From mboxrd@z Thu Jan  1 00:00:00 1970
From: Nikita Danilov <danilov@gmail.com>
Subject: Re: [PATCH 30/45] vmscan: lumpy pageout
Date: Wed, 7 Oct 2009 18:50:17 +0400
Message-ID: <8acda98c0910070750x6428b96fgdeee5946d1408888@mail.gmail.com>
References: <8acda98c0910070338n7220fdabo8c7f8f9e7d21ef6c@mail.gmail.com>
	 <20091007111454.GB15936@localhost>
	 <8acda98c0910070437g1498f99eua9a5ad71e6c2bae4@mail.gmail.com>
	 <20091007132924.GB20855@localhost> <20091007134254.GA26244@localhost>
	 <20091007142054.GA6798@localhost>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: QUOTED-PRINTABLE
Cc: 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 qw-out-2122.google.com ([74.125.92.24]:39501 "EHLO
	qw-out-2122.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1753937AbZJGO4c convert rfc822-to-8bit (ORCPT
	<rfc822;linux-fsdevel@vger.kernel.org>);
	Wed, 7 Oct 2009 10:56:32 -0400
Received: by qw-out-2122.google.com with SMTP id 3so1878346qwe.37
        for <linux-fsdevel@vger.kernel.org>; Wed, 07 Oct 2009 07:55:25 -0700 (PDT)
In-Reply-To: <20091007142054.GA6798@localhost>
Sender: linux-fsdevel-owner@vger.kernel.org
List-ID: <linux-fsdevel.vger.kernel.org>

2009/10/7 Wu Fengguang <fengguang.wu@intel.com>:

[...]

> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 if (bdi_cap_writeback_dirty(mapping->ba=
cking_dev_info) &&
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 !mapping->a_ops->writepages) {
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 wbc.range_start =3D (pa=
ge->index + 1) << PAGE_CACHE_SHIFT;
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 wbc.nr_to_write =3D LUM=
PY_PAGEOUT_PAGES - 1;
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 generic_writepages(mapp=
ing, &wbc);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 iput(inode);

I am afraid calling iput() from within pageout code is not generally
safe: it can trigger a lot of file system activity (think
open-unlinked file) that is not supposed to happen in the
direct-reclaim context. Limiting pageout clustering to kswapd might be
a better idea---this would improve direct-reclaim latency too, but
still, file systems are not designed for re-entrant calls to iput().

Thank you,
Nikita.
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel=
" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html