Date: Tue, 24 May 2005 13:21:19 -0700 From: Kris Kennaway <kris@obsecurity.org> To: Bohdan Horst <nexus@hoth.amu.edu.pl> Cc: freebsd-stable@freebsd.org, Kris Kennaway <kris@obsecurity.org> Subject: Re: Performance of 4.x vs 5.x (nbench results) Message-ID: <20050524202118.GB28257@xor.obsecurity.org> In-Reply-To: <20050524201701.GB35326@aristo> References: <20050524193117.GA35326@aristo> <20050524193707.GA11906@xor.obsecurity.org> <20050524201701.GB35326@aristo>
next in thread | previous in thread | raw e-mail | index | archive | help
[-- Attachment #1 --] On Tue, May 24, 2005 at 10:17:01PM +0200, Bohdan Horst wrote: > On Tue, May 24, 2005 at 12:37:08PM -0700, Kris Kennaway wrote: > > > > Thanks, but if the machines are not completely idle then it's > > impossible to tell whether these numbers are meaningful :-( > > nbench give almost exact results under load : > > (1,2,3 nbenchs running) > > load 1: 496.1 > load 2: 497.7 > load 3: 498.78 > > and all machines have load: > > 4.11: 0.00 0.00 0.00 > 4.11: 0.03 0.03 0.03 > > 5.4: 0.00 0.00 0.00 > 5.4: 0.00 0.00 0.00 OK, it might be trustable..but you're still testing gcc 2/gcc 3 as pointed out by another poster. If you use the same 4.x binaries on both machines it might be better. Kris [-- Attachment #2 --] -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.1 (FreeBSD) iD8DBQFCk4y+Wry0BWjoQKURAsu6AJ9g6jTW8EF4/k8NwaEA2BasHqRTzwCfW0yr 9ZwOlHHaDl7wDFCCu7VN5X8= =gW/Q -----END PGP SIGNATURE-----
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050524202118.GB28257>