Be more wary of missing statistics in eqjoinsel_semi().

tglsfdc · tglsfdc · commit 159c47dc7170 · 2011-04-12T01:59:42.000-04:00
In particular, if we don't have real ndistinct estimates for both sides,
fall back to assuming that half of the left-hand rows have join partners.
This is what was done in 8.2 and 8.3 (cf nulltestsel() in those versions).
It's pretty stupid but it won't lead us to think that an antijoin produces
no rows out, as seen in recent example from Uwe Schroeder.
diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c
@@ -2329,7 +2329,9 @@ eqjoinsel_semi(Oid operator,
 		bool	   *hasmatch1;
 		bool	   *hasmatch2;
 		double		nullfrac1 = stats1->stanullfrac;
-		double		matchfreq1;
+		double		matchfreq1,
+					uncertainfrac,
+					uncertain;
 		int			i,
 					nmatches;
 
@@ -2382,18 +2384,26 @@ eqjoinsel_semi(Oid operator,
 		 * the uncertain rows that a fraction nd2/nd1 have join partners. We
 		 * can discount the known-matched MCVs from the distinct-values counts
 		 * before doing the division.
+		 *
+		 * Crude as the above is, it's completely useless if we don't have
+		 * reliable ndistinct values for both sides.  Hence, if either nd1
+		 * or nd2 is default, punt and assume half of the uncertain rows
+		 * have join partners.
 		 */
-		nd1 -= nmatches;
-		nd2 -= nmatches;
-		if (nd1 <= nd2 || nd2 <= 0)
-			selec = Max(matchfreq1, 1.0 - nullfrac1);
-		else
+		if (nd1 != DEFAULT_NUM_DISTINCT && nd2 != DEFAULT_NUM_DISTINCT)
 		{
-			double		uncertain = 1.0 - matchfreq1 - nullfrac1;
-
-			CLAMP_PROBABILITY(uncertain);
-			selec = matchfreq1 + (nd2 / nd1) * uncertain;
+			nd1 -= nmatches;
+			nd2 -= nmatches;
+			if (nd1 <= nd2 || nd2 <= 0)
+				uncertainfrac = 1.0;
+			else
+				uncertainfrac = nd2 / nd1;
 		}
+		else
+			uncertainfrac = 0.5;
+		uncertain = 1.0 - matchfreq1 - nullfrac1;
+		CLAMP_PROBABILITY(uncertain);
+		selec = matchfreq1 + uncertainfrac * uncertain;
 	}
 	else
 	{
@@ -2403,15 +2413,20 @@ eqjoinsel_semi(Oid operator,
 		 */
 		double		nullfrac1 = stats1 ? stats1->stanullfrac : 0.0;
 
-		if (vardata1->rel)
-			nd1 = Min(nd1, vardata1->rel->rows);
-		if (vardata2->rel)
-			nd2 = Min(nd2, vardata2->rel->rows);
+		if (nd1 != DEFAULT_NUM_DISTINCT && nd2 != DEFAULT_NUM_DISTINCT)
+		{
+			if (vardata1->rel)
+				nd1 = Min(nd1, vardata1->rel->rows);
+			if (vardata2->rel)
+				nd2 = Min(nd2, vardata2->rel->rows);
 
-		if (nd1 <= nd2 || nd2 <= 0)
-			selec = 1.0 - nullfrac1;
+			if (nd1 <= nd2 || nd2 <= 0)
+				selec = 1.0 - nullfrac1;
+			else
+				selec = (nd2 / nd1) * (1.0 - nullfrac1);
+		}
 		else
-			selec = (nd2 / nd1) * (1.0 - nullfrac1);
+			selec = 0.5 * (1.0 - nullfrac1);
 	}
 
 	if (have_mcvs1)
