On Wed, Nov 10, 2004 at 05:54:08PM +0000, James Wilkinson wrote: > What about the 4G/4G split? Are we still where we were in April over the > performance losses due to that? It's still not proven that it causes significant performance problems other than those picked up by microbenchmarks, which are uninteresting. *every* benchmark comparison I've seen between 4g/4g and a non-4g/4g kernel has been skewed due to sillyness like also disabling HIGHMEM support completely. > (In > http://www.redhat.com/archives/fedora-test-list/2004-April/msg01888.html > Alan Cox said that "its also about 10% slower on my laptop" and you > replied: > > It's somewhat strange that a few weeks ago when 4g/4g was temporarily > > disabled, absolutely *no-one* said "Hey, it got 10% faster!" > ) *shrug* nothing changed since then. Dave
