From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Martin K. Petersen" Subject: Re: remove REQ_OP_WRITE_SAME Date: Thu, 13 Apr 2017 22:23:10 -0400 Message-ID: References: <20170412084809.8245-1-hch@lst.de> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20170412084809.8245-1-hch-jcswGhMUV9g@public.gmane.org> (Christoph Hellwig's message of "Wed, 12 Apr 2017 10:48:01 +0200") List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: drbd-dev-bounces-cunTk1MwBs8qoQakbn7OcQ@public.gmane.org Errors-To: drbd-dev-bounces-cunTk1MwBs8qoQakbn7OcQ@public.gmane.org To: Christoph Hellwig Cc: axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org, linux-scsi-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, martin.petersen-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org, philipp.reisner-63ez5xqkn6DQT0dZR+AlfA@public.gmane.org, linux-block-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, dm-devel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org, target-devel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, lars.ellenberg-63ez5xqkn6DQT0dZR+AlfA@public.gmane.org, drbd-dev-cunTk1MwBs8qoQakbn7OcQ@public.gmane.org List-Id: dm-devel.ids Christoph, > Now that we are using REQ_OP_WRITE_ZEROES for all zeroing needs in the > kernel there is very little use left for REQ_OP_WRITE_SAME. We only > have two callers left, and both just export optional protocol features > to remote systems: DRBD and the target code. While I'm not particularly married to WRITE SAME, I do think it's a shame that the RAID5/6 code never started using it. It does make a difference when initializing RAID sets. The other thing that keeps me a bit on the fence is that a bunch of the plumbing to handle a bio with a payload different from bi_size is needed for the copy offload token. I'm hoping to have those patches ready for 4.13. Right now there are a bunch of places where handling of REQ_OP_COPY_IN and REQ_OP_COPY_OUT share conditionals with WRITE SAME. So I suggest postponing the decision about whether to rip out WRITE SAME until I finish the token stuff. -- Martin K. Petersen Oracle Linux Engineering From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: To: Christoph Hellwig Cc: axboe@kernel.dk, martin.petersen@oracle.com, philipp.reisner@linbit.com, lars.ellenberg@linbit.com, target-devel@vger.kernel.org, linux-block@vger.kernel.org, linux-scsi@vger.kernel.org, drbd-dev@lists.linbit.com, dm-devel@redhat.com Subject: Re: remove REQ_OP_WRITE_SAME From: "Martin K. Petersen" References: <20170412084809.8245-1-hch@lst.de> Date: Thu, 13 Apr 2017 22:23:10 -0400 In-Reply-To: <20170412084809.8245-1-hch@lst.de> (Christoph Hellwig's message of "Wed, 12 Apr 2017 10:48:01 +0200") Message-ID: MIME-Version: 1.0 Content-Type: text/plain List-ID: Christoph, > Now that we are using REQ_OP_WRITE_ZEROES for all zeroing needs in the > kernel there is very little use left for REQ_OP_WRITE_SAME. We only > have two callers left, and both just export optional protocol features > to remote systems: DRBD and the target code. While I'm not particularly married to WRITE SAME, I do think it's a shame that the RAID5/6 code never started using it. It does make a difference when initializing RAID sets. The other thing that keeps me a bit on the fence is that a bunch of the plumbing to handle a bio with a payload different from bi_size is needed for the copy offload token. I'm hoping to have those patches ready for 4.13. Right now there are a bunch of places where handling of REQ_OP_COPY_IN and REQ_OP_COPY_OUT share conditionals with WRITE SAME. So I suggest postponing the decision about whether to rip out WRITE SAME until I finish the token stuff. -- Martin K. Petersen Oracle Linux Engineering From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from userp1040.oracle.com (userp1040.oracle.com [156.151.31.81]) by mail09.linbit.com (LINBIT Mail Daemon) with ESMTP id A5981105645E for ; Fri, 14 Apr 2017 04:23:24 +0200 (CEST) To: Christoph Hellwig From: "Martin K. Petersen" References: <20170412084809.8245-1-hch@lst.de> Date: Thu, 13 Apr 2017 22:23:10 -0400 In-Reply-To: <20170412084809.8245-1-hch@lst.de> (Christoph Hellwig's message of "Wed, 12 Apr 2017 10:48:01 +0200") Message-ID: MIME-Version: 1.0 Content-Type: text/plain Cc: axboe@kernel.dk, linux-scsi@vger.kernel.org, martin.petersen@oracle.com, philipp.reisner@linbit.com, linux-block@vger.kernel.org, dm-devel@redhat.com, target-devel@vger.kernel.org, lars.ellenberg@linbit.com, drbd-dev@lists.linbit.com Subject: Re: [Drbd-dev] remove REQ_OP_WRITE_SAME List-Id: "*Coordination* of development, patches, contributions -- *Questions* \(even to developers\) go to drbd-user, please." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Christoph, > Now that we are using REQ_OP_WRITE_ZEROES for all zeroing needs in the > kernel there is very little use left for REQ_OP_WRITE_SAME. We only > have two callers left, and both just export optional protocol features > to remote systems: DRBD and the target code. While I'm not particularly married to WRITE SAME, I do think it's a shame that the RAID5/6 code never started using it. It does make a difference when initializing RAID sets. The other thing that keeps me a bit on the fence is that a bunch of the plumbing to handle a bio with a payload different from bi_size is needed for the copy offload token. I'm hoping to have those patches ready for 4.13. Right now there are a bunch of places where handling of REQ_OP_COPY_IN and REQ_OP_COPY_OUT share conditionals with WRITE SAME. So I suggest postponing the decision about whether to rip out WRITE SAME until I finish the token stuff. -- Martin K. Petersen Oracle Linux Engineering