Date: Thu, 26 Sep 1996 14:40:45 +0900 (JST) From: Michael Hancock <michaelh@cet.co.jp> To: dyson@FreeBSD.ORG Cc: Jake Hamby <jehamby@lightside.com>, hackers@FreeBSD.ORG Subject: Re: Anyone tried HURD yet? Message-ID: <Pine.SV4.3.93.960926143757.12224C-100000@parkplace.cet.co.jp> In-Reply-To: <199609260241.VAA21054@dyson.iquest.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, 25 Sep 1996, John S. Dyson wrote:
> >
> > If anyone else has tried HURD, I'd be interested in your opinions. I'm
> > also curious if anyone is seriously using Lites. As an aside, I currently
> > have _five_ OS's on four partitions of two SCSI hard drives of a single
> > 486: Windows 95, NT, Linux, FreeBSD, and Solaris/x86, _all_ accessible
> > from BootEasy. Adding HURD would make a grand total of six. Is this some
> > sort of world record? :-)
> >
> I had recently tried out Lites (during one of my benchmarking runs.) It
> is certainly an achievement in technology (IMO.) However, the performance
> of certain ops was quite slow. I passed around some performance numbers
> to -core, but have lost my harddrive with the results.
>
> Please don't take my performance comments as putting down the Mach or
> Lites projects -- otherwise they are very interesting -- but OS perf
> under certain circumstances was very far behind FreeBSD/Linux. There
> are many reasons for using the Mach based OSes, but perf is probably
> not going to be one of them. In particular I remember fork/exec as
> being maybe 10x-20x slower... Perhaps someone in -core could forward
> my results that I had measured?
These came off a Chorus page. How did they compare to these numbers?
7 microseconds Interrupt Latency
8 microseconds Context Switch on i486 at 50 Mhz
28 microseconds light-weight RPC on i486 at 50 Mhz
See, http://www.chorus.com/Products/Datasheets/nucleusv3.html
Regards,
Mike Hancock
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.SV4.3.93.960926143757.12224C-100000>