[Fwd: Re: [OpenAFS] OpenAFS speed - some benchmarks]

[Jon Bendtsen]

This is a multi-part message in MIME format.
--------------040006080604000301070405
Content-Type: text/plain; charset=us-ascii; format=flowed
Content-Transfer-Encoding: 7bit

i keep sending them not to the mailing list :(

Anyway, what is a large file? 10MB? 100MB?
several G?



JonB

--------------040006080604000301070405
Content-Type: message/rfc822;
 name="Re: [OpenAFS] OpenAFS speed - some benchmarks"
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="Re: [OpenAFS] OpenAFS speed - some benchmarks"

Message-ID: <3EF98F08.70907@silicide.dk>
Date: Wed, 25 Jun 2003 14:01:12 +0200
From: Jon Bendtsen <jon+openafs@silicide.dk>
Organization: Silicide A/S
User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.0.0) Gecko/20020623 Debian/1.0.0-0.woody.1
X-Accept-Language: en
MIME-Version: 1.0
To: Andrei Maslennikov <andrei@caspur.it>
Subject: Re: [OpenAFS] OpenAFS speed - some benchmarks
References: <Pine.LNX.4.44.0306242008130.7320-100000@kiwi2.caspur.it>
Content-Type: text/plain; charset=us-ascii; format=flowed
Content-Transfer-Encoding: 7bit

Andrei Maslennikov wrote:
> 
> Well, if we escape cache on the client and do a direct
> copy to/from fileserver we gain almost a factor of 2
> on reads and up to 25% on writes (we used the "Atrans" 
> binary authored by Rainer Toebbicke in our tests). 
> 
> Without cache on client, AFS is still some 25% less 
> performant than NFS. This is (fileserver+rx). Of course,
> namei contributes visibly. We could probably estimate namei 
> vs inode using Solaris x86 on a recent pc hardware (may be
> rather tricky, as the newest hardware may be not supported
> by this os). 


Does NFS use "namei" or inodes?
Are we talking user-mode NFS server, or kernel-mode NFS server?




JonB


--------------040006080604000301070405--