Brian Likosar wrote: > > ----- Original Message ---- > > From: Prentice Bisbal <prent...@ias.edu> > To: Red Hat Enterprise Linux 6 (Santiago) Beta releases discussion > mailing-list > <rhelv6-beta-list@redhat.com> > Sent: Tue, November 9, 2010 3:51:05 PM > Subject: Re: [rhelv6-beta-list] Apache benchmark RHEL 5 vs. RHEL 6 > >>>> This is probably it. This was discussed ad infinitum when it was >>>> changed upstream, and caused a huge performance regression across >>>> pretty much every workload. >>> But don't barriers affect mostly writes? If yes, is it because of the logs >>> and atime? 80% still looks like too much, maybe it's so bad because of the >>> virtualized environment? >> Multiple posters keep trying to blame this performance discrepancy on >> the virtualized environment. >> >> This makes no sense. The original poster has stated that both systems >> used the same virtualized environment, thereby eliminating that as a >> source of variability. >> > > If the virtualized environment is VMWare, there are versions of VMWare tools > which exist for RHEL 5 that probably don't exist for RHEL 6 (yet). That > could > cause a great performance discrepancy.
Good point. > >> I believe the OP also said he tested on both configurations directly on >> the hardware with the same results. > > I agree - and that is key here. It'd be interesting to see the tests re-run > with the ext4 optimizations on bare metal to see if the difference is as > great > as it was. > > -Brian > -- Prentice _______________________________________________ rhelv6-beta-list mailing list rhelv6-beta-list@redhat.com https://www.redhat.com/mailman/listinfo/rhelv6-beta-list
