Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 14 Oct 1998 08:30:17 -0700
From:      Mike Smith <mike@smith.net.au>
To:        bag@sinbin.demos.su (Alex G. Bulushev)
Cc:        rock@cs.uni-sb.de (Daniel Rock), current@FreeBSD.ORG
Subject:   Re: -current NFS problem 
Message-ID:  <199810141530.IAA00811@dingo.cdrom.com>
In-Reply-To: Your message of "Wed, 14 Oct 1998 11:37:18 %2B0400." <199810140737.LAA13612@sinbin.demos.su> 

next in thread | previous in thread | raw e-mail | index | archive | help
> another known problem exist for nfsv3
> 
> we use www server working over nfs with about 1500000 hits/day
> it work fine with nfsv2 (load 0.1 - 0.8), but with nfsv3
> we see load > 130 and server replay is very slow ...
> i think this is a bug in fbsd nfsv3 realization, the
> same scheme with solaris/sparc nfsv3 client/server work
> without this problems ...

The problem here is almost certainly that we don't cache the results of 
ACCESS RPC calls.  There's an outstanding request from NetApp for us to 
address this; their testing indicates that 80% or more of NFS traffic 
generated by FreeBSD systems consists of ACCESS RPC calls.

-- 
\\  Sometimes you're ahead,       \\  Mike Smith
\\  sometimes you're behind.      \\  mike@smith.net.au
\\  The race is long, and in the  \\  msmith@freebsd.org
\\  end it's only with yourself.  \\  msmith@cdrom.com



To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-current" in the body of the message



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199810141530.IAA00811>