Do ScalarArrayOp estimation correctly when array is a stable expression.

tglsfdc · tglsfdc · commit 77585bce0304 · 2014-02-21T17:10:46.000-05:00
Most estimation functions apply estimate_expression_value to see if they
can reduce an expression to a constant; the key difference is that it
allows evaluation of stable as well as immutable functions in hopes of
ending up with a simple Const node.  scalararraysel didn't get the memo
though, and neither did gincost_opexpr/gincost_scalararrayopexpr.  Fix
that, and remove a now-unnecessary estimate_expression_value step in the
subsidiary function scalararraysel_containment.

Per complaint from Alexey Klyukin.  Back-patch to 9.3.  The problem
goes back further, but I'm hesitant to change estimation behavior in
long-stable release branches.
diff --git a/src/backend/utils/adt/array_selfuncs.c b/src/backend/utils/adt/array_selfuncs.c
@@ -68,11 +68,13 @@ static int	float_compare_desc(const void *key1, const void *key2);
  * scalararraysel_containment
  *		Estimate selectivity of ScalarArrayOpExpr via array containment.
  *
- * scalararraysel() has already verified that the operator of a
- * ScalarArrayOpExpr is the array element type's default equality or
- * inequality operator.  If we have const =/<> ANY/ALL (array_var)
- * then we can estimate the selectivity as though this were an array
- * containment operator, array_var op ARRAY[const].
+ * If we have const =/<> ANY/ALL (array_var) then we can estimate the
+ * selectivity as though this were an array containment operator,
+ * array_var op ARRAY[const].
+ *
+ * scalararraysel() has already verified that the ScalarArrayOpExpr's operator
+ * is the array element type's default equality or inequality operator, and
+ * has aggressively simplified both inputs to constants.
  *
  * Returns selectivity (0..1), or -1 if we fail to estimate selectivity.
  */
@@ -99,9 +101,8 @@ scalararraysel_containment(PlannerInfo *root,
 	}
 
 	/*
-	 * Aggressively reduce leftop to a constant, if possible.
+	 * leftop must be a constant, else punt.
 	 */
-	leftop = estimate_expression_value(root, leftop);
 	if (!IsA(leftop, Const))
 	{
 		ReleaseVariableStats(vardata);
diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c
@@ -1735,6 +1735,10 @@ scalararraysel(PlannerInfo *root,
 	leftop = (Node *) linitial(clause->args);
 	rightop = (Node *) lsecond(clause->args);
 
+	/* aggressively reduce both sides to constants */
+	leftop = estimate_expression_value(root, leftop);
+	rightop = estimate_expression_value(root, rightop);
+
 	/* get nominal (after relabeling) element type of rightop */
 	nominal_element_type = get_base_element_type(exprType(rightop));
 	if (!OidIsValid(nominal_element_type))
@@ -6856,7 +6860,8 @@ gincost_pattern(IndexOptInfo *index, int indexcol,
  * appropriately.  If the query is unsatisfiable, return false.
  */
 static bool
-gincost_opexpr(IndexOptInfo *index, OpExpr *clause, GinQualCounts *counts)
+gincost_opexpr(PlannerInfo *root, IndexOptInfo *index, OpExpr *clause,
+			   GinQualCounts *counts)
 {
 	Node	   *leftop = get_leftop((Expr *) clause);
 	Node	   *rightop = get_rightop((Expr *) clause);
@@ -6880,6 +6885,9 @@ gincost_opexpr(IndexOptInfo *index, OpExpr *clause, GinQualCounts *counts)
 		operand = NULL;			/* keep compiler quiet */
 	}
 
+	/* aggressively reduce to a constant, and look through relabeling */
+	operand = estimate_expression_value(root, operand);
+
 	if (IsA(operand, RelabelType))
 		operand = (Node *) ((RelabelType *) operand)->arg;
 
@@ -6918,7 +6926,8 @@ gincost_opexpr(IndexOptInfo *index, OpExpr *clause, GinQualCounts *counts)
  * by N, causing gincostestimate to scale up its estimates accordingly.
  */
 static bool
-gincost_scalararrayopexpr(IndexOptInfo *index, ScalarArrayOpExpr *clause,
+gincost_scalararrayopexpr(PlannerInfo *root,
+						  IndexOptInfo *index, ScalarArrayOpExpr *clause,
 						  double numIndexEntries,
 						  GinQualCounts *counts)
 {
@@ -6943,6 +6952,9 @@ gincost_scalararrayopexpr(IndexOptInfo *index, ScalarArrayOpExpr *clause,
 	if ((indexcol = find_index_column(leftop, index)) < 0)
 		elog(ERROR, "could not match index to operand");
 
+	/* aggressively reduce to a constant, and look through relabeling */
+	rightop = estimate_expression_value(root, rightop);
+
 	if (IsA(rightop, RelabelType))
 		rightop = (Node *) ((RelabelType *) rightop)->arg;
 
@@ -7160,15 +7172,17 @@ gincostestimate(PG_FUNCTION_ARGS)
 		clause = rinfo->clause;
 		if (IsA(clause, OpExpr))
 		{
-			matchPossible = gincost_opexpr(index,
+			matchPossible = gincost_opexpr(root,
+										   index,
 										   (OpExpr *) clause,
 										   &counts);
 			if (!matchPossible)
 				break;
 		}
 		else if (IsA(clause, ScalarArrayOpExpr))
 		{
-			matchPossible = gincost_scalararrayopexpr(index,
+			matchPossible = gincost_scalararrayopexpr(root,
+													  index,
 												(ScalarArrayOpExpr *) clause,
 													  numEntries,
 													  &counts);
