database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-03 20:02:46 +03:00
Code Activity

Fix handling of NULL distances in KNN-GiST

Browse Source 
In order to implement NULL LAST semantic GiST previously assumed distance to
the NULL value to be Inf.  However, our distance functions can return Inf and
NaN for non-null values.  In such cases, NULL LAST semantic appears to be
broken.  This commit fixes that by introducing separate array of null flags for
distances.

Backpatch to all supported versions.

Discussion: https://postgr.es/m/CAPpHfdsNvNdA0DBS%2BwMpFrgwT6C3-q50sFVGLSiuWnV3FqOJuQ%40mail.gmail.com
Author: Alexander Korotkov
Backpatch-through: 9.4
This commit is contained in:
Alexander Korotkov
2019-09-08 21:13:40 +03:00
parent e5d8f35961
commit 02f90879e7
7 changed files with 106 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
src/backend/access/gist/gistscan.c
View File

@ -33,14 +33,30 @@ pairingheap_GISTSearchItem_cmp(const pairingheap_node *a, const pairingheap_node
const GISTSearchItem *sb = (const GISTSearchItem *) b;
IndexScanDesc scan = (IndexScanDesc) arg;
int i;
double *da = GISTSearchItemDistanceValues(sa, scan->numberOfOrderBys),
*db = GISTSearchItemDistanceValues(sb, scan->numberOfOrderBys);
bool *na = GISTSearchItemDistanceNulls(sa, scan->numberOfOrderBys),
*nb = GISTSearchItemDistanceNulls(sb, scan->numberOfOrderBys);
/* Order according to distance comparison */
for (i = 0; i < scan->numberOfOrderBys; i++)
{
int cmp = -float8_cmp_internal(sa->distances[i], sb->distances[i]);
if (na[i])
{
if (!nb[i])
return -1;
}
else if (nb[i])
{
return 1;
}
else
{
int cmp = -float8_cmp_internal(da[i], db[i]);
if (cmp != 0)
return cmp;
if (cmp != 0)
return cmp;
}
}
/* Heap items go before inner pages, to ensure a depth-first search */
@ -84,7 +100,8 @@ gistbeginscan(Relation r, int nkeys, int norderbys)
so->queueCxt = giststate->scanCxt; /* see gistrescan */
/* workspaces with size dependent on numberOfOrderBys: */
so->distances = palloc(sizeof(double) * scan->numberOfOrderBys);
so->distanceValues = palloc(sizeof(double) * scan->numberOfOrderBys);
so->distanceNulls = palloc(sizeof(bool) * scan->numberOfOrderBys);
so->qual_ok = true; /* in case there are zero keys */
if (scan->numberOfOrderBys > 0)
{