database/postgres
database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-05-01 01:04:50 +03:00
Code

Remove useless "rough estimate" path from mcelem_array_contained_selec.

Browse Source 
The code in this function that tried to cope with a missing count histogram
was quite ineffective for anything except a perfectly flat distribution.
Furthermore, since we were already punting for missing MCELEM slot, it's
rather useless to sweat over missing DECHIST: there are no cases where
ANALYZE will create the first but not the second.  So just simplify the
code by punting rather than pretending we can do something useful.
This commit is contained in:
Tom Lane 2012-03-04 16:03:38 -05:00
parent 4fb694aebc
commit e2eed78910
1 changed files with 67 additions and 81 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

54
src/backend/utils/adt/array_selfuncs.c
View File

@ -242,8 +242,7 @@ scalararraysel_containment(PlannerInfo *root,
}
/*
* arraycontsel -- restriction selectivity for "arraycolumn @> const",
* "arraycolumn && const" or "arraycolumn <@ const"
* arraycontsel -- restriction selectivity for array @>, &&, <@ operators
*/
Datum
arraycontsel(PG_FUNCTION_ARGS)
@ -323,8 +322,7 @@ arraycontsel(PG_FUNCTION_ARGS)
}
/*
* arraycontjoinsel -- join selectivity for "arraycolumn @> const",
* "arraycolumn && const" or "arraycolumn <@ const"
* arraycontjoinsel -- join selectivity for array @>, &&, <@ operators
*/
Datum
arraycontjoinsel(PG_FUNCTION_ARGS)
@ -744,6 +742,10 @@ mcelem_array_contained_selec(Datum *mcelem, int nmcelem,
if (numbers == NULL || nnumbers != nmcelem + 3)
return DEFAULT_CONTAIN_SEL;
/* Can't do much without a count histogram, either */
if (hist == NULL || nhist < 3)
return DEFAULT_CONTAIN_SEL;
/*
* Grab some of the summary statistics that compute_array_stats() stores:
* lowest frequency, frequency of null elements, and average distinct
@ -751,11 +753,7 @@ mcelem_array_contained_selec(Datum *mcelem, int nmcelem,
*/
minfreq = numbers[nmcelem];
nullelem_freq = numbers[nmcelem + 2];
if (hist && nhist > 0)
avg_count = hist[nhist - 1];
else
avg_count = 10.0f; /* default assumption */
/*
* "rest" will be the sum of the frequencies of all elements not
@ -853,28 +851,23 @@ mcelem_array_contained_selec(Datum *mcelem, int nmcelem,
*/
mult *= exp(-rest);
/* Check we have nonempty distinct element count histogram */
if (hist && nhist >= 3)
{
/*----------
* Using the distinct element count histogram requires
* O(unique_nitems * (nmcelem + unique_nitems))
* operations. Beyond a certain computational cost threshold, it's
* reasonable to sacrifice accuracy for decreased planning time.
* We limit the number of operations to EFFORT * nmcelem; since
* nmcelem is limited by the column's statistics target, the work
* done is user-controllable.
* reasonable to sacrifice accuracy for decreased planning time. We limit
* the number of operations to EFFORT * nmcelem; since nmcelem is limited
* by the column's statistics target, the work done is user-controllable.
*
* If the number of operations would be too large, we can reduce it
* without losing all accuracy by reducing unique_nitems and
* considering only the most-common elements of the constant array.
* To make the results exactly match what we would have gotten with
* only those elements to start with, we'd have to remove any
* discarded elements' frequencies from "mult", but since this is only
* an approximation anyway, we don't bother with that. Therefore it's
* sufficient to qsort elem_selec[] and take the largest elements.
* (They will no longer match up with the elements of array_data[],
* but we don't care.)
* without losing all accuracy by reducing unique_nitems and considering
* only the most-common elements of the constant array. To make the
* results exactly match what we would have gotten with only those
* elements to start with, we'd have to remove any discarded elements'
* frequencies from "mult", but since this is only an approximation
* anyway, we don't bother with that. Therefore it's sufficient to qsort
* elem_selec[] and take the largest elements. (They will no longer match
* up with the elements of array_data[], but we don't care.)
*----------
*/
#define EFFORT 100
@ -883,8 +876,8 @@ mcelem_array_contained_selec(Datum *mcelem, int nmcelem,
unique_nitems > EFFORT * nmcelem / (nmcelem + unique_nitems))
{
/*
* Use the quadratic formula to solve for largest allowable N;
* we have A = 1, B = nmcelem, C = - EFFORT * nmcelem.
* Use the quadratic formula to solve for largest allowable N. We
* have A = 1, B = nmcelem, C = - EFFORT * nmcelem.
*/
double b = (double) nmcelem;
int n;
@ -905,7 +898,7 @@ mcelem_array_contained_selec(Datum *mcelem, int nmcelem,
dist = calc_distr(elem_selec, unique_nitems, unique_nitems, 0.0f);
mcelem_dist = calc_distr(numbers, nmcelem, unique_nitems, rest);
/* ignore hist[nhist-1], which is the avg not a histogram member */
/* ignore hist[nhist-1], which is the average not a histogram member */
hist_part = calc_hist(hist, nhist - 1, unique_nitems);
selec = 0.0f;
@ -923,13 +916,6 @@ mcelem_array_contained_selec(Datum *mcelem, int nmcelem,
pfree(dist);
pfree(mcelem_dist);
pfree(hist_part);
}
else
{
/* We don't have histogram. Use a rough estimate. */
selec = mult;
}
pfree(elem_selec);
/* Take into account occurrence of NULL element. */