Log Message:
-----------
Adjust spawn_process() to avoid unnecessary overhead processes: we can
just exec instead of creating a subprocess. This reduces process usage
from four processes per parallel test to two. I have no idea whether
a comparable optimization is possible or useful in the Windows port.
Modified Files:
--------------
pgsql/doc/src/sgml:
regress.sgml (r1.53 -> r1.54)
(http://developer.postgresql.org/cvsweb.cgi/pgsql/doc/src/sgml/regress.sgml.diff?r1=1.53&r2=1.54)
pgsql/src/test/regress:
GNUmakefile (r1.59 -> r1.60)
(http://developer.postgresql.org/cvsweb.cgi/pgsql/src/test/regress/GNUmakefile.diff?r1=1.59&r2=1.60)
pg_regress.c (r1.4 -> r1.5)
(http://developer.postgresql.org/cvsweb.cgi/pgsql/src/test/regress/pg_regress.c.diff?r1=1.4&r2=1.5)
---------------------------(end of broadcast)---------------------------
TIP 6: explain analyze is your friend