From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752697AbZH2XLY (ORCPT ); Sat, 29 Aug 2009 19:11:24 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752590AbZH2XLW (ORCPT ); Sat, 29 Aug 2009 19:11:22 -0400 Received: from bombadil.infradead.org ([18.85.46.34]:58937 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752231AbZH2XLV (ORCPT ); Sat, 29 Aug 2009 19:11:21 -0400 Message-Id: <20090829230332.017137693@bombadil.infradead.org> User-Agent: quilt/0.47-1 Date: Sat, 29 Aug 2009 19:03:32 -0400 From: Christoph Hellwig To: linux-scsi@vger.kernel.org, linux-ide@vger.kernel.org, linux-kernel@vger.kernel.org Cc: liml@rtr.ca, jens.axboe@oracle.com, matthew@wil.cx, dwmw2@infradead.org Subject: [PATCH 0/7] discard support revisited X-SRS-Rewrite: SMTP reverse-path rewritten from by bombadil.infradead.org See http://www.infradead.org/rpr.html Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org I've started working on discard support a little bit more, and I think it's time to get an overview over the state we're in right now. This patchswt is what I needed to get the batched discard support in XFS properly working. Many patches are just forward ported from Matthew's SSD tree and I hope quilt mail didn't lose the attributions. There are however a few significant changes: - blkdev_issue_discard is now a lot more generic - it grows a flags argument to control if we issue a barrier discard request or not or if we wait or not. That is needed for the batched discard support in XFS which wants to wait just like the ioctl interface. - I have implemented support for sending WRITE SAME requests with the unmap bit set in sd. This has been tested with a qemu-based backed only so far, but we'll get some real array coverage soon. - there is a new patch to allow larger discard requests. - the last patch is just my old batched discard patch for xfs ported to work ontop of this series. I would really love to see some progress on this in the 2.6.32 circle. We should at least get the block layer bits in that allow implementing a somewhat useful discard function. I would also love to see the actual scsi and libata implementations in so that we can start playing around with it. But given the speed up the current TRIM implementations and the expectations for WRITE SAME we should make sure the exact TRIM tracking is not actually enabled anywhere by default for now.