From mboxrd@z Thu Jan  1 00:00:00 1970
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: Re: [PATCH 3/5] mm: Implement IO-less balance_dirty_pages()
Date: Fri, 04 Feb 2011 14:09:16 +0100
Message-ID: <1296824956.26581.650.camel@laptop>
References: <1296783534-11585-1-git-send-email-jack@suse.cz>
	 <1296783534-11585-4-git-send-email-jack@suse.cz>
Mime-Version: 1.0
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: 7bit
Cc: linux-fsdevel@vger.kernel.org, linux-mm@kvack.org,
	Andrew Morton <akpm@linux-foundation.org>,
	Christoph Hellwig <hch@infradead.org>,
	Dave Chinner <david@fromorbit.com>,
	Wu Fengguang <fengguang.wu@intel.com>
To: Jan Kara <jack@suse.cz>
Return-path: <linux-fsdevel-owner@vger.kernel.org>
Received: from bombadil.infradead.org ([18.85.46.34]:60140 "EHLO
	bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1752701Ab1BDNP6 (ORCPT
	<rfc822;linux-fsdevel@vger.kernel.org>);
	Fri, 4 Feb 2011 08:15:58 -0500
Received: from canuck.infradead.org ([2001:4978:20e::1])
	by bombadil.infradead.org with esmtps (Exim 4.72 #1 (Red Hat Linux))
	id 1PlLW1-0005Cq-UO
	for linux-fsdevel@vger.kernel.org; Fri, 04 Feb 2011 13:15:58 +0000
Received: from j77219.upc-j.chello.nl ([24.132.77.219] helo=dyad.programming.kicks-ass.net)
	by canuck.infradead.org with esmtpsa (Exim 4.72 #1 (Red Hat Linux))
	id 1PlLW1-0001mk-0r
	for linux-fsdevel@vger.kernel.org; Fri, 04 Feb 2011 13:15:57 +0000
In-Reply-To: <1296783534-11585-4-git-send-email-jack@suse.cz>
Sender: linux-fsdevel-owner@vger.kernel.org
List-ID: <linux-fsdevel.vger.kernel.org>

On Fri, 2011-02-04 at 02:38 +0100, Jan Kara wrote:
> +static int check_dirty_limits(struct backing_dev_info *bdi,
> +                             struct dirty_limit_state *pst)
> +{
> +       struct dirty_limit_state st;
> +       unsigned long bdi_thresh;
> +       unsigned long min_bdi_thresh;
> +       int ret = DIRTY_OK;
>  
> +       get_global_dirty_limit_state(&st);
> +       /*
> +        * Throttle it only when the background writeback cannot catch-up. This
> +        * avoids (excessively) small writeouts when the bdi limits are ramping
> +        * up.
> +        */
> +       if (st.nr_reclaimable + st.nr_writeback <=
> +                       (st.background_thresh + st.dirty_thresh) / 2)
> +               goto out;
>  
> +       get_bdi_dirty_limit_state(bdi, &st);
> +       min_bdi_thresh = task_min_dirty_limit(st.bdi_thresh);
> +       bdi_thresh = task_dirty_limit(current, st.bdi_thresh);
> +
> +       /*
> +        * The bdi thresh is somehow "soft" limit derived from the global
> +        * "hard" limit. The former helps to prevent heavy IO bdi or process
> +        * from holding back light ones; The latter is the last resort
> +        * safeguard.
> +        */
> +       if ((st.bdi_nr_reclaimable + st.bdi_nr_writeback > bdi_thresh)
> +           || (st.nr_reclaimable + st.nr_writeback > st.dirty_thresh)) {
> +               ret = DIRTY_EXCEED_LIMIT;
> +               goto out;
> +       }
> +       if (st.bdi_nr_reclaimable + st.bdi_nr_writeback > min_bdi_thresh) {
> +               ret = DIRTY_MAY_EXCEED_LIMIT;
> +               goto out;
> +       }
> +       if (st.nr_reclaimable > st.background_thresh)
> +               ret = DIRTY_EXCEED_BACKGROUND;
> +out:
> +       if (pst)
> +               *pst = st;

By mandating pst is always provided you can reduce the total stack
footprint, avoid the memcopy and clean up the control flow ;-)

> +       return ret;
> +}