From 3c155bafa59b26e0bb38b8e70b9034183c946d39 Mon Sep 17 00:00:00 2001 From: Alexander Korotkov Date: Sun, 8 Sep 2019 21:13:40 +0300 Subject: Fix handling of NULL distances in KNN-GiST 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 --- src/backend/access/gist/gistscan.c | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) (limited to 'src/backend/access/gist/gistscan.c') diff --git a/src/backend/access/gist/gistscan.c b/src/backend/access/gist/gistscan.c index ff28ad8423f..e805cf2c1b7 100644 --- a/src/backend/access/gist/gistscan.c +++ b/src/backend/access/gist/gistscan.c @@ -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 */ @@ -87,7 +103,8 @@ gistbeginscan(PG_FUNCTION_ARGS) 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) { -- cgit v1.2.3