Date: Thu, 17 Sep 2009 11:09:14 +0200
From: Jan Kara <jack@suse.cz>
To: Jens Axboe <jens.axboe@oracle.com>
Cc: Jan Kara <jack@suse.cz>, LKML <linux-kernel@vger.kernel.org>,
       Wu Fengguang <fengguang.wu@intel.com>
Subject: Re: [PATCH] fs: Fix busyloop in wb_writeback()
Message-ID: <20090917090914.GA16381@duck.suse.cz>
References: <1253121768-20673-1-git-send-email-jack@suse.cz> <20090916184106.GT23126@kernel.dk>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20090916184106.GT23126@kernel.dk>
User-Agent: Mutt/1.5.17 (2007-11-01)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1352
Lines: 30

On Wed 16-09-09 20:41:06, Jens Axboe wrote:
> On Wed, Sep 16 2009, Jan Kara wrote:
> > If all inodes are under writeback (e.g. in case when there's only one inode
> > with dirty pages), wb_writeback() with WB_SYNC_NONE work basically degrades
> > to busylooping until I_SYNC flags of the inode is cleared. Fix the problem by
> > waiting on I_SYNC flags of an inode on b_more_io list in case we failed to
> > write anything.
> 
> Interesting, so this will happen if the dirtier and flush thread end up
> "fighting" each other over the same inode. I'll throw this into the
> testing mix.
  Yes, exactly. When you do "dd if=/dev/zero of=/mnt/mydisk" you're quite
likely to observe that.

> How did you notice?
  Well, UML linux doesn't seem to preempt when a process when it is in the
kernel and thus such busyloop simply deadlocks it. BTW another similar
deadlock happens in UML linux in balance_dirty_pages() (process cycles
there waiting for nr_writeback to drop but that never seems to happen). But
I'd blame that to a problem in UML scheduling...

									Honza
-- 
Jan Kara <jack@suse.cz>
SUSE Labs, CR
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/