Fix handling of NULL distances in KNN-GiST

akorotkov · akorotkov · commit 1df4123048c4 · 2019-09-08T22:30:12.000+03:00
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
diff --git a/src/backend/access/gist/gistget.c b/src/backend/access/gist/gistget.c
@@ -34,8 +34,9 @@
  * request it.  recheck is not interesting when examining a non-leaf entry,
  * since we must visit the lower index page if there's any doubt.
  *
- * If we are doing an ordered scan, so->distances[] is filled with distance
- * data from the distance() functions before returning success.
+ * If we are doing an ordered scan, so->distancesValues[] and
+ * so->distancesNulls[] 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).
@@ -55,7 +56,8 @@ gistindex_keytest(IndexScanDesc scan,
 	GISTSTATE  *giststate = so->giststate;
 	ScanKey		key = scan->keyData;
 	int			keySize = scan->numberOfKeys;
-	double	   *distance_p;
+	double	   *distance_value_p;
+	bool	   *distance_null_p;
 	Relation	r = scan->indexRelation;
 
 	*recheck_p = false;
@@ -72,7 +74,10 @@ gistindex_keytest(IndexScanDesc scan,
 		if (GistPageIsLeaf(page))		/* shouldn't happen */
 			elog(ERROR, "invalid GiST tuple found on leaf page");
 		for (i = 0; i < scan->numberOfOrderBys; i++)
-			so->distances[i] = -get_float8_infinity();
+		{
+			so->distanceValues[i] = -get_float8_infinity();
+			so->distanceNulls[i] = false;
+		}
 		return true;
 	}
 
@@ -155,7 +160,8 @@ gistindex_keytest(IndexScanDesc scan,
 
 	/* OK, it passes --- now let's compute the distances */
 	key = scan->orderByData;
-	distance_p = so->distances;
+	distance_value_p = so->distanceValues;
+	distance_null_p = so->distanceNulls;
 	keySize = scan->numberOfOrderBys;
 	while (keySize > 0)
 	{
@@ -169,8 +175,9 @@ gistindex_keytest(IndexScanDesc scan,
 
 		if ((key->sk_flags & SK_ISNULL) || isNull)
 		{
-			/* Assume distance computes as null and sorts to the end */
-			*distance_p = get_float8_infinity();
+			/* Assume distance computes as null */
+			*distance_value_p = 0.0;
+			*distance_null_p = true;
 		}
 		else
 		{
@@ -199,14 +206,15 @@ gistindex_keytest(IndexScanDesc scan,
 									 key->sk_collation,
 									 PointerGetDatum(&de),
 									 key->sk_argument,
-									 Int32GetDatum(key->sk_strategy),
+									 Int16GetDatum(key->sk_strategy),
 									 ObjectIdGetDatum(key->sk_subtype));
-
-			*distance_p = DatumGetFloat8(dist);
+			*distance_value_p = DatumGetFloat8(dist);
+			*distance_null_p = false;
 		}
 
 		key++;
-		distance_p++;
+		distance_value_p++;
+		distance_null_p++;
 		keySize--;
 	}
 
@@ -219,7 +227,8 @@ gistindex_keytest(IndexScanDesc scan,
  *
  * scan: index scan we are executing
  * pageItem: search queue item identifying an index page to scan
- * myDistances: distances array associated with pageItem, or NULL at the root
+ * myDistanceValues: distances array associated with pageItem, or NULL at the root
+ * myDistanceNulls: null flags for myDistanceValues array, or NULL at the root
  * tbm: if not NULL, gistgetbitmap's output bitmap
  * ntids: if not NULL, gistgetbitmap's output tuple counter
  *
@@ -234,7 +243,8 @@ gistindex_keytest(IndexScanDesc scan,
  * sibling will be processed next.
  */
 static void
-gistScanPage(IndexScanDesc scan, GISTSearchItem *pageItem, double *myDistances,
+gistScanPage(IndexScanDesc scan, GISTSearchItem *pageItem,
+			 double *myDistanceValues, bool *myDistanceNulls,
 			 TIDBitmap *tbm, int64 *ntids)
 {
 	GISTScanOpaque so = (GISTScanOpaque) scan->opaque;
@@ -270,7 +280,7 @@ gistScanPage(IndexScanDesc scan, GISTSearchItem *pageItem, double *myDistances,
 		GISTSearchItem *item;
 
 		/* This can't happen when starting at the root */
-		Assert(myDistances != NULL);
+		Assert(myDistanceValues != NULL && myDistanceNulls != NULL);
 
 		oldcxt = MemoryContextSwitchTo(so->queueCxt);
 
@@ -283,8 +293,10 @@ gistScanPage(IndexScanDesc scan, GISTSearchItem *pageItem, double *myDistances,
 		/* Insert it into the queue using same distances as for this page */
 		tmpItem->head = item;
 		tmpItem->lastHeap = NULL;
-		memcpy(tmpItem->distances, myDistances,
-			   sizeof(double) * scan->numberOfOrderBys);
+		memcpy(GISTSearchTreeItemDistanceValues(tmpItem, scan->numberOfOrderBys),
+			   myDistanceValues, sizeof(double) * scan->numberOfOrderBys);
+		memcpy(GISTSearchTreeItemDistanceNulls(tmpItem, scan->numberOfOrderBys),
+			   myDistanceNulls, sizeof(bool) * scan->numberOfOrderBys);
 
 		(void) rb_insert(so->queue, (RBNode *) tmpItem, &isNew);
 
@@ -344,6 +356,7 @@ gistScanPage(IndexScanDesc scan, GISTSearchItem *pageItem, double *myDistances,
 			 * search.
 			 */
 			GISTSearchItem *item;
+			int			nOrderBys = scan->numberOfOrderBys;
 
 			oldcxt = MemoryContextSwitchTo(so->queueCxt);
 
@@ -374,8 +387,10 @@ gistScanPage(IndexScanDesc scan, GISTSearchItem *pageItem, double *myDistances,
 			/* Insert it into the queue using new distance data */
 			tmpItem->head = item;
 			tmpItem->lastHeap = GISTSearchItemIsHeap(*item) ? item : NULL;
-			memcpy(tmpItem->distances, so->distances,
-				   sizeof(double) * scan->numberOfOrderBys);
+			memcpy(GISTSearchTreeItemDistanceValues(tmpItem, nOrderBys),
+				   so->distanceValues, sizeof(double) * nOrderBys);
+			memcpy(GISTSearchTreeItemDistanceNulls(tmpItem, nOrderBys),
+				   so->distanceNulls, sizeof(bool) * nOrderBys);
 
 			(void) rb_insert(so->queue, (RBNode *) tmpItem, &isNew);
 
@@ -458,7 +473,10 @@ getNextNearest(IndexScanDesc scan)
 			/* visit an index page, extract its items into queue */
 			CHECK_FOR_INTERRUPTS();
 
-			gistScanPage(scan, item, so->curTreeItem->distances, NULL, NULL);
+			gistScanPage(scan, item,
+						 GISTSearchTreeItemDistanceValues(so->curTreeItem, scan->numberOfOrderBys),
+						 GISTSearchTreeItemDistanceNulls(so->curTreeItem, scan->numberOfOrderBys),
+						 NULL, NULL);
 		}
 
 		pfree(item);
@@ -496,7 +514,7 @@ gistgettuple(PG_FUNCTION_ARGS)
 
 		fakeItem.blkno = GIST_ROOT_BLKNO;
 		memset(&fakeItem.data.parentlsn, 0, sizeof(GistNSN));
-		gistScanPage(scan, &fakeItem, NULL, NULL, NULL);
+		gistScanPage(scan, &fakeItem, NULL, NULL, NULL, NULL);
 	}
 
 	if (scan->numberOfOrderBys > 0)
@@ -534,7 +552,10 @@ gistgettuple(PG_FUNCTION_ARGS)
 				 * this page, we fall out of the inner "do" and loop around to
 				 * return them.
 				 */
-				gistScanPage(scan, item, so->curTreeItem->distances, NULL, NULL);
+				gistScanPage(scan, item,
+							 GISTSearchTreeItemDistanceValues(so->curTreeItem, scan->numberOfOrderBys),
+							 GISTSearchTreeItemDistanceNulls(so->curTreeItem, scan->numberOfOrderBys),
+							 NULL, NULL);
 
 				pfree(item);
 			} while (so->nPageData == 0);
@@ -565,7 +586,7 @@ gistgetbitmap(PG_FUNCTION_ARGS)
 
 	fakeItem.blkno = GIST_ROOT_BLKNO;
 	memset(&fakeItem.data.parentlsn, 0, sizeof(GistNSN));
-	gistScanPage(scan, &fakeItem, NULL, tbm, &ntids);
+	gistScanPage(scan, &fakeItem, NULL, NULL, tbm, &ntids);
 
 	/*
 	 * While scanning a leaf page, ItemPointers of matching heap tuples will
@@ -580,7 +601,10 @@ gistgetbitmap(PG_FUNCTION_ARGS)
 
 		CHECK_FOR_INTERRUPTS();
 
-		gistScanPage(scan, item, so->curTreeItem->distances, tbm, &ntids);
+		gistScanPage(scan, item,
+					 GISTSearchTreeItemDistanceValues(so->curTreeItem, scan->numberOfOrderBys),
+					 GISTSearchTreeItemDistanceNulls(so->curTreeItem, scan->numberOfOrderBys),
+					 tbm, &ntids);
 
 		pfree(item);
 	}
diff --git a/src/backend/access/gist/gistscan.c b/src/backend/access/gist/gistscan.c
@@ -33,14 +33,30 @@ GISTSearchTreeItemComparator(const RBNode *a, const RBNode *b, void *arg)
 	const GISTSearchTreeItem *sb = (const GISTSearchTreeItem *) b;
 	IndexScanDesc scan = (IndexScanDesc) arg;
 	int			i;
+	double	   *da = GISTSearchTreeItemDistanceValues(sa, scan->numberOfOrderBys),
+			   *db = GISTSearchTreeItemDistanceValues(sb, scan->numberOfOrderBys);
+	bool	   *na = GISTSearchTreeItemDistanceNulls(sa, scan->numberOfOrderBys),
+			   *nb = GISTSearchTreeItemDistanceNulls(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;
+		}
 	}
 
 	return 0;
@@ -86,7 +102,7 @@ GISTSearchTreeItemAllocator(void *arg)
 {
 	IndexScanDesc scan = (IndexScanDesc) arg;
 
-	return palloc(GSTIHDRSZ + sizeof(double) * scan->numberOfOrderBys);
+	return palloc(SizeOfGISTSearchTreeItem(scan->numberOfOrderBys));
 }
 
 static void
@@ -130,8 +146,9 @@ gistbeginscan(PG_FUNCTION_ARGS)
 	so->queueCxt = giststate->scanCxt;	/* see gistrescan */
 
 	/* workspaces with size dependent on numberOfOrderBys: */
-	so->tmpTreeItem = palloc(GSTIHDRSZ + sizeof(double) * scan->numberOfOrderBys);
-	so->distances = palloc(sizeof(double) * scan->numberOfOrderBys);
+	so->tmpTreeItem = palloc(SizeOfGISTSearchTreeItem(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 */
 
 	scan->opaque = so;
@@ -191,7 +208,7 @@ gistrescan(PG_FUNCTION_ARGS)
 
 	/* create new, empty RBTree for search queue */
 	oldCxt = MemoryContextSwitchTo(so->queueCxt);
-	so->queue = rb_create(GSTIHDRSZ + sizeof(double) * scan->numberOfOrderBys,
+	so->queue = rb_create(SizeOfGISTSearchTreeItem(scan->numberOfOrderBys),
 						  GISTSearchTreeItemComparator,
 						  GISTSearchTreeItemCombiner,
 						  GISTSearchTreeItemAllocator,
diff --git a/src/include/access/gist_private.h b/src/include/access/gist_private.h
@@ -144,10 +144,28 @@ typedef struct GISTSearchTreeItem
 	RBNode		rbnode;			/* this is an RBTree item */
 	GISTSearchItem *head;		/* first chain member */
 	GISTSearchItem *lastHeap;	/* last heap-tuple member, if any */
-	double		distances[1];	/* array with numberOfOrderBys entries */
+
+	/*
+	 * 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.
+	 */
 } GISTSearchTreeItem;
 
-#define GSTIHDRSZ offsetof(GISTSearchTreeItem, distances)
+#define SizeOfGISTSearchTreeItem(n_distances) (DOUBLEALIGN(sizeof(GISTSearchTreeItem)) + \
+	(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 GISTSearchTreeItemDistanceValues(item, n_distances) \
+	((double *) ((Pointer) (item) + DOUBLEALIGN(sizeof(GISTSearchTreeItem))))
+
+#define GISTSearchTreeItemDistanceNulls(item, n_distances) \
+	((bool *) ((Pointer) (item) + DOUBLEALIGN(sizeof(GISTSearchTreeItem)) + sizeof(double) * (n_distances)))
 
 /*
  * GISTScanOpaqueData: private state for a scan of a GiST index
@@ -164,7 +182,8 @@ typedef struct GISTScanOpaqueData
 
 	/* pre-allocated workspace arrays */
 	GISTSearchTreeItem *tmpTreeItem;	/* workspace to pass to rb_insert */
-	double	   *distances;		/* output area for gistindex_keytest */
+	double	   *distanceValues; /* output area for gistindex_keytest */
+	bool	   *distanceNulls;
 
 	/* In a non-ordered search, returnable heap items are stored here: */
 	GISTSearchHeapItem pageData[BLCKSZ / sizeof(IndexTupleData)];
