From: Ming Lei <ming.lei@redhat.com>
To: Nitesh Shetty <nj.shetty@samsung.com>
Cc: axboe@kernel.dk, agk@redhat.com, snitzer@kernel.org,
dm-devel@redhat.com, kbusch@kernel.org, hch@lst.de,
sagi@grimberg.me, james.smart@broadcom.com, kch@nvidia.com,
damien.lemoal@opensource.wdc.com, naohiro.aota@wdc.com,
jth@kernel.org, viro@zeniv.linux.org.uk,
linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-nvme@lists.infradead.org, linux-fsdevel@vger.kernel.org,
anuj20.g@samsung.com, joshi.k@samsung.com, p.raghav@samsung.com,
nitheshshetty@gmail.com, gost.dev@samsung.com,
ming.lei@redhat.com
Subject: Re: [PATCH v5 02/10] block: Add copy offload support infrastructure
Date: Wed, 23 Nov 2022 16:04:18 +0800 [thread overview]
Message-ID: <Y33UAp6ncSPO84XI@T590> (raw)
In-Reply-To: <20221123055827.26996-3-nj.shetty@samsung.com>
On Wed, Nov 23, 2022 at 11:28:19AM +0530, Nitesh Shetty wrote:
> Introduce blkdev_issue_copy which supports source and destination bdevs,
> and an array of (source, destination and copy length) tuples.
> Introduce REQ_COPY copy offload operation flag. Create a read-write
> bio pair with a token as payload and submitted to the device in order.
> Read request populates token with source specific information which
> is then passed with write request.
> This design is courtesy Mikulas Patocka's token based copy
I thought this patchset is just for enabling copy command which is
supported by hardware. But turns out it isn't, because blk_copy_offload()
still submits read/write bios for doing the copy.
I am just wondering why not let copy_file_range() cover this kind of copy,
and the framework has been there.
When I was researching pipe/splice code for supporting ublk zero copy[1], I
have got idea for async copy_file_range(), such as: io uring based
direct splice, user backed intermediate buffer, still zero copy, if these
ideas are finally implemented, we could get super-fast generic offload copy,
and bdev copy is really covered too.
[1] https://lore.kernel.org/linux-block/20221103085004.1029763-1-ming.lei@redhat.com/
thanks,
Ming
WARNING: multiple messages have this Message-ID (diff)
From: Ming Lei <ming.lei@redhat.com>
To: Nitesh Shetty <nj.shetty@samsung.com>
Cc: linux-nvme@lists.infradead.org, dm-devel@redhat.com, hch@lst.de,
agk@redhat.com, naohiro.aota@wdc.com, sagi@grimberg.me,
gost.dev@samsung.com, damien.lemoal@opensource.wdc.com,
james.smart@broadcom.com, p.raghav@samsung.com, kch@nvidia.com,
anuj20.g@samsung.com, snitzer@kernel.org, ming.lei@redhat.com,
linux-block@vger.kernel.org, viro@zeniv.linux.org.uk,
kbusch@kernel.org, axboe@kernel.dk, joshi.k@samsung.com,
linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
jth@kernel.org, nitheshshetty@gmail.com
Subject: Re: [dm-devel] [PATCH v5 02/10] block: Add copy offload support infrastructure
Date: Wed, 23 Nov 2022 16:04:18 +0800 [thread overview]
Message-ID: <Y33UAp6ncSPO84XI@T590> (raw)
In-Reply-To: <20221123055827.26996-3-nj.shetty@samsung.com>
On Wed, Nov 23, 2022 at 11:28:19AM +0530, Nitesh Shetty wrote:
> Introduce blkdev_issue_copy which supports source and destination bdevs,
> and an array of (source, destination and copy length) tuples.
> Introduce REQ_COPY copy offload operation flag. Create a read-write
> bio pair with a token as payload and submitted to the device in order.
> Read request populates token with source specific information which
> is then passed with write request.
> This design is courtesy Mikulas Patocka's token based copy
I thought this patchset is just for enabling copy command which is
supported by hardware. But turns out it isn't, because blk_copy_offload()
still submits read/write bios for doing the copy.
I am just wondering why not let copy_file_range() cover this kind of copy,
and the framework has been there.
When I was researching pipe/splice code for supporting ublk zero copy[1], I
have got idea for async copy_file_range(), such as: io uring based
direct splice, user backed intermediate buffer, still zero copy, if these
ideas are finally implemented, we could get super-fast generic offload copy,
and bdev copy is really covered too.
[1] https://lore.kernel.org/linux-block/20221103085004.1029763-1-ming.lei@redhat.com/
thanks,
Ming
--
dm-devel mailing list
dm-devel@redhat.com
https://listman.redhat.com/mailman/listinfo/dm-devel
next prev parent reply other threads:[~2022-11-23 8:05 UTC|newest]
Thread overview: 69+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CGME20221123061010epcas5p21cef9d23e4362b01f2b19d1117e1cdf5@epcas5p2.samsung.com>
2022-11-23 5:58 ` [PATCH v5 00/10] Implement copy offload support Nitesh Shetty
2022-11-23 5:58 ` [dm-devel] " Nitesh Shetty
[not found] ` <CGME20221123061014epcas5p150fd8add12fe6d09b63c56972818e6a2@epcas5p1.samsung.com>
2022-11-23 5:58 ` [PATCH v5 01/10] block: Introduce queue limits for copy-offload support Nitesh Shetty
2022-11-23 5:58 ` [dm-devel] " Nitesh Shetty
[not found] ` <CGME20221123061017epcas5p246a589e20eac655ac340cfda6028ff35@epcas5p2.samsung.com>
2022-11-23 5:58 ` [PATCH v5 02/10] block: Add copy offload support infrastructure Nitesh Shetty
2022-11-23 5:58 ` [dm-devel] " Nitesh Shetty
2022-11-23 8:04 ` Ming Lei [this message]
2022-11-23 8:04 ` Ming Lei
2022-11-23 10:07 ` Nitesh Shetty
2022-11-23 10:07 ` [dm-devel] " Nitesh Shetty
2022-11-24 0:03 ` Ming Lei
2022-11-24 0:03 ` [dm-devel] " Ming Lei
2022-11-29 11:44 ` Nitesh Shetty
2022-11-29 11:44 ` [dm-devel] " Nitesh Shetty
2022-12-07 5:54 ` Nitesh Shetty
2022-12-07 5:54 ` [dm-devel] " Nitesh Shetty
2022-12-07 11:19 ` Ming Lei
2022-12-07 11:19 ` [dm-devel] " Ming Lei
2022-12-09 8:16 ` Nitesh Shetty
2022-12-09 8:16 ` [dm-devel] " Nitesh Shetty
[not found] ` <CGME20221123061021epcas5p276b6d48db889932282d017b27c9a3291@epcas5p2.samsung.com>
2022-11-23 5:58 ` [PATCH v5 03/10] block: add emulation for copy Nitesh Shetty
2022-11-23 5:58 ` [dm-devel] " Nitesh Shetty
[not found] ` <CGME20221123061024epcas5p28fd0296018950d722b5a97e2875cf391@epcas5p2.samsung.com>
2022-11-23 5:58 ` [PATCH v5 04/10] block: Introduce a new ioctl " Nitesh Shetty
2022-11-23 5:58 ` [dm-devel] " Nitesh Shetty
[not found] ` <CGME20221123061028epcas5p1aecd27b2f4f694b5a18b51d3df5d7432@epcas5p1.samsung.com>
2022-11-23 5:58 ` [PATCH v5 05/10] nvme: add copy offload support Nitesh Shetty
2022-11-23 5:58 ` [dm-devel] " Nitesh Shetty
[not found] ` <CGME20221123061031epcas5p3745558c2caffd2fd21d15feff00495e9@epcas5p3.samsung.com>
2022-11-23 5:58 ` [PATCH v5 06/10] nvmet: add copy command support for bdev and file ns Nitesh Shetty
2022-11-23 5:58 ` [dm-devel] " Nitesh Shetty
2022-11-23 8:17 ` Guixin Liu
2022-11-23 9:39 ` Nitesh Shetty
2022-11-23 9:39 ` [dm-devel] " Nitesh Shetty
2022-12-06 9:22 ` kernel test robot
2022-12-06 9:22 ` [dm-devel] " kernel test robot
[not found] ` <CGME20221123061034epcas5p3fe90293ad08df4901f98bae2d7cfc1ba@epcas5p3.samsung.com>
2022-11-23 5:58 ` [PATCH v5 07/10] dm: Add support for copy offload Nitesh Shetty
2022-11-23 5:58 ` [dm-devel] " Nitesh Shetty
[not found] ` <CGME20221123061037epcas5p4d57436204fbe0065819b156eeeddbfac@epcas5p4.samsung.com>
2022-11-23 5:58 ` [PATCH v5 08/10] dm: Enable copy offload for dm-linear target Nitesh Shetty
2022-11-23 5:58 ` [dm-devel] " Nitesh Shetty
[not found] ` <CGME20221123061041epcas5p4413569a46ee730cd3033a9025c8f134a@epcas5p4.samsung.com>
2022-11-23 5:58 ` [PATCH v5 09/10] dm kcopyd: use copy offload support Nitesh Shetty
2022-11-23 5:58 ` [dm-devel] " Nitesh Shetty
[not found] ` <CGME20221123061044epcas5p2ac082a91fc8197821f29e84278b6203c@epcas5p2.samsung.com>
2022-11-23 5:58 ` [PATCH v5 10/10] fs: add support for copy file range in zonefs Nitesh Shetty
2022-11-23 5:58 ` [dm-devel] " Nitesh Shetty
2022-11-23 6:53 ` Amir Goldstein
2022-11-23 6:53 ` [dm-devel] " Amir Goldstein
2022-11-23 10:13 ` Nitesh Shetty
2022-11-23 10:13 ` [dm-devel] " Nitesh Shetty
2022-11-24 1:32 ` Damien Le Moal
2022-11-24 1:32 ` [dm-devel] " Damien Le Moal
2022-11-24 1:47 ` Damien Le Moal
2022-11-24 1:47 ` [dm-devel] " Damien Le Moal
2022-11-25 4:18 ` Al Viro
2022-11-25 4:18 ` [dm-devel] " Al Viro
2022-11-29 12:22 ` Nitesh Shetty
2022-11-29 12:22 ` [dm-devel] " Nitesh Shetty
2022-11-29 23:45 ` Damien Le Moal
2022-11-29 23:45 ` [dm-devel] " Damien Le Moal
2022-11-30 4:17 ` Nitesh Shetty
2022-11-30 4:17 ` [dm-devel] " Nitesh Shetty
2022-11-30 9:55 ` Damien Le Moal
2022-11-30 9:55 ` [dm-devel] " Damien Le Moal
2022-11-23 22:56 ` [PATCH v5 00/10] Implement copy offload support Chaitanya Kulkarni
2022-11-23 22:56 ` [dm-devel] " Chaitanya Kulkarni
2022-11-29 12:16 ` Nitesh Shetty
2022-11-29 12:16 ` [dm-devel] " Nitesh Shetty
2022-11-30 0:05 ` Chaitanya Kulkarni
2022-11-30 0:05 ` [dm-devel] " Chaitanya Kulkarni
2022-11-30 4:14 ` Nitesh Shetty
2022-11-30 4:14 ` [dm-devel] " Nitesh Shetty
2022-12-02 16:45 [PATCH v5 02/10] block: Add copy offload support infrastructure kernel test robot
2022-12-06 23:31 kernel test robot
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=Y33UAp6ncSPO84XI@T590 \
--to=ming.lei@redhat.com \
--cc=agk@redhat.com \
--cc=anuj20.g@samsung.com \
--cc=axboe@kernel.dk \
--cc=damien.lemoal@opensource.wdc.com \
--cc=dm-devel@redhat.com \
--cc=gost.dev@samsung.com \
--cc=hch@lst.de \
--cc=james.smart@broadcom.com \
--cc=joshi.k@samsung.com \
--cc=jth@kernel.org \
--cc=kbusch@kernel.org \
--cc=kch@nvidia.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=naohiro.aota@wdc.com \
--cc=nitheshshetty@gmail.com \
--cc=nj.shetty@samsung.com \
--cc=p.raghav@samsung.com \
--cc=sagi@grimberg.me \
--cc=snitzer@kernel.org \
--cc=viro@zeniv.linux.org.uk \
/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: link
Be 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.