From: Mike Snitzer Subject: Re: Ext4 and xfs problems in dm-thin on allocation and discard Date: Tue, 19 Jun 2012 10:44:14 -0400 Message-ID: <20120619144413.GA7225@redhat.com> References: <4FDF9EBE.2030809@shiftmail.org> <20120619015745.GJ25389@dastard> <20120619031241.GA3884@redhat.com> <20120619131649.GA6811@redhat.com> <20120619133041.GB6811@redhat.com> <4FE0840F.2050704@shiftmail.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: =?utf-8?B?THVrw6HFoQ==?= Czerner , Dave Chinner , device-mapper development , linux-ext4@vger.kernel.org, xfs@oss.sgi.com To: Spelic Return-path: Received: from mx1.redhat.com ([209.132.183.28]:5696 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754444Ab2FSOoX (ORCPT ); Tue, 19 Jun 2012 10:44:23 -0400 Content-Disposition: inline In-Reply-To: <4FE0840F.2050704@shiftmail.org> Sender: linux-ext4-owner@vger.kernel.org List-ID: On Tue, Jun 19 2012 at 9:52am -0400, Spelic wrote: > On 06/19/12 15:30, Mike Snitzer wrote: > >I don't recall Spelic saying anything about EOPNOTSUPP. So what > >has made you zero in on an -EOPNOTSUPP return (which should not be > >happening)? > > Exactly: I do not know if EOPNOTSUPP is being returned or not. > > If this helps, I have configured dm-thin via lvm2 > LVM version: 2.02.95(2) (2012-03-06) > Library version: 1.02.74 (2012-03-06) > Driver version: 4.22.0 > > from dmsetup table I only see one option : "skip_block_zeroing", if > and only if I configure it with -Zn . I do not see anything > regarding ignore_discard > > vg1-pooltry1-tpool: 0 20971520 thin-pool 252:1 252:2 2048 0 1 > skip_block_zeroing > vg1-pooltry1_tdata: 0 20971520 linear 9:20 62922752 > vg1-pooltry1_tmeta: 0 8192 linear 9:20 83894272 > vg1-thinlv1: 0 31457280 thin 252:3 1 > > > and in dmesg: > [ 33.685200] device-mapper: thin: Discard unsupported by data > device (dm-2): Disabling discard passdown. > [ 33.709586] device-mapper: thin: Discard unsupported by data > device (dm-6): Disabling discard passdown. > > > I do not know what is the mechanism for which xfs cannot unmap > blocks from dm-thin, but it really can't. > If anyone has dm-thin installed he can try. This is 100% > reproducible for me. I was initially surprised by this considering the thinp-test-suite does test a compilebench workload against xfs and ext4 using online discard (-o discard). But I just modified that test to use a thin-pool with 'ignore_discard' and the test still passed on both ext4 and xfs. So there is more work needed in the thinp-test-suite to use blktrace hooks to verify that discards are occuring when the compilebench generated files are removed. I'll work through that and report back.