index 43ad57253ef27596c96ca31381fe0a1d02c3ea8a..c7ec749d0a60142bd944a14a780ab0a22ba36632 100644 (file)
@@ -389,18 +389,20 @@ tablename | null_frac | n_distinct | most_common_vals
</programlisting>
In this case there is no <acronym>MCV</acronym> information for
- <structfield>unique2</structfield> because all the values appear to be
- unique, so we use an algorithm that relies only on the number of
- distinct values for both relations together with their null fractions:
+ <structname>unique2</structname> and all the values appear to be
+ unique (n_distinct = -1), so we use an algorithm that relies on the row
+ count estimates for both relations (num_rows, not shown, but "tenk")
+ together with the column null fractions (zero for both):
<programlisting>
-selectivity = (1 - null_frac1) * (1 - null_frac2) * min(1/num_distinct1, 1/num_distinct2)
+selectivity = (1 - null_frac1) * (1 - null_frac2) / max(num_rows1, num_rows2)
= (1 - 0) * (1 - 0) / max(10000, 10000)
= 0.0001
</programlisting>
This is, subtract the null fraction from one for each of the relations,
- and divide by the maximum of the numbers of distinct values.
+ and divide by the row count of the larger relation (this value does get
+ scaled in the non-unique case).
The number of rows
that the join is likely to emit is calculated as the cardinality of the
Cartesian product of the two inputs, multiplied by the