From: Ingo Molnar <mingo-X9Un+BFzKDI@public.gmane.org>
To: Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
Cc: kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org
Subject: Re: Paravirt KVM capabilities
Date: Wed, 10 Jan 2007 12:14:42 +0100 [thread overview]
Message-ID: <20070110111442.GA16867@elte.hu> (raw)
In-Reply-To: <45A4C7ED.8090003-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
* Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org> wrote:
> For i386 Xen does not switch cr3 IIRC. [...]
correct.
> [...] Perhaps even not for x86_64 if it can use the segment limits
> which AMD re-added (I think it does?)
i'm not sure. Older ones definitely used cr3 switching and on Intel
there's no segment limits on 64-bit AFAIK.
> I think for i386 Xen does not go through the hypervisor at all: it
> hacks int 0x80 to trap directly to ring 1. So there's still the
> overhead of using int rather than sysenter, but not much more. [...]
that alone is already ~100-200 cycles overhead, it essentially doubles
the null syscall overhead. It matters at millions of syscalls per second
workloads, 100 cycles overhead at 1 million syscalls a second means 5%
performance difference at 2GHz.
and longer-term, the cost of VM exit due to IRQs is expected to get
cheaper. The cost of int $0x80 versus SYSENTER will stay constant, or
will get worse.
Ingo
-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys - and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV
next prev parent reply other threads:[~2007-01-10 11:14 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-01-09 14:19 Paravirt KVM capabilities Hugo Mills
[not found] ` <20070109141916.GA13276-qdzjUQGjHNdnxAzMjxVBUbVCufUGDwFn@public.gmane.org>
2007-01-09 14:27 ` Avi Kivity
[not found] ` <45A3A642.1030604-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
2007-01-09 23:20 ` Rusty Russell
[not found] ` <1168384852.19646.161.camel-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
2007-01-10 9:47 ` Ingo Molnar
[not found] ` <20070110094750.GA934-X9Un+BFzKDI@public.gmane.org>
2007-01-10 10:09 ` Ulrich Drepper
[not found] ` <45A4BB74.9010102-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2007-01-10 10:18 ` Ingo Molnar
[not found] ` <20070110101839.GA6444-X9Un+BFzKDI@public.gmane.org>
2007-01-10 10:43 ` Avi Kivity
[not found] ` <45A4C345.5050404-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
2007-01-10 10:52 ` Ingo Molnar
[not found] ` <20070110105202.GA13412-X9Un+BFzKDI@public.gmane.org>
2007-01-10 11:03 ` Avi Kivity
[not found] ` <45A4C7ED.8090003-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
2007-01-10 11:14 ` Ingo Molnar [this message]
[not found] ` <20070110111442.GA16867-X9Un+BFzKDI@public.gmane.org>
2007-01-10 11:42 ` Avi Kivity
2007-01-10 18:00 ` Ulrich Drepper
[not found] ` <45A529DB.4030009-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2007-01-10 18:12 ` Avi Kivity
[not found] ` <45A52C8B.70608-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
2007-01-10 18:27 ` Ulrich Drepper
[not found] ` <45A53005.30300-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2007-01-10 18:35 ` Avi Kivity
2007-01-10 17:00 ` Anthony Liguori
[not found] ` <45A51BA2.9090005-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
2007-01-10 17:23 ` Avi Kivity
2007-01-11 0:42 ` Rusty Russell
[not found] ` <1168476120.19646.209.camel-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
2007-01-11 0:49 ` Ingo Molnar
[not found] ` <20070111004957.GA3279-X9Un+BFzKDI@public.gmane.org>
2007-01-11 2:39 ` Rusty Russell
[not found] ` <1168483188.19646.241.camel-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
2007-01-11 2:51 ` Ingo Molnar
[not found] ` <20070111025130.GB21368-X9Un+BFzKDI@public.gmane.org>
2007-01-11 3:21 ` Rusty Russell
[not found] ` <1168485696.19646.250.camel-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
2007-01-11 9:38 ` Ingo Molnar
2007-01-10 10:46 ` Rusty Russell
[not found] ` <1168425985.19646.205.camel-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
2007-01-10 11:00 ` sean-cz32UWRuVxBIf6P1QZMOBw
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=20070110111442.GA16867@elte.hu \
--to=mingo-x9un+bfzkdi@public.gmane.org \
--cc=avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org \
--cc=kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.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