Subject: Re: IDE write cache and journaling file systems
From: Steve Lord <lord@sgi.com>
To: Jens Axboe <axboe@suse.de>
Cc: Andi Kleen <ak@suse.de>, Jim Buzbee <James.Buzbee@echostar.com>,
   XFS List
	 <linux-xfs@oss.sgi.com>
In-Reply-To: <20020418160344.GM2492@suse.de>
References: <3CBEE618.B220A393@echostar.com>
	<1019144692.10200.8.camel@jen.americas.sgi.com>
	<20020418175314.A21976@wotan.suse.de>  <20020418160344.GM2492@suse.de>
Content-Type: text/plain
Content-Transfer-Encoding: 7bit
Date: 18 Apr 2002 11:04:03 -0500
Message-Id: <1019145843.10294.10.camel@jen.americas.sgi.com>
Mime-Version: 1.0
Sender: owner-linux-xfs@oss.sgi.com
Precedence: bulk

On Thu, 2002-04-18 at 11:03, Jens Axboe wrote:
> On Thu, Apr 18 2002, Andi Kleen wrote:
> > > 
> > > Andi Kleen was experimenting with the ide cache flushing code in the
> > > Suse kernel and adding some flushing calls to XFS. We talked about
> > > the right place to add them, I am not sure if he has tried it yet.
> > 
> > I've tried it and also got it to work in an experimental state, but decided
> > to rewrite it to use barriers instead. I didn't yet get around to do this 
> > rewrite. The reason for the rewrite is that just doing the flush slows
> > it down a lot.
> 
> Using barriers is surely the right approach, and lets the kernel use
> flushes or tag barriers as provided by the hardware.
> 
> > It requires considerable infrastructure not in the standard kernel.
> 
> ? Both the SuSE kernel has the infrastructure, and the 2.5 kernels so as
> well.

Unless I am mistaken, Jim is tied down to a fairly old kernel.

Steve


-- 

Steve Lord                                      voice: +1-651-683-3511
Principal Engineer, Filesystem Software         email: lord@sgi.com