public inbox for linux-nvme@lists.infradead.org
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: linux-block@vger.kernel.org
Cc: linux-scsi@vger.kernel.org, linux-nvme@lists.infradead.org
Subject: [PATCHSET 0/5] Enable alloc caching and batched freeing for passthrough
Date: Thu, 22 Sep 2022 12:28:00 -0600	[thread overview]
Message-ID: <20220922182805.96173-1-axboe@kernel.dk> (raw)

Hi,

The passthrough IO path currently doesn't do any request allocation
batching like we do for normal IO. Wire this up through the usual
blk_mq_alloc_request() allocation helper.

Similarly, we don't currently supported batched completions for
passthrough IO. Allow the request->end_io() handler to return back
whether or not it retains ownership of the request. By default all
handlers are converted to returning RQ_END_IO_NONE, which retains
the existing behavior. But with that in place, we can tweak the
nvme uring_cmd end_io handler to pass back ownership, and hence enable
completion batching for passthrough requests as well.

This is good for a 10% improvement for passthrough performance. For
a non-drive limited test case, passthrough IO is now more efficient
than the regular bdev O_DIRECT path.

-- 
Jens Axboe




             reply	other threads:[~2022-09-22 18:28 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-22 18:28 Jens Axboe [this message]
2022-09-22 18:28 ` [PATCH 1/5] block: enable batched allocation for blk_mq_alloc_request() Jens Axboe
2022-09-23 14:52   ` Pankaj Raghav
2022-09-23 15:13     ` Pankaj Raghav
2022-09-23 20:54       ` Jens Axboe
2022-09-24  0:59         ` Damien Le Moal
2022-09-24  1:01           ` Jens Axboe
2022-09-24  1:22             ` Damien Le Moal
2022-09-24 11:56         ` Pankaj Raghav
2022-09-24 14:44           ` Jens Axboe
2022-09-22 18:28 ` [PATCH 2/5] block: change request end_io handler to pass back a return value Jens Axboe
2022-09-22 18:28 ` [PATCH 3/5] block: allow end_io based requests in the completion batch handling Jens Axboe
2022-09-22 18:28 ` [PATCH 4/5] nvme: split out metadata vs non metadata end_io uring_cmd completions Jens Axboe
2022-09-23 15:21   ` Christoph Hellwig
2022-09-23 20:52     ` Jens Axboe
2022-09-26 14:41       ` Christoph Hellwig
2022-09-26 14:41         ` Jens Axboe
2022-09-26 14:43           ` Christoph Hellwig
2022-09-26 14:50             ` Jens Axboe
2022-09-26 14:52               ` Christoph Hellwig
2022-09-26 14:54                 ` Jens Axboe
2022-09-22 18:28 ` [PATCH 5/5] nvme: enable batched completions of passthrough IO Jens Axboe
2022-09-23 15:16 ` [PATCHSET 0/5] Enable alloc caching and batched freeing for passthrough Christoph Hellwig
2022-09-23 15:19   ` Jens Axboe
2022-09-23 15:21     ` Christoph Hellwig
2022-09-23 15:22       ` 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=20220922182805.96173-1-axboe@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=linux-scsi@vger.kernel.org \
    /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