xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
From: "Jan Beulich" <JBeulich@suse.com>
To: Tomasz Wroblewski <tomasz.wroblewski@gmail.com>
Cc: xen-devel@lists.xenproject.org
Subject: Re: GPU passthrough performance regression in >4GB vms due to XSA-60 changes
Date: Mon, 19 May 2014 12:01:04 +0100	[thread overview]
Message-ID: <537A00900200007800013832@mail.emea.novell.com> (raw)
In-Reply-To: <5379E004.1080107@gmail.com>

>>> On 19.05.14 at 12:42, <tomasz.wroblewski@gmail.com> wrote:
> Actually seems to be like the plausible explanation for the performance 
> issues we see could be that
> 
> - some region of guest space has been relocated by hvmloader out to 
> 64bit memory to enlarge pci mmio hole (which stays in 32bit space)
> - BUT the caching on that relocated region is UC since at the time of 
> the relocation MTRR was disabled and that caused the EPT entry to get UC 
> type.

But this would be easily seen from 'D' debug key output - did you
check this is what is the case?

Jan

  reply	other threads:[~2014-05-19 11:01 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-05-15  9:11 GPU passthrough performance regression in >4GB vms due to XSA-60 changes Tomasz Wroblewski
2014-05-15 12:32 ` Jan Beulich
2014-05-15 12:10   ` Tomasz Wroblewski
2014-05-15 13:23     ` Jan Beulich
2014-05-15 13:39       ` Tomasz Wroblewski
2014-05-15 14:34         ` Tomasz Wroblewski
2014-05-15 14:56           ` Tomasz Wroblewski
2014-05-15 16:07             ` Jan Beulich
2014-05-15 15:39               ` Tomasz Wroblewski
2014-05-16  6:33                 ` Jan Beulich
2014-05-16 11:18                   ` Tomasz Wroblewski
2014-05-16 11:38                     ` Jan Beulich
2014-05-16 14:36                       ` Jan Beulich
2014-05-19 10:29                         ` Tomasz Wroblewski
2014-05-19 10:38                           ` Jan Beulich
2014-05-19 10:47                             ` Tomasz Wroblewski
2014-05-19 11:07                               ` Jan Beulich
2014-05-19 11:32                                 ` Tomasz Wroblewski
2014-05-19 12:06                                   ` Jan Beulich
2014-05-19 12:17                                     ` Tomasz Wroblewski
2014-05-19 12:44                                       ` Jan Beulich
2014-05-19 14:20                                         ` Tomasz Wroblewski
2014-05-19 15:24                                           ` Jan Beulich
2014-05-19 15:48                                             ` Tomasz Wroblewski
2014-05-19 17:36                                             ` Tim Deegan
2014-05-20  6:31                                               ` Jan Beulich
2014-05-19 10:42                           ` Tomasz Wroblewski
2014-05-19 11:01                             ` Jan Beulich [this message]
2014-05-19 11:09                               ` Tomasz Wroblewski
2014-05-19 11:19                                 ` Jan Beulich
2014-05-15 16:01         ` Jan Beulich

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=537A00900200007800013832@mail.emea.novell.com \
    --to=jbeulich@suse.com \
    --cc=tomasz.wroblewski@gmail.com \
    --cc=xen-devel@lists.xenproject.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).