From: Anuj Gupta <[email protected]>
To: [email protected], [email protected], [email protected]
Cc: [email protected], [email protected],
[email protected], [email protected],
[email protected], Anuj Gupta <[email protected]>
Subject: [PATCH for-next v11 00/13] Fixed-buffer for uring-cmd/passthru
Date: Thu, 29 Sep 2022 17:36:19 +0530 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: CGME20220929121630epcas5p3e1ed2c5251276d557f8f921e8186620f@epcas5p3.samsung.com
Hi
uring-cmd lacks the ability to leverage the pre-registered buffers.
This series adds that support in uring-cmd, and plumbs nvme passthrough
to work with it.
Patch 3 and 4 contains a bunch of general nvme cleanups, which got added
along the iterations.
Patches 11, 12 and 13 carve out a block helper and scsi/nvme then use it to
avoid duplication of code.
Using registered-buffers showed IOPS hike from 1.65M to 2.04M.
Without fixedbufs
*****************
# taskset -c 0 t/io_uring -b512 -d128 -c32 -s32 -p1 -F1 -B0 -O0 -n1 -u1 /dev/ng0n1
submitter=0, tid=2481, file=/dev/ng0n1, node=-1
polled=1, fixedbufs=0/0, register_files=1, buffered=1, QD=128
Engine=io_uring, sq_ring=128, cq_ring=128
IOPS=2.60M, BW=1271MiB/s, IOS/call=32/31
IOPS=2.60M, BW=1271MiB/s, IOS/call=32/32
IOPS=2.61M, BW=1272MiB/s, IOS/call=32/32
IOPS=2.59M, BW=1266MiB/s, IOS/call=32/32
^CExiting on signal
Maximum IOPS=2.61M
With fixedbufs
**************
# taskset -c 0 t/io_uring -b512 -d128 -c32 -s32 -p1 -F1 -B1 -O0 -n1 -u1 /dev/ng0n1
submitter=0, tid=2487, file=/dev/ng0n1, node=-1
polled=1, fixedbufs=1/0, register_files=1, buffered=1, QD=128
Engine=io_uring, sq_ring=128, cq_ring=128
IOPS=3.15M, BW=1540MiB/s, IOS/call=32/31
IOPS=3.15M, BW=1538MiB/s, IOS/call=32/32
IOPS=3.15M, BW=1536MiB/s, IOS/call=32/32
IOPS=3.15M, BW=1537MiB/s, IOS/call=32/32
^CExiting on signal
Maximum IOPS=3.15M
Changes since v10:
- Patch 3: Fix overly long line (Christoph)
- Patch 4: create a helper in block-map for vectored and non-vectored-io,
to be used by scsi and nvme (Christoph)
- Patch 5: Rename bio_map_get to blk_rq_map_bio_alloc and bio_map_put to
blk_mq_map_bio_put (Christoph)
- Patch 6: Split it into a prep patch and avoid duplicate checks (Christoph)
- Patch 7: Put changes to pass ubuffer as a integer in a separate prep patch and
simplify condition checks in nvme (Christoph)
Changes since v9:
- Patch 6: Make blk_rq_map_user_iov() to operate on bvec iterator
(Christoph)
- Patch 7: Change nvme to use the above
Changes since v8:
- Split some patches further; now 7 patches rather than 5 (Christoph)
- Applied a bunch of other suggested cleanups (Christoph)
Changes since v7:
- Patch 3: added many cleanups/refactoring suggested by Christoph
- Patch 4: added copying-pages fallback for bounce-buffer/dma-alignment case
(Christoph)
Changes since v6:
- Patch 1: fix warning for io_uring_cmd_import_fixed (robot)
-
Changes since v5:
- Patch 4: newly addd, to split a nvme function into two
- Patch 3: folded cleanups in bio_map_user_iov (Chaitanya, Pankaj)
- Rebase to latest for-next
Changes since v4:
- Patch 1, 2: folded all review comments of Jens
Changes since v3:
- uring_cmd_flags, change from u16 to u32 (Jens)
- patch 3, add another helper to reduce code-duplication (Jens)
Changes since v2:
- Kill the new opcode, add a flag instead (Pavel)
- Fix standalone build issue with patch 1 (Pavel)
Changes since v1:
- Fix a naming issue for an exported helper
Anuj Gupta (6):
io_uring: add io_uring_cmd_import_fixed
io_uring: introduce fixed buffer support for io_uring_cmd
block: rename bio_map_put to blk_mq_map_bio_put
block: add blk_rq_map_user_io
scsi: Use blk_rq_map_user_io helper
nvme: Use blk_rq_map_user_io helper
Kanchan Joshi (7):
nvme: refactor nvme_add_user_metadata
nvme: refactor nvme_alloc_request
block: factor out blk_rq_map_bio_alloc helper
block: add blk_rq_map_user_bvec
block: extend functionality to map bvec iterator
nvme: pass ubuffer as an integer
nvme: wire up fixed buffer support for nvme passthrough
block/blk-map.c | 150 ++++++++++++++++++++++++++++++----
drivers/nvme/host/ioctl.c | 149 +++++++++++++++++++--------------
drivers/scsi/scsi_ioctl.c | 22 +----
drivers/scsi/sg.c | 22 +----
include/linux/blk-mq.h | 2 +
include/linux/io_uring.h | 10 ++-
include/uapi/linux/io_uring.h | 9 ++
io_uring/uring_cmd.c | 26 +++++-
8 files changed, 268 insertions(+), 122 deletions(-)
--
2.25.1
next parent reply other threads:[~2022-09-29 12:21 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CGME20220929121630epcas5p3e1ed2c5251276d557f8f921e8186620f@epcas5p3.samsung.com>
2022-09-29 12:06 ` Anuj Gupta [this message]
[not found] ` <CGME20220929121634epcas5p27400b84f8a8b43a91c4199ec39d50b51@epcas5p2.samsung.com>
2022-09-29 12:06 ` [PATCH for-next v11 01/13] io_uring: add io_uring_cmd_import_fixed Anuj Gupta
[not found] ` <CGME20220929121637epcas5p2ff344c7951037f79d117d000e405dd45@epcas5p2.samsung.com>
2022-09-29 12:06 ` [PATCH for-next v11 02/13] io_uring: introduce fixed buffer support for io_uring_cmd Anuj Gupta
2022-09-30 1:26 ` Jens Axboe
[not found] ` <CGME20220929121640epcas5p400a71aa51f374f016e2143d0228879bc@epcas5p4.samsung.com>
2022-09-29 12:06 ` [PATCH for-next v11 03/13] nvme: refactor nvme_add_user_metadata Anuj Gupta
[not found] ` <CGME20220929121643epcas5p4c58f6ebb794bde58981272cd33c69f9f@epcas5p4.samsung.com>
2022-09-29 12:06 ` [PATCH for-next v11 04/13] nvme: refactor nvme_alloc_request Anuj Gupta
2022-09-29 13:25 ` Christoph Hellwig
[not found] ` <CGME20220929121647epcas5p2d4ca8ae0b83a1fce230914f586ee3cc0@epcas5p2.samsung.com>
2022-09-29 12:06 ` [PATCH for-next v11 05/13] block: rename bio_map_put to blk_mq_map_bio_put Anuj Gupta
2022-09-29 13:25 ` Christoph Hellwig
[not found] ` <CGME20220929121650epcas5p424925af86ec6941bb53e5c102fd0ffc8@epcas5p4.samsung.com>
2022-09-29 12:06 ` [PATCH for-next v11 06/13] block: factor out blk_rq_map_bio_alloc helper Anuj Gupta
[not found] ` <CGME20220929121653epcas5p4ee82ef35b46d6686820dc4d870b6588e@epcas5p4.samsung.com>
2022-09-29 12:06 ` [PATCH for-next v11 07/13] block: add blk_rq_map_user_bvec Anuj Gupta
2022-09-29 13:26 ` Christoph Hellwig
[not found] ` <CGME20220929121657epcas5p213b7a187fd77b0783adb4b9389579b44@epcas5p2.samsung.com>
2022-09-29 12:06 ` [PATCH for-next v11 08/13] block: extend functionality to map bvec iterator Anuj Gupta
[not found] ` <CGME20220929121701epcas5p287a6d3f851626a5c7580d9a534432e9b@epcas5p2.samsung.com>
2022-09-29 12:06 ` [PATCH for-next v11 09/13] nvme: pass ubuffer as an integer Anuj Gupta
2022-09-29 13:27 ` Christoph Hellwig
[not found] ` <CGME20220929121704epcas5p3415fd4782cbcffa7b1e6ddf774bebb03@epcas5p3.samsung.com>
2022-09-29 12:06 ` [PATCH for-next v11 10/13] nvme: wire up fixed buffer support for nvme passthrough Anuj Gupta
[not found] ` <CGME20220929121709epcas5p325553d10a7ada7717c2f51ddb566a3e5@epcas5p3.samsung.com>
2022-09-29 12:06 ` [PATCH for-next v11 11/13] block: add blk_rq_map_user_io Anuj Gupta
2022-09-29 13:28 ` Christoph Hellwig
[not found] ` <CGME20220929121713epcas5p1824ed0c48c9e9ceeb18954d9c23564ed@epcas5p1.samsung.com>
2022-09-29 12:06 ` [PATCH for-next v11 12/13] scsi: Use blk_rq_map_user_io helper Anuj Gupta
2022-09-29 13:28 ` Christoph Hellwig
[not found] ` <CGME20220929121715epcas5p488759f34f6e55d940c6dca523e24f464@epcas5p4.samsung.com>
2022-09-29 12:06 ` [PATCH for-next v11 13/13] nvme: " Anuj Gupta
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 \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox