From: Trond Myklebust <trond.myklebust@fys.uio.no>
Subject: Re: NFS regression? Odd delays and lockups accessing an NFS export.
Date: Mon, 25 Aug 2008 12:54:13 -0400
Message-ID: <1219683253.7665.13.camel@localhost>
References: <p6lha4te54h04qdbnos1mcemdmn1cfca6s@4ax.com>
	 <1219087258.7192.19.camel@localhost>
	 <1219400624.18774.67.camel@zakaz.uk.xensource.com>
	 <1219428489.6919.21.camel@localhost>
	 <1219428818.27921.43.camel@localhost.localdomain>
	 <56a8daef0808221233h68853587n6015ca7d809b17e1@mail.gmail.com>
	 <1219435207.27921.51.camel@localhost.localdomain>
	 <1219440202.9097.14.camel@localhost>
	 <1219441041.27921.57.camel@localhost.localdomain>
	 <1219442213.9097.25.camel@localhost>
	 <1219603981.27921.145.camel@localhost.localdomain>
	 <1219605422.14389.2.camel@localhost>  <1219605596.14389.5.camel@localhost>
	 <1219615789.27921.152.camel@localhost.localdomain>
	 <1219616136.14389.12.camel@localhost>
	 <48B2D7F8.5020206@opengridcomputing.com>
Mime-Version: 1.0
Content-Type: text/plain
Cc: Ian Campbell <ijc@hellion.org.uk>,
	John Ronciak <john.ronciak@gmail.com>,
	Grant Coady <gcoady.lk@gmail.com>,
	linux-kernel@vger.kernel.org, neilb@suse.de, bfields@fieldses.org,
	linux-nfs@vger.kernel.org,
	Jeff Kirsher <jeffrey.t.kirsher@intel.com>,
	Jesse Brandeburg <jesse.brandeburg@intel.com>,
	Bruce Allan <bruce.w.allan@intel.com>,
	PJ Waskiewicz <peter.p.waskiewicz.jr@intel.com>,
	John Ronciak <john.ronciak@intel.com>,
	e1000-devel@lists.sourceforge.net
To: Tom Tucker <tom@opengridcomputing.com>
Return-path: <linux-kernel-owner+glk-linux-kernel-3=40m.gmane.org-S1755511AbYHYQyf@vger.kernel.org>
In-Reply-To: <48B2D7F8.5020206@opengridcomputing.com>
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-nfs.vger.kernel.org>

On Mon, 2008-08-25 at 11:04 -0500, Tom Tucker wrote:
> I don't think it should matter how long the connection stays in FIN WAIT,
> the client should reconnect anyway.

Which would break the replay cache, since we can't reconnect using the
same port.

> Since the client seems to be the variable, I would think it might be an
> issue with the client reconnect logic?

No.

Trond