From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jens Axboe Subject: Re: get_fs_excl/put_fs_excl/has_fs_excl Date: Thu, 23 Apr 2009 21:21:24 +0200 Message-ID: <20090423192123.GL4593@kernel.dk> References: <20090423191817.GA22521@lst.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org To: Christoph Hellwig Return-path: Received: from brick.kernel.dk ([93.163.65.50]:34127 "EHLO kernel.dk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753199AbZDWTVZ (ORCPT ); Thu, 23 Apr 2009 15:21:25 -0400 Content-Disposition: inline In-Reply-To: <20090423191817.GA22521@lst.de> Sender: linux-fsdevel-owner@vger.kernel.org List-ID: On Thu, Apr 23 2009, Christoph Hellwig wrote: > Stumbled over these gems recently when investigating the > lock_super/unlock_super removal. > > These were added in commit 22e2c507c301c3dbbcf91b4948b88f78842ee6c9 > > [PATCH] Update cfq io scheduler to time sliced design > > which unfortunately doesn't contain any comments about it. It seems to > be used to allow boosting priority for some sort of central fs metadata > updates, at least what the usage in the reiserfs journal code > looks like that. > > Do you happen to have some notes/anecdotes about it so that we can > document it, give it saner naming and use it directly in the > spots that need it (including inside xfs, btrfs, etc) instead of lock_super? The intent was to add some sort of notification mechanism from the file system to inform the IO scheduler (and others?) that this process is how holding a file system wide resource. So if you have a low priority process getting access to such a resource, you want to boost its priority to avoid higher priority apps getting stuck beind it. Sort of a poor mans priority inheritance. It would be wonderful if you could kick this process more into gear on the fs side... -- Jens Axboe