qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Fam Zheng <famz@redhat.com>
To: "Bryan D. Payne" <bdpayne@acm.org>
Cc: qemu-devel@nongnu.org, Markus Armbruster <armbru@redhat.com>,
	lcapitulino@redhat.com
Subject: Re: [Qemu-devel] [PATCH] qmp: extend QMP to provide read/write access to physical memory
Date: Fri, 12 Dec 2014 11:29:55 +0800	[thread overview]
Message-ID: <20141212032955.GA808@ad.nay.redhat.com> (raw)
In-Reply-To: <CAFpPvXBxq_O1L6KuGumRRFd6oZJfM+vaHmFsUrEs1EJJTSF4Kg@mail.gmail.com>

On Thu, 12/11 20:28, Bryan D. Payne wrote:
> >
> > > For those that prefer text, here's the numbers (in microseconds):
> > > QMP/pmemsave: 77706
> > > HMC/xp command: 92552
> > > QMP/pmemaccess: 95
> >
> 
> I completed a proof of concept implementation for doing this memory access
> completely over QMP.  Basically, it works much like pmemsave except instead
> of sending the data to a file it does a base64 encode and sends it back
> over the QMP connection.  Interestingly, my testing shows that this is
> slightly slower than the pmemsave option.  Running the same test as before
> (virtual address translation), I get 88063 microsecs on average.  So I
> don't believe this option is viable.

How did you setup your QMP, and how does the QMP transactions look like in your
test? Is it Unix domain socket? If the # of requests are in a high rate, I
think the overhead may come from QMP framework, mostly event loop
synchronization: QMP messages are not processed if the device emulation code is
running.

Also did you try to compress the memory data with zlib, to compensate for the
base64 encoding inflation?

> 
> 
> Look good. I believe QMP will be in between, and if it doesn't work as well,
> > could you also try to use QEMU's char dev instead of limit this to unix
> > socket?
> 
> 
> I'm moving forward to try the Qemu chardev approach now.  I haven't working
> much with this construct before, so any pointers are appreciated.  From
> what I'm seeing, it looks like the user would create a chardev using one of
> the QMP @chardev* commands?  The schema doesn't indicate that these
> commands return the chardev id, which seems odd as I was then assuming that
> one could obtain the id and pass this into the pmemaccess QMP command.
> Thoughts?

The chardev will be assigned an "id" by user, as the paremeter of chardev-add,
and later the user will pass id to pmemaccess.

In pmemaccess implementation, we will find the chardev by qemu_chr_find, and
read/write with qemu_chr_* functions. You can take examples from hw/char/* for
devices' usage.

Fam

  reply	other threads:[~2014-12-12  3:37 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-11-26  8:41 [Qemu-devel] [PATCH 0/1] qmp: extend QMP to provide read/write access to physical memory Bryan D. Payne
2014-11-26  8:41 ` [Qemu-devel] [PATCH 1/1] " Bryan D. Payne
2014-11-26 15:16   ` Eric Blake
2014-11-26 20:27 ` [Qemu-devel] [PATCH v2] " Bryan D. Payne
2014-11-26 20:27   ` [Qemu-devel] [PATCH] " Bryan D. Payne
2014-11-27  2:04     ` Fam Zheng
2014-12-04  3:37       ` Bryan D. Payne
2014-12-04  4:57         ` Fam Zheng
2014-12-04  6:28           ` Bryan D. Payne
2014-12-04  7:38             ` Fam Zheng
2014-12-04 16:43               ` Bryan D. Payne
2014-12-05  1:20                 ` Fam Zheng
2014-12-04  9:08         ` Markus Armbruster
2014-12-04 16:49           ` Bryan D. Payne
2014-12-05  8:44             ` Markus Armbruster
2014-12-05 21:25               ` Bryan D. Payne
2014-12-08 15:06                 ` Markus Armbruster
2014-12-09 15:12                   ` Bryan D. Payne
2014-12-11  3:33                     ` Bryan D. Payne
2014-12-11  5:45                       ` Fam Zheng
2014-12-11  6:07                         ` Bryan D. Payne
2014-12-12  2:28                         ` Bryan D. Payne
2014-12-12  3:29                           ` Fam Zheng [this message]
2014-12-01 22:10     ` Eric Blake
2014-12-03 23:07       ` Bryan D. Payne
2014-12-04 15:08         ` Eric Blake
2014-12-04 16:50           ` Bryan D. Payne
2014-12-04 18:40           ` Bryan D. Payne
2014-12-04 22:43             ` Eric Blake
2014-12-01 22:12   ` [Qemu-devel] [PATCH v2] " Eric Blake
2014-12-02  4:36     ` Bryan D. Payne
2014-12-02  5:26       ` Fam Zheng

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=20141212032955.GA808@ad.nay.redhat.com \
    --to=famz@redhat.com \
    --cc=armbru@redhat.com \
    --cc=bdpayne@acm.org \
    --cc=lcapitulino@redhat.com \
    --cc=qemu-devel@nongnu.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).