From: "Michael S. Tsirkin" <mst@redhat.com>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: Orit Wasserman <owasserm@redhat.com>,
chegu_vinod@hp.com, qemu-devel@nongnu.org, quintela@redhat.com
Subject: Re: [Qemu-devel] [RFC 00/12] Migration: Remove copying of guest ram pages
Date: Thu, 21 Mar 2013 13:09:10 +0200 [thread overview]
Message-ID: <20130321110910.GB24024@redhat.com> (raw)
In-Reply-To: <514AD8B3.8060901@redhat.com>
On Thu, Mar 21, 2013 at 10:53:55AM +0100, Paolo Bonzini wrote:
> Il 21/03/2013 10:48, Michael S. Tsirkin ha scritto:
> > A recent discussion about overcommitted memory made me think:
> > this will still need to read pages into memory even
> > if all we will do is send it out on the wire immediately,
> > dirtying cache etc.
> >
> > Now, one property of RAM writes is that if guest changes
> > the memory that we are migrating, we really
> > don't care that remote will get a new copy and not
> > the old copy.
>
> Orit's patches already do this (patch 11). The only copy that remains
> is from memory to socket buffers.
>
>
> > For this to work, however, we need to have a way
> > for QEMUFile to know whether a specific iovec
> > references RAM (so it's ok to use vmsplice)
> > or a malloced buffer for device state (so it must use write
> > to ensure kernel copies data).
> >
> > What do you think?
>
> Was SPLICE_F_GIFT/SPLICE_F_MOVE ever implemented in the end? If not,
> patch 11 of this series does the same thing you are suggesting, without
> the indirection of an additional pipe file descriptor that is required
> for splice/vmsplice.
>
> Paolo
GIFT seems to be implemented so no problem there.
MOVE seems not to be needed for TCP - I think it just uses sendpage
internally which will do zero copy without special hints.
> >> Orit Wasserman (12):
> >> Add iov_writev to use writev to send iovec (also for files)
> >> Add QemuFileWritevBuffer QemuFileOps
> >> Add socket_writev_buffer function
> >> Add stdio_writev_buffer function
> >> Add block_writev_buffer function
> >> Update bytes_xfer in qemu_put_byte
> >> Store the data to send also in iovec
> >> Use writev ops instead of put_buffer ops
> >> More optimized qemu_put_be64/32/16
> >> Add qemu_put_buffer_no_copy
> >> Use qemu_put_buffer_no_copy for guest memory pages
> >> Bye Bye put_buffer
> >>
> >> arch_init.c | 2 +-
> >> include/migration/qemu-file.h | 20 ++++---
> >> include/qemu/iov.h | 12 ++++
> >> savevm.c | 130 +++++++++++++++++++++++++-----------------
> >> util/iov.c | 36 ++++++++++++
> >> 5 files changed, 139 insertions(+), 61 deletions(-)
> >>
> >> --
> >> 1.7.11.7
prev parent reply other threads:[~2013-03-21 11:08 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-03-21 9:09 [Qemu-devel] [RFC 00/12] Migration: Remove copying of guest ram pages Orit Wasserman
2013-03-21 9:09 ` [Qemu-devel] [RFC 01/12] Add iov_writev to use writev to send iovec (also for files) Orit Wasserman
2013-03-21 9:23 ` Paolo Bonzini
2013-03-21 9:09 ` [Qemu-devel] [RFC 02/12] Add QemuFileWritevBuffer QemuFileOps Orit Wasserman
2013-03-21 9:09 ` [Qemu-devel] [RFC 03/12] Add socket_writev_buffer function Orit Wasserman
2013-03-21 9:18 ` Paolo Bonzini
2013-03-21 9:47 ` Orit Wasserman
2013-03-21 9:47 ` Paolo Bonzini
2013-03-21 10:17 ` Orit Wasserman
2013-03-21 9:09 ` [Qemu-devel] [RFC 04/12] Add stdio_writev_buffer function Orit Wasserman
2013-03-21 9:28 ` Paolo Bonzini
2013-03-21 9:09 ` [Qemu-devel] [RFC 05/12] Add block_writev_buffer function Orit Wasserman
2013-03-21 9:09 ` [Qemu-devel] [RFC 06/12] Update bytes_xfer in qemu_put_byte Orit Wasserman
2013-03-21 9:09 ` [Qemu-devel] [RFC 07/12] Store the data to send also in iovec Orit Wasserman
2013-03-21 9:56 ` Paolo Bonzini
2013-03-21 11:10 ` Orit Wasserman
2013-03-21 11:14 ` Michael S. Tsirkin
2013-03-21 12:50 ` Orit Wasserman
2013-03-21 13:00 ` Paolo Bonzini
2013-03-21 9:09 ` [Qemu-devel] [RFC 08/12] Use writev ops instead of put_buffer ops Orit Wasserman
2013-03-21 9:09 ` [Qemu-devel] [RFC 09/12] More optimized qemu_put_be64/32/16 Orit Wasserman
2013-03-21 9:09 ` [Qemu-devel] [RFC 10/12] Add qemu_put_buffer_no_copy Orit Wasserman
2013-03-21 9:25 ` Paolo Bonzini
2013-03-23 16:27 ` Michael R. Hines
2013-03-25 8:11 ` Orit Wasserman
2013-03-25 13:05 ` Paolo Bonzini
2013-03-25 15:18 ` Michael R. Hines
2013-03-25 15:59 ` Paolo Bonzini
2013-03-21 9:09 ` [Qemu-devel] [RFC 11/12] Use qemu_put_buffer_no_copy for guest memory pages Orit Wasserman
2013-03-21 9:09 ` [Qemu-devel] [RFC 12/12] Bye Bye put_buffer Orit Wasserman
2013-03-21 9:29 ` [Qemu-devel] [RFC 00/12] Migration: Remove copying of guest ram pages Paolo Bonzini
2013-03-21 10:05 ` Orit Wasserman
2013-03-21 9:48 ` Michael S. Tsirkin
2013-03-21 9:53 ` Paolo Bonzini
2013-03-21 11:09 ` Michael S. Tsirkin [this message]
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=20130321110910.GB24024@redhat.com \
--to=mst@redhat.com \
--cc=chegu_vinod@hp.com \
--cc=owasserm@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=quintela@redhat.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).