qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Amit Shah <amit.shah@redhat.com>
To: Liang Li <liang.z.li@intel.com>
Cc: ehabkost@redhat.com, kvm@vger.kernel.org, mst@redhat.com,
	quintela@redhat.com, linux-kernel@vger.kernel.org,
	qemu-devel@nongnu.org, linux-mm@kvack.org, pbonzini@redhat.com,
	akpm@linux-foundation.org,
	virtualization@lists.linux-foundation.org, dgilbert@redhat.com,
	rth@twiddle.net
Subject: Re: [Qemu-devel] [RFC qemu 0/4] A PV solution for live migration optimization
Date: Tue, 8 Mar 2016 16:43:43 +0530	[thread overview]
Message-ID: <20160308111343.GM15443@grmbl.mre> (raw)
In-Reply-To: <1457001868-15949-1-git-send-email-liang.z.li@intel.com>

On (Thu) 03 Mar 2016 [18:44:24], Liang Li wrote:
> The current QEMU live migration implementation mark the all the
> guest's RAM pages as dirtied in the ram bulk stage, all these pages
> will be processed and that takes quit a lot of CPU cycles.
> 
> From guest's point of view, it doesn't care about the content in free
> pages. We can make use of this fact and skip processing the free
> pages in the ram bulk stage, it can save a lot CPU cycles and reduce
> the network traffic significantly while speed up the live migration
> process obviously.
> 
> This patch set is the QEMU side implementation.
> 
> The virtio-balloon is extended so that QEMU can get the free pages
> information from the guest through virtio.
> 
> After getting the free pages information (a bitmap), QEMU can use it
> to filter out the guest's free pages in the ram bulk stage. This make
> the live migration process much more efficient.
> 
> This RFC version doesn't take the post-copy and RDMA into
> consideration, maybe both of them can benefit from this PV solution
> by with some extra modifications.

I like the idea, just have to prove (review) and test it a lot to
ensure we don't end up skipping pages that matter.

However, there are a couple of points:

In my opinion, the information that's exchanged between the guest and
the host should be exchanged over a virtio-serial channel rather than
virtio-balloon.  First, there's nothing related to the balloon here.
It just happens to be memory info.  Second, I would never enable
balloon in a guest that I want to be performance-sensitive.  So even
if you add this as part of balloon, you'll find no one is using this
solution.

Secondly, I suggest virtio-serial, because it's meant exactly to
exchange free-flowing information between a host and a guest, and you
don't need to extend any part of the protocol for it (hence no changes
necessary to the spec).  You can see how spice, vnc, etc., use
virtio-serial to exchange data.


		Amit

  parent reply	other threads:[~2016-03-08 11:14 UTC|newest]

Thread overview: 72+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-03-03 10:44 [Qemu-devel] [RFC qemu 0/4] A PV solution for live migration optimization Liang Li
2016-03-03 10:44 ` [Qemu-devel] [RFC qemu 1/4] pc: Add code to get the lowmem form PCMachineState Liang Li
2016-03-03 10:44 ` [Qemu-devel] [RFC qemu 2/4] virtio-balloon: Add a new feature to balloon device Liang Li
2016-03-03 12:23   ` Cornelia Huck
2016-03-04  2:38     ` Li, Liang Z
2016-03-03 12:56   ` Michael S. Tsirkin
2016-03-04  2:29     ` Li, Liang Z
2016-03-03 10:44 ` [Qemu-devel] [RFC qemu 3/4] migration: not set migration bitmap in setup stage Liang Li
2016-03-03 10:44 ` [Qemu-devel] [RFC qemu 4/4] migration: filter out guest's free pages in ram bulk stage Liang Li
2016-03-03 12:16   ` Cornelia Huck
2016-03-04  2:32     ` Li, Liang Z
2016-03-03 12:45   ` Daniel P. Berrange
2016-03-04  2:43     ` Li, Liang Z
2016-03-03 13:58 ` [Qemu-devel] [RFC qemu 0/4] A PV solution for live migration optimization Roman Kagan
2016-03-04  1:35   ` Li, Liang Z
2016-03-03 17:46 ` Dr. David Alan Gilbert
2016-03-04  1:52   ` Li, Liang Z
2016-03-04  8:14     ` Roman Kagan
2016-03-04  9:08       ` Li, Liang Z
2016-03-04 10:23         ` Roman Kagan
2016-03-04 14:26           ` Li, Liang Z
2016-03-04 14:45             ` Michael S. Tsirkin
2016-03-04 15:49               ` Li, Liang Z
2016-03-05 19:55                 ` Michael S. Tsirkin
2016-03-07  6:49                   ` Li, Liang Z
2016-03-07 11:40                     ` Michael S. Tsirkin
2016-03-07 15:06                       ` Li, Liang Z
2016-03-09 14:28                       ` Roman Kagan
2016-03-09 15:27                         ` Li, Liang Z
2016-03-09 15:30                           ` Michael S. Tsirkin
2016-03-10  1:41                             ` Li, Liang Z
2016-03-10 12:29                               ` Michael S. Tsirkin
2016-03-09 15:41                         ` Michael S. Tsirkin
2016-03-09 17:04                           ` Roman Kagan
2016-03-09 17:39                             ` Michael S. Tsirkin
2016-03-10 10:21                               ` Roman Kagan
2016-03-09 19:38                             ` Rik van Riel
2016-03-10  9:30                               ` Roman Kagan
2016-03-04 16:24             ` Paolo Bonzini
2016-03-04 18:51               ` Dr. David Alan Gilbert
2016-03-07  5:34                 ` Li, Liang Z
2016-03-09 13:22                 ` Roman Kagan
2016-03-09 14:19                   ` Li, Liang Z
2016-03-09  6:18               ` Li, Liang Z
2016-03-04  7:55   ` Roman Kagan
2016-03-04  8:23     ` Li, Liang Z
2016-03-04  8:35       ` Roman Kagan
2016-03-04  9:08         ` Dr. David Alan Gilbert
2016-03-04  9:12           ` Li, Liang Z
2016-03-04  9:47             ` Michael S. Tsirkin
2016-03-04 10:11               ` Li, Liang Z
2016-03-04 10:36                 ` Michael S. Tsirkin
2016-03-04 15:13                   ` Li, Liang Z
2016-03-08 14:03                     ` Michael S. Tsirkin
2016-03-08 14:17                       ` Li, Liang Z
2016-03-04  9:35           ` Roman Kagan
2016-03-08 11:13 ` Amit Shah [this message]
2016-03-08 13:11   ` Li, Liang Z
2016-03-10  7:44   ` Li, Liang Z
2016-03-10  7:57     ` Amit Shah
2016-03-10  8:36       ` Li, Liang Z
2016-03-10 11:18         ` Dr. David Alan Gilbert
2016-03-11  2:38           ` Li, Liang Z
2016-03-14 17:03             ` Dr. David Alan Gilbert
2016-03-15  3:31               ` Li, Liang Z
2016-03-15 10:29               ` Michael S. Tsirkin
2016-03-15 11:11                 ` Li, Liang Z
2016-03-15 19:55                   ` Dr. David Alan Gilbert
2016-03-16  1:20                     ` Li, Liang Z
  -- strict thread matches above, loose matches on Subject: below --
2016-03-04  9:32 Jitendra Kolhe
2016-03-04  9:36 ` Li, Liang Z
2016-03-08 11:14 ` Amit Shah

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=20160308111343.GM15443@grmbl.mre \
    --to=amit.shah@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=dgilbert@redhat.com \
    --cc=ehabkost@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=liang.z.li@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mst@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=quintela@redhat.com \
    --cc=rth@twiddle.net \
    --cc=virtualization@lists.linux-foundation.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).