From: Kevin Wolf <kwolf@redhat.com>
To: Ori Mamluk <omamluk@zerto.com>
Cc: dlaor@redhat.com, "עודד קדם" <oded@zerto.com>,
"תומר בן אור" <tomer@zertodata.com>,
qemu-devel@nongnu.org, "Yair Kuszpet" <yairk@zerto.com>,
"Paolo Bonzini" <pbonzini@redhat.com>
Subject: Re: [Qemu-devel] [RFC PATCH] replication agent module
Date: Wed, 08 Feb 2012 11:04:10 +0100 [thread overview]
Message-ID: <4F32489A.80307@redhat.com> (raw)
In-Reply-To: <4F3244C2.1040604@zerto.com>
Am 08.02.2012 10:47, schrieb Ori Mamluk:
> On 08/02/2012 10:55, Kevin Wolf wrote:
>> Am 08.02.2012 07:10, schrieb Ori Mamluk:
>>> On 07/02/2012 17:47, Paolo Bonzini wrote:
>>>>
>>>> Why can't QEMU itself stream the full volume in the background, and
>>>> send that together with any new I/O? Is it because the rephub knows
>>>> which parts are out-of-date and need recovery? In that case, as a
>>>> first approximation the rephub can pass the sector at which streaming
>>>> should start.
>>> Yes - it's because rephub knows. The parts that need recovery may be a
>>> series of random IOs that were lost because of a network outage
>>> somewhere along the replication pipe.
>>> Easy to think of it as a bitmap holding the not-yet-replicated IOs. The
>>> rephub occasionally reads those areas to 'sync' them, so in effect the
>>> rephub needs read access - it's not really to trigger streaming from an
>>> offset.
>> So how does the rephub know which areas were touched by lost requests?
>> Isn't qemu the only one who could know what it sent?
>>
>> Kevin
> You're right. Currently only Qemu knows.
How could it change later on? If the network is down, qemu can't
communicate it to anyone else, so it stays the only one who knows.
> The problem is that if we move the responsibility to a layer below Qemu
> - then rephub will never know.
> Our (Zerto's) solution for vmware has a different design, but it has 3
> parts relevant to this discussion:
> 1. Tapping to protected writes / read protected volume
> 2. Maintain a bitmap
> 3. Provide cross-VM consistency for recovery.
>
> I want to simplify our design by taking it one step at a time.
> My first goal for Qemu is to have only step 1 - meaning tap all
> protected writes, and be able to read.
> I think it will be simpler for all of us to complete that first, and it
> provides a basic ability (though not optimal) for protection and recovery.
>
> I think using an external streaming mechanism will make the next stages
> impossible.
Well, then we need to discuss all stages now. If you tell only part of
what you're going to do, you'll get a design that will only work for
part of what you need.
Kevin
next prev parent reply other threads:[~2012-02-08 10:00 UTC|newest]
Thread overview: 66+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-02-07 10:29 [Qemu-devel] [RFC PATCH] replication agent module Ori Mamluk
2012-02-07 12:12 ` Anthony Liguori
2012-02-07 12:25 ` Dor Laor
2012-02-07 12:30 ` Ori Mamluk
2012-02-07 12:40 ` Anthony Liguori
2012-02-07 14:06 ` Ori Mamluk
2012-02-07 14:40 ` Paolo Bonzini
2012-02-07 14:48 ` Ori Mamluk
2012-02-07 15:47 ` Paolo Bonzini
2012-02-08 6:10 ` Ori Mamluk
2012-02-08 8:49 ` Dor Laor
2012-02-08 11:59 ` Stefan Hajnoczi
2012-02-08 8:55 ` Kevin Wolf
2012-02-08 9:47 ` Ori Mamluk
2012-02-08 10:04 ` Kevin Wolf [this message]
2012-02-08 13:28 ` [Qemu-devel] [RFC] Replication agent design (was [RFC PATCH] replication agent module) Ori Mamluk
2012-02-08 14:59 ` Stefan Hajnoczi
2012-02-08 14:59 ` Stefan Hajnoczi
2012-02-19 13:40 ` Ori Mamluk
2012-02-20 14:32 ` Paolo Bonzini
2012-02-21 9:03 ` [Qemu-devel] BlockDriverState stack and BlockListeners (was: [RFC] Replication agent design) Kevin Wolf
2012-02-21 9:15 ` [Qemu-devel] BlockDriverState stack and BlockListeners Paolo Bonzini
2012-02-21 9:49 ` Kevin Wolf
2012-02-21 10:09 ` Paolo Bonzini
2012-02-21 10:51 ` Kevin Wolf
2012-02-21 11:36 ` Paolo Bonzini
2012-02-21 12:22 ` Stefan Hajnoczi
2012-02-21 12:57 ` Paolo Bonzini
2012-02-21 15:49 ` Markus Armbruster
2012-02-21 13:10 ` Kevin Wolf
2012-02-21 13:21 ` Paolo Bonzini
2012-02-21 15:56 ` Markus Armbruster
2012-02-21 16:04 ` Kevin Wolf
2012-02-21 16:19 ` Markus Armbruster
2012-02-21 16:39 ` Kevin Wolf
2012-02-21 17:16 ` Stefan Hajnoczi
2012-02-21 10:20 ` Ori Mamluk
2012-02-29 8:38 ` Ori Mamluk
2012-03-03 11:46 ` Stefan Hajnoczi
2012-03-04 5:14 ` Ori Mamluk
2012-03-04 8:56 ` Paolo Bonzini
2012-03-05 12:04 ` Stefan Hajnoczi
2012-02-08 11:02 ` [Qemu-devel] [RFC PATCH] replication agent module Stefan Hajnoczi
2012-02-08 13:00 ` [Qemu-devel] [RFC] Replication agent requirements (was [RFC PATCH] replication agent module) Ori Mamluk
2012-02-08 13:30 ` Anthony Liguori
2012-02-08 12:03 ` [Qemu-devel] [RFC PATCH] replication agent module Stefan Hajnoczi
2012-02-08 12:46 ` Paolo Bonzini
2012-02-08 14:39 ` Stefan Hajnoczi
2012-02-08 14:55 ` Paolo Bonzini
2012-02-08 15:07 ` Stefan Hajnoczi
2012-02-07 14:53 ` Kevin Wolf
2012-02-07 15:00 ` Anthony Liguori
2012-02-07 13:34 ` Kevin Wolf
2012-02-07 13:50 ` Stefan Hajnoczi
2012-02-07 13:58 ` Paolo Bonzini
2012-02-07 14:05 ` Paolo Bonzini
2012-02-08 12:17 ` Orit Wasserman
2012-02-07 14:18 ` Ori Mamluk
2012-02-07 14:59 ` Anthony Liguori
2012-02-07 15:20 ` Stefan Hajnoczi
2012-02-07 16:25 ` Anthony Liguori
2012-02-21 16:01 ` Markus Armbruster
2012-02-21 17:31 ` Stefan Hajnoczi
2012-02-07 14:45 ` Ori Mamluk
2012-02-08 12:29 ` Orit Wasserman
2012-02-08 11:45 ` Luiz Capitulino
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=4F32489A.80307@redhat.com \
--to=kwolf@redhat.com \
--cc=dlaor@redhat.com \
--cc=oded@zerto.com \
--cc=omamluk@zerto.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=tomer@zertodata.com \
--cc=yairk@zerto.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).