mirror of
https://github.com/postgres/postgres.git
synced 2025-04-22 23:02:54 +03:00
Partially revert commit 3d3bf62f30200500637b24fdb7b992a99f9704c3.
On reflection, the pre-existing logic in ANALYZE is specifically meant to compare the frequency of a candidate MCV against the estimated frequency of a random distinct value across the whole table. The change to compare it against the average frequency of values actually seen in the sample doesn't seem very principled, and if anything it would make us less likely not more likely to consider a value an MCV. So revert that, but keep the aspect of considering only nonnull values, which definitely is correct. In passing, rename the local variables in these stanzas to "ndistinct_table", to avoid confusion with the "ndistinct" that appears at an outer scope in compute_scalar_stats.
This commit is contained in:
parent
c9ff752a85
commit
391159e03a
@ -2133,13 +2133,15 @@ compute_distinct_stats(VacAttrStatsP stats,
|
|||||||
}
|
}
|
||||||
else
|
else
|
||||||
{
|
{
|
||||||
/* d here is the same as d in the Haas-Stokes formula */
|
double ndistinct_table = stats->stadistinct;
|
||||||
int d = nonnull_cnt - summultiple + nmultiple;
|
|
||||||
double avgcount,
|
double avgcount,
|
||||||
mincount;
|
mincount;
|
||||||
|
|
||||||
|
/* Re-extract estimate of # distinct nonnull values in table */
|
||||||
|
if (ndistinct_table < 0)
|
||||||
|
ndistinct_table = -ndistinct_table * totalrows;
|
||||||
/* estimate # occurrences in sample of a typical nonnull value */
|
/* estimate # occurrences in sample of a typical nonnull value */
|
||||||
avgcount = (double) nonnull_cnt / (double) d;
|
avgcount = (double) nonnull_cnt / ndistinct_table;
|
||||||
/* set minimum threshold count to store a value */
|
/* set minimum threshold count to store a value */
|
||||||
mincount = avgcount * 1.25;
|
mincount = avgcount * 1.25;
|
||||||
if (mincount < 2)
|
if (mincount < 2)
|
||||||
@ -2493,14 +2495,16 @@ compute_scalar_stats(VacAttrStatsP stats,
|
|||||||
}
|
}
|
||||||
else
|
else
|
||||||
{
|
{
|
||||||
/* d here is the same as d in the Haas-Stokes formula */
|
double ndistinct_table = stats->stadistinct;
|
||||||
int d = ndistinct + toowide_cnt;
|
|
||||||
double avgcount,
|
double avgcount,
|
||||||
mincount,
|
mincount,
|
||||||
maxmincount;
|
maxmincount;
|
||||||
|
|
||||||
|
/* Re-extract estimate of # distinct nonnull values in table */
|
||||||
|
if (ndistinct_table < 0)
|
||||||
|
ndistinct_table = -ndistinct_table * totalrows;
|
||||||
/* estimate # occurrences in sample of a typical nonnull value */
|
/* estimate # occurrences in sample of a typical nonnull value */
|
||||||
avgcount = (double) values_cnt / (double) d;
|
avgcount = (double) nonnull_cnt / ndistinct_table;
|
||||||
/* set minimum threshold count to store a value */
|
/* set minimum threshold count to store a value */
|
||||||
mincount = avgcount * 1.25;
|
mincount = avgcount * 1.25;
|
||||||
if (mincount < 2)
|
if (mincount < 2)
|
||||||
|
Loading…
x
Reference in New Issue
Block a user