From: Michal Hocko <mhocko@suse.cz>
Subject: Re: Lockup in wait_transaction_locked under memory pressure
Date: Wed, 1 Jul 2015 16:21:57 +0200
Message-ID: <20150701142157.GB6287@dhcp22.suse.cz>
References: <20150625115025.GD17237@dhcp22.suse.cz>
 <20150625133138.GH14324@thunk.org>
 <5591097D.6010602@kyup.com>
 <20150629093640.GD28471@dhcp22.suse.cz>
 <20150630015206.GL22807@dastard>
 <20150630123033.GB4578@dhcp22.suse.cz>
 <20150630143158.GD4578@dhcp22.suse.cz>
 <20150630225851.GK7943@dastard>
 <20150701061014.GA6286@dhcp22.suse.cz>
 <20150701111355.GA22423@thunk.org>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: Dave Chinner <david@fromorbit.com>,
	Nikolay Borisov <kernel@kyup.com>, linux-ext4@vger.kernel.org,
	Marian Marinov <mm@1h.com>
To: Theodore Ts'o <tytso@mit.edu>
Content-Disposition: inline
In-Reply-To: <20150701111355.GA22423@thunk.org>
Sender: linux-ext4-owner@vger.kernel.org

On Wed 01-07-15 07:13:55, Theodore Ts'o wrote:
[...]
> Perhaps we need to make the documentation a bit more explicit?
> All which is stated in include/slab.h:
> 
>  * %GFP_NOIO - Do not do any I/O at all while trying to get memory.
>  *
>  * %GFP_NOFS - Do not make any fs calls while trying to get memory.
> 
> I thought this was obvious, but these flags are used by code which in
> the I/O or FS paths, and so it's always possible that they are trying
> to write back the page which you decide to blocking on when trying to
> do the memory allocation, at which point, *boom*, deadlock.
> 
> So it's just not "do not make any FS or I/O calls", but also "the mm
> layer must not not wait for any FS or I/O operations from completing,
> since the operation you block on might be the one they were in the
> middle of trying to complete --- or they may be holding a lock at the
> time when they were trying to do a memory allocation which blocks the
> I/O or FS operation from completing".

Sure any refinement here would be more than welcome.
-- 
Michal Hocko
SUSE Labs