From: Orit Wasserman <owasserm@redhat.com>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: mst@redhat.com, chegu_vinod@hp.com, qemu-devel@nongnu.org,
quintela@redhat.com
Subject: Re: [Qemu-devel] [PATCH v3 0/9] Migration: Remove copying of guest ram pages
Date: Thu, 21 Mar 2013 19:35:17 +0200 [thread overview]
Message-ID: <514B44D5.5020602@redhat.com> (raw)
In-Reply-To: <514B3F9A.107@redhat.com>
On 03/21/2013 07:12 PM, Paolo Bonzini wrote:
> Il 21/03/2013 17:05, Orit Wasserman ha scritto:
>> In migration all data is copied to a static buffer in QEMUFile,
>> this hurts our network bandwidth and CPU usage especially with large guests.
>> We switched to iovec for storing different buffers to send (even a byte field is
>> considered as a buffer) and use writev to send the iovec.
>> writev was chosen (as apposed to sendmsg) because it supprts non socket fds.
>>
>> Guest memory pages are not copied by calling a new function
>> qemu_put_buffer_no_copy.
>> The page header data and device state data are still copied into the static
>> buffer. This data consists of a lot of bytes and integer fields and the static
>> buffer is used to store it during batching.
>> Another improvement is changing qemu_putbe64/32/16 to create a single
>> buffer instead of several byte sized buffer.
>>
>> git repository: git://github.com/oritwas/qemu.git sendv_v2
>>
>> Change from v2:
>> Always send data for the iovec even if writev_buffer is not implemented.
>> Coalesce adjacent iovecs to create one big buffer from small adjacent buffer.
>>
>> Changes from v1:
>> Use iov_send for socket.
>> Make writev_buffer optional and if it is not implemented use put_buffer
>
> I didn't review it too closely, so I don't feel like giving my
> Reviewed-by. Still, I must say it is a very nice and simple solution.
> Kudos!
>
> Just one question: patch 6 is not strictly needed anymore now that you
> have coalescing, no? Should Juan leave it out?
true, Juan had a small fix so I'm sending v4 I will remove it.
>
> Paolo
>
next prev parent reply other threads:[~2013-03-21 17:34 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-03-21 16:05 [Qemu-devel] [PATCH v3 0/9] Migration: Remove copying of guest ram pages Orit Wasserman
2013-03-21 16:05 ` [Qemu-devel] [PATCH v3 1/9] Add QemuFileWritevBuffer QemuFileOps Orit Wasserman
2013-03-21 16:57 ` Juan Quintela
2013-03-21 16:05 ` [Qemu-devel] [PATCH v3 2/9] Add socket_writev_buffer function Orit Wasserman
2013-03-21 16:55 ` Juan Quintela
2013-03-21 16:05 ` [Qemu-devel] [PATCH v3 3/9] Update bytes_xfer in qemu_put_byte Orit Wasserman
2013-03-21 17:06 ` Juan Quintela
2013-03-21 17:38 ` Eric Blake
2013-03-21 17:41 ` Orit Wasserman
2013-03-21 16:05 ` [Qemu-devel] [PATCH v3 4/9] Store the data to send also in iovec Orit Wasserman
2013-03-21 17:11 ` Juan Quintela
2013-03-21 16:05 ` [Qemu-devel] [PATCH v3 5/9] Use writev ops if available Orit Wasserman
2013-03-21 17:17 ` Juan Quintela
2013-03-21 16:05 ` [Qemu-devel] [PATCH v3 6/9] More optimized qemu_put_be64/32/16 Orit Wasserman
2013-03-21 17:18 ` Juan Quintela
2013-03-21 16:05 ` [Qemu-devel] [PATCH v3 7/9] Add qemu_put_buffer_no_copy Orit Wasserman
2013-03-21 17:34 ` Juan Quintela
2013-03-21 17:39 ` Orit Wasserman
2013-03-21 16:05 ` [Qemu-devel] [PATCH v3 8/9] Use qemu_put_buffer_no_copy for guest memory pages Orit Wasserman
2013-03-21 16:14 ` Michael S. Tsirkin
2013-03-21 17:37 ` Juan Quintela
2013-03-21 18:08 ` Orit Wasserman
2013-03-21 18:21 ` Michael S. Tsirkin
2013-03-21 16:05 ` [Qemu-devel] [PATCH v3 9/9] coalesce adjacent iovecs Orit Wasserman
2013-03-21 16:16 ` Michael S. Tsirkin
2013-03-21 16:27 ` Orit Wasserman
2013-03-21 16:29 ` Michael S. Tsirkin
2013-03-21 16:40 ` Orit Wasserman
2013-03-21 17:10 ` Michael S. Tsirkin
2013-03-21 17:44 ` Juan Quintela
2013-03-21 17:46 ` Michael S. Tsirkin
2013-03-21 18:22 ` Juan Quintela
2013-03-21 18:33 ` Michael S. Tsirkin
2013-03-21 17:41 ` Juan Quintela
2013-03-21 17:12 ` [Qemu-devel] [PATCH v3 0/9] Migration: Remove copying of guest ram pages Paolo Bonzini
2013-03-21 17:35 ` Orit Wasserman [this message]
2013-03-21 17:42 ` Juan Quintela
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=514B44D5.5020602@redhat.com \
--to=owasserm@redhat.com \
--cc=chegu_vinod@hp.com \
--cc=mst@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).