From: Palmer Dabbelt <palmer@dabbelt.com>
To: snitzer@redhat.com
Cc: Christoph Hellwig <hch@infradead.org>,
josef@toxicpanda.com, bvanassche@acm.org, corbet@lwn.net,
kernel-team@android.com, linux-doc@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-raid@vger.kernel.org,
song@kernel.org, dm-devel@redhat.com,
linux-kselftest@vger.kernel.org, shuah@kernel.org,
agk@redhat.com, michael.christie@oracle.com
Subject: Re: [PATCH v1 0/5] dm: dm-user: New target that proxies BIOs to userspace
Date: Tue, 22 Dec 2020 12:38:28 -0800 (PST) [thread overview]
Message-ID: <mhng-26d96d8e-77aa-415b-a8ee-518a0e91b6ef@palmerdabbelt-glaptop> (raw)
In-Reply-To: <20201222143616.GB12885@redhat.com>
On Tue, 22 Dec 2020 06:36:16 PST (-0800), snitzer@redhat.com wrote:
> On Tue, Dec 22 2020 at 8:32am -0500,
> Christoph Hellwig <hch@infradead.org> wrote:
>
>> On Mon, Dec 14, 2020 at 07:00:57PM -0800, Palmer Dabbelt wrote:
>> > I haven't gotten a whole lot of feedback, so I'm inclined to at least have some
>> > reasonable performance numbers before bothering with a v2.
>>
>> FYI, my other main worry beside duplicating nbd is that device mapper
>> really is a stacked interface that sits on top of other block device.
>> Turning this into something else that just pipes data to userspace
>> seems very strange.
>
> I agree. Only way I'd be interested is if it somehow tackled enabling
> much more efficient IO. Earlier discussion in this thread mentioned
> that zero-copy and low overhead wasn't a priority (because it is hard,
> etc). But the hard work has already been done with io_uring. If
> dm-user had a prereq of leaning heavily on io_uring and also enabled IO
> polling for bio-based then there may be a win to supporting it.
>
> But unless lower latency (or some other more significant win) is made
> possible I just don't care to prop up an unnatural DM bolt-on.
I don't remember if I mentioned this in the thread, but it was definately in
the Plumbers talk, but I'd had the general idea bouncing around that it would
be possible to write a high-performance version of this using an interface
similar to the one provided here while relying on io_uring for the
high-performance userspace. That definately won't work with exactly the
current interface, but my hope was to avoid writing my own high-performance
ring buffer. My worry was that it'll be too tricky to map this all to
zero-copy, and I guess I forgot about it.
Now that you bring it up, it certainly seems worth taking a shot at. We'd
essentially have the best of both worlds: userspace implementations that want
to be simple could just use read()/write(), while those that want to be higher
performance could have their implicit ring buffer.
I'm currently trying to put together a benchmarking setup that is of sufficient
fidelity that I would believe the numbers, which is really why I don't have any
performance numbers yet (no sense posting numbers I would shoot down :)). I'll
try to remember to take a shot at an io_uring based userspace (probably with
some dm-user interface modifications) to see how it feels.
next prev parent reply other threads:[~2020-12-22 20:39 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-03 21:58 [PATCH v1 0/5] dm: dm-user: New target that proxies BIOs to userspace Palmer Dabbelt
2020-12-03 21:58 ` [PATCH v1 1/5] Documentation: Describe dm-user Palmer Dabbelt
2020-12-03 21:58 ` [PATCH v1 2/5] uapi: Add dm-user structure definition Palmer Dabbelt
2020-12-03 21:58 ` [PATCH v1 3/5] dm: dm-user: New target that proxies BIOs to userspace Palmer Dabbelt
2020-12-03 21:58 ` [PATCH v1 4/5] selftests/dm-user: A handful of tests for dm-user Palmer Dabbelt
2020-12-03 21:58 ` [PATCH v1 5/5] MAINTAINERS: Add myself as a dm-user maintainer Palmer Dabbelt
2020-12-04 10:33 ` [PATCH v1 0/5] dm: dm-user: New target that proxies BIOs to userspace Christoph Hellwig
2020-12-07 18:55 ` Palmer Dabbelt
2020-12-10 3:38 ` [dm-devel] " Bart Van Assche
2020-12-10 17:03 ` Josef Bacik
2020-12-15 3:00 ` Palmer Dabbelt
2020-12-16 18:24 ` Vitaly Mayatskih
2020-12-17 6:55 ` Palmer Dabbelt
2020-12-22 13:32 ` Christoph Hellwig
2020-12-22 14:36 ` Mike Snitzer
2020-12-22 20:38 ` Palmer Dabbelt [this message]
2020-12-23 7:48 ` Christoph Hellwig
2020-12-23 16:59 ` Bart Van Assche
2020-12-22 20:31 ` [dm-devel] " Palmer Dabbelt
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=mhng-26d96d8e-77aa-415b-a8ee-518a0e91b6ef@palmerdabbelt-glaptop \
--to=palmer@dabbelt.com \
--cc=agk@redhat.com \
--cc=bvanassche@acm.org \
--cc=corbet@lwn.net \
--cc=dm-devel@redhat.com \
--cc=hch@infradead.org \
--cc=josef@toxicpanda.com \
--cc=kernel-team@android.com \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=linux-raid@vger.kernel.org \
--cc=michael.christie@oracle.com \
--cc=shuah@kernel.org \
--cc=snitzer@redhat.com \
--cc=song@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;
as well as URLs for NNTP newsgroup(s).