From: Bart Van Assche <bvanassche@acm.org> To: Mikulas Patocka <mpatocka@redhat.com> Cc: "linux-block@vger.kernel.org" <linux-block@vger.kernel.org>, "linux-scsi@vger.kernel.org" <linux-scsi@vger.kernel.org>, "dm-devel@redhat.com" <dm-devel@redhat.com>, "linux-nvme@lists.infradead.org" <linux-nvme@lists.infradead.org>, linux-fsdevel <linux-fsdevel@vger.kernel.org> Subject: Re: [RFC PATCH 1/3] block: add copy offload support Date: Tue, 1 Feb 2022 11:18:41 -0800 [thread overview] Message-ID: <efd2e976-4d2d-178e-890d-9bde1a89c47f@acm.org> (raw) In-Reply-To: <alpine.LRH.2.02.2202011331570.22481@file01.intranet.prod.int.rdu2.redhat.com> On 2/1/22 10:32, Mikulas Patocka wrote: > /** > + * blk_queue_max_copy_sectors - set maximum copy offload sectors for the queue > + * @q: the request queue for the device > + * @size: the maximum copy offload sectors > + */ > +void blk_queue_max_copy_sectors(struct request_queue *q, unsigned int size) > +{ > + q->limits.max_copy_sectors = size; > +} > +EXPORT_SYMBOL_GPL(blk_queue_max_copy_sectors); Please either change the unit of 'size' into bytes or change its type into sector_t. > +extern int blkdev_issue_copy(struct block_device *bdev1, sector_t sector1, > + struct block_device *bdev2, sector_t sector2, > + sector_t nr_sects, sector_t *copied, gfp_t gfp_mask); > + Only supporting copying between contiguous LBA ranges seems restrictive to me. I expect garbage collection by filesystems for UFS devices to perform better if multiple LBA ranges are submitted as a single SCSI XCOPY command. A general comment about the approach: encoding the LBA range information in a bio payload is not compatible with bio splitting. How can the dm driver implement copy offloading without the ability to split copy offload bio's? > +int blkdev_issue_copy(struct block_device *bdev1, sector_t sector1, > + struct block_device *bdev2, sector_t sector2, > + sector_t nr_sects, sector_t *copied, gfp_t gfp_mask) > +{ > + struct page *token; > + sector_t m; > + int r = 0; > + struct completion comp; Consider using DECLARE_COMPLETION_ONSTACK() instead of a separate declaration and init_completion() call. Thanks, Bart.
WARNING: multiple messages have this Message-ID (diff)
From: Bart Van Assche <bvanassche@acm.org> To: Mikulas Patocka <mpatocka@redhat.com> Cc: "linux-block@vger.kernel.org" <linux-block@vger.kernel.org>, linux-fsdevel <linux-fsdevel@vger.kernel.org>, "dm-devel@redhat.com" <dm-devel@redhat.com>, "linux-nvme@lists.infradead.org" <linux-nvme@lists.infradead.org>, "linux-scsi@vger.kernel.org" <linux-scsi@vger.kernel.org> Subject: Re: [dm-devel] [RFC PATCH 1/3] block: add copy offload support Date: Tue, 1 Feb 2022 11:18:41 -0800 [thread overview] Message-ID: <efd2e976-4d2d-178e-890d-9bde1a89c47f@acm.org> (raw) In-Reply-To: <alpine.LRH.2.02.2202011331570.22481@file01.intranet.prod.int.rdu2.redhat.com> On 2/1/22 10:32, Mikulas Patocka wrote: > /** > + * blk_queue_max_copy_sectors - set maximum copy offload sectors for the queue > + * @q: the request queue for the device > + * @size: the maximum copy offload sectors > + */ > +void blk_queue_max_copy_sectors(struct request_queue *q, unsigned int size) > +{ > + q->limits.max_copy_sectors = size; > +} > +EXPORT_SYMBOL_GPL(blk_queue_max_copy_sectors); Please either change the unit of 'size' into bytes or change its type into sector_t. > +extern int blkdev_issue_copy(struct block_device *bdev1, sector_t sector1, > + struct block_device *bdev2, sector_t sector2, > + sector_t nr_sects, sector_t *copied, gfp_t gfp_mask); > + Only supporting copying between contiguous LBA ranges seems restrictive to me. I expect garbage collection by filesystems for UFS devices to perform better if multiple LBA ranges are submitted as a single SCSI XCOPY command. A general comment about the approach: encoding the LBA range information in a bio payload is not compatible with bio splitting. How can the dm driver implement copy offloading without the ability to split copy offload bio's? > +int blkdev_issue_copy(struct block_device *bdev1, sector_t sector1, > + struct block_device *bdev2, sector_t sector2, > + sector_t nr_sects, sector_t *copied, gfp_t gfp_mask) > +{ > + struct page *token; > + sector_t m; > + int r = 0; > + struct completion comp; Consider using DECLARE_COMPLETION_ONSTACK() instead of a separate declaration and init_completion() call. Thanks, Bart. -- dm-devel mailing list dm-devel@redhat.com https://listman.redhat.com/mailman/listinfo/dm-devel
next prev parent reply other threads:[~2022-02-01 19:18 UTC|newest] Thread overview: 183+ messages / expand[flat|nested] mbox.gz Atom feed top [not found] <CGME20220127071544uscas1p2f70f4d2509f3ebd574b7ed746d3fa551@uscas1p2.samsung.com> 2022-01-27 7:14 ` [LSF/MM/BFP ATTEND] [LSF/MM/BFP TOPIC] Storage: Copy Offload Chaitanya Kulkarni 2022-01-28 19:59 ` Adam Manzanares 2022-01-28 19:59 ` [dm-devel] " Adam Manzanares 2022-01-31 11:49 ` Johannes Thumshirn 2022-01-31 11:49 ` Johannes Thumshirn 2022-01-31 19:03 ` Bart Van Assche 2022-01-31 19:03 ` [dm-devel] " Bart Van Assche 2022-02-01 1:54 ` Luis Chamberlain 2022-02-01 1:54 ` Luis Chamberlain 2022-02-01 10:21 ` Javier González 2022-02-01 18:31 ` [RFC PATCH 0/3] NVMe copy offload patches Mikulas Patocka 2022-02-01 18:31 ` [dm-devel] " Mikulas Patocka 2022-02-01 18:32 ` [RFC PATCH 1/3] block: add copy offload support Mikulas Patocka 2022-02-01 18:32 ` [dm-devel] " Mikulas Patocka 2022-02-01 19:18 ` Bart Van Assche [this message] 2022-02-01 19:18 ` Bart Van Assche 2022-02-03 18:50 ` Mikulas Patocka 2022-02-03 18:50 ` Mikulas Patocka 2022-02-03 20:11 ` Keith Busch 2022-02-03 20:11 ` [dm-devel] " Keith Busch 2022-02-03 22:49 ` Bart Van Assche 2022-02-03 22:49 ` Bart Van Assche 2022-02-04 12:09 ` [dm-devel] " Mikulas Patocka 2022-02-04 12:09 ` Mikulas Patocka 2022-02-04 13:34 ` Jens Axboe 2022-02-04 13:34 ` [dm-devel] " Jens Axboe 2022-02-02 16:21 ` Keith Busch 2022-02-02 16:21 ` [dm-devel] " Keith Busch 2022-02-02 16:40 ` Mikulas Patocka 2022-02-02 16:40 ` [dm-devel] " Mikulas Patocka 2022-02-02 18:40 ` Knight, Frederick 2022-02-02 18:40 ` [dm-devel] " Knight, Frederick 2022-02-01 18:33 ` [RFC PATCH 2/3] nvme: " Mikulas Patocka 2022-02-01 18:33 ` [dm-devel] " Mikulas Patocka 2022-02-01 19:18 ` Bart Van Assche 2022-02-01 19:18 ` [dm-devel] " Bart Van Assche 2022-02-01 19:25 ` Mikulas Patocka 2022-02-01 19:25 ` [dm-devel] " Mikulas Patocka 2022-02-01 18:33 ` [RFC PATCH 3/3] nvme: add the "debug" host driver Mikulas Patocka 2022-02-01 18:33 ` [dm-devel] " Mikulas Patocka 2022-02-01 21:32 ` kernel test robot 2022-02-02 6:01 ` Adam Manzanares 2022-02-02 6:01 ` [dm-devel] " Adam Manzanares 2022-02-03 16:06 ` Luis Chamberlain 2022-02-03 16:06 ` Luis Chamberlain 2022-02-03 16:15 ` [dm-devel] " Christoph Hellwig 2022-02-03 16:15 ` Christoph Hellwig 2022-02-03 19:34 ` Luis Chamberlain 2022-02-03 19:34 ` [dm-devel] " Luis Chamberlain 2022-02-03 19:46 ` Adam Manzanares 2022-02-03 19:46 ` [dm-devel] " Adam Manzanares 2022-02-03 20:57 ` Mikulas Patocka 2022-02-03 20:57 ` Mikulas Patocka 2022-02-03 22:52 ` Adam Manzanares 2022-02-03 22:52 ` [dm-devel] " Adam Manzanares 2022-02-04 3:00 ` Chaitanya Kulkarni 2022-02-04 3:00 ` [dm-devel] " Chaitanya Kulkarni 2022-02-04 3:05 ` Chaitanya Kulkarni 2022-02-04 3:05 ` [dm-devel] " Chaitanya Kulkarni 2022-02-02 7:23 ` kernel test robot 2022-02-02 7:23 ` kernel test robot 2022-02-02 8:00 ` Chaitanya Kulkarni 2022-02-02 8:00 ` [dm-devel] " Chaitanya Kulkarni 2022-02-02 12:38 ` Klaus Jensen 2022-02-02 12:38 ` [dm-devel] " Klaus Jensen 2022-02-03 15:38 ` Luis Chamberlain 2022-02-03 15:38 ` Luis Chamberlain 2022-02-03 16:52 ` Keith Busch 2022-02-03 16:52 ` [dm-devel] " Keith Busch 2022-02-03 19:50 ` Adam Manzanares 2022-02-03 19:50 ` [dm-devel] " Adam Manzanares 2022-02-04 3:12 ` Chaitanya Kulkarni 2022-02-04 3:12 ` [dm-devel] " Chaitanya Kulkarni 2022-02-04 6:28 ` Damien Le Moal 2022-02-04 6:28 ` [dm-devel] " Damien Le Moal 2022-02-04 7:58 ` Chaitanya Kulkarni 2022-02-04 7:58 ` [dm-devel] " Chaitanya Kulkarni 2022-02-04 8:24 ` Javier González 2022-02-04 8:24 ` [dm-devel] " Javier González 2022-02-04 9:58 ` Chaitanya Kulkarni 2022-02-04 9:58 ` [dm-devel] " Chaitanya Kulkarni 2022-02-04 11:34 ` Javier González 2022-02-04 11:34 ` [dm-devel] " Javier González 2022-02-04 14:15 ` Hannes Reinecke 2022-02-04 14:15 ` [dm-devel] " Hannes Reinecke 2022-02-04 14:24 ` Keith Busch 2022-02-04 14:24 ` [dm-devel] " Keith Busch 2022-02-04 16:01 ` Christoph Hellwig 2022-02-04 16:01 ` [dm-devel] " Christoph Hellwig 2022-02-04 19:41 ` [RFC PATCH 0/3] NVMe copy offload patches Nitesh Shetty 2022-02-04 19:41 ` [dm-devel] " Nitesh Shetty [not found] ` <CGME20220207141901epcas5p162ec2387815be7a1fd67ce0ab7082119@epcas5p1.samsung.com> 2022-02-07 14:13 ` [PATCH v2 00/10] Add Copy offload support Nitesh Shetty 2022-02-07 14:13 ` [dm-devel] " Nitesh Shetty [not found] ` <CGME20220207141908epcas5p4f270c89fc32434ea8b525fa973098231@epcas5p4.samsung.com> 2022-02-07 14:13 ` [PATCH v2 01/10] block: make bio_map_kern() non static Nitesh Shetty 2022-02-07 14:13 ` [dm-devel] " Nitesh Shetty [not found] ` <CGME20220207141913epcas5p4d41cb549b7cca1ede5c7a66bbd110da0@epcas5p4.samsung.com> 2022-02-07 14:13 ` [PATCH v2 02/10] block: Introduce queue limits for copy-offload support Nitesh Shetty 2022-02-07 14:13 ` [dm-devel] " Nitesh Shetty 2022-02-08 7:01 ` Damien Le Moal 2022-02-08 7:01 ` [dm-devel] " Damien Le Moal 2022-02-08 18:43 ` Nitesh Shetty 2022-02-08 18:43 ` [dm-devel] " Nitesh Shetty [not found] ` <CGME20220207141918epcas5p4f9badc0c3f3f0913f091c850d2d3bd81@epcas5p4.samsung.com> 2022-02-07 14:13 ` [PATCH v2 03/10] block: Add copy offload support infrastructure Nitesh Shetty 2022-02-07 14:13 ` [dm-devel] " Nitesh Shetty 2022-02-07 22:45 ` kernel test robot 2022-02-07 22:45 ` kernel test robot 2022-02-07 22:45 ` [dm-devel] " kernel test robot 2022-02-07 23:26 ` kernel test robot 2022-02-07 23:26 ` kernel test robot 2022-02-07 23:26 ` [dm-devel] " kernel test robot 2022-02-08 7:21 ` Damien Le Moal 2022-02-08 7:21 ` [dm-devel] " Damien Le Moal 2022-02-09 10:22 ` Nitesh Shetty 2022-02-09 10:22 ` [dm-devel] " Nitesh Shetty [not found] ` <CGME20220207141924epcas5p26ad9cf5de732224f408aded12ed0a577@epcas5p2.samsung.com> 2022-02-07 14:13 ` [PATCH v2 04/10] block: Introduce a new ioctl for copy Nitesh Shetty 2022-02-07 14:13 ` [dm-devel] " Nitesh Shetty 2022-02-09 3:39 ` kernel test robot 2022-02-09 3:39 ` kernel test robot 2022-02-09 3:39 ` kernel test robot [not found] ` <CGME20220207141930epcas5p2bcbff65f78ad1dede64648d73ddb3770@epcas5p2.samsung.com> 2022-02-07 14:13 ` [PATCH v2 05/10] block: add emulation " Nitesh Shetty 2022-02-07 14:13 ` [dm-devel] " Nitesh Shetty 2022-02-08 3:20 ` kernel test robot 2022-02-08 3:20 ` kernel test robot 2022-02-08 3:20 ` [dm-devel] " kernel test robot 2022-02-16 13:32 ` Mikulas Patocka 2022-02-16 13:32 ` Mikulas Patocka 2022-02-17 13:18 ` Nitesh Shetty 2022-02-17 13:18 ` [dm-devel] " Nitesh Shetty [not found] ` <CGME20220207141937epcas5p2bd57ae35056c69b3e2f9ee2348d6af19@epcas5p2.samsung.com> 2022-02-07 14:13 ` [PATCH v2 06/10] nvme: add copy support Nitesh Shetty 2022-02-07 14:13 ` [dm-devel] " Nitesh Shetty 2022-02-10 7:08 ` kernel test robot 2022-02-10 7:08 ` kernel test robot 2022-02-10 7:08 ` kernel test robot [not found] ` <CGME20220207141942epcas5p4bda894a5833513c9211dcecc7928a951@epcas5p4.samsung.com> 2022-02-07 14:13 ` [PATCH v2 07/10] nvmet: add copy command support for bdev and file ns Nitesh Shetty 2022-02-07 14:13 ` [dm-devel] " Nitesh Shetty 2022-02-07 18:10 ` kernel test robot 2022-02-07 18:10 ` kernel test robot 2022-02-07 18:10 ` [dm-devel] " kernel test robot 2022-02-07 20:12 ` kernel test robot 2022-02-07 20:12 ` kernel test robot 2022-02-07 20:12 ` [dm-devel] " kernel test robot 2022-02-10 8:31 ` kernel test robot 2022-02-10 8:31 ` kernel test robot 2022-02-10 8:31 ` kernel test robot [not found] ` <CGME20220207141948epcas5p4534f6bdc5a1e2e676d7d09c04f8b4a5b@epcas5p4.samsung.com> 2022-02-07 14:13 ` [PATCH v2 08/10] dm: Add support for copy offload Nitesh Shetty 2022-02-07 14:13 ` [dm-devel] " Nitesh Shetty 2022-02-16 13:51 ` Mikulas Patocka 2022-02-16 13:51 ` Mikulas Patocka 2022-02-24 12:42 ` Nitesh Shetty 2022-02-24 12:42 ` [dm-devel] " Nitesh Shetty 2022-02-25 9:12 ` Mikulas Patocka 2022-02-25 9:12 ` [dm-devel] " Mikulas Patocka [not found] ` <CGME20220207141953epcas5p32ccc3c0bbe642cea074edefcc32302a5@epcas5p3.samsung.com> 2022-02-07 14:13 ` [PATCH v2 09/10] dm: Enable copy offload for dm-linear target Nitesh Shetty 2022-02-07 14:13 ` [dm-devel] " Nitesh Shetty [not found] ` <CGME20220207141958epcas5p25f1cd06726217696d13c2dfbea010565@epcas5p2.samsung.com> 2022-02-07 14:13 ` [PATCH v2 10/10] dm kcopyd: use copy offload support Nitesh Shetty 2022-02-07 14:13 ` [dm-devel] " Nitesh Shetty 2022-02-07 9:57 ` [LSF/MM/BFP ATTEND] [LSF/MM/BFP TOPIC] Storage: Copy Offload Nitesh Shetty 2022-02-07 9:57 ` [dm-devel] " Nitesh Shetty 2022-02-02 5:57 ` Kanchan Joshi 2022-02-02 5:57 ` [dm-devel] " Kanchan Joshi 2022-02-07 10:45 ` David Disseldorp 2022-02-07 10:45 ` [dm-devel] " David Disseldorp 2022-03-01 17:34 ` Nikos Tsironis 2022-03-01 17:34 ` [dm-devel] " Nikos Tsironis 2022-03-01 21:32 ` Chaitanya Kulkarni 2022-03-03 18:36 ` [dm-devel] " Nikos Tsironis 2022-03-03 18:36 ` Nikos Tsironis 2022-03-08 20:48 ` Nikos Tsironis 2022-03-08 20:48 ` [dm-devel] " Nikos Tsironis 2022-03-09 8:51 ` Mikulas Patocka 2022-03-09 8:51 ` Mikulas Patocka 2022-03-09 15:49 ` Nikos Tsironis 2022-03-09 15:49 ` [dm-devel] " Nikos Tsironis [not found] <CGME20220209075901epcas5p3cff468deadd8ef836522f032bd4ed36c@epcas5p3.samsung.com> 2022-02-08 23:31 ` [PATCH v2 03/10] block: Add copy offload support infrastructure kernel test robot 2022-02-09 7:48 ` Dan Carpenter 2022-02-09 7:48 ` [dm-devel] " Dan Carpenter 2022-02-09 7:48 ` Dan Carpenter 2022-02-09 10:32 ` Nitesh Shetty 2022-02-10 6:13 ` Nitesh Shetty 2022-02-09 10:32 ` [dm-devel] " Nitesh Shetty 2022-02-10 22:49 [PATCH v2 07/10] nvmet: add copy command support for bdev and file ns kernel test robot 2022-02-11 7:52 ` Dan Carpenter 2022-02-11 7:52 ` [dm-devel] " Dan Carpenter 2022-02-11 7:52 ` Dan Carpenter
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=efd2e976-4d2d-178e-890d-9bde1a89c47f@acm.org \ --to=bvanassche@acm.org \ --cc=dm-devel@redhat.com \ --cc=linux-block@vger.kernel.org \ --cc=linux-fsdevel@vger.kernel.org \ --cc=linux-nvme@lists.infradead.org \ --cc=linux-scsi@vger.kernel.org \ --cc=mpatocka@redhat.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.