Date: Sun, 17 Aug 2003 16:16:27 -0500 From: Dan Nelson <dnelson@allantgroup.com> To: Pawel Jakub Dawidek <nick@garage.freebsd.pl> Cc: Buckie <freebsd1@centrum.cz> Subject: Re: GEOM Gate. Message-ID: <20030817211627.GC2653@dan.emsphone.com> In-Reply-To: <20030817020236.GX395@garage.freebsd.pl> References: <20030815111856.GN395@garage.freebsd.pl> <Pine.NEB.3.96L.1030815114948.94219A-100000@fledge.watson.org> <20030817011545.GW395@garage.freebsd.pl> <20030817015029.GA2653@dan.emsphone.com> <20030817020236.GX395@garage.freebsd.pl>
next in thread | previous in thread | raw e-mail | index | archive | help
In the last episode (Aug 17), Pawel Jakub Dawidek said: > On Sat, Aug 16, 2003 at 08:50:30PM -0500, Dan Nelson wrote: > +> What kind of hardware were you using? 2.5MB/sec NFS sounds > +> abysmal. > > I don't think it is a hardware problem. > > Run this test on 5.1-CURRENT with: > > options INVARIANTS > options INVARIANT_SUPPORT > options WITNESS > > and without any network and NFS optimization. Yes, another test system (P5 MMX/233 laptop) drops its NFS throughput from 4MB/sec to 2.5MB/sec when built with those flags. So I'm assuming you're doing these benchmarks on a comparable system? I think this just demonstrates that you should not run benchmarks with all your debugging flags enabled :) Most people will not be running production systems with WITNESS, and parts of the kernel that bog down under the heavy load of WITNESS may work just fine on a regular kernal config. -- Dan Nelson dnelson@allantgroup.com
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20030817211627.GC2653>