Improve handling of NULLs in KNN-GiST and KNN-SP-GiST

This commit improves subject in two ways:

 * It removes ugliness of 02f90879e7, which stores distance values and null
   flags in two separate arrays after GISTSearchItem struct.  Instead we pack
   both distance value and null flag in IndexOrderByDistance struct.  Alignment
   overhead should be negligible, because we typically deal with at most few
   "col op const" expressions in ORDER BY clause.
 * It fixes handling of "col op NULL" expression in KNN-SP-GiST.  Now, these
   expression are not passed to support functions, which can't deal with them.
   Instead, NULL result is implicitly assumed.  It future we may decide to
   teach support functions to deal with NULL arguments, but current solution is
   bugfix suitable for backpatch.

Reported-by: Nikita Glukhov
Discussion: https://postgr.es/m/826f57ee-afc7-8977-c44c-6111d18b02ec%40postgrespro.ru
Author: Nikita Glukhov
Reviewed-by: Alexander Korotkov
Backpatch-through: 9.4

diff --git a/src/backend/access/gist/gistget.c b/src/backend/access/gist/gistget.c
index d86fe9c64be856a2e1513b9866151b4f8b7346bc..0760269c06a1e70da2f6c0b568aa5d13f8202592 100644 (file)
--- a/src/backend/access/gist/gistget.c
+++ b/src/backend/access/gist/gistget.c
@@ -112,9 +112,8 @@ gistkillitems(IndexScanDesc scan)
  * Similarly, *recheck_distances_p is set to indicate whether the distances
  * need to be rechecked, and it is also ignored for non-leaf entries.
  *
- * If we are doing an ordered scan, so->distancesValues[] and
- * so->distancesNulls[] is filled with distance data from the distance()
- * functions before returning success.
+ * If we are doing an ordered scan, so->distances[] is filled with distance
+ * data from the distance() functions before returning success.
  *
  * We must decompress the key in the IndexTuple before passing it to the
  * sk_funcs (which actually are the opclass Consistent or Distance methods).
@@ -135,8 +134,7 @@ gistindex_keytest(IndexScanDesc scan,
        GISTSTATE  *giststate = so->giststate;
        ScanKey         key = scan->keyData;
        int                     keySize = scan->numberOfKeys;
-       double     *distance_value_p;
-       bool       *distance_null_p;
+       IndexOrderByDistance *distance_p;
        Relation        r = scan->indexRelation;
 
        *recheck_p = false;
@@ -155,8 +153,8 @@ gistindex_keytest(IndexScanDesc scan,
                        elog(ERROR, "invalid GiST tuple found on leaf page");
                for (i = 0; i < scan->numberOfOrderBys; i++)
                {
-                       so->distanceValues[i] = -get_float8_infinity();
-                       so->distanceNulls[i] = false;
+                       so->distances[i].value = -get_float8_infinity();
+                       so->distances[i].isnull = false;
                }
                return true;
        }
@@ -240,8 +238,7 @@ gistindex_keytest(IndexScanDesc scan,
 
        /* OK, it passes --- now let's compute the distances */
        key = scan->orderByData;
-       distance_value_p = so->distanceValues;
-       distance_null_p = so->distanceNulls;
+       distance_p = so->distances;
        keySize = scan->numberOfOrderBys;
        while (keySize > 0)
        {
@@ -256,8 +253,8 @@ gistindex_keytest(IndexScanDesc scan,
                if ((key->sk_flags & SK_ISNULL) || isNull)
                {
                        /* Assume distance computes as null */
-                       *distance_value_p = 0.0;
-                       *distance_null_p = true;
+                       distance_p->value = 0.0;
+                       distance_p->isnull = true;
                }
                else
                {
@@ -294,13 +291,12 @@ gistindex_keytest(IndexScanDesc scan,
                                                                         ObjectIdGetDatum(key->sk_subtype),
                                                                         PointerGetDatum(&recheck));
                        *recheck_distances_p |= recheck;
-                       *distance_value_p = DatumGetFloat8(dist);
-                       *distance_null_p = false;
+                       distance_p->value = DatumGetFloat8(dist);
+                       distance_p->isnull = false;
                }
 
                key++;
-               distance_value_p++;
-               distance_null_p++;
+               distance_p++;
                keySize--;
        }
 
@@ -313,8 +309,7 @@ gistindex_keytest(IndexScanDesc scan,
  *
  * scan: index scan we are executing
  * pageItem: search queue item identifying an index page to scan
- * myDistanceValues: distances array associated with pageItem, or NULL at the root
- * myDistanceNulls: null flags for myDistanceValues array, or NULL at the root
+ * myDistances: distances array associated with pageItem, or NULL at the root
  * tbm: if not NULL, gistgetbitmap's output bitmap
  * ntids: if not NULL, gistgetbitmap's output tuple counter
  *
@@ -332,8 +327,7 @@ gistindex_keytest(IndexScanDesc scan,
  */
 static void
 gistScanPage(IndexScanDesc scan, GISTSearchItem *pageItem,
-                        double *myDistanceValues, bool *myDistanceNulls,
-                        TIDBitmap *tbm, int64 *ntids)
+                        IndexOrderByDistance *myDistances, TIDBitmap *tbm, int64 *ntids)
 {
        GISTScanOpaque so = (GISTScanOpaque) scan->opaque;
        GISTSTATE  *giststate = so->giststate;
@@ -370,7 +364,7 @@ gistScanPage(IndexScanDesc scan, GISTSearchItem *pageItem,
                GISTSearchItem *item;
 
                /* This can't happen when starting at the root */
-               Assert(myDistanceValues != NULL && myDistanceNulls != NULL);
+               Assert(myDistances != NULL);
 
                oldcxt = MemoryContextSwitchTo(so->queueCxt);
 
@@ -380,10 +374,8 @@ gistScanPage(IndexScanDesc scan, GISTSearchItem *pageItem,
                item->data.parentlsn = pageItem->data.parentlsn;
 
                /* Insert it into the queue using same distances as for this page */
-               memcpy(GISTSearchItemDistanceValues(item, scan->numberOfOrderBys),
-                          myDistanceValues, sizeof(double) * scan->numberOfOrderBys);
-               memcpy(GISTSearchItemDistanceNulls(item, scan->numberOfOrderBys),
-                          myDistanceNulls, sizeof(bool) * scan->numberOfOrderBys);
+               memcpy(item->distances, myDistances,
+                          sizeof(item->distances[0]) * scan->numberOfOrderBys);
 
                pairingheap_add(so->queue, &item->phNode);
 
@@ -513,10 +505,8 @@ gistScanPage(IndexScanDesc scan, GISTSearchItem *pageItem,
                        }
 
                        /* Insert it into the queue using new distance data */
-                       memcpy(GISTSearchItemDistanceValues(item, nOrderBys),
-                                  so->distanceValues, sizeof(double) * nOrderBys);
-                       memcpy(GISTSearchItemDistanceNulls(item, nOrderBys),
-                                  so->distanceNulls, sizeof(bool) * nOrderBys);
+                       memcpy(item->distances, so->distances,
+                                  sizeof(item->distances[0]) * nOrderBys);
 
                        pairingheap_add(so->queue, &item->phNode);
 
@@ -571,8 +561,6 @@ getNextNearest(IndexScanDesc scan)
        do
        {
                GISTSearchItem *item = getNextGISTSearchItem(so);
-               float8 *distanceValues = GISTSearchItemDistanceValues(item, scan->numberOfOrderBys);
-               bool *distanceNulls = GISTSearchItemDistanceNulls(item, scan->numberOfOrderBys);
 
                if (!item)
                        break;
@@ -592,8 +580,8 @@ getNextNearest(IndexScanDesc scan)
                                        if (!scan->xs_orderbynulls[i])
                                                pfree(DatumGetPointer(scan->xs_orderbyvals[i]));
 #endif
-                                       scan->xs_orderbyvals[i] = Float8GetDatum(distanceValues[i]);
-                                       scan->xs_orderbynulls[i] = distanceNulls[i];
+                                       scan->xs_orderbyvals[i] = item->distances[i].value;
+                                       scan->xs_orderbynulls[i] = item->distances[i].isnull;
                                }
                                else if (so->orderByTypes[i] == FLOAT4OID)
                                {
@@ -603,8 +591,8 @@ getNextNearest(IndexScanDesc scan)
                                        if (!scan->xs_orderbynulls[i])
                                                pfree(DatumGetPointer(scan->xs_orderbyvals[i]));
 #endif
-                                       scan->xs_orderbyvals[i] = Float4GetDatum(distanceValues[i]);
-                                       scan->xs_orderbynulls[i] = distanceNulls[i];
+                                       scan->xs_orderbyvals[i] = Float4GetDatum(item->distances[i].value);
+                                       scan->xs_orderbynulls[i] = item->distances[i].isnull;
                                }
                                else
                                {
@@ -632,10 +620,7 @@ getNextNearest(IndexScanDesc scan)
                        /* visit an index page, extract its items into queue */
                        CHECK_FOR_INTERRUPTS();
 
-                       gistScanPage(scan, item,
-                                                GISTSearchItemDistanceValues(item, scan->numberOfOrderBys),
-                                                GISTSearchItemDistanceNulls(item, scan->numberOfOrderBys),
-                                                NULL, NULL);
+                       gistScanPage(scan, item, item->distances, NULL, NULL);
                }
 
                pfree(item);
@@ -673,7 +658,7 @@ gistgettuple(IndexScanDesc scan, ScanDirection dir)
 
                fakeItem.blkno = GIST_ROOT_BLKNO;
                memset(&fakeItem.data.parentlsn, 0, sizeof(GistNSN));
-               gistScanPage(scan, &fakeItem, NULL, NULL, NULL, NULL);
+               gistScanPage(scan, &fakeItem, NULL, NULL, NULL);
        }
 
        if (scan->numberOfOrderBys > 0)
@@ -767,10 +752,7 @@ gistgettuple(IndexScanDesc scan, ScanDirection dir)
                                 * this page, we fall out of the inner "do" and loop around to
                                 * return them.
                                 */
-                               gistScanPage(scan, item,
-                                                        GISTSearchItemDistanceValues(item, scan->numberOfOrderBys),
-                                                        GISTSearchItemDistanceNulls(item, scan->numberOfOrderBys),
-                                                        NULL, NULL);
+                               gistScanPage(scan, item, item->distances, NULL, NULL);
 
                                pfree(item);
                        } while (so->nPageData == 0);
@@ -801,7 +783,7 @@ gistgetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
 
        fakeItem.blkno = GIST_ROOT_BLKNO;
        memset(&fakeItem.data.parentlsn, 0, sizeof(GistNSN));
-       gistScanPage(scan, &fakeItem, NULL, NULL, tbm, &ntids);
+       gistScanPage(scan, &fakeItem, NULL, tbm, &ntids);
 
        /*
         * While scanning a leaf page, ItemPointers of matching heap tuples will
@@ -816,10 +798,7 @@ gistgetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
 
                CHECK_FOR_INTERRUPTS();
 
-               gistScanPage(scan, item,
-                                        GISTSearchItemDistanceValues(item, scan->numberOfOrderBys),
-                                        GISTSearchItemDistanceNulls(item, scan->numberOfOrderBys),
-                                        tbm, &ntids);
+               gistScanPage(scan, item, item->distances, tbm, &ntids);
 
                pfree(item);
        }

diff --git a/src/backend/access/gist/gistscan.c b/src/backend/access/gist/gistscan.c
index 0d69df98fcd3b84fff517be8297aa9c32136f633..df336b077eefc2e6ae57e5daf80254eeee1574a4 100644 (file)
--- a/src/backend/access/gist/gistscan.c
+++ b/src/backend/access/gist/gistscan.c
@@ -33,26 +33,23 @@ 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++)
        {
-               if (na[i])
+               if (sa->distances[i].isnull)
                {
-                       if (!nb[i])
+                       if (!sb->distances[i].isnull)
                                return -1;
                }
-               else if (nb[i])
+               else if (sb->distances[i].isnull)
                {
                        return 1;
                }
                else
                {
-                       int                     cmp = -float8_cmp_internal(da[i], db[i]);
+                       int                     cmp = -float8_cmp_internal(sa->distances[i].value,
+                                                                                                  sb->distances[i].value);
 
                        if (cmp != 0)
                                return cmp;
@@ -100,8 +97,7 @@ gistbeginscan(Relation r, int nkeys, int norderbys)
        so->queueCxt = giststate->scanCxt;      /* see gistrescan */
 
        /* workspaces with size dependent on numberOfOrderBys: */
-       so->distanceValues = palloc(sizeof(double) * scan->numberOfOrderBys);
-       so->distanceNulls = palloc(sizeof(bool) * scan->numberOfOrderBys);
+       so->distances = palloc(sizeof(so->distances[0]) * scan->numberOfOrderBys);
        so->qual_ok = true;                     /* in case there are zero keys */
        if (scan->numberOfOrderBys > 0)
        {

diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index 24c720bf421d3c6a4619c7452987a443ee50e6a3..2070eeb0c119175594dc41a19867e3eea5433d0c 100644 (file)
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -117,6 +117,13 @@ typedef enum IndexUniqueCheck
 } IndexUniqueCheck;
 
 
+/* Nullable "ORDER BY col op const" distance */
+typedef struct IndexOrderByDistance
+{
+       double          value;
+       bool            isnull;
+} IndexOrderByDistance;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */

diff --git a/src/include/access/gist_private.h b/src/include/access/gist_private.h
index 68faa5bc28a2196696bf83db96f321d0463ed837..41f496c258003b8e78428f6ec9ae7c3065bdafb5 100644 (file)
--- a/src/include/access/gist_private.h
+++ b/src/include/access/gist_private.h
@@ -137,29 +137,15 @@ typedef struct GISTSearchItem
                GISTSearchHeapItem heap;        /* heap info, if heap tuple */
        }                       data;
 
-       /*
-        * This data structure is followed by arrays of distance values and
-        * distance null flags.  Size of both arrays is
-        * IndexScanDesc->numberOfOrderBys. See macros below for accessing those
-        * arrays.
-        */
+       /* numberOfOrderBys entries */
+       IndexOrderByDistance distances[FLEXIBLE_ARRAY_MEMBER];
 } GISTSearchItem;
 
 #define GISTSearchItemIsHeap(item)     ((item).blkno == InvalidBlockNumber)
 
-#define SizeOfGISTSearchItem(n_distances) (DOUBLEALIGN(sizeof(GISTSearchItem)) + \
-       (sizeof(double) + sizeof(bool)) * (n_distances))
-
-/*
- * We actually don't need n_distances compute pointer to distance values.
- * Nevertheless take n_distances as argument to have same arguments list for
- * GISTSearchItemDistanceValues() and GISTSearchItemDistanceNulls().
- */
-#define GISTSearchItemDistanceValues(item, n_distances) \
-       ((double *) ((Pointer) (item) + DOUBLEALIGN(sizeof(GISTSearchItem))))
-
-#define GISTSearchItemDistanceNulls(item, n_distances) \
-       ((bool *) ((Pointer) (item) + DOUBLEALIGN(sizeof(GISTSearchItem)) + sizeof(double) * (n_distances)))
+#define SizeOfGISTSearchItem(n_distances) \
+       (offsetof(GISTSearchItem, distances) + \
+        sizeof(IndexOrderByDistance) * (n_distances))
 
 /*
  * GISTScanOpaqueData: private state for a scan of a GiST index
@@ -175,8 +161,7 @@ typedef struct GISTScanOpaqueData
        bool            firstCall;              /* true until first gistgettuple call */
 
        /* pre-allocated workspace arrays */
-       double     *distanceValues; /* output area for gistindex_keytest */
-       bool       *distanceNulls;
+       IndexOrderByDistance *distances;        /* output area for gistindex_keytest */
 
        /* info about killed items if any (killedItems is NULL if never used) */
        OffsetNumber *killedItems;      /* offset numbers of killed items */

diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index ed68cc4085e008bbf393ab2b820645740192454f..bbe62ab90b8b92e4b842e7dbd5152b00d9d20b72 100644 (file)
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1022,6 +1022,7 @@ IndexList
 IndexOnlyScan
 IndexOnlyScanState
 IndexOptInfo
+IndexOrderByDistance
 IndexPath
 IndexQualInfo
 IndexRuntimeKeyInfo