From: Ming Lei <ming.lei@redhat.com>
To: Jens Axboe <axboe@kernel.dk>, linux-block@vger.kernel.org
Cc: Caleb Sander Mateos <csander@purestorage.com>,
Uday Shankar <ushankar@purestorage.com>
Subject: Re: [PATCH V6 00/24] ublk: add UBLK_F_BATCH_IO
Date: Fri, 23 Jan 2026 10:24:48 +0800 [thread overview]
Message-ID: <aXLb8PwEsyszFuiz@fedora> (raw)
In-Reply-To: <20260116141859.719929-1-ming.lei@redhat.com>
On Fri, Jan 16, 2026 at 10:18:33PM +0800, Ming Lei wrote:
> Hello,
>
> This patchset adds UBLK_F_BATCH_IO feature for communicating between kernel and ublk
> server in batching way:
>
> - Per-queue vs Per-I/O: Commands operate on queues rather than individual I/Os
>
> - Batch processing: Multiple I/Os are handled in single operation
>
> - Multishot commands: Use io_uring multishot for reducing submission overhead
>
> - Flexible task assignment: Any task can handle any I/O (no per-I/O daemons)
>
> - Better load balancing: Tasks can adjust their workload dynamically
>
> - help for future optimizations:
> - blk-mq batch tags free
> - support io-poll
> - per-task batch for avoiding per-io lock
> - fetch command priority
>
> - simplify command cancel process with per-queue lock
>
> selftest are provided.
>
>
> Performance test result(IOPS) on V3:
>
> - page copy
>
> tools/testing/selftests/ublk//kublk add -t null -q 16 [-b]
>
> - zero copy(--auto_zc)
> tools/testing/selftests/ublk//kublk add -t null -q 16 --auto_zc [-b]
>
> - IO test
> taskset -c 0-31 fio/t/io_uring -p0 -n $JOBS -r 30 /dev/ublkb0
>
> 1) 16 jobs IO
> - page copy: 37.77M vs. 42.40M(BATCH_IO), +12%
> - zero copy(--auto_zc): 42.83M vs. 44.43M(BATCH_IO), +3.7%
>
>
> 2) single job IO
> - page copy: 2.54M vs. 2.6M(BATCH_IO), +2.3%
> - zero copy(--auto_zc): 3.13M vs. 3.35M(BATCH_IO), +7%
>
>
> Links: https://lore.kernel.org/linux-block/20251202121917.1412280-1-ming.lei@redhat.com/
> Links: https://lore.kernel.org/linux-block/20251121015851.3672073-1-ming.lei@redhat.com/
> Links: https://lore.kernel.org/linux-block/20251112093808.2134129-1-ming.lei@redhat.com/
> Links: https://lore.kernel.org/linux-block/20251023153234.2548062-1-ming.lei@redhat.com/
> Links: https://lore.kernel.org/linux-block/20250901100242.3231000-1-ming.lei@redhat.com/
>
>
> This patchset is based on for-7.0/block with the following two patches:
>
> [PATCH v4] ublk: fix ublksrv pid handling for pid namespaces ( https://lore.kernel.org/linux-block/20260115025952.2321238-1-sconnor@purestorage.com/ )
>
> [PATCH 0/3] selftests/ublk: three bug fixes ( https://lore.kernel.org/linux-block/20260113085805.233214-1-ming.lei@redhat.com/ )
>
>
> V6:
> - rebase on for-7.0/block
> - fix ublk_handle_non_batch_cmd() (Caleb Sander Mateos)
> - add `ublk: refactor ublk_queue_rq() and add ublk_batch_queue_rq()` (Caleb Sander Mateos)
> - add `ublk: fix batch I/O recovery -ENODEV error`
> - increase selftest timeout for running more things in some generic tests
> - fix kublk utility wrt. ->cmd_inflight accounting for BATCH_IO
> - pass all selftest after applying the io_uring cancel fix
Hi Jens,
Any chance to queue it for-7.0/block? And it is applied cleanly.
Thanks,
Ming
next prev parent reply other threads:[~2026-01-23 2:25 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-01-16 14:18 [PATCH V6 00/24] ublk: add UBLK_F_BATCH_IO Ming Lei
2026-01-16 14:18 ` [PATCH V6 01/24] ublk: define ublk_ch_batch_io_fops for the coming feature F_BATCH_IO Ming Lei
2026-01-16 14:18 ` [PATCH V6 02/24] ublk: prepare for not tracking task context for command batch Ming Lei
2026-01-16 14:18 ` [PATCH V6 03/24] ublk: add new batch command UBLK_U_IO_PREP_IO_CMDS & UBLK_U_IO_COMMIT_IO_CMDS Ming Lei
2026-01-16 14:18 ` [PATCH V6 04/24] ublk: handle UBLK_U_IO_PREP_IO_CMDS Ming Lei
2026-01-23 3:31 ` Jens Axboe
2026-01-16 14:18 ` [PATCH V6 05/24] ublk: handle UBLK_U_IO_COMMIT_IO_CMDS Ming Lei
2026-01-16 14:18 ` [PATCH V6 06/24] ublk: add io events fifo structure Ming Lei
2026-01-16 14:18 ` [PATCH V6 07/24] ublk: add batch I/O dispatch infrastructure Ming Lei
2026-01-23 3:32 ` Jens Axboe
2026-01-23 8:10 ` Ming Lei
2026-01-16 14:18 ` [PATCH V6 08/24] ublk: add UBLK_U_IO_FETCH_IO_CMDS for batch I/O processing Ming Lei
2026-01-16 14:18 ` [PATCH V6 09/24] ublk: refactor ublk_queue_rq() and add ublk_batch_queue_rq() Ming Lei
2026-01-23 3:04 ` Caleb Sander Mateos
2026-01-16 14:18 ` [PATCH V6 10/24] ublk: abort requests filled in event kfifo Ming Lei
2026-01-16 14:18 ` [PATCH V6 11/24] ublk: add new feature UBLK_F_BATCH_IO Ming Lei
2026-01-16 14:18 ` [PATCH V6 12/24] ublk: document " Ming Lei
2026-01-16 14:18 ` [PATCH V6 13/24] ublk: implement batch request completion via blk_mq_end_request_batch() Ming Lei
2026-01-16 14:18 ` [PATCH V6 14/24] ublk: fix batch I/O recovery -ENODEV error Ming Lei
2026-01-23 3:33 ` Jens Axboe
2026-01-16 14:18 ` [PATCH V6 15/24] selftests: ublk: fix user_data truncation for tgt_data >= 256 Ming Lei
2026-01-16 14:18 ` [PATCH V6 16/24] selftests: ublk: replace assert() with ublk_assert() Ming Lei
2026-01-16 14:18 ` [PATCH V6 17/24] selftests: ublk: add ublk_io_buf_idx() for returning io buffer index Ming Lei
2026-01-16 14:18 ` [PATCH V6 18/24] selftests: ublk: add batch buffer management infrastructure Ming Lei
2026-01-16 14:18 ` [PATCH V6 19/24] selftests: ublk: handle UBLK_U_IO_PREP_IO_CMDS Ming Lei
2026-01-16 14:18 ` [PATCH V6 20/24] selftests: ublk: handle UBLK_U_IO_COMMIT_IO_CMDS Ming Lei
2026-01-16 14:18 ` [PATCH V6 21/24] selftests: ublk: handle UBLK_U_IO_FETCH_IO_CMDS Ming Lei
2026-01-16 14:18 ` [PATCH V6 22/24] selftests: ublk: increase timeout to 150 seconds Ming Lei
2026-01-16 14:18 ` [PATCH V6 23/24] selftests: ublk: add --batch/-b for enabling F_BATCH_IO Ming Lei
2026-01-16 14:18 ` [PATCH V6 24/24] selftests: ublk: support arbitrary threads/queues combination Ming Lei
2026-01-23 2:24 ` Ming Lei [this message]
2026-01-23 3:06 ` [PATCH V6 00/24] ublk: add UBLK_F_BATCH_IO Jens Axboe
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=aXLb8PwEsyszFuiz@fedora \
--to=ming.lei@redhat.com \
--cc=axboe@kernel.dk \
--cc=csander@purestorage.com \
--cc=linux-block@vger.kernel.org \
--cc=ushankar@purestorage.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: 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