From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <d.csapak@proxmox.com>
Received: from firstgate.proxmox.com (firstgate.proxmox.com [212.224.123.68])
 (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)
 key-exchange X25519 server-signature RSA-PSS (2048 bits))
 (No client certificate requested)
 by lists.proxmox.com (Postfix) with UTF8SMTPS id 0AB96799C8
 for <pve-devel@lists.proxmox.com>; Wed,  5 May 2021 11:23:07 +0200 (CEST)
Received: from firstgate.proxmox.com (localhost [127.0.0.1])
 by firstgate.proxmox.com (Proxmox) with UTF8SMTP id E9F1312BF5
 for <pve-devel@lists.proxmox.com>; Wed,  5 May 2021 11:22:36 +0200 (CEST)
Received: from proxmox-new.maurer-it.com (proxmox-new.maurer-it.com
 [94.136.29.106])
 (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)
 key-exchange X25519 server-signature RSA-PSS (2048 bits))
 (No client certificate requested)
 by firstgate.proxmox.com (Proxmox) with UTF8SMTPS id 7CA4112BE7
 for <pve-devel@lists.proxmox.com>; Wed,  5 May 2021 11:22:36 +0200 (CEST)
Received: from proxmox-new.maurer-it.com (localhost.localdomain [127.0.0.1])
 by proxmox-new.maurer-it.com (Proxmox) with UTF8SMTP id 4992E45A92
 for <pve-devel@lists.proxmox.com>; Wed,  5 May 2021 11:22:36 +0200 (CEST)
Message-ID: <9a7572b0-1d7b-56b3-7daf-3667a7d85cdc@proxmox.com>
Date: Wed, 5 May 2021 11:22:35 +0200
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:89.0) Gecko/20100101
 Thunderbird/89.0
Content-Language: en-US
To: pve-devel@lists.proxmox.com
References: <1618496842.5t56y2jruz.astroid@nora.none>
 <bb5e0698-c0c1-ffa9-49b5-becb5bb296e8@gmail.com>
 <d5d445e0b0eff39ff5f750c6ab65ba1bbd3df791.camel@odiso.com>
From: Dominik Csapak <d.csapak@proxmox.com>
In-Reply-To: <d5d445e0b0eff39ff5f750c6ab65ba1bbd3df791.camel@odiso.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
X-SPAM-LEVEL: Spam detection results:  0
 AWL 0.016 Adjusted score from AWL reputation of From: address
 KAM_DMARC_STATUS 0.01 Test Rule for DKIM or SPF Failure with Strict Alignment
 NICE_REPLY_A           -0.001 Looks like a legit reply (A)
 SPF_HELO_NONE           0.001 SPF: HELO does not publish an SPF Record
 SPF_PASS               -0.001 SPF: sender matches SPF record
Subject: Re: [pve-devel] [RFC qemu-server++ 0/22] remote migration
X-BeenThere: pve-devel@lists.proxmox.com
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Proxmox VE development discussion <pve-devel.lists.proxmox.com>
List-Unsubscribe: <https://lists.proxmox.com/cgi-bin/mailman/options/pve-devel>, 
 <mailto:pve-devel-request@lists.proxmox.com?subject=unsubscribe>
List-Archive: <http://lists.proxmox.com/pipermail/pve-devel/>
List-Post: <mailto:pve-devel@lists.proxmox.com>
List-Help: <mailto:pve-devel-request@lists.proxmox.com?subject=help>
List-Subscribe: <https://lists.proxmox.com/cgi-bin/mailman/listinfo/pve-devel>, 
 <mailto:pve-devel-request@lists.proxmox.com?subject=subscribe>
X-List-Received-Date: Wed, 05 May 2021 09:23:07 -0000

On 5/5/21 08:02, aderumier@odiso.com wrote:
> Hi Moula,
> 
> local device migration is not related to this remote migration serie,
> but maybe some improvement could be done.
> 
> I'm think about usb device, where we could have the same device on
> multiple hosts. (like a security dongle for example).
> 
> I think for usb we should be able to detach/migrate/rettach. (it should
> work for stateless device, but not a usb drive for example)
> 
> Maybe for local nic pci passthroug too.
> 
> But for gpu I'm really not sure it's possible, if you have some data in
> the local gpu memory, I don't see how it's possible to get it working.
> 
> Do you known an hypervisor with this kind of gpu migration
> implementation ?
> 

afaik, this is being worked on in qemu/kvm but needs hardware support,
i.e. you can dump the internal state of a supported pci device,
and migrate it to the target

will probably still take a while until normal (non big datacenter)
customers can use this...