From mboxrd@z Thu Jan  1 00:00:00 1970
From: Anthony Liguori <anthony@codemonkey.ws>
Subject: Re: [PATCH, RFC] virtio_blk: add cache flush command
Date: Mon, 11 May 2009 09:51:40 -0500
Message-ID: <4A083B7C.1000703@codemonkey.ws>
References: <20090511083908.GB20082@lst.de>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Cc: Rusty Russell <rusty@rustcorp.com.au>, kvm@vger.kernel.org
To: Christoph Hellwig <hch@lst.de>
Return-path: <kvm-owner@vger.kernel.org>
Received: from an-out-0708.google.com ([209.85.132.250]:40551 "EHLO
	an-out-0708.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1753174AbZEKOvm (ORCPT <rfc822;kvm@vger.kernel.org>);
	Mon, 11 May 2009 10:51:42 -0400
Received: by an-out-0708.google.com with SMTP id d40so10057403and.1
        for <kvm@vger.kernel.org>; Mon, 11 May 2009 07:51:42 -0700 (PDT)
In-Reply-To: <20090511083908.GB20082@lst.de>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

Christoph Hellwig wrote:
> Currently virtio-blk does support barriers for ordering requests which
> is enough to guarantee filesystem metadata integrity with write back
> caches, but it does not support any way to flush that writeback cache,
> to guarantee that data is stable on disk on a fsync.
>
> This patch implements a new VIRTIO_BLK_T_FLUSH command to flush the
> cache and exposes the functionality to the block layer by implementing
> a prepare_flush method.
>   

What typically triggers a flush operation?

I would assume an fsync would, but would a flush happen after every 
O_DIRECT write?

If the backend implementation of T_FLUSH is fsync, I would think that 
this would result in rather poor performance for O_DIRECT operations in 
the guest.

Regards,

Anthony Liguori