qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Anthony Liguori <anthony@codemonkey.ws>
To: Orit Wasserman <owasserm@redhat.com>
Cc: quintela@redhat.com, stefanha@gmail.com, qemu-devel@nongnu.org,
	blauwirbel@gmail.com, Petter Svard <petters@cs.umu.se>,
	Benoit Hudzia <benoit.hudzia@sap.com>,
	Aidan Shribman <aidan.shribman@sap.com>
Subject: Re: [Qemu-devel] [PATCH v5 0/9] XBZRLE delta for live migration of large memory apps
Date: Tue, 03 Jan 2012 10:32:39 -0600	[thread overview]
Message-ID: <4F032DA7.30803@codemonkey.ws> (raw)
In-Reply-To: <1325604879-15862-1-git-send-email-owasserm@redhat.com>

On 01/03/2012 09:34 AM, Orit Wasserman wrote:
> Changes from v4:
> 1) Rebase
> 2) divide patch into 9 patches
> 3) move memory allocation into cache_insert
>
> By using XBZRLE (Xor Binary Zero Run-Length-Encoding) we can reduce VM downtime
> and total live-migration time of VMs running memory write intensive workloads
> typical of large enterprise applications such as SAP ERP Systems, and generally
> speaking for any application with a sparse memory update pattern.
>
> On the sender side XBZRLE is used as a compact delta encoding of page updates,
> retrieving the old page content from an LRU cache (default size of 64 MB). The
> receiving side uses the existing page content and XBZRLE to decode the new page
> content.
>
> Work was originally based on research results published VEE 2011: Evaluation of
> Delta Compression Techniques for Efficient Live Migration of Large Virtual
> Machines by Benoit, Svard, Tordsson and Elmroth. Additionally the delta encoder
> XBRLE was improved further using XBZRLE instead.
>
> XBZRLE has a sustained bandwidth of 2-2.5 GB/s for typical workloads making it
> ideal for in-line, real-time encoding such as is needed for live-migration.
>
> A typical usage scenario:
>      {qemu} migrate_set_cachesize 256m

How does one intelligently choose a cache size?  How bad is it to choose the 
wrong cache size?

>      {qemu} migrate -x -d tcp:destination.host:4444

We need to make this a negotiated feature, not a requirement for the user to 
figure out.

Please go back to the previous thread for more details on this.

Regards,

Anthony Liguori

>      {qemu} info migrate
>      ...
>      transferred ram-duplicate: A kbytes
>      transferred ram-duplicate: B pages
>      transferred ram-normal: C kbytes
>      transferred ram-normal: D pages
>      transferred ram-xbrle: E kbytes
>      transferred ram-xbrle: F pages
>      overflow ram-xbrle: G pages
>      cache-hit ram-xbrle: H pages
>      cache-lookup ram-xbrle: J pages
>
> Testing: live migration with XBZRLE completed in 110 seconds, without live
> migration was not able to complete.
>
> A simple synthetic memory r/w load generator:
> ..    include<stdlib.h>
> ..    include<stdio.h>
> ..    int main()
> ..    {
> ..        char *buf = (char *) calloc(4096, 4096);
> ..        while (1) {
> ..            int i;
> ..            for (i = 0; i<  4096 * 4; i++) {
> ..                buf[i * 4096 / 4]++;
> ..            }
> ..            printf(".");
> ..        }
> ..    }
>
> Signed-off-by: Benoit Hudzia<benoit.hudzia@sap.com>
> Signed-off-by: Petter Svard<petters@cs.umu.se>
> Signed-off-by: Aidan Shribman<aidan.shribman@sap.com>
>
>   arch_init.c       |  546 +++++++++++++++++++++++++++++++++++++++++++++++++----
>   block-migration.c |    4 +-
>   hmp-commands.hx   |   34 +++-
>   hw/hw.h           |    4 +-
>   migration.c       |   51 +++++-
>   migration.h       |   19 ++
>   qmp-commands.hx   |   44 ++++-
>   savevm.c          |   11 +-
>   sysemu.h          |    4 +-
>   9 files changed, 653 insertions(+), 64 deletions(-)
>

  parent reply	other threads:[~2012-01-03 16:32 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-01-03 15:34 [Qemu-devel] [PATCH v5 0/9] XBZRLE delta for live migration of large memory apps Orit Wasserman
2012-01-03 15:34 ` [Qemu-devel] [PATCH v5 1/9] Add cache handling functions Orit Wasserman
2012-01-03 19:54   ` Anthony Liguori
2012-01-04  9:29     ` Orit Wasserman
2012-01-04 22:20       ` Michael Roth
2012-01-04 11:46   ` Stefan Hajnoczi
2012-01-04 13:27     ` Orit Wasserman
2012-01-03 15:34 ` [Qemu-devel] [PATCH v5 2/9] Add rle_encode and rle_decode functions Implement Run Length Encoding compression Orit Wasserman
2012-01-03 19:57   ` Anthony Liguori
2012-01-04  9:31     ` Orit Wasserman
2012-01-04 16:52       ` Paolo Bonzini
2012-01-04 12:59   ` Avi Kivity
2012-01-04 13:35     ` Stefan Hajnoczi
2012-01-04 13:45       ` Avi Kivity
2012-01-03 15:34 ` [Qemu-devel] [PATCH v5 3/9] Add save_block_hdr function Orit Wasserman
2012-01-03 15:34 ` [Qemu-devel] [PATCH v5 4/9] Add host_from_stream_offset_versioned function Orit Wasserman
2012-01-04 12:00   ` Stefan Hajnoczi
2012-01-04 20:59     ` Michael Roth
2012-01-03 15:34 ` [Qemu-devel] [PATCH v5 5/9] Add XBRLE to ram_save_block and ram_save_live Orit Wasserman
2012-01-04 12:14   ` Stefan Hajnoczi
2012-01-04 13:29     ` Orit Wasserman
2012-01-03 15:34 ` [Qemu-devel] [PATCH v5 6/9] Add xbrle parameters to MigrationState Orit Wasserman
2012-01-04 21:17   ` Michael Roth
2012-01-03 15:34 ` [Qemu-devel] [PATCH v5 7/9] Add set_cachesize to change XBRLE cache size Orit Wasserman
2012-01-03 15:34 ` [Qemu-devel] [PATCH v5 8/9] QMP commands changes Orit Wasserman
2012-01-03 15:47   ` Stefan Hajnoczi
2012-01-03 15:57     ` Orit Wasserman
2012-01-03 16:20       ` Stefan Hajnoczi
2012-01-03 15:34 ` [Qemu-devel] [PATCH v5 9/9] Add XBRLE statistics information Orit Wasserman
2012-01-04 22:45   ` Michael Roth
2012-01-07 16:31   ` Blue Swirl
2012-01-03 16:32 ` Anthony Liguori [this message]
2012-01-03 17:02   ` [Qemu-devel] [PATCH v5 0/9] XBZRLE delta for live migration of large memory apps Orit Wasserman
2012-01-04 13:02 ` Avi Kivity
2012-01-04 16:03   ` Orit Wasserman
  -- strict thread matches above, loose matches on Subject: below --
2012-01-03 13:35 Orit Wasserman

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=4F032DA7.30803@codemonkey.ws \
    --to=anthony@codemonkey.ws \
    --cc=aidan.shribman@sap.com \
    --cc=benoit.hudzia@sap.com \
    --cc=blauwirbel@gmail.com \
    --cc=owasserm@redhat.com \
    --cc=petters@cs.umu.se \
    --cc=qemu-devel@nongnu.org \
    --cc=quintela@redhat.com \
    --cc=stefanha@gmail.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 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).