From: Theodore Tso Subject: Re: Potential bug in mballoc --- reusing data blocks before txn commit Date: Mon, 29 Sep 2008 19:00:31 -0400 Message-ID: <20080929230031.GK10831@mit.edu> References: <48E138B2.8080707@sun.com> <20080929205712.GH10831@mit.edu> <48E142C4.7090809@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Alex Tomas , Andreas Dilger , linux-ext4@vger.kernel.org To: Ric Wheeler Return-path: Received: from www.church-of-our-saviour.org ([69.25.196.31]:53256 "EHLO thunker.thunk.org" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751337AbYI2XAd (ORCPT ); Mon, 29 Sep 2008 19:00:33 -0400 Content-Disposition: inline In-Reply-To: <48E142C4.7090809@redhat.com> Sender: linux-ext4-owner@vger.kernel.org List-ID: On Mon, Sep 29, 2008 at 05:04:04PM -0400, Ric Wheeler wrote: > > I don't disagree with any of the above, just want to point out that TRIM > has a SCSI T10 cousin that is very similar (used to implement thinly > provisioned luns). We should make sure as much as possible to make our > file system level support work for both... > That's shouldn't be a problem. David Woodhouse created a standard block device interface that should be suitable both for ATA and SCSI: int blkdev_issue_discard(struct block_device *bdev, sector_t sector, unsigned nr_sects, bio_end_io_t end_io); - Ted