;
    run_cost += cpu_per_tuple * baserel->tuples;
 
    path->startup_cost = startup_cost;
    path->total_cost = startup_cost + run_cost;
}

References Assert(), cpu_tuple_cost, get_restriction_qual_cost(), QualCost::per_tuple, ParamPathInfo::ppi_rows, RelOptInfo::relid, RelOptInfo::rows, Path::rows, RTE_RESULT, RelOptInfo::rtekind, QualCost::startup, Path::startup_cost, Path::total_cost, and RelOptInfo::tuples.

Referenced by create_resultscan_path().

cost_samplescan()

void cost_samplescan	(	Path *	path,
		PlannerInfo *	root,
		RelOptInfo *	baserel,
		ParamPathInfo *	param_info
	)

Definition at line 333 of file costsize.c.

{
    Cost        startup_cost = 0;
    Cost        run_cost = 0;
    RangeTblEntry *rte;
    TableSampleClause *tsc;
    TsmRoutine *tsm;
    double      spc_seq_page_cost,
                spc_random_page_cost,
                spc_page_cost;
    QualCost    qpqual_cost;
    Cost        cpu_per_tuple;
 
    /* Should only be applied to base relations with tablesample clauses */
    Assert(baserel->relid > 0);
    rte = planner_rt_fetch(baserel->relid, root);
    Assert(rte->rtekind == RTE_RELATION);
    tsc = rte->tablesample;
    Assert(tsc != NULL);
    tsm = GetTsmRoutine(tsc->tsmhandler);
 
    /* Mark the path with the correct row estimate */
    if (param_info)
        path->rows = param_info->ppi_rows;
    else
        path->rows = baserel->rows;
 
    /* fetch estimated page cost for tablespace containing table */
    get_tablespace_page_costs(baserel->reltablespace,
                              &spc_random_page_cost,
                              &spc_seq_page_cost);
 
    /* if NextSampleBlock is used, assume random access, else sequential */
    spc_page_cost = (tsm->NextSampleBlock != NULL) ?
        spc_random_page_cost : spc_seq_page_cost;
 
    /*
     * disk costs (recall that baserel->pages has already been set to the
     * number of pages the sampling method will visit)
     */
    run_cost += spc_page_cost * baserel->pages;
 
    /*
     * CPU costs (recall that baserel->tuples has already been set to the
     * number of tuples the sampling method will select).  Note that we ignore
     * execution cost of the TABLESAMPLE parameter expressions; they will be
     * evaluated only once per scan, and in most usages they'll likely be
     * simple constants anyway.  We also don't charge anything for the
     * calculations the sampling method might do internally.
     */
    get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
 
    startup_cost += qpqual_cost.startup;
    cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple;
    run_cost += cpu_per_tuple * baserel->tuples;
    /* tlist eval costs are paid per output row, not per tuple scanned */
    startup_cost += path->pathtarget->cost.startup;
    run_cost += path->pathtarget->cost.per_tuple * path->rows;
 
    path->startup_cost = startup_cost;
    path->total_cost = startup_cost + run_cost;
}

References Assert(), cpu_tuple_cost, get_restriction_qual_cost(), get_tablespace_page_costs(), GetTsmRoutine(), TsmRoutine::NextSampleBlock, RelOptInfo::pages, QualCost::per_tuple, planner_rt_fetch, ParamPathInfo::ppi_rows, RelOptInfo::relid, RelOptInfo::reltablespace, RelOptInfo::rows, Path::rows, RTE_RELATION, RangeTblEntry::rtekind, QualCost::startup, Path::startup_cost, RangeTblEntry::tablesample, Path::total_cost, TableSampleClause::tsmhandler, and RelOptInfo::tuples.

Referenced by create_samplescan_path().

cost_seqscan()

void cost_seqscan	(	Path *	path,
		PlannerInfo *	root,
		RelOptInfo *	baserel,
		ParamPathInfo *	param_info
	)

Definition at line 256 of file costsize.c.

{
    Cost        startup_cost = 0;
    Cost        cpu_run_cost;
    Cost        disk_run_cost;
    double      spc_seq_page_cost;
    QualCost    qpqual_cost;
    Cost        cpu_per_tuple;
 
    /* Should only be applied to base relations */
    Assert(baserel->relid > 0);
    Assert(baserel->rtekind == RTE_RELATION);
 
    /* Mark the path with the correct row estimate */
    if (param_info)
        path->rows = param_info->ppi_rows;
    else
        path->rows = baserel->rows;
 
    if (!enable_seqscan)
        startup_cost += disable_cost;
 
    /* fetch estimated page cost for tablespace containing table */
    get_tablespace_page_costs(baserel->reltablespace,
                              NULL,
                              &spc_seq_page_cost);
 
    /*
     * disk costs
     */
    disk_run_cost = spc_seq_page_cost * baserel->pages;
 
    /* CPU costs */
    get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
 
    startup_cost += qpqual_cost.startup;
    cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple;
    cpu_run_cost = cpu_per_tuple * baserel->tuples;
    /* tlist eval costs are paid per output row, not per tuple scanned */
    startup_cost += path->pathtarget->cost.startup;
    cpu_run_cost += path->pathtarget->cost.per_tuple * path->rows;
 
    /* Adjust costing for parallelism, if used. */
    if (path->parallel_workers > 0)
    {
        double      parallel_divisor = get_parallel_divisor(path);
 
        /* The CPU cost is divided among all the workers. */
        cpu_run_cost /= parallel_divisor;
 
        /*
         * It may be possible to amortize some of the I/O cost, but probably
         * not very much, because most operating systems already do aggressive
         * prefetching.  For now, we assume that the disk run cost can't be
         * amortized at all.
         */
 
        /*
         * In the case of a parallel plan, the row count needs to represent
         * the number of tuples processed per worker.
         */
        path->rows = clamp_row_est(path->rows / parallel_divisor);
    }
 
    path->startup_cost = startup_cost;
    path->total_cost = startup_cost + cpu_run_cost + disk_run_cost;
}

References Assert(), clamp_row_est(), cpu_tuple_cost, disable_cost, enable_seqscan, get_parallel_divisor(), get_restriction_qual_cost(), get_tablespace_page_costs(), RelOptInfo::pages, Path::parallel_workers, QualCost::per_tuple, ParamPathInfo::ppi_rows, RelOptInfo::relid, RelOptInfo::reltablespace, RelOptInfo::rows, Path::rows, RTE_RELATION, RelOptInfo::rtekind, QualCost::startup, Path::startup_cost, Path::total_cost, and RelOptInfo::tuples.

Referenced by create_seqscan_path().

cost_sort()

void cost_sort	(	Path *	path,
		PlannerInfo *	root,
		List *	pathkeys,
		Cost	input_cost,
		double	tuples,
		int	width,
		Cost	comparison_cost,
		int	sort_mem,
		double	limit_tuples
	)

Definition at line 2096 of file costsize.c.

{
    Cost        startup_cost;
    Cost        run_cost;
 
    cost_tuplesort(&startup_cost, &run_cost,
                   tuples, width,
                   comparison_cost, sort_mem,
                   limit_tuples);
 
    if (!enable_sort)
        startup_cost += disable_cost;
 
    startup_cost += input_cost;
 
    path->rows = tuples;
    path->startup_cost = startup_cost;
    path->total_cost = startup_cost + run_cost;
}

References cost_tuplesort(), disable_cost, enable_sort, Path::rows, Path::startup_cost, and Path::total_cost.

Referenced by adjust_foreign_grouping_path_cost(), choose_hashed_setop(), cost_append(), create_gather_merge_path(), create_groupingsets_path(), create_merge_append_path(), create_sort_path(), create_unique_path(), initial_cost_mergejoin(), label_sort_with_costsize(), and plan_cluster_use_sort().

cost_subplan()

void cost_subplan	(	PlannerInfo *	root,
		SubPlan *	subplan,
		Plan *	plan
	)

Definition at line 4165 of file costsize.c.

{
    QualCost    sp_cost;
 
    /* Figure any cost for evaluating the testexpr */
    cost_qual_eval(&sp_cost,
                   make_ands_implicit((Expr *) subplan->testexpr),
                   root);
 
    if (subplan->useHashTable)
    {
        /*
         * If we are using a hash table for the subquery outputs, then the
         * cost of evaluating the query is a one-time cost.  We charge one
         * cpu_operator_cost per tuple for the work of loading the hashtable,
         * too.
         */
        sp_cost.startup += plan->total_cost +
            cpu_operator_cost * plan->plan_rows;
 
        /*
         * The per-tuple costs include the cost of evaluating the lefthand
         * expressions, plus the cost of probing the hashtable.  We already
         * accounted for the lefthand expressions as part of the testexpr, and
         * will also have counted one cpu_operator_cost for each comparison
         * operator.  That is probably too low for the probing cost, but it's
         * hard to make a better estimate, so live with it for now.
         */
    }
    else
    {
        /*
         * Otherwise we will be rescanning the subplan output on each
         * evaluation.  We need to estimate how much of the output we will
         * actually need to scan.  NOTE: this logic should agree with the
         * tuple_fraction estimates used by make_subplan() in
         * plan/subselect.c.
         */
        Cost        plan_run_cost = plan->total_cost - plan->startup_cost;
 
        if (subplan->subLinkType == EXISTS_SUBLINK)
        {
            /* we only need to fetch 1 tuple; clamp to avoid zero divide */
            sp_cost.per_tuple += plan_run_cost / clamp_row_est(plan->plan_rows);
        }
        else if (subplan->subLinkType == ALL_SUBLINK ||
                 subplan->subLinkType == ANY_SUBLINK)
        {
            /* assume we need 50% of the tuples */
            sp_cost.per_tuple += 0.50 * plan_run_cost;
            /* also charge a cpu_operator_cost per row examined */
            sp_cost.per_tuple += 0.50 * plan->plan_rows * cpu_operator_cost;
        }
        else
        {
            /* assume we need all tuples */
            sp_cost.per_tuple += plan_run_cost;
        }
 
        /*
         * Also account for subplan's startup cost. If the subplan is
         * uncorrelated or undirect correlated, AND its topmost node is one
         * that materializes its output, assume that we'll only need to pay
         * its startup cost once; otherwise assume we pay the startup cost
         * every time.
         */
        if (subplan->parParam == NIL &&
            ExecMaterializesOutput(nodeTag(plan)))
            sp_cost.startup += plan->startup_cost;
        else
            sp_cost.per_tuple += plan->startup_cost;
    }
 
    subplan->startup_cost = sp_cost.startup;
    subplan->per_call_cost = sp_cost.per_tuple;
}

References ALL_SUBLINK, ANY_SUBLINK, clamp_row_est(), cost_qual_eval(), cpu_operator_cost, ExecMaterializesOutput(), EXISTS_SUBLINK, make_ands_implicit(), NIL, nodeTag, SubPlan::parParam, SubPlan::per_call_cost, QualCost::per_tuple, plan, QualCost::startup, SubPlan::startup_cost, SubPlan::subLinkType, SubPlan::testexpr, and SubPlan::useHashTable.

Referenced by build_subplan(), SS_make_initplan_from_plan(), and SS_process_ctes().

cost_subqueryscan()

void cost_subqueryscan	(	SubqueryScanPath *	path,
		PlannerInfo *	root,
		RelOptInfo *	baserel,
		ParamPathInfo *	param_info,
		bool	trivial_pathtarget
	)

Definition at line 1423 of file costsize.c.

{
    Cost        startup_cost;
    Cost        run_cost;
    List       *qpquals;
    QualCost    qpqual_cost;
    Cost        cpu_per_tuple;
 
    /* Should only be applied to base relations that are subqueries */
    Assert(baserel->relid > 0);
    Assert(baserel->rtekind == RTE_SUBQUERY);
 
    /*
     * We compute the rowcount estimate as the subplan's estimate times the
     * selectivity of relevant restriction clauses.  In simple cases this will
     * come out the same as baserel->rows; but when dealing with parallelized
     * paths we must do it like this to get the right answer.
     */
    if (param_info)
        qpquals = list_concat_copy(param_info->ppi_clauses,
                                   baserel->baserestrictinfo);
    else
        qpquals = baserel->baserestrictinfo;
 
    path->path.rows = clamp_row_est(path->subpath->rows *
                                    clauselist_selectivity(root,
                                                           qpquals,
                                                           0,
                                                           JOIN_INNER,
                                                           NULL));
 
    /*
     * Cost of path is cost of evaluating the subplan, plus cost of evaluating
     * any restriction clauses and tlist that will be attached to the
     * SubqueryScan node, plus cpu_tuple_cost to account for selection and
     * projection overhead.
     */
    path->path.startup_cost = path->subpath->startup_cost;
    path->path.total_cost = path->subpath->total_cost;
 
    /*
     * However, if there are no relevant restriction clauses and the
     * pathtarget is trivial, then we expect that setrefs.c will optimize away
     * the SubqueryScan plan node altogether, so we should just make its cost
     * and rowcount equal to the input path's.
     *
     * Note: there are some edge cases where createplan.c will apply a
     * different targetlist to the SubqueryScan node, thus falsifying our
     * current estimate of whether the target is trivial, and making the cost
     * estimate (though not the rowcount) wrong.  It does not seem worth the
     * extra complication to try to account for that exactly, especially since
     * that behavior falsifies other cost estimates as well.
     */
    if (qpquals == NIL && trivial_pathtarget)
        return;
 
    get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
 
    startup_cost = qpqual_cost.startup;
    cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple;
    run_cost = cpu_per_tuple * path->subpath->rows;
 
    /* tlist eval costs are paid per output row, not per tuple scanned */
    startup_cost += path->path.pathtarget->cost.startup;
    run_cost += path->path.pathtarget->cost.per_tuple * path->path.rows;
 
    path->path.startup_cost += startup_cost;
    path->path.total_cost += startup_cost + run_cost;
}

References Assert(), RelOptInfo::baserestrictinfo, clamp_row_est(), clauselist_selectivity(), cpu_tuple_cost, get_restriction_qual_cost(), JOIN_INNER, list_concat_copy(), NIL, SubqueryScanPath::path, QualCost::per_tuple, ParamPathInfo::ppi_clauses, RelOptInfo::relid, Path::rows, RTE_SUBQUERY, RelOptInfo::rtekind, QualCost::startup, Path::startup_cost, SubqueryScanPath::subpath, and Path::total_cost.

Referenced by create_subqueryscan_path().

cost_tablefuncscan()

void cost_tablefuncscan	(	Path *	path,
		PlannerInfo *	root,
		RelOptInfo *	baserel,
		ParamPathInfo *	param_info
	)

Definition at line 1564 of file costsize.c.

{
    Cost        startup_cost = 0;
    Cost        run_cost = 0;
    QualCost    qpqual_cost;
    Cost        cpu_per_tuple;
    RangeTblEntry *rte;
    QualCost    exprcost;
 
    /* Should only be applied to base relations that are functions */
    Assert(baserel->relid > 0);
    rte = planner_rt_fetch(baserel->relid, root);
    Assert(rte->rtekind == RTE_TABLEFUNC);
 
    /* Mark the path with the correct row estimate */
    if (param_info)
        path->rows = param_info->ppi_rows;
    else
        path->rows = baserel->rows;
 
    /*
     * Estimate costs of executing the table func expression(s).
     *
     * XXX in principle we ought to charge tuplestore spill costs if the
     * number of rows is large.  However, given how phony our rowcount
     * estimates for tablefuncs tend to be, there's not a lot of point in that
     * refinement right now.
     */
    cost_qual_eval_node(&exprcost, (Node *) rte->tablefunc, root);
 
    startup_cost += exprcost.startup + exprcost.per_tuple;
 
    /* Add scanning CPU costs */
    get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
 
    startup_cost += qpqual_cost.startup;
    cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple;
    run_cost += cpu_per_tuple * baserel->tuples;
 
    /* tlist eval costs are paid per output row, not per tuple scanned */
    startup_cost += path->pathtarget->cost.startup;
    run_cost += path->pathtarget->cost.per_tuple * path->rows;
 
    path->startup_cost = startup_cost;
    path->total_cost = startup_cost + run_cost;
}

References Assert(), cost_qual_eval_node(), cpu_tuple_cost, get_restriction_qual_cost(), QualCost::per_tuple, planner_rt_fetch, ParamPathInfo::ppi_rows, RelOptInfo::relid, RelOptInfo::rows, Path::rows, RTE_TABLEFUNC, RangeTblEntry::rtekind, QualCost::startup, Path::startup_cost, RangeTblEntry::tablefunc, Path::total_cost, and RelOptInfo::tuples.

Referenced by create_tablefuncscan_path().

cost_tidrangescan()

void cost_tidrangescan	(	Path *	path,
		PlannerInfo *	root,
		RelOptInfo *	baserel,
		List *	tidrangequals,
		ParamPathInfo *	param_info
	)

Definition at line 1329 of file costsize.c.

{
    Selectivity selectivity;
    double      pages;
    Cost        startup_cost = 0;
    Cost        run_cost = 0;
    QualCost    qpqual_cost;
    Cost        cpu_per_tuple;
    QualCost    tid_qual_cost;
    double      ntuples;
    double      nseqpages;
    double      spc_random_page_cost;
    double      spc_seq_page_cost;
 
    /* Should only be applied to base relations */
    Assert(baserel->relid > 0);
    Assert(baserel->rtekind == RTE_RELATION);
 
    /* Mark the path with the correct row estimate */
    if (param_info)
        path->rows = param_info->ppi_rows;
    else
        path->rows = baserel->rows;
 
    /* Count how many tuples and pages we expect to scan */
    selectivity = clauselist_selectivity(root, tidrangequals, baserel->relid,
                                         JOIN_INNER, NULL);
    pages = ceil(selectivity * baserel->pages);
 
    if (pages <= 0.0)
        pages = 1.0;
 
    /*
     * The first page in a range requires a random seek, but each subsequent
     * page is just a normal sequential page read. NOTE: it's desirable for
     * TID Range Scans to cost more than the equivalent Sequential Scans,
     * because Seq Scans have some performance advantages such as scan
     * synchronization and parallelizability, and we'd prefer one of them to
     * be picked unless a TID Range Scan really is better.
     */
    ntuples = selectivity * baserel->tuples;
    nseqpages = pages - 1.0;
 
    if (!enable_tidscan)
        startup_cost += disable_cost;
 
    /*
     * The TID qual expressions will be computed once, any other baserestrict
     * quals once per retrieved tuple.
     */
    cost_qual_eval(&tid_qual_cost, tidrangequals, root);
 
    /* fetch estimated page cost for tablespace containing table */
    get_tablespace_page_costs(baserel->reltablespace,
                              &spc_random_page_cost,
                              &spc_seq_page_cost);
 
    /* disk costs; 1 random page and the remainder as seq pages */
    run_cost += spc_random_page_cost + spc_seq_page_cost * nseqpages;
 
    /* Add scanning CPU costs */
    get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
 
    /*
     * XXX currently we assume TID quals are a subset of qpquals at this
     * point; they will be removed (if possible) when we create the plan, so
     * we subtract their cost from the total qpqual cost.  (If the TID quals
     * can't be removed, this is a mistake and we're going to underestimate
     * the CPU cost a bit.)
     */
    startup_cost += qpqual_cost.startup + tid_qual_cost.per_tuple;
    cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple -
        tid_qual_cost.per_tuple;
    run_cost += cpu_per_tuple * ntuples;
 
    /* tlist eval costs are paid per output row, not per tuple scanned */
    startup_cost += path->pathtarget->cost.startup;
    run_cost += path->pathtarget->cost.per_tuple * path->rows;
 
    path->startup_cost = startup_cost;
    path->total_cost = startup_cost + run_cost;
}

References Assert(), clauselist_selectivity(), cost_qual_eval(), cpu_tuple_cost, disable_cost, enable_tidscan, get_restriction_qual_cost(), get_tablespace_page_costs(), JOIN_INNER, RelOptInfo::pages, QualCost::per_tuple, ParamPathInfo::ppi_rows, RelOptInfo::relid, RelOptInfo::reltablespace, RelOptInfo::rows, Path::rows, RTE_RELATION, RelOptInfo::rtekind, QualCost::startup, Path::startup_cost, Path::total_cost, and RelOptInfo::tuples.

Referenced by create_tidrangescan_path().

cost_tidscan()

void cost_tidscan	(	Path *	path,
		PlannerInfo *	root,
		RelOptInfo *	baserel,
		List *	tidquals,
		ParamPathInfo *	param_info
	)

Definition at line 1221 of file costsize.c.

{
    Cost        startup_cost = 0;
    Cost        run_cost = 0;
    bool        isCurrentOf = false;
    QualCost    qpqual_cost;
    Cost        cpu_per_tuple;
    QualCost    tid_qual_cost;
    int         ntuples;
    ListCell   *l;
    double      spc_random_page_cost;
 
    /* Should only be applied to base relations */
    Assert(baserel->relid > 0);
    Assert(baserel->rtekind == RTE_RELATION);
 
    /* Mark the path with the correct row estimate */
    if (param_info)
        path->rows = param_info->ppi_rows;
    else
        path->rows = baserel->rows;
 
    /* Count how many tuples we expect to retrieve */
    ntuples = 0;
    foreach(l, tidquals)
    {
        RestrictInfo *rinfo = lfirst_node(RestrictInfo, l);
        Expr       *qual = rinfo->clause;
 
        if (IsA(qual, ScalarArrayOpExpr))
        {
            /* Each element of the array yields 1 tuple */
            ScalarArrayOpExpr *saop = (ScalarArrayOpExpr *) qual;
            Node       *arraynode = (Node *) lsecond(saop->args);
 
            ntuples += estimate_array_length(arraynode);
        }
        else if (IsA(qual, CurrentOfExpr))
        {
            /* CURRENT OF yields 1 tuple */
            isCurrentOf = true;
            ntuples++;
        }
        else
        {
            /* It's just CTID = something, count 1 tuple */
            ntuples++;
        }
    }
 
    /*
     * We must force TID scan for WHERE CURRENT OF, because only nodeTidscan.c
     * understands how to do it correctly.  Therefore, honor enable_tidscan
     * only when CURRENT OF isn't present.  Also note that cost_qual_eval
     * counts a CurrentOfExpr as having startup cost disable_cost, which we
     * subtract off here; that's to prevent other plan types such as seqscan
     * from winning.
     */
    if (isCurrentOf)
    {
        Assert(baserel->baserestrictcost.startup >= disable_cost);
        startup_cost -= disable_cost;
    }
    else if (!enable_tidscan)
        startup_cost += disable_cost;
 
    /*
     * The TID qual expressions will be computed once, any other baserestrict
     * quals once per retrieved tuple.
     */
    cost_qual_eval(&tid_qual_cost, tidquals, root);
 
    /* fetch estimated page cost for tablespace containing table */
    get_tablespace_page_costs(baserel->reltablespace,
                              &spc_random_page_cost,
                              NULL);
 
    /* disk costs --- assume each tuple on a different page */
    run_cost += spc_random_page_cost * ntuples;
 
    /* Add scanning CPU costs */
    get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
 
    /* XXX currently we assume TID quals are a subset of qpquals */
    startup_cost += qpqual_cost.startup + tid_qual_cost.per_tuple;
    cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple -
        tid_qual_cost.per_tuple;
    run_cost += cpu_per_tuple * ntuples;
 
    /* tlist eval costs are paid per output row, not per tuple scanned */
    startup_cost += path->pathtarget->cost.startup;
    run_cost += path->pathtarget->cost.per_tuple * path->rows;
 
    path->startup_cost = startup_cost;
    path->total_cost = startup_cost + run_cost;
}

References ScalarArrayOpExpr::args, Assert(), RelOptInfo::baserestrictcost, RestrictInfo::clause, cost_qual_eval(), cpu_tuple_cost, disable_cost, enable_tidscan, estimate_array_length(), get_restriction_qual_cost(), get_tablespace_page_costs(), IsA, lfirst_node, lsecond, QualCost::per_tuple, ParamPathInfo::ppi_rows, RelOptInfo::relid, RelOptInfo::reltablespace, RelOptInfo::rows, Path::rows, RTE_RELATION, RelOptInfo::rtekind, QualCost::startup, Path::startup_cost, and Path::total_cost.

Referenced by create_tidscan_path().

cost_tuplesort()

static void cost_tuplesort ( Cost *  startup_cost, Cost *  run_cost, double  tuples, int  width, Cost  comparison_cost, int  sort_mem, double  limit_tuples  )

static

Definition at line 1856 of file costsize.c.

{
    double      input_bytes = relation_byte_size(tuples, width);
    double      output_bytes;
    double      output_tuples;
    long        sort_mem_bytes = sort_mem * 1024L;
 
    /*
     * We want to be sure the cost of a sort is never estimated as zero, even
     * if passed-in tuple count is zero.  Besides, mustn't do log(0)...
     */
    if (tuples < 2.0)
        tuples = 2.0;
 
    /* Include the default cost-per-comparison */
    comparison_cost += 2.0 * cpu_operator_cost;
 
    /* Do we have a useful LIMIT? */
    if (limit_tuples > 0 && limit_tuples < tuples)
    {
        output_tuples = limit_tuples;
        output_bytes = relation_byte_size(output_tuples, width);
    }
    else
    {
        output_tuples = tuples;
        output_bytes = input_bytes;
    }
 
    if (output_bytes > sort_mem_bytes)
    {
        /*
         * We'll have to use a disk-based sort of all the tuples
         */
        double      npages = ceil(input_bytes / BLCKSZ);
        double      nruns = input_bytes / sort_mem_bytes;
        double      mergeorder = tuplesort_merge_order(sort_mem_bytes);
        double      log_runs;
        double      npageaccesses;
 
        /*
         * CPU costs
         *
         * Assume about N log2 N comparisons
         */
        *startup_cost = comparison_cost * tuples * LOG2(tuples);
 
        /* Disk costs */
 
        /* Compute logM(r) as log(r) / log(M) */
        if (nruns > mergeorder)
            log_runs = ceil(log(nruns) / log(mergeorder));
        else
            log_runs = 1.0;
        npageaccesses = 2.0 * npages * log_runs;
        /* Assume 3/4ths of accesses are sequential, 1/4th are not */
        *startup_cost += npageaccesses *
            (seq_page_cost * 0.75 + random_page_cost * 0.25);
    }
    else if (tuples > 2 * output_tuples || input_bytes > sort_mem_bytes)
    {
        /*
         * We'll use a bounded heap-sort keeping just K tuples in memory, for
         * a total number of tuple comparisons of N log2 K; but the constant
         * factor is a bit higher than for quicksort.  Tweak it so that the
         * cost curve is continuous at the crossover point.
         */
        *startup_cost = comparison_cost * tuples * LOG2(2.0 * output_tuples);
    }
    else
    {
        /* We'll use plain quicksort on all the input tuples */
        *startup_cost = comparison_cost * tuples * LOG2(tuples);
    }
 
    /*
     * Also charge a small amount (arbitrarily set equal to operator cost) per
     * extracted tuple.  We don't charge cpu_tuple_cost because a Sort node
     * doesn't do qual-checking or projection, so it has less overhead than
     * most plan nodes.  Note it's correct to use tuples not output_tuples
     * here --- the upper LIMIT will pro-rate the run cost so we'd be double
     * counting the LIMIT otherwise.
     */
    *run_cost = cpu_operator_cost * tuples;
}

References cpu_operator_cost, LOG2, random_page_cost, relation_byte_size(), seq_page_cost, and tuplesort_merge_order().

Referenced by cost_incremental_sort(), and cost_sort().

cost_valuesscan()

void cost_valuesscan	(	Path *	path,
		PlannerInfo *	root,
		RelOptInfo *	baserel,
		ParamPathInfo *	param_info
	)

Definition at line 1620 of file costsize.c.

{
    Cost        startup_cost = 0;
    Cost        run_cost = 0;
    QualCost    qpqual_cost;
    Cost        cpu_per_tuple;
 
    /* Should only be applied to base relations that are values lists */
    Assert(baserel->relid > 0);
    Assert(baserel->rtekind == RTE_VALUES);
 
    /* Mark the path with the correct row estimate */
    if (param_info)
        path->rows = param_info->ppi_rows;
    else
        path->rows = baserel->rows;
 
    /*
     * For now, estimate list evaluation cost at one operator eval per list
     * (probably pretty bogus, but is it worth being smarter?)
     */
    cpu_per_tuple = cpu_operator_cost;
 
    /* Add scanning CPU costs */
    get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
 
    startup_cost += qpqual_cost.startup;
    cpu_per_tuple += cpu_tuple_cost + qpqual_cost.per_tuple;
    run_cost += cpu_per_tuple * baserel->tuples;
 
    /* tlist eval costs are paid per output row, not per tuple scanned */
    startup_cost += path->pathtarget->cost.startup;
    run_cost += path->pathtarget->cost.per_tuple * path->rows;
 
    path->startup_cost = startup_cost;
    path->total_cost = startup_cost + run_cost;
}

References Assert(), cpu_operator_cost, cpu_tuple_cost, get_restriction_qual_cost(), QualCost::per_tuple, ParamPathInfo::ppi_rows, RelOptInfo::relid, RelOptInfo::rows, Path::rows, RTE_VALUES, RelOptInfo::rtekind, QualCost::startup, Path::startup_cost, Path::total_cost, and RelOptInfo::tuples.

Referenced by create_valuesscan_path().

cost_windowagg()

void cost_windowagg	(	Path *	path,
		PlannerInfo *	root,
		List *	windowFuncs,
		int	numPartCols,
		int	numOrderCols,
		Cost	input_startup_cost,
		Cost	input_total_cost,
		double	input_tuples
	)

Definition at line 2820 of file costsize.c.

{
    Cost        startup_cost;
    Cost        total_cost;
    ListCell   *lc;
 
    startup_cost = input_startup_cost;
    total_cost = input_total_cost;
 
    /*
     * Window functions are assumed to cost their stated execution cost, plus
     * the cost of evaluating their input expressions, per tuple.  Since they
     * may in fact evaluate their inputs at multiple rows during each cycle,
     * this could be a drastic underestimate; but without a way to know how
     * many rows the window function will fetch, it's hard to do better.  In
     * any case, it's a good estimate for all the built-in window functions,
     * so we'll just do this for now.
     */
    foreach(lc, windowFuncs)
    {
        WindowFunc *wfunc = lfirst_node(WindowFunc, lc);
        Cost        wfunccost;
        QualCost    argcosts;
 
        argcosts.startup = argcosts.per_tuple = 0;
        add_function_cost(root, wfunc->winfnoid, (Node *) wfunc,
                          &argcosts);
        startup_cost += argcosts.startup;
        wfunccost = argcosts.per_tuple;
 
        /* also add the input expressions' cost to per-input-row costs */
        cost_qual_eval_node(&argcosts, (Node *) wfunc->args, root);
        startup_cost += argcosts.startup;
        wfunccost += argcosts.per_tuple;
 
        /*
         * Add the filter's cost to per-input-row costs.  XXX We should reduce
         * input expression costs according to filter selectivity.
         */
        cost_qual_eval_node(&argcosts, (Node *) wfunc->aggfilter, root);
        startup_cost += argcosts.startup;
        wfunccost += argcosts.per_tuple;
 
        total_cost += wfunccost * input_tuples;
    }
 
    /*
     * We also charge cpu_operator_cost per grouping column per tuple for
     * grouping comparisons, plus cpu_tuple_cost per tuple for general
     * overhead.
     *
     * XXX this neglects costs of spooling the data to disk when it overflows
     * work_mem.  Sooner or later that should get accounted for.
     */
    total_cost += cpu_operator_cost * (numPartCols + numOrderCols) * input_tuples;
    total_cost += cpu_tuple_cost * input_tuples;
 
    path->rows = input_tuples;
    path->startup_cost = startup_cost;
    path->total_cost = total_cost;
}

References add_function_cost(), WindowFunc::aggfilter, WindowFunc::args, cost_qual_eval_node(), cpu_operator_cost, cpu_tuple_cost, lfirst_node, QualCost::per_tuple, Path::rows, QualCost::startup, Path::startup_cost, Path::total_cost, and WindowFunc::winfnoid.

Referenced by create_windowagg_path().

extract_nonindex_conditions()

static List * extract_nonindex_conditions ( List *  qual_clauses, List *  indexclauses  )

static

Definition at line 812 of file costsize.c.

{
    List       *result = NIL;
    ListCell   *lc;
 
    foreach(lc, qual_clauses)
    {
        RestrictInfo *rinfo = lfirst_node(RestrictInfo, lc);
 
        if (rinfo->pseudoconstant)
            continue;           /* we may drop pseudoconstants here */
        if (is_redundant_with_indexclauses(rinfo, indexclauses))
            continue;           /* dup or derived from same EquivalenceClass */
        /* ... skip the predicate proof attempt createplan.c will try ... */
        result = lappend(result, rinfo);
    }
    return result;
}

References is_redundant_with_indexclauses(), lappend(), lfirst_node, and NIL.

Referenced by cost_index().

final_cost_hashjoin()

void final_cost_hashjoin	(	PlannerInfo *	root,
		HashPath *	path,
		JoinCostWorkspace *	workspace,
		JoinPathExtraData *	extra
	)

Definition at line 3911 of file costsize.c.

{
    Path       *outer_path = path->jpath.outerjoinpath;
    Path       *inner_path = path->jpath.innerjoinpath;
    double      outer_path_rows = outer_path->rows;
    double      inner_path_rows = inner_path->rows;
    double      inner_path_rows_total = workspace->inner_rows_total;
    List       *hashclauses = path->path_hashclauses;
    Cost        startup_cost = workspace->startup_cost;
    Cost        run_cost = workspace->run_cost;
    int         numbuckets = workspace->numbuckets;
    int         numbatches = workspace->numbatches;
    Cost        cpu_per_tuple;
    QualCost    hash_qual_cost;
    QualCost    qp_qual_cost;
    double      hashjointuples;
    double      virtualbuckets;
    Selectivity innerbucketsize;
    Selectivity innermcvfreq;
    ListCell   *hcl;
 
    /* Mark the path with the correct row estimate */
    if (path->jpath.path.param_info)
        path->jpath.path.rows = path->jpath.path.param_info->ppi_rows;
    else
        path->jpath.path.rows = path->jpath.path.parent->rows;
 
    /* For partial paths, scale row estimate. */
    if (path->jpath.path.parallel_workers > 0)
    {
        double      parallel_divisor = get_parallel_divisor(&path->jpath.path);
 
        path->jpath.path.rows =
            clamp_row_est(path->jpath.path.rows / parallel_divisor);
    }
 
    /*
     * We could include disable_cost in the preliminary estimate, but that
     * would amount to optimizing for the case where the join method is
     * disabled, which doesn't seem like the way to bet.
     */
    if (!enable_hashjoin)
        startup_cost += disable_cost;
 
    /* mark the path with estimated # of batches */
    path->num_batches = numbatches;
 
    /* store the total number of tuples (sum of partial row estimates) */
    path->inner_rows_total = inner_path_rows_total;
 
    /* and compute the number of "virtual" buckets in the whole join */
    virtualbuckets = (double) numbuckets * (double) numbatches;
 
    /*
     * Determine bucketsize fraction and MCV frequency for the inner relation.
     * We use the smallest bucketsize or MCV frequency estimated for any
     * individual hashclause; this is undoubtedly conservative.
     *
     * BUT: if inner relation has been unique-ified, we can assume it's good
     * for hashing.  This is important both because it's the right answer, and
     * because we avoid contaminating the cache with a value that's wrong for
     * non-unique-ified paths.
     */
    if (IsA(inner_path, UniquePath))
    {
        innerbucketsize = 1.0 / virtualbuckets;
        innermcvfreq = 0.0;
    }
    else
    {
        innerbucketsize = 1.0;
        innermcvfreq = 1.0;
        foreach(hcl, hashclauses)
        {
            RestrictInfo *restrictinfo = lfirst_node(RestrictInfo, hcl);
            Selectivity thisbucketsize;
            Selectivity thismcvfreq;
 
            /*
             * First we have to figure out which side of the hashjoin clause
             * is the inner side.
             *
             * Since we tend to visit the same clauses over and over when
             * planning a large query, we cache the bucket stats estimates in
             * the RestrictInfo node to avoid repeated lookups of statistics.
             */
            if (bms_is_subset(restrictinfo->right_relids,
                              inner_path->parent->relids))
            {
                /* righthand side is inner */
                thisbucketsize = restrictinfo->right_bucketsize;
                if (thisbucketsize < 0)
                {
                    /* not cached yet */
                    estimate_hash_bucket_stats(root,
                                               get_rightop(restrictinfo->clause),
                                               virtualbuckets,
                                               &restrictinfo->right_mcvfreq,
                                               &restrictinfo->right_bucketsize);
                    thisbucketsize = restrictinfo->right_bucketsize;
                }
                thismcvfreq = restrictinfo->right_mcvfreq;
            }
            else
            {
                Assert(bms_is_subset(restrictinfo->left_relids,
                                     inner_path->parent->relids));
                /* lefthand side is inner */
                thisbucketsize = restrictinfo->left_bucketsize;
                if (thisbucketsize < 0)
                {
                    /* not cached yet */
                    estimate_hash_bucket_stats(root,
                                               get_leftop(restrictinfo->clause),
                                               virtualbuckets,
                                               &restrictinfo->left_mcvfreq,
                                               &restrictinfo->left_bucketsize);
                    thisbucketsize = restrictinfo->left_bucketsize;
                }
                thismcvfreq = restrictinfo->left_mcvfreq;
            }
 
            if (innerbucketsize > thisbucketsize)
                innerbucketsize = thisbucketsize;
            if (innermcvfreq > thismcvfreq)
                innermcvfreq = thismcvfreq;
        }
    }
 
    /*
     * If the bucket holding the inner MCV would exceed hash_mem, we don't
     * want to hash unless there is really no other alternative, so apply
     * disable_cost.  (The executor normally copes with excessive memory usage
     * by splitting batches, but obviously it cannot separate equal values
     * that way, so it will be unable to drive the batch size below hash_mem
     * when this is true.)
     */
    if (relation_byte_size(clamp_row_est(inner_path_rows * innermcvfreq),
                           inner_path->pathtarget->width) > get_hash_memory_limit())
        startup_cost += disable_cost;
 
    /*
     * Compute cost of the hashquals and qpquals (other restriction clauses)
     * separately.
     */
    cost_qual_eval(&hash_qual_cost, hashclauses, root);
    cost_qual_eval(&qp_qual_cost, path->jpath.joinrestrictinfo, root);
    qp_qual_cost.startup -= hash_qual_cost.startup;
    qp_qual_cost.per_tuple -= hash_qual_cost.per_tuple;
 
    /* CPU costs */
 
    if (path->jpath.jointype == JOIN_SEMI ||
        path->jpath.jointype == JOIN_ANTI ||
        extra->inner_unique)
    {
        double      outer_matched_rows;
        Selectivity inner_scan_frac;
 
        /*
         * With a SEMI or ANTI join, or if the innerrel is known unique, the
         * executor will stop after the first match.
         *
         * For an outer-rel row that has at least one match, we can expect the
         * bucket scan to stop after a fraction 1/(match_count+1) of the
         * bucket's rows, if the matches are evenly distributed.  Since they
         * probably aren't quite evenly distributed, we apply a fuzz factor of
         * 2.0 to that fraction.  (If we used a larger fuzz factor, we'd have
         * to clamp inner_scan_frac to at most 1.0; but since match_count is
         * at least 1, no such clamp is needed now.)
         */
        outer_matched_rows = rint(outer_path_rows * extra->semifactors.outer_match_frac);
        inner_scan_frac = 2.0 / (extra->semifactors.match_count + 1.0);
 
        startup_cost += hash_qual_cost.startup;
        run_cost += hash_qual_cost.per_tuple * outer_matched_rows *
            clamp_row_est(inner_path_rows * innerbucketsize * inner_scan_frac) * 0.5;
 
        /*
         * For unmatched outer-rel rows, the picture is quite a lot different.
         * In the first place, there is no reason to assume that these rows
         * preferentially hit heavily-populated buckets; instead assume they
         * are uncorrelated with the inner distribution and so they see an
         * average bucket size of inner_path_rows / virtualbuckets.  In the
         * second place, it seems likely that they will have few if any exact
         * hash-code matches and so very few of the tuples in the bucket will
         * actually require eval of the hash quals.  We don't have any good
         * way to estimate how many will, but for the moment assume that the
         * effective cost per bucket entry is one-tenth what it is for
         * matchable tuples.
         */
        run_cost += hash_qual_cost.per_tuple *
            (outer_path_rows - outer_matched_rows) *
            clamp_row_est(inner_path_rows / virtualbuckets) * 0.05;
 
        /* Get # of tuples that will pass the basic join */
        if (path->jpath.jointype == JOIN_ANTI)
            hashjointuples = outer_path_rows - outer_matched_rows;
        else
            hashjointuples = outer_matched_rows;
    }
    else
    {
        /*
         * The number of tuple comparisons needed is the number of outer
         * tuples times the typical number of tuples in a hash bucket, which
         * is the inner relation size times its bucketsize fraction.  At each
         * one, we need to evaluate the hashjoin quals.  But actually,
         * charging the full qual eval cost at each tuple is pessimistic,
         * since we don't evaluate the quals unless the hash values match
         * exactly.  For lack of a better idea, halve the cost estimate to
         * allow for that.
         */
        startup_cost += hash_qual_cost.startup;
        run_cost += hash_qual_cost.per_tuple * outer_path_rows *
            clamp_row_est(inner_path_rows * innerbucketsize) * 0.5;
 
        /*
         * Get approx # tuples passing the hashquals.  We use
         * approx_tuple_count here because we need an estimate done with
         * JOIN_INNER semantics.
         */
        hashjointuples = approx_tuple_count(root, &path->jpath, hashclauses);
    }
 
    /*
     * For each tuple that gets through the hashjoin proper, we charge
     * cpu_tuple_cost plus the cost of evaluating additional restriction
     * clauses that are to be applied at the join.  (This is pessimistic since
     * not all of the quals may get evaluated at each tuple.)
     */
    startup_cost += qp_qual_cost.startup;
    cpu_per_tuple = cpu_tuple_cost + qp_qual_cost.per_tuple;
    run_cost += cpu_per_tuple * hashjointuples;
 
    /* tlist eval costs are paid per output row, not per tuple scanned */
    startup_cost += path->jpath.path.pathtarget->cost.startup;
    run_cost += path->jpath.path.pathtarget->cost.per_tuple * path->jpath.path.rows;
 
    path->jpath.path.startup_cost = startup_cost;
    path->jpath.path.total_cost = startup_cost + run_cost;
}

References approx_tuple_count(), Assert(), bms_is_subset(), clamp_row_est(), RestrictInfo::clause, cost_qual_eval(), cpu_tuple_cost, disable_cost, enable_hashjoin, estimate_hash_bucket_stats(), get_hash_memory_limit(), get_leftop(), get_parallel_divisor(), get_rightop(), HashPath::inner_rows_total, JoinCostWorkspace::inner_rows_total, JoinPathExtraData::inner_unique, JoinPath::innerjoinpath, IsA, JOIN_ANTI, JOIN_SEMI, JoinPath::joinrestrictinfo, JoinPath::jointype, HashPath::jpath, lfirst_node, SemiAntiJoinFactors::match_count, HashPath::num_batches, JoinCostWorkspace::numbatches, JoinCostWorkspace::numbuckets, SemiAntiJoinFactors::outer_match_frac, JoinPath::outerjoinpath, HashPath::path_hashclauses, QualCost::per_tuple, relation_byte_size(), Path::rows, JoinCostWorkspace::run_cost, JoinPathExtraData::semifactors, QualCost::startup, and JoinCostWorkspace::startup_cost.

Referenced by create_hashjoin_path().

final_cost_mergejoin()

void final_cost_mergejoin	(	PlannerInfo *	root,
		MergePath *	path,
		JoinCostWorkspace *	workspace,
		JoinPathExtraData *	extra
	)

Definition at line 3475 of file costsize.c.

{
    Path       *outer_path = path->jpath.outerjoinpath;
    Path       *inner_path = path->jpath.innerjoinpath;
    double      inner_path_rows = inner_path->rows;
    List       *mergeclauses = path->path_mergeclauses;
    List       *innersortkeys = path->innersortkeys;
    Cost        startup_cost = workspace->startup_cost;
    Cost        run_cost = workspace->run_cost;
    Cost        inner_run_cost = workspace->inner_run_cost;
    double      outer_rows = workspace->outer_rows;
    double      inner_rows = workspace->inner_rows;
    double      outer_skip_rows = workspace->outer_skip_rows;
    double      inner_skip_rows = workspace->inner_skip_rows;
    Cost        cpu_per_tuple,
                bare_inner_cost,
                mat_inner_cost;
    QualCost    merge_qual_cost;
    QualCost    qp_qual_cost;
    double      mergejointuples,
                rescannedtuples;
    double      rescanratio;
 
    /* Protect some assumptions below that rowcounts aren't zero */
    if (inner_path_rows <= 0)
        inner_path_rows = 1;
 
    /* Mark the path with the correct row estimate */
    if (path->jpath.path.param_info)
        path->jpath.path.rows = path->jpath.path.param_info->ppi_rows;
    else
        path->jpath.path.rows = path->jpath.path.parent->rows;
 
    /* For partial paths, scale row estimate. */
    if (path->jpath.path.parallel_workers > 0)
    {
        double      parallel_divisor = get_parallel_divisor(&path->jpath.path);
 
        path->jpath.path.rows =
            clamp_row_est(path->jpath.path.rows / parallel_divisor);
    }
 
    /*
     * We could include disable_cost in the preliminary estimate, but that
     * would amount to optimizing for the case where the join method is
     * disabled, which doesn't seem like the way to bet.
     */
    if (!enable_mergejoin)
        startup_cost += disable_cost;
 
    /*
     * Compute cost of the mergequals and qpquals (other restriction clauses)
     * separately.
     */
    cost_qual_eval(&merge_qual_cost, mergeclauses, root);
    cost_qual_eval(&qp_qual_cost, path->jpath.joinrestrictinfo, root);
    qp_qual_cost.startup -= merge_qual_cost.startup;
    qp_qual_cost.per_tuple -= merge_qual_cost.per_tuple;
 
    /*
     * With a SEMI or ANTI join, or if the innerrel is known unique, the
     * executor will stop scanning for matches after the first match.  When
     * all the joinclauses are merge clauses, this means we don't ever need to
     * back up the merge, and so we can skip mark/restore overhead.
     */
    if ((path->jpath.jointype == JOIN_SEMI ||
         path->jpath.jointype == JOIN_ANTI ||
         extra->inner_unique) &&
        (list_length(path->jpath.joinrestrictinfo) ==
         list_length(path->path_mergeclauses)))
        path->skip_mark_restore = true;
    else
        path->skip_mark_restore = false;
 
    /*
     * Get approx # tuples passing the mergequals.  We use approx_tuple_count
     * here because we need an estimate done with JOIN_INNER semantics.
     */
    mergejointuples = approx_tuple_count(root, &path->jpath, mergeclauses);
 
    /*
     * When there are equal merge keys in the outer relation, the mergejoin
     * must rescan any matching tuples in the inner relation. This means
     * re-fetching inner tuples; we have to estimate how often that happens.
     *
     * For regular inner and outer joins, the number of re-fetches can be
     * estimated approximately as size of merge join output minus size of
     * inner relation. Assume that the distinct key values are 1, 2, ..., and
     * denote the number of values of each key in the outer relation as m1,
     * m2, ...; in the inner relation, n1, n2, ...  Then we have
     *
     * size of join = m1 * n1 + m2 * n2 + ...
     *
     * number of rescanned tuples = (m1 - 1) * n1 + (m2 - 1) * n2 + ... = m1 *
     * n1 + m2 * n2 + ... - (n1 + n2 + ...) = size of join - size of inner
     * relation
     *
     * This equation works correctly for outer tuples having no inner match
     * (nk = 0), but not for inner tuples having no outer match (mk = 0); we
     * are effectively subtracting those from the number of rescanned tuples,
     * when we should not.  Can we do better without expensive selectivity
     * computations?
     *
     * The whole issue is moot if we are working from a unique-ified outer
     * input, or if we know we don't need to mark/restore at all.
     */
    if (IsA(outer_path, UniquePath) || path->skip_mark_restore)
        rescannedtuples = 0;
    else
    {
        rescannedtuples = mergejointuples - inner_path_rows;
        /* Must clamp because of possible underestimate */
        if (rescannedtuples < 0)
            rescannedtuples = 0;
    }
 
    /*
     * We'll inflate various costs this much to account for rescanning.  Note
     * that this is to be multiplied by something involving inner_rows, or
     * another number related to the portion of the inner rel we'll scan.
     */
    rescanratio = 1.0 + (rescannedtuples / inner_rows);
 
    /*
     * Decide whether we want to materialize the inner input to shield it from
     * mark/restore and performing re-fetches.  Our cost model for regular
     * re-fetches is that a re-fetch costs the same as an original fetch,
     * which is probably an overestimate; but on the other hand we ignore the
     * bookkeeping costs of mark/restore.  Not clear if it's worth developing
     * a more refined model.  So we just need to inflate the inner run cost by
     * rescanratio.
     */
    bare_inner_cost = inner_run_cost * rescanratio;
 
    /*
     * When we interpose a Material node the re-fetch cost is assumed to be
     * just cpu_operator_cost per tuple, independently of the underlying
     * plan's cost; and we charge an extra cpu_operator_cost per original
     * fetch as well.  Note that we're assuming the materialize node will
     * never spill to disk, since it only has to remember tuples back to the
     * last mark.  (If there are a huge number of duplicates, our other cost
     * factors will make the path so expensive that it probably won't get
     * chosen anyway.)  So we don't use cost_rescan here.
     *
     * Note: keep this estimate in sync with create_mergejoin_plan's labeling
     * of the generated Material node.
     */
    mat_inner_cost = inner_run_cost +
        cpu_operator_cost * inner_rows * rescanratio;
 
    /*
     * If we don't need mark/restore at all, we don't need materialization.
     */
    if (path->skip_mark_restore)
        path->materialize_inner = false;
 
    /*
     * Prefer materializing if it looks cheaper, unless the user has asked to
     * suppress materialization.
     */
    else if (enable_material && mat_inner_cost < bare_inner_cost)
        path->materialize_inner = true;
 
    /*
     * Even if materializing doesn't look cheaper, we *must* do it if the
     * inner path is to be used directly (without sorting) and it doesn't
     * support mark/restore.
     *
     * Since the inner side must be ordered, and only Sorts and IndexScans can
     * create order to begin with, and they both support mark/restore, you
     * might think there's no problem --- but you'd be wrong.  Nestloop and
     * merge joins can *preserve* the order of their inputs, so they can be
     * selected as the input of a mergejoin, and they don't support
     * mark/restore at present.
     *
     * We don't test the value of enable_material here, because
     * materialization is required for correctness in this case, and turning
     * it off does not entitle us to deliver an invalid plan.
     */
    else if (innersortkeys == NIL &&
             !ExecSupportsMarkRestore(inner_path))
        path->materialize_inner = true;
 
    /*
     * Also, force materializing if the inner path is to be sorted and the
     * sort is expected to spill to disk.  This is because the final merge
     * pass can be done on-the-fly if it doesn't have to support mark/restore.
     * We don't try to adjust the cost estimates for this consideration,
     * though.
     *
     * Since materialization is a performance optimization in this case,
     * rather than necessary for correctness, we skip it if enable_material is
     * off.
     */
    else if (enable_material && innersortkeys != NIL &&
             relation_byte_size(inner_path_rows,
                                inner_path->pathtarget->width) >
             (work_mem * 1024L))
        path->materialize_inner = true;
    else
        path->materialize_inner = false;
 
    /* Charge the right incremental cost for the chosen case */
    if (path->materialize_inner)
        run_cost += mat_inner_cost;
    else
        run_cost += bare_inner_cost;
 
    /* CPU costs */
 
    /*
     * The number of tuple comparisons needed is approximately number of outer
     * rows plus number of inner rows plus number of rescanned tuples (can we
     * refine this?).  At each one, we need to evaluate the mergejoin quals.
     */
    startup_cost += merge_qual_cost.startup;
    startup_cost += merge_qual_cost.per_tuple *
        (outer_skip_rows + inner_skip_rows * rescanratio);
    run_cost += merge_qual_cost.per_tuple *
        ((outer_rows - outer_skip_rows) +
         (inner_rows - inner_skip_rows) * rescanratio);
 
    /*
     * For each tuple that gets through the mergejoin proper, we charge
     * cpu_tuple_cost plus the cost of evaluating additional restriction
     * clauses that are to be applied at the join.  (This is pessimistic since
     * not all of the quals may get evaluated at each tuple.)
     *
     * Note: we could adjust for SEMI/ANTI joins skipping some qual
     * evaluations here, but it's probably not worth the trouble.
     */
    startup_cost += qp_qual_cost.startup;
    cpu_per_tuple = cpu_tuple_cost + qp_qual_cost.per_tuple;
    run_cost += cpu_per_tuple * mergejointuples;
 
    /* tlist eval costs are paid per output row, not per tuple scanned */
    startup_cost += path->jpath.path.pathtarget->cost.startup;
    run_cost += path->jpath.path.pathtarget->cost.per_tuple * path->jpath.path.rows;
 
    path->jpath.path.startup_cost = startup_cost;
    path->jpath.path.total_cost = startup_cost + run_cost;
}

References approx_tuple_count(), clamp_row_est(), cost_qual_eval(), cpu_operator_cost, cpu_tuple_cost, disable_cost, enable_material, enable_mergejoin, ExecSupportsMarkRestore(), get_parallel_divisor(), if(), JoinCostWorkspace::inner_rows, JoinCostWorkspace::inner_run_cost, JoinCostWorkspace::inner_skip_rows, JoinPathExtraData::inner_unique, JoinPath::innerjoinpath, MergePath::innersortkeys, IsA, JOIN_ANTI, JOIN_SEMI, JoinPath::joinrestrictinfo, JoinPath::jointype, MergePath::jpath, list_length(), MergePath::materialize_inner, NIL, JoinCostWorkspace::outer_rows, JoinCostWorkspace::outer_skip_rows, JoinPath::outerjoinpath, MergePath::path_mergeclauses, QualCost::per_tuple, relation_byte_size(), Path::rows, JoinCostWorkspace::run_cost, MergePath::skip_mark_restore, QualCost::startup, JoinCostWorkspace::startup_cost, and work_mem.

Referenced by create_mergejoin_path().

final_cost_nestloop()

void final_cost_nestloop	(	PlannerInfo *	root,
		NestPath *	path,
		JoinCostWorkspace *	workspace,
		JoinPathExtraData *	extra
	)

Definition at line 3039 of file costsize.c.

{
    Path       *outer_path = path->jpath.outerjoinpath;
    Path       *inner_path = path->jpath.innerjoinpath;
    double      outer_path_rows = outer_path->rows;
    double      inner_path_rows = inner_path->rows;
    Cost        startup_cost = workspace->startup_cost;
    Cost        run_cost = workspace->run_cost;
    Cost        cpu_per_tuple;
    QualCost    restrict_qual_cost;
    double      ntuples;
 
    /* Protect some assumptions below that rowcounts aren't zero */
    if (outer_path_rows <= 0)
        outer_path_rows = 1;
    if (inner_path_rows <= 0)
        inner_path_rows = 1;
    /* Mark the path with the correct row estimate */
    if (path->jpath.path.param_info)
        path->jpath.path.rows = path->jpath.path.param_info->ppi_rows;
    else
        path->jpath.path.rows = path->jpath.path.parent->rows;
 
    /* For partial paths, scale row estimate. */
    if (path->jpath.path.parallel_workers > 0)
    {
        double      parallel_divisor = get_parallel_divisor(&path->jpath.path);
 
        path->jpath.path.rows =
            clamp_row_est(path->jpath.path.rows / parallel_divisor);
    }
 
    /*
     * We could include disable_cost in the preliminary estimate, but that
     * would amount to optimizing for the case where the join method is
     * disabled, which doesn't seem like the way to bet.
     */
    if (!enable_nestloop)
        startup_cost += disable_cost;
 
    /* cost of inner-relation source data (we already dealt with outer rel) */
 
    if (path->jpath.jointype == JOIN_SEMI || path->jpath.jointype == JOIN_ANTI ||
        extra->inner_unique)
    {
        /*
         * With a SEMI or ANTI join, or if the innerrel is known unique, the
         * executor will stop after the first match.
         */
        Cost        inner_run_cost = workspace->inner_run_cost;
        Cost        inner_rescan_run_cost = workspace->inner_rescan_run_cost;
        double      outer_matched_rows;
        double      outer_unmatched_rows;
        Selectivity inner_scan_frac;
 
        /*
         * For an outer-rel row that has at least one match, we can expect the
         * inner scan to stop after a fraction 1/(match_count+1) of the inner
         * rows, if the matches are evenly distributed.  Since they probably
         * aren't quite evenly distributed, we apply a fuzz factor of 2.0 to
         * that fraction.  (If we used a larger fuzz factor, we'd have to
         * clamp inner_scan_frac to at most 1.0; but since match_count is at
         * least 1, no such clamp is needed now.)
         */
        outer_matched_rows = rint(outer_path_rows * extra->semifactors.outer_match_frac);
        outer_unmatched_rows = outer_path_rows - outer_matched_rows;
        inner_scan_frac = 2.0 / (extra->semifactors.match_count + 1.0);
 
        /*
         * Compute number of tuples processed (not number emitted!).  First,
         * account for successfully-matched outer rows.
         */
        ntuples = outer_matched_rows * inner_path_rows * inner_scan_frac;
 
        /*
         * Now we need to estimate the actual costs of scanning the inner
         * relation, which may be quite a bit less than N times inner_run_cost
         * due to early scan stops.  We consider two cases.  If the inner path
         * is an indexscan using all the joinquals as indexquals, then an
         * unmatched outer row results in an indexscan returning no rows,
         * which is probably quite cheap.  Otherwise, the executor will have
         * to scan the whole inner rel for an unmatched row; not so cheap.
         */
        if (has_indexed_join_quals(path))
        {
            /*
             * Successfully-matched outer rows will only require scanning
             * inner_scan_frac of the inner relation.  In this case, we don't
             * need to charge the full inner_run_cost even when that's more
             * than inner_rescan_run_cost, because we can assume that none of
             * the inner scans ever scan the whole inner relation.  So it's
             * okay to assume that all the inner scan executions can be
             * fractions of the full cost, even if materialization is reducing
             * the rescan cost.  At this writing, it's impossible to get here
             * for a materialized inner scan, so inner_run_cost and
             * inner_rescan_run_cost will be the same anyway; but just in
             * case, use inner_run_cost for the first matched tuple and
             * inner_rescan_run_cost for additional ones.
             */
            run_cost += inner_run_cost * inner_scan_frac;
            if (outer_matched_rows > 1)
                run_cost += (outer_matched_rows - 1) * inner_rescan_run_cost * inner_scan_frac;
 
            /*
             * Add the cost of inner-scan executions for unmatched outer rows.
             * We estimate this as the same cost as returning the first tuple
             * of a nonempty scan.  We consider that these are all rescans,
             * since we used inner_run_cost once already.
             */
            run_cost += outer_unmatched_rows *
                inner_rescan_run_cost / inner_path_rows;
 
            /*
             * We won't be evaluating any quals at all for unmatched rows, so
             * don't add them to ntuples.
             */
        }
        else
        {
            /*
             * Here, a complicating factor is that rescans may be cheaper than
             * first scans.  If we never scan all the way to the end of the
             * inner rel, it might be (depending on the plan type) that we'd
             * never pay the whole inner first-scan run cost.  However it is
             * difficult to estimate whether that will happen (and it could
             * not happen if there are any unmatched outer rows!), so be
             * conservative and always charge the whole first-scan cost once.
             * We consider this charge to correspond to the first unmatched
             * outer row, unless there isn't one in our estimate, in which
             * case blame it on the first matched row.
             */
 
            /* First, count all unmatched join tuples as being processed */
            ntuples += outer_unmatched_rows * inner_path_rows;
 
            /* Now add the forced full scan, and decrement appropriate count */
            run_cost += inner_run_cost;
            if (outer_unmatched_rows >= 1)
                outer_unmatched_rows -= 1;
            else
                outer_matched_rows -= 1;
 
            /* Add inner run cost for additional outer tuples having matches */
            if (outer_matched_rows > 0)
                run_cost += outer_matched_rows * inner_rescan_run_cost * inner_scan_frac;
 
            /* Add inner run cost for additional unmatched outer tuples */
            if (outer_unmatched_rows > 0)
                run_cost += outer_unmatched_rows * inner_rescan_run_cost;
        }
    }
    else
    {
        /* Normal-case source costs were included in preliminary estimate */
 
        /* Compute number of tuples processed (not number emitted!) */
        ntuples = outer_path_rows * inner_path_rows;
    }
 
    /* CPU costs */
    cost_qual_eval(&restrict_qual_cost, path->jpath.joinrestrictinfo, root);
    startup_cost += restrict_qual_cost.startup;
    cpu_per_tuple = cpu_tuple_cost + restrict_qual_cost.per_tuple;
    run_cost += cpu_per_tuple * ntuples;
 
    /* tlist eval costs are paid per output row, not per tuple scanned */
    startup_cost += path->jpath.path.pathtarget->cost.startup;
    run_cost += path->jpath.path.pathtarget->cost.per_tuple * path->jpath.path.rows;
 
    path->jpath.path.startup_cost = startup_cost;
    path->jpath.path.total_cost = startup_cost + run_cost;
}

References clamp_row_est(), cost_qual_eval(), cpu_tuple_cost, disable_cost, enable_nestloop, get_parallel_divisor(), has_indexed_join_quals(), JoinCostWorkspace::inner_rescan_run_cost, JoinCostWorkspace::inner_run_cost, JoinPathExtraData::inner_unique, JoinPath::innerjoinpath, JOIN_ANTI, JOIN_SEMI, JoinPath::joinrestrictinfo, JoinPath::jointype, NestPath::jpath, SemiAntiJoinFactors::match_count, SemiAntiJoinFactors::outer_match_frac, JoinPath::outerjoinpath, QualCost::per_tuple, Path::rows, JoinCostWorkspace::run_cost, JoinPathExtraData::semifactors, QualCost::startup, and JoinCostWorkspace::startup_cost.

Referenced by create_nestloop_path().

get_expr_width()

static int32 get_expr_width ( PlannerInfo *  root, const Node *  expr  )

static

Definition at line 6053 of file costsize.c.

{
    int32       width;
 
    if (IsA(expr, Var))
    {
        const Var  *var = (const Var *) expr;
 
        /* We should not see any upper-level Vars here */
        Assert(var->varlevelsup == 0);
 
        /* Try to get data from RelOptInfo cache */
        if (!IS_SPECIAL_VARNO(var->varno) &&
            var->varno < root->simple_rel_array_size)
        {
            RelOptInfo *rel = root->simple_rel_array[var->varno];
 
            if (rel != NULL &&
                var->varattno >= rel->min_attr &&
                var->varattno <= rel->max_attr)
            {
                int         ndx = var->varattno - rel->min_attr;
 
                if (rel->attr_widths[ndx] > 0)
                    return rel->attr_widths[ndx];
            }
        }
 
        /*
         * No cached data available, so estimate using just the type info.
         */
        width = get_typavgwidth(var->vartype, var->vartypmod);
        Assert(width > 0);
 
        return width;
    }
 
    width = get_typavgwidth(exprType(expr), exprTypmod(expr));
    Assert(width > 0);
    return width;
}

References Assert(), exprType(), exprTypmod(), get_typavgwidth(), IS_SPECIAL_VARNO, IsA, RelOptInfo::max_attr, RelOptInfo::min_attr, PlannerInfo::simple_rel_array_size, Var::varattno, Var::varlevelsup, and Var::varno.

Referenced by cost_memoize_rescan(), and set_pathtarget_cost_width().

get_foreign_key_join_selectivity()

static Selectivity get_foreign_key_join_selectivity ( PlannerInfo *  root, Relids  outer_relids, Relids  inner_relids, SpecialJoinInfo *  sjinfo, List **  restrictlist  )

static

Definition at line 5298 of file costsize.c.

{
    Selectivity fkselec = 1.0;
    JoinType    jointype = sjinfo->jointype;
    List       *worklist = *restrictlist;
    ListCell   *lc;
 
    /* Consider each FK constraint that is known to match the query */
    foreach(lc, root->fkey_list)
    {
        ForeignKeyOptInfo *fkinfo = (ForeignKeyOptInfo *) lfirst(lc);
        bool        ref_is_outer;
        List       *removedlist;
        ListCell   *cell;
 
        /*
         * This FK is not relevant unless it connects a baserel on one side of
         * this join to a baserel on the other side.
         */
        if (bms_is_member(fkinfo->con_relid, outer_relids) &&
            bms_is_member(fkinfo->ref_relid, inner_relids))
            ref_is_outer = false;
        else if (bms_is_member(fkinfo->ref_relid, outer_relids) &&
                 bms_is_member(fkinfo->con_relid, inner_relids))
            ref_is_outer = true;
        else
            continue;
 
        /*
         * If we're dealing with a semi/anti join, and the FK's referenced
         * relation is on the outside, then knowledge of the FK doesn't help
         * us figure out what we need to know (which is the fraction of outer
         * rows that have matches).  On the other hand, if the referenced rel
         * is on the inside, then all outer rows must have matches in the
         * referenced table (ignoring nulls).  But any restriction or join
         * clauses that filter that table will reduce the fraction of matches.
         * We can account for restriction clauses, but it's too hard to guess
         * how many table rows would get through a join that's inside the RHS.
         * Hence, if either case applies, punt and ignore the FK.
         */
        if ((jointype == JOIN_SEMI || jointype == JOIN_ANTI) &&
            (ref_is_outer || bms_membership(inner_relids) != BMS_SINGLETON))
            continue;
 
        /*
         * Modify the restrictlist by removing clauses that match the FK (and
         * putting them into removedlist instead).  It seems unsafe to modify
         * the originally-passed List structure, so we make a shallow copy the
         * first time through.
         */
        if (worklist == *restrictlist)
            worklist = list_copy(worklist);
 
        removedlist = NIL;
        foreach(cell, worklist)
        {
            RestrictInfo *rinfo = (RestrictInfo *) lfirst(cell);
            bool        remove_it = false;
            int         i;
 
            /* Drop this clause if it matches any column of the FK */
            for (i = 0; i < fkinfo->nkeys; i++)
            {
                if (rinfo->parent_ec)
                {
                    /*
                     * EC-derived clauses can only match by EC.  It is okay to
                     * consider any clause derived from the same EC as
                     * matching the FK: even if equivclass.c chose to generate
                     * a clause equating some other pair of Vars, it could
                     * have generated one equating the FK's Vars.  So for
                     * purposes of estimation, we can act as though it did so.
                     *
                     * Note: checking parent_ec is a bit of a cheat because
                     * there are EC-derived clauses that don't have parent_ec
                     * set; but such clauses must compare expressions that
                     * aren't just Vars, so they cannot match the FK anyway.
                     */
                    if (fkinfo->eclass[i] == rinfo->parent_ec)
                    {
                        remove_it = true;
                        break;
                    }
                }
                else
                {
                    /*
                     * Otherwise, see if rinfo was previously matched to FK as
                     * a "loose" clause.
                     */
                    if (list_member_ptr(fkinfo->rinfos[i], rinfo))
                    {
                        remove_it = true;
                        break;
                    }
                }
            }
            if (remove_it)
            {
                worklist = foreach_delete_current(worklist, cell);
                removedlist = lappend(removedlist, rinfo);
            }
        }
 
        /*
         * If we failed to remove all the matching clauses we expected to
         * find, chicken out and ignore this FK; applying its selectivity
         * might result in double-counting.  Put any clauses we did manage to
         * remove back into the worklist.
         *
         * Since the matching clauses are known not outerjoin-delayed, they
         * would normally have appeared in the initial joinclause list.  If we
         * didn't find them, there are two possibilities:
         *
         * 1. If the FK match is based on an EC that is ec_has_const, it won't
         * have generated any join clauses at all.  We discount such ECs while
         * checking to see if we have "all" the clauses.  (Below, we'll adjust
         * the selectivity estimate for this case.)
         *
         * 2. The clauses were matched to some other FK in a previous
         * iteration of this loop, and thus removed from worklist.  (A likely
         * case is that two FKs are matched to the same EC; there will be only
         * one EC-derived clause in the initial list, so the first FK will
         * consume it.)  Applying both FKs' selectivity independently risks
         * underestimating the join size; in particular, this would undo one
         * of the main things that ECs were invented for, namely to avoid
         * double-counting the selectivity of redundant equality conditions.
         * Later we might think of a reasonable way to combine the estimates,
         * but for now, just punt, since this is a fairly uncommon situation.
         */
        if (removedlist == NIL ||
            list_length(removedlist) !=
            (fkinfo->nmatched_ec - fkinfo->nconst_ec + fkinfo->nmatched_ri))
        {
            worklist = list_concat(worklist, removedlist);
            continue;
        }
 
        /*
         * Finally we get to the payoff: estimate selectivity using the
         * knowledge that each referencing row will match exactly one row in
         * the referenced table.
         *
         * XXX that's not true in the presence of nulls in the referencing
         * column(s), so in principle we should derate the estimate for those.
         * However (1) if there are any strict restriction clauses for the
         * referencing column(s) elsewhere in the query, derating here would
         * be double-counting the null fraction, and (2) it's not very clear
         * how to combine null fractions for multiple referencing columns. So
         * we do nothing for now about correcting for nulls.
         *
         * XXX another point here is that if either side of an FK constraint
         * is an inheritance parent, we estimate as though the constraint
         * covers all its children as well.  This is not an unreasonable
         * assumption for a referencing table, ie the user probably applied
         * identical constraints to all child tables (though perhaps we ought
         * to check that).  But it's not possible to have done that for a
         * referenced table.  Fortunately, precisely because that doesn't
         * work, it is uncommon in practice to have an FK referencing a parent
         * table.  So, at least for now, disregard inheritance here.
         */
        if (jointype == JOIN_SEMI || jointype == JOIN_ANTI)
        {
            /*
             * For JOIN_SEMI and JOIN_ANTI, we only get here when the FK's
             * referenced table is exactly the inside of the join.  The join
             * selectivity is defined as the fraction of LHS rows that have
             * matches.  The FK implies that every LHS row has a match *in the
             * referenced table*; but any restriction clauses on it will
             * reduce the number of matches.  Hence we take the join
             * selectivity as equal to the selectivity of the table's
             * restriction clauses, which is rows / tuples; but we must guard
             * against tuples == 0.
             */
            RelOptInfo *ref_rel = find_base_rel(root, fkinfo->ref_relid);
            double      ref_tuples = Max(ref_rel->tuples, 1.0);
 
            fkselec *= ref_rel->rows / ref_tuples;
        }
        else
        {
            /*
             * Otherwise, selectivity is exactly 1/referenced-table-size; but
             * guard against tuples == 0.  Note we should use the raw table
             * tuple count, not any estimate of its filtered or joined size.
             */
            RelOptInfo *ref_rel = find_base_rel(root, fkinfo->ref_relid);
            double      ref_tuples = Max(ref_rel->tuples, 1.0);
 
            fkselec *= 1.0 / ref_tuples;
        }
 
        /*
         * If any of the FK columns participated in ec_has_const ECs, then
         * equivclass.c will have generated "var = const" restrictions for
         * each side of the join, thus reducing the sizes of both input
         * relations.  Taking the fkselec at face value would amount to
         * double-counting the selectivity of the constant restriction for the
         * referencing Var.  Hence, look for the restriction clause(s) that
         * were applied to the referencing Var(s), and divide out their
         * selectivity to correct for this.
         */
        if (fkinfo->nconst_ec > 0)
        {
            for (int i = 0; i < fkinfo->nkeys; i++)
            {
                EquivalenceClass *ec = fkinfo->eclass[i];
 
                if (ec && ec->ec_has_const)
                {
                    EquivalenceMember *em = fkinfo->fk_eclass_member[i];
                    RestrictInfo *rinfo = find_derived_clause_for_ec_member(ec,
                                                                            em);
 
                    if (rinfo)
                    {
                        Selectivity s0;
 
                        s0 = clause_selectivity(root,
                                                (Node *) rinfo,
                                                0,
                                                jointype,
                                                sjinfo);
                        if (s0 > 0)
                            fkselec /= s0;
                    }
                }
            }
        }
    }
 
    *restrictlist = worklist;
    CLAMP_PROBABILITY(fkselec);
    return fkselec;
}

References bms_is_member(), bms_membership(), BMS_SINGLETON, CLAMP_PROBABILITY, clause_selectivity(), ForeignKeyOptInfo::con_relid, EquivalenceClass::ec_has_const, ForeignKeyOptInfo::eclass, find_base_rel(), find_derived_clause_for_ec_member(), ForeignKeyOptInfo::fk_eclass_member, PlannerInfo::fkey_list, foreach_delete_current, i, JOIN_ANTI, JOIN_SEMI, SpecialJoinInfo::jointype, lappend(), lfirst, list_concat(), list_copy(), list_length(), list_member_ptr(), Max, ForeignKeyOptInfo::nconst_ec, NIL, ForeignKeyOptInfo::nkeys, ForeignKeyOptInfo::nmatched_ec, ForeignKeyOptInfo::nmatched_ri, ForeignKeyOptInfo::ref_relid, ForeignKeyOptInfo::rinfos, RelOptInfo::rows, and RelOptInfo::tuples.

Referenced by calc_joinrel_size_estimate().

get_indexpath_pages()

static double get_indexpath_pages ( Path *  bitmapqual )

static

Definition at line 935 of file costsize.c.

{
    double      result = 0;
    ListCell   *l;
 
    if (IsA(bitmapqual, BitmapAndPath))
    {
        BitmapAndPath *apath = (BitmapAndPath *) bitmapqual;
 
        foreach(l, apath->bitmapquals)
        {
            result += get_indexpath_pages((Path *) lfirst(l));
        }
    }
    else if (IsA(bitmapqual, BitmapOrPath))
    {
        BitmapOrPath *opath = (BitmapOrPath *) bitmapqual;
 
        foreach(l, opath->bitmapquals)
        {
            result += get_indexpath_pages((Path *) lfirst(l));
        }
    }
    else if (IsA(bitmapqual, IndexPath))
    {
        IndexPath  *ipath = (IndexPath *) bitmapqual;
 
        result = (double) ipath->indexinfo->pages;
    }
    e