From: Paolo Bonzini <pbonzini@redhat.com>
To: Vladimir Sementsov-Ogievskiy <vsementsov@parallels.com>,
qemu-devel@nongnu.org
Cc: kwolf@redhat.com, den@openvz.org, jsnow@redhat.com, stefanha@redhat.com
Subject: Re: [Qemu-devel] [PATCH 9/9] block-migration: add named dirty bitmaps migration
Date: Mon, 12 Jan 2015 15:42:45 +0100 [thread overview]
Message-ID: <54B3DD65.7030200@redhat.com> (raw)
In-Reply-To: <54B3D84A.8000207@parallels.com>
On 12/01/2015 15:20, Vladimir Sementsov-Ogievskiy wrote:
>
> On 09.01.2015 01:36, Paolo Bonzini wrote:
>> The bitmaps are transmitted many times in their entirety, but only the
>> last copy actually means something. The others are lost. This means
>> you should use the non-live interface (register_savevm). This will
>> simplify the code a lot.
>
> But what if the dirty bitmap is really big?
>
> For example, for 5 Pb drive the bitmap with granularity 65536 will be of
> 2 Gb size. So, shouldn't it be migrated iteratively for live migration?
But your code is not attempting to do that. It is not attempting to
track the dirtiness of the dirty bitmap, so to speak.
For such a huge storage, in any case, I suspect the solution is to not
use QEMU's live operations and, instead, operate at the storage level.
Paolo
next prev parent reply other threads:[~2015-01-12 14:42 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-12-11 14:17 [Qemu-devel] [PATCH 0/8] Dirty bitmaps migration Vladimir Sementsov-Ogievskiy
2014-12-11 14:17 ` [Qemu-devel] [PATCH 1/9] block: rename bdrv_reset_dirty_bitmap Vladimir Sementsov-Ogievskiy
2015-01-08 21:19 ` John Snow
2014-12-11 14:17 ` [Qemu-devel] [PATCH 2/9] block-migration: fix pending() return value Vladimir Sementsov-Ogievskiy
2015-01-08 21:20 ` John Snow
2015-01-09 19:01 ` Dr. David Alan Gilbert
2014-12-11 14:17 ` [Qemu-devel] [PATCH 3/9] block: fix spoiling all dirty bitmaps by mirror and migration Vladimir Sementsov-Ogievskiy
2015-01-08 21:20 ` John Snow
2014-12-11 14:17 ` [Qemu-devel] [PATCH 4/9] hbitmap: store / restore Vladimir Sementsov-Ogievskiy
2015-01-08 21:21 ` John Snow
2015-01-08 21:37 ` Paolo Bonzini
2015-01-13 12:59 ` Vladimir Sementsov-Ogievskiy
2015-01-13 17:08 ` John Snow
2015-01-14 10:29 ` Vladimir Sementsov-Ogievskiy
2014-12-11 14:17 ` [Qemu-devel] [PATCH 5/9] block: BdrvDirtyBitmap store/restore interface Vladimir Sementsov-Ogievskiy
2015-01-08 21:22 ` John Snow
2015-01-14 11:27 ` Vladimir Sementsov-Ogievskiy
2014-12-11 14:17 ` [Qemu-devel] [PATCH 6/9] block-migration: tiny refactoring Vladimir Sementsov-Ogievskiy
2015-01-08 21:23 ` John Snow
2015-01-14 12:26 ` Vladimir Sementsov-Ogievskiy
2015-01-14 16:53 ` John Snow
2014-12-11 14:17 ` [Qemu-devel] [PATCH 7/9] block-migration: remove not needed iothread lock Vladimir Sementsov-Ogievskiy
2015-01-08 21:24 ` John Snow
2015-01-16 12:54 ` Vladimir Sementsov-Ogievskiy
2015-01-08 22:28 ` Paolo Bonzini
2015-01-16 13:03 ` Vladimir Sementsov-Ogievskiy
2014-12-11 14:17 ` [Qemu-devel] [PATCH 8/9] migration: add dirty parameter Vladimir Sementsov-Ogievskiy
2014-12-11 15:18 ` Eric Blake
2014-12-15 8:33 ` Vladimir Sementsov-Ogievskiy
2015-01-08 21:51 ` John Snow
2015-01-08 22:29 ` Eric Blake
2015-01-08 22:31 ` John Snow
2015-01-08 22:37 ` Paolo Bonzini
2014-12-11 14:17 ` [Qemu-devel] [PATCH 9/9] block-migration: add named dirty bitmaps migration Vladimir Sementsov-Ogievskiy
2015-01-08 22:05 ` John Snow
2015-01-17 17:17 ` Vladimir Sementsov-Ogievskiy
2015-01-20 17:25 ` John Snow
2015-01-08 22:36 ` Paolo Bonzini
2015-01-08 22:45 ` Eric Blake
2015-01-08 22:49 ` Paolo Bonzini
2015-01-12 14:20 ` Vladimir Sementsov-Ogievskiy
2015-01-12 14:42 ` Paolo Bonzini [this message]
2015-01-12 16:48 ` Paolo Bonzini
2015-01-12 17:31 ` John Snow
2015-01-12 19:09 ` Paolo Bonzini
2015-01-13 9:16 ` Vladimir Sementsov-Ogievskiy
2015-01-13 16:35 ` John Snow
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=54B3DD65.7030200@redhat.com \
--to=pbonzini@redhat.com \
--cc=den@openvz.org \
--cc=jsnow@redhat.com \
--cc=kwolf@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=stefanha@redhat.com \
--cc=vsementsov@parallels.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).