From: Kyungmin Park Subject: Re: [PATCH 1/2] fs: Do not dispatch FITRIM through separate super_operation Date: Fri, 3 Jun 2011 13:25:21 +0900 Message-ID: References: <20101118142918.GA18510@infradead.org> <1290100750.3041.72.camel@mulgrave.site> <4CE59C9E.6050902@teksavvy.com> <1290177488-sup-6540@think> <4CE68F80.7000607@teksavvy.com> <20101119145748.GB27919@infradead.org> <4CE695FF.20601@teksavvy.com> <20101207092749.GA26100@infradead.org> <1291740643-sup-2494@think> <20110603020615.GZ561@dastard> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Chris Mason , Lukas Czerner , Christoph Hellwig , Mark Lord , James Bottomley , Matthew Wilcox , Josef Bacik , tytso , linux-ext4 , linux-kernel , linux-fsdevel , sandeen To: Dave Chinner Return-path: Received: from mail-vx0-f174.google.com ([209.85.220.174]:62654 "EHLO mail-vx0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750745Ab1FCEZX convert rfc822-to-8bit (ORCPT ); Fri, 3 Jun 2011 00:25:23 -0400 In-Reply-To: <20110603020615.GZ561@dastard> Sender: linux-ext4-owner@vger.kernel.org List-ID: On Fri, Jun 3, 2011 at 11:06 AM, Dave Chinner wro= te: > On Thu, Jun 02, 2011 at 01:52:12PM +0900, Kyungmin Park wrote: >> On Wed, Dec 8, 2010 at 1:52 AM, Chris Mason = wrote: >> > Excerpts from Christoph Hellwig's message of 2010-12-07 04:27:49 -= 0500: >> >> On Fri, Nov 19, 2010 at 10:21:35AM -0500, Mark Lord wrote: >> >> > >I really hate to rely on this third party hearsay (from all si= des), and >> >> > >have implement TRIM support in qemu now. =A0I'll soon install = win7 and >> >> > >will check out the TRIM patters myself. >> >> > >> >> > Excellent! >> >> >> >> I did a Windows 7 installation under qemu today, and the result i= s: >> > >> > Great, thanks for testing this. >> > >> >> >> >> =A0- it TRIMs the whole device early during the installation >> >> =A0- after that I see a constant stream of small trims during the >> >> =A0 =A0installation. =A0It's using lots of non-contiguous ranges = in a single >> >> =A0 =A0TRIM command, with sizes down to 8 sectors (4k) for a sing= le range. >> >> =A0- after installation there's is some background-trimming going= on >> >> =A0 =A0even when doing no user interaction with the VM at all. >> >> Hi Lukas, >> >> Now FITRIM is based on user interaction. So how about to implement t= he >> AUTO batched discard at kernel level? >> Idea is same as windows, make a single thread and iterate the >> superblocks and call the trim. > > Surely this the responsibility of a userspace daemon and a config > file to decide and implement the background trim policy? It seems to run as crond. BTW, what's config file? time based or behavi= or? my rough idea to run at kernel level. 1. Block I/O aware notification. 2. Explicit filesystem call 3. user space request. (same as current) Thank you, Kyungmin Park > > Cheers, > > Dave. > -- > Dave Chinner > david@fromorbit.com > -- To unsubscribe from this list: send the line "unsubscribe linux-ext4" i= n the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html