From: Jeremy Fitzhardinge <jeremy@goop.org>
To: Anthony Liguori <anthony@codemonkey.ws>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>,
Xen-devel <xen-devel@lists.xensource.com>,
Andrew Morton <akpm@linux-foundation.org>,
the arch/x86 maintainers <x86@kernel.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
"H. Peter Anvin" <hpa@zytor.com>
Subject: Re: [PATCH] xen: core dom0 support
Date: Wed, 04 Mar 2009 09:38:42 -0800 [thread overview]
Message-ID: <49AEBCA2.8020307@goop.org> (raw)
In-Reply-To: <49AEBB8C.2000405@codemonkey.ws>
Anthony Liguori wrote:
> Jeremy Fitzhardinge wrote:
>> Nick Piggin wrote:
>
>> It really depends on the workload. There's three cases to consider:
>> software shadow pagetables, hardware nested pagetables, and Xen
>> direct pagetables. Even now, Xen's (highly optimised) shadow
>> pagetable code generally out-performs modern nested pagetables, at
>> least when running Windows (for which that code was most heavily tuned).
>
> Can you point to benchmarks? I have a hard time believing this.
Erm, not that I know of off-hand. I don't really have any interest in
Windows performance, so I'm reduced to repeating (highly reliable) Xen
Summit corridor chat.
> How can shadow paging beat nested paging assuming the presence of
> large pages?
I think large pages do turn the tables, and its close to parity with
shadow with 4k pages on recent cpus. But see above for reliability on
that info.
J
WARNING: multiple messages have this Message-ID (diff)
From: Jeremy Fitzhardinge <jeremy@goop.org>
To: Anthony Liguori <anthony@codemonkey.ws>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>,
Xen-devel <xen-devel@lists.xensource.com>,
the arch/x86 maintainers <x86@kernel.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
"H. Peter Anvin" <hpa@zytor.com>,
Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [PATCH] xen: core dom0 support
Date: Wed, 04 Mar 2009 09:38:42 -0800 [thread overview]
Message-ID: <49AEBCA2.8020307@goop.org> (raw)
In-Reply-To: <49AEBB8C.2000405@codemonkey.ws>
Anthony Liguori wrote:
> Jeremy Fitzhardinge wrote:
>> Nick Piggin wrote:
>
>> It really depends on the workload. There's three cases to consider:
>> software shadow pagetables, hardware nested pagetables, and Xen
>> direct pagetables. Even now, Xen's (highly optimised) shadow
>> pagetable code generally out-performs modern nested pagetables, at
>> least when running Windows (for which that code was most heavily tuned).
>
> Can you point to benchmarks? I have a hard time believing this.
Erm, not that I know of off-hand. I don't really have any interest in
Windows performance, so I'm reduced to repeating (highly reliable) Xen
Summit corridor chat.
> How can shadow paging beat nested paging assuming the presence of
> large pages?
I think large pages do turn the tables, and its close to parity with
shadow with 4k pages on recent cpus. But see above for reliability on
that info.
J
next prev parent reply other threads:[~2009-03-04 17:38 UTC|newest]
Thread overview: 123+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-02-28 1:59 [PATCH] xen: core dom0 support Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] xen dom0: Make hvc_xen console work for dom0 Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] xen dom0: Initialize xenbus " Jeremy Fitzhardinge
2009-02-28 1:59 ` Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] xen dom0: Set up basic IO permissions " Jeremy Fitzhardinge
2009-02-28 1:59 ` Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] xen-dom0: only selectively disable cpu features Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] xen dom0: Add support for the platform_ops hypercall Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] xen mtrr: Add mtrr_ops support for Xen mtrr Jeremy Fitzhardinge
2009-02-28 1:59 ` Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] xen: disable PAT Jeremy Fitzhardinge
2009-02-28 1:59 ` Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] xen/dom0: use _PAGE_IOMAP in ioremap to do machine mappings Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] paravirt/xen: add pvop for page_is_ram Jeremy Fitzhardinge
2009-03-10 1:07 ` H. Peter Anvin
2009-03-10 21:19 ` Jeremy Fitzhardinge
2009-03-10 21:19 ` Jeremy Fitzhardinge
2009-03-10 22:21 ` H. Peter Anvin
2009-03-10 22:44 ` Jeremy Fitzhardinge
2009-03-10 22:44 ` Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] xen/dom0: Use host E820 map Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] xen: implement XENMEM_machphys_mapping Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] xen: clear reserved bits in l3 entries given in the initial pagetables Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] xen/dom0: add XEN_DOM0 config option Jeremy Fitzhardinge
2009-02-28 1:59 ` Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] xen: allow enable use of VGA console on dom0 Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] xen mtrr: Use specific cpu_has_foo macros instead of generic cpu_has() Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] xen mtrr: Kill some unneccessary includes Jeremy Fitzhardinge
2009-02-28 1:59 ` Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] xen mtrr: Use generic_validate_add_page() Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] xen mtrr: Implement xen_get_free_region() Jeremy Fitzhardinge
2009-02-28 1:59 ` [PATCH] xen mtrr: Add xen_{get,set}_mtrr() implementations Jeremy Fitzhardinge
2009-02-28 5:28 ` [PATCH] xen: core dom0 support Andrew Morton
2009-02-28 6:52 ` Jeremy Fitzhardinge
2009-02-28 6:52 ` Jeremy Fitzhardinge
2009-02-28 7:20 ` Ingo Molnar
2009-02-28 7:20 ` Ingo Molnar
2009-02-28 8:05 ` Jeremy Fitzhardinge
2009-02-28 8:05 ` Jeremy Fitzhardinge
2009-02-28 8:36 ` Ingo Molnar
2009-02-28 8:36 ` Ingo Molnar
2009-02-28 9:57 ` Jeremy Fitzhardinge
2009-02-28 9:57 ` Jeremy Fitzhardinge
2009-03-02 9:26 ` Gerd Hoffmann
2009-03-02 9:26 ` Gerd Hoffmann
2009-03-02 12:04 ` Ingo Molnar
2009-03-02 12:04 ` Ingo Molnar
2009-03-02 12:26 ` Gerd Hoffmann
2009-03-02 12:26 ` Gerd Hoffmann
2009-02-28 12:09 ` Nick Piggin
2009-02-28 12:09 ` Nick Piggin
2009-02-28 18:11 ` [Xen-devel] " Jody Belka
2009-02-28 18:11 ` Jody Belka
2009-02-28 18:15 ` Andi Kleen
2009-03-01 23:38 ` Jeremy Fitzhardinge
2009-03-01 23:38 ` Jeremy Fitzhardinge
2009-03-02 0:14 ` Andi Kleen
2009-03-01 23:27 ` Jeremy Fitzhardinge
2009-03-01 23:27 ` Jeremy Fitzhardinge
2009-03-02 6:37 ` Nick Piggin
2009-03-02 6:37 ` Nick Piggin
2009-03-02 8:05 ` Jeremy Fitzhardinge
2009-03-02 8:05 ` Jeremy Fitzhardinge
2009-03-02 8:19 ` Nick Piggin
2009-03-02 8:19 ` Nick Piggin
2009-03-02 9:05 ` Jeremy Fitzhardinge
2009-03-04 17:34 ` Anthony Liguori
2009-03-04 17:34 ` Anthony Liguori
2009-03-04 17:38 ` Jeremy Fitzhardinge [this message]
2009-03-04 17:38 ` Jeremy Fitzhardinge
2009-03-05 10:59 ` [Xen-devel] " George Dunlap
2009-03-05 10:59 ` George Dunlap
2009-03-05 14:37 ` [Xen-devel] " Anthony Liguori
2009-03-05 14:37 ` Anthony Liguori
2009-03-04 17:31 ` Anthony Liguori
2009-03-04 17:31 ` Anthony Liguori
2009-03-04 19:03 ` Anthony Liguori
2009-03-04 19:16 ` H. Peter Anvin
2009-03-04 19:33 ` Anthony Liguori
2009-03-04 19:33 ` Anthony Liguori
2009-02-28 16:14 ` Andi Kleen
2009-03-01 23:34 ` Jeremy Fitzhardinge
2009-03-01 23:34 ` Jeremy Fitzhardinge
2009-03-01 23:52 ` H. Peter Anvin
2009-03-02 0:08 ` Jeremy Fitzhardinge
2009-03-02 0:08 ` Jeremy Fitzhardinge
2009-03-02 0:14 ` H. Peter Anvin
2009-03-02 0:42 ` Jeremy Fitzhardinge
2009-03-02 0:42 ` Jeremy Fitzhardinge
2009-03-02 0:46 ` H. Peter Anvin
2009-03-02 0:10 ` Andi Kleen
2009-02-28 8:42 ` Ingo Molnar
2009-02-28 8:42 ` Ingo Molnar
2009-02-28 9:46 ` Jeremy Fitzhardinge
2009-02-28 9:46 ` Jeremy Fitzhardinge
2009-03-02 12:08 ` Ingo Molnar
2009-03-02 12:08 ` Ingo Molnar
2009-03-07 9:06 ` Jeremy Fitzhardinge
2009-03-07 9:06 ` Jeremy Fitzhardinge
2009-03-08 11:01 ` Ingo Molnar
2009-03-08 11:01 ` Ingo Molnar
2009-03-08 21:56 ` H. Peter Anvin
2009-03-08 22:06 ` Ingo Molnar
2009-03-08 22:06 ` Ingo Molnar
2009-03-08 22:08 ` H. Peter Anvin
2009-03-08 22:12 ` Ingo Molnar
2009-03-08 22:12 ` Ingo Molnar
2009-03-09 18:06 ` Jeremy Fitzhardinge
2009-03-09 18:06 ` Jeremy Fitzhardinge
2009-03-10 12:44 ` Ingo Molnar
2009-03-10 12:44 ` Ingo Molnar
2009-03-10 12:49 ` Nick Piggin
2009-03-10 12:49 ` Nick Piggin
2009-03-05 13:52 ` Morten P.D. Stevens
2009-03-08 14:25 ` Manfred Knick
2009-03-09 19:51 ` Morten P.D. Stevens
2009-03-09 20:00 ` Morten P.D. Stevens
2009-02-28 6:17 ` Boris Derzhavets
2009-02-28 6:23 ` [Xen-devel] " Jeremy Fitzhardinge
2009-02-28 6:23 ` Jeremy Fitzhardinge
2009-02-28 6:28 ` Boris Derzhavets
-- strict thread matches above, loose matches on Subject: below --
2009-03-11 19:58 devzero
2009-03-14 1:08 ` Morten P.D. Stevens
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=49AEBCA2.8020307@goop.org \
--to=jeremy@goop.org \
--cc=akpm@linux-foundation.org \
--cc=anthony@codemonkey.ws \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=nickpiggin@yahoo.com.au \
--cc=x86@kernel.org \
--cc=xen-devel@lists.xensource.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.