From mboxrd@z Thu Jan  1 00:00:00 1970
From: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Subject: Re: [PATCH 30/45] vmscan: lumpy pageout
Date: Thu, 8 Oct 2009 09:20:03 +0100 (BST)
Message-ID: <Pine.LNX.4.64.0910080916490.24232@sister.anvils>
References: <8acda98c0910070338n7220fdabo8c7f8f9e7d21ef6c@mail.gmail.com>
 <20091007111454.GB15936@localhost> <8acda98c0910070437g1498f99eua9a5ad71e6c2bae4@mail.gmail.com>
 <20091007132924.GB20855@localhost> <20091007134254.GA26244@localhost>
 <20091007142054.GA6798@localhost> <8acda98c0910070750x6428b96fgdeee5946d1408888@mail.gmail.com>
 <20091007150047.GA9848@localhost> <8acda98c0910070850x14614e0fh832f5cd29b1588f0@mail.gmail.com>
 <20091008023701.GA20021@localhost>
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Cc: Nikita Danilov <danilov@gmail.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Theodore Tso <tytso@mit.edu>,
	Christoph Hellwig <hch@infradead.org>,
	Dave Chinner <david@fromorbit.com>,
	Chris Mason <chris.mason@oracle.com>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	"Li, Shaohua" <shaohua.li@intel.com>,
	Myklebust Trond <Trond.Myklebust@netapp.com>,
	"jens.axboe@oracle.com" <jens.axboe@oracle.com>,
	Jan Kara <jack@suse.cz>, Nick Piggin <npiggin@suse.de>,
	"linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>
To: Wu Fengguang <fengguang.wu@intel.com>
Return-path: <linux-fsdevel-owner@vger.kernel.org>
Received: from mk-filter-2-a-1.mail.uk.tiscali.com ([212.74.100.53]:16460 "EHLO
	mk-filter-2-a-1.mail.uk.tiscali.com" rhost-flags-OK-OK-OK-OK)
	by vger.kernel.org with ESMTP id S1755702AbZJHIUv (ORCPT
	<rfc822;linux-fsdevel@vger.kernel.org>);
	Thu, 8 Oct 2009 04:20:51 -0400
In-Reply-To: <20091008023701.GA20021@localhost>
Sender: linux-fsdevel-owner@vger.kernel.org
List-ID: <linux-fsdevel.vger.kernel.org>

On Thu, 8 Oct 2009, Wu Fengguang wrote:
> On Wed, Oct 07, 2009 at 11:50:58PM +0800, Nikita Danilov wrote:
> > 
> > One potential problem with this is that generic_writepages() waits on
> > page locks and this can stall kswapd (always bad). This can be worked
> > around by replacing lock_page() with trylock_page() conditionally on
> > wbc->for_reclaim (or wbc->nonblocking?), but then, this almost look
> > like a separate function would be better.
> 
> IMHO trylock_page() is not necessary. Locked pages are rare in normal
> states. kswapd already do lock_page() for all pages it try to examine
> state for reclaim. So it makes sense for lumpy pageout to follow the
> (simple) convention.

You're mistaken?  The only lock_page() I see in vmscan.c is in
handle_write_error(), the important ones are all trylock_page().
And I agree with Nikita that they need to be trylock_page().

Hugh