From: Paolo Bonzini <pbonzini@redhat.com>
To: Alexey Kardashevskiy <aik@ozlabs.ru>
Cc: "qemu-ppc@nongnu.org" <qemu-ppc@nongnu.org>,
Peter Lieven <pl@kamp.de>,
"qemu-devel@nongnu.org" <qemu-devel@nongnu.org>,
David Gibson <david@gibson.dropbear.id.au>
Subject: Re: [Qemu-devel] broken incoming migration
Date: Thu, 30 May 2013 16:08:51 +0200 [thread overview]
Message-ID: <51A75D73.3020805@redhat.com> (raw)
In-Reply-To: <51A7564D.5090202@ozlabs.ru>
Il 30/05/2013 15:38, Alexey Kardashevskiy ha scritto:
>>> does this problem only occur on pseries emulation?
>>
>> Probably not. On a PC, it would occur if you had 4K of zeros in the
>> source BIOS but not in the destination BIOS. When you reboot, the BIOS
>> image is wrong.
>>
>>> not sending zero pages is not only a performance benefit it also makes
>>> overcomitted memory usable. the madv_dontneed seems to kick in asynchronously
>>> and memory is not available immediately.
>>
>> You could also scan the page for nonzero values before writing it.
>
> Scan where? On the source? It is there already. On the destination? Won't
> just trying to read a page kill all effect from MADV_DONTNEED?
No, zero pages are handled with special copy-on-write magic by the
kernel. :) So, reading works but writing doesn't.
Paolo
next prev parent reply other threads:[~2013-05-30 14:09 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-05-30 7:44 [Qemu-devel] broken incoming migration Alexey Kardashevskiy
2013-05-30 7:49 ` Alexey Kardashevskiy
2013-05-30 7:49 ` Paolo Bonzini
2013-05-30 8:18 ` Alexey Kardashevskiy
2013-05-30 9:08 ` Peter Lieven
2013-05-30 9:31 ` Alexey Kardashevskiy
2013-05-30 13:00 ` Paolo Bonzini
2013-05-30 13:38 ` Alexey Kardashevskiy
2013-05-30 14:08 ` Paolo Bonzini [this message]
2013-05-30 14:38 ` Peter Lieven
2013-05-30 14:41 ` Paolo Bonzini
2013-06-04 13:52 ` Peter Lieven
2013-06-04 14:14 ` Paolo Bonzini
2013-06-04 14:38 ` Peter Lieven
2013-06-04 14:40 ` Paolo Bonzini
2013-06-04 14:48 ` Peter Lieven
2013-06-04 15:17 ` Paolo Bonzini
2013-06-04 19:15 ` Peter Lieven
2013-06-05 3:37 ` Alexey Kardashevskiy
2013-06-05 6:09 ` Peter Lieven
2013-06-09 4:12 ` liu ping fan
2013-06-09 7:22 ` Peter Lieven
2013-06-04 15:10 ` Peter Lieven
2013-06-08 8:27 ` Wenchao Xia
2013-06-08 8:30 ` Alexey Kardashevskiy
2013-06-09 2:16 ` Wenchao Xia
2013-06-09 2:34 ` Alexey Kardashevskiy
2013-06-09 2:52 ` [Qemu-devel] [Qemu-ppc] " Benjamin Herrenschmidt
2013-06-09 3:01 ` Alexey Kardashevskiy
2013-06-09 3:01 ` [Qemu-devel] " Wenchao Xia
2013-06-09 3:09 ` Alexey Kardashevskiy
2013-06-09 3:31 ` Wenchao Xia
2013-06-09 7:27 ` Peter Lieven
2013-06-10 6:39 ` Alexey Kardashevskiy
2013-06-10 6:50 ` Peter Lieven
2013-06-10 6:55 ` Alexey Kardashevskiy
2013-06-10 8:44 ` Peter Lieven
2013-06-10 9:10 ` Alexey Kardashevskiy
2013-06-10 9:33 ` [Qemu-devel] [Qemu-ppc] " Benjamin Herrenschmidt
2013-06-10 9:42 ` Peter Lieven
2013-06-09 2:53 ` Benjamin Herrenschmidt
2013-06-12 14:00 ` Paolo Bonzini
2013-06-12 14:11 ` Benjamin Herrenschmidt
2013-06-12 20:10 ` Paolo Bonzini
2013-06-13 2:41 ` Wenchao Xia
2013-06-03 10:04 ` [Qemu-devel] " Alexey Kardashevskiy
2013-06-04 10:56 ` Peter Lieven
2013-06-08 8:24 ` Wenchao Xia
2013-05-30 10:18 ` Peter Maydell
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=51A75D73.3020805@redhat.com \
--to=pbonzini@redhat.com \
--cc=aik@ozlabs.ru \
--cc=david@gibson.dropbear.id.au \
--cc=pl@kamp.de \
--cc=qemu-devel@nongnu.org \
--cc=qemu-ppc@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 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.