Redesign get_attstatsslot()/free_attstatsslot() for more safety and speed.

The mess cleaned up in commit da0759600 is clear evidence that it's a
bug hazard to expect the caller of get_attstatsslot()/free_attstatsslot()
to provide the correct type OID for the array elements in the slot.
Moreover, we weren't even getting any performance benefit from that,
since get_attstatsslot() was extracting the real type OID from the array
anyway.  So we ought to get rid of that requirement; indeed, it would
make more sense for get_attstatsslot() to pass back the type OID it found,
in case the caller isn't sure what to expect, which is likely in binary-
compatible-operator cases.

Another problem with the current implementation is that if the stats array
element type is pass-by-reference, we incur a palloc/memcpy/pfree cycle
for each element.  That seemed acceptable when the code was written because
we were targeting O(10) array sizes --- but these days, stats arrays are
almost always bigger than that, sometimes much bigger.  We can save a
significant number of cycles by doing one palloc/memcpy/pfree of the whole
array.  Indeed, in the now-probably-common case where the array is toasted,
that happens anyway so this method is basically free.  (Note: although the
catcache code will inline any out-of-line toasted values, it doesn't
decompress them.  At the other end of the size range, it doesn't expand
short-header datums either.  In either case, DatumGetArrayTypeP would have
to make a copy.  We do end up using an extra array copy step if the element
type is pass-by-value and the array length is neither small enough for a
short header nor large enough to have suffered compression.  But that
seems like a very acceptable price for winning in pass-by-ref cases.)

Hence, redesign to take these insights into account.  While at it,
convert to an API in which we fill a struct rather than passing a bunch
of pointers to individual output arguments.  That will make it less
painful if we ever want further expansion of what get_attstatsslot can
pass back.

It's certainly arguable that this is new development and not something to
push post-feature-freeze.  However, I view it as primarily bug-proofing
and therefore something that's better to have sooner not later.  Since
we aren't quite at beta phase yet, let's put it in.

Discussion: https://postgr.es/m/16364.1494520862@sss.pgh.pa.us

1 files changed, 31 insertions, 54 deletions

diff --git a/src/backend/utils/adt/array_selfuncs.c b/src/backend/utils/adt/array_selfuncs.c
index cfaf87335a8..3ae6018c67e 100644
--- a/src/backend/utils/adt/array_selfuncs.c
+++ b/src/backend/utils/adt/array_selfuncs.c
@@ -137,35 +137,22 @@ scalararraysel_containment(PlannerInfo *root,
 		statistic_proc_security_check(&vardata, cmpfunc->fn_oid))
 	{
 		Form_pg_statistic stats;
-		Datum	   *values;
-		int			nvalues;
-		float4	   *numbers;
-		int			nnumbers;
-		float4	   *hist;
-		int			nhist;
+		AttStatsSlot sslot;
+		AttStatsSlot hslot;
 
 		stats = (Form_pg_statistic) GETSTRUCT(vardata.statsTuple);
 
 		/* MCELEM will be an array of same type as element */
-		if (get_attstatsslot(vardata.statsTuple,
-							 elemtype, vardata.atttypmod,
+		if (get_attstatsslot(&sslot, vardata.statsTuple,
 							 STATISTIC_KIND_MCELEM, InvalidOid,
-							 NULL,
-							 &values, &nvalues,
-							 &numbers, &nnumbers))
+							 ATTSTATSSLOT_VALUES | ATTSTATSSLOT_NUMBERS))
 		{
 			/* For ALL case, also get histogram of distinct-element counts */
 			if (useOr ||
-				!get_attstatsslot(vardata.statsTuple,
-								  elemtype, vardata.atttypmod,
+				!get_attstatsslot(&hslot, vardata.statsTuple,
 								  STATISTIC_KIND_DECHIST, InvalidOid,
-								  NULL,
-								  NULL, NULL,
-								  &hist, &nhist))
-			{
-				hist = NULL;
-				nhist = 0;
-			}
+								  ATTSTATSSLOT_NUMBERS))
+				memset(&hslot, 0, sizeof(hslot));
 
 			/*
 			 * For = ANY, estimate as var @> ARRAY[const].
@@ -173,22 +160,26 @@ scalararraysel_containment(PlannerInfo *root,
 			 * For = ALL, estimate as var <@ ARRAY[const].
 			 */
 			if (useOr)
-				selec = mcelem_array_contain_overlap_selec(values, nvalues,
-														   numbers, nnumbers,
+				selec = mcelem_array_contain_overlap_selec(sslot.values,
+														   sslot.nvalues,
+														   sslot.numbers,
+														   sslot.nnumbers,
 														   &constval, 1,
 													   OID_ARRAY_CONTAINS_OP,
 														   cmpfunc);
 			else
-				selec = mcelem_array_contained_selec(values, nvalues,
-													 numbers, nnumbers,
+				selec = mcelem_array_contained_selec(sslot.values,
+													 sslot.nvalues,
+													 sslot.numbers,
+													 sslot.nnumbers,
 													 &constval, 1,
-													 hist, nhist,
+													 hslot.numbers,
+													 hslot.nnumbers,
 													 OID_ARRAY_CONTAINED_OP,
 													 cmpfunc);
 
-			if (hist)
-				free_attstatsslot(elemtype, NULL, 0, hist, nhist);
-			free_attstatsslot(elemtype, values, nvalues, numbers, nnumbers);
+			free_attstatsslot(&hslot);
+			free_attstatsslot(&sslot);
 		}
 		else
 		{
@@ -369,49 +360,35 @@ calc_arraycontsel(VariableStatData *vardata, Datum constval,
 		statistic_proc_security_check(vardata, cmpfunc->fn_oid))
 	{
 		Form_pg_statistic stats;
-		Datum	   *values;
-		int			nvalues;
-		float4	   *numbers;
-		int			nnumbers;
-		float4	   *hist;
-		int			nhist;
+		AttStatsSlot sslot;
+		AttStatsSlot hslot;
 
 		stats = (Form_pg_statistic) GETSTRUCT(vardata->statsTuple);
 
 		/* MCELEM will be an array of same type as column */
-		if (get_attstatsslot(vardata->statsTuple,
-							 elemtype, vardata->atttypmod,
+		if (get_attstatsslot(&sslot, vardata->statsTuple,
 							 STATISTIC_KIND_MCELEM, InvalidOid,
-							 NULL,
-							 &values, &nvalues,
-							 &numbers, &nnumbers))
+							 ATTSTATSSLOT_VALUES | ATTSTATSSLOT_NUMBERS))
 		{
 			/*
 			 * For "array <@ const" case we also need histogram of distinct
 			 * element counts.
 			 */
 			if (operator != OID_ARRAY_CONTAINED_OP ||
-				!get_attstatsslot(vardata->statsTuple,
-								  elemtype, vardata->atttypmod,
+				!get_attstatsslot(&hslot, vardata->statsTuple,
 								  STATISTIC_KIND_DECHIST, InvalidOid,
-								  NULL,
-								  NULL, NULL,
-								  &hist, &nhist))
-			{
-				hist = NULL;
-				nhist = 0;
-			}
+								  ATTSTATSSLOT_NUMBERS))
+				memset(&hslot, 0, sizeof(hslot));
 
 			/* Use the most-common-elements slot for the array Var. */
 			selec = mcelem_array_selec(array, typentry,
-									   values, nvalues,
-									   numbers, nnumbers,
-									   hist, nhist,
+									   sslot.values, sslot.nvalues,
+									   sslot.numbers, sslot.nnumbers,
+									   hslot.numbers, hslot.nnumbers,
 									   operator, cmpfunc);
 
-			if (hist)
-				free_attstatsslot(elemtype, NULL, 0, hist, nhist);
-			free_attstatsslot(elemtype, values, nvalues, numbers, nnumbers);
+			free_attstatsslot(&hslot);
+			free_attstatsslot(&sslot);
 		}
 		else
 		{