All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Lan, Tianyu" <tianyu.lan@intel.com>
To: Alexander Duyck <alexander.duyck@gmail.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>,
	aik@ozlabs.ru, Alex Williamson <alex.williamson@redhat.com>,
	amit.shah@redhat.com, Anthony Liguori <anthony@codemonkey.ws>,
	Ard Biesheuvel <ard.biesheuvel@linaro.org>,
	Blue Swirl <blauwirbel@gmail.com>,
	cornelia.huck@de.ibm.com, "Dong, Eddie" <eddie.dong@intel.com>,
	"Jani, Nrupal" <nrupal.jani@intel.com>,
	Alexander Graf <agraf@suse.de>,
	kvm@vger.kernel.org, Paolo Bonzini <pbonzini@redhat.com>,
	qemu-devel@nongnu.org, "Tantilov,
	Emil S" <emil.s.tantilov@intel.com>,
	Or Gerlitz <gerlitz.or@gmail.com>,
	"Skidmore, Donald C" <donald.c.skidmore@intel.com>,
	"Rustad, Mark D" <mark.d.rustad@intel.com>,
	kraxel@redhat.com, lcapitulino@redhat.com, quintela@redhat.com
Subject: Re: live migration vs device assignment (motivation)
Date: Thu, 10 Dec 2015 11:15:59 +0800	[thread overview]
Message-ID: <5668EE6F.90200@intel.com> (raw)
In-Reply-To: <CAKgT0UeKRAS7YG3A=2hHTpexMCUb5bFbA+n=jxR9Zv0GSUMxpg@mail.gmail.com>



On 12/10/2015 1:14 AM, Alexander Duyck wrote:
> On Wed, Dec 9, 2015 at 8:26 AM, Lan, Tianyu <tianyu.lan@intel.com> wrote:
>
>> For other kind of devices, it's hard to work.
>> We are also adding migration support for QAT(QuickAssist Technology) device.
>>
>> QAT device user case introduction.
>> Server, networking, big data, and storage applications use QuickAssist
>> Technology to offload servers from handling compute-intensive operations,
>> such as:
>> 1) Symmetric cryptography functions including cipher operations and
>> authentication operations
>> 2) Public key functions including RSA, Diffie-Hellman, and elliptic curve
>> cryptography
>> 3) Compression and decompression functions including DEFLATE and LZS
>>
>> PCI hotplug will not work for such devices during migration and these
>> operations will fail when unplug device.
>
> I assume the problem is that with a PCI hotplug event you are losing
> the state information for the device, do I have that right?
>
> Looking over the QAT drivers it doesn't seem like any of them support
> the suspend/resume PM calls.  I would imagine it makes it difficult
> for a system with a QAT card in it to be able to drop the system to a
> low power state.  You might want to try enabling suspend/resume
> support for the devices on bare metal before you attempt to take on
> migration as it would provide you with a good testing framework to see
> what needs to be saved/restored within the device and in what order
> before you attempt to do the same while migrating from one system to
> another.

Sure. The suspend/resume job is under way.
Actually, we have enabled QAT work for migration internally. Doing more 
test and fixing bugs.

>
> - Alex
>

WARNING: multiple messages have this Message-ID (diff)
From: "Lan, Tianyu" <tianyu.lan@intel.com>
To: Alexander Duyck <alexander.duyck@gmail.com>
Cc: qemu-devel@nongnu.org, "Tantilov,
	Emil S" <emil.s.tantilov@intel.com>,
	kvm@vger.kernel.org, Ard Biesheuvel <ard.biesheuvel@linaro.org>,
	aik@ozlabs.ru, "Skidmore, Donald C" <donald.c.skidmore@intel.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	"Dong, Eddie" <eddie.dong@intel.com>,
	"Jani, Nrupal" <nrupal.jani@intel.com>,
	quintela@redhat.com, Alexander Graf <agraf@suse.de>,
	Blue Swirl <blauwirbel@gmail.com>,
	cornelia.huck@de.ibm.com,
	Alex Williamson <alex.williamson@redhat.com>,
	kraxel@redhat.com, Anthony Liguori <anthony@codemonkey.ws>,
	amit.shah@redhat.com, Paolo Bonzini <pbonzini@redhat.com>,
	"Rustad, Mark D" <mark.d.rustad@intel.com>,
	lcapitulino@redhat.com, Or Gerlitz <gerlitz.or@gmail.com>
Subject: Re: [Qemu-devel] live migration vs device assignment (motivation)
Date: Thu, 10 Dec 2015 11:15:59 +0800	[thread overview]
Message-ID: <5668EE6F.90200@intel.com> (raw)
In-Reply-To: <CAKgT0UeKRAS7YG3A=2hHTpexMCUb5bFbA+n=jxR9Zv0GSUMxpg@mail.gmail.com>



On 12/10/2015 1:14 AM, Alexander Duyck wrote:
> On Wed, Dec 9, 2015 at 8:26 AM, Lan, Tianyu <tianyu.lan@intel.com> wrote:
>
>> For other kind of devices, it's hard to work.
>> We are also adding migration support for QAT(QuickAssist Technology) device.
>>
>> QAT device user case introduction.
>> Server, networking, big data, and storage applications use QuickAssist
>> Technology to offload servers from handling compute-intensive operations,
>> such as:
>> 1) Symmetric cryptography functions including cipher operations and
>> authentication operations
>> 2) Public key functions including RSA, Diffie-Hellman, and elliptic curve
>> cryptography
>> 3) Compression and decompression functions including DEFLATE and LZS
>>
>> PCI hotplug will not work for such devices during migration and these
>> operations will fail when unplug device.
>
> I assume the problem is that with a PCI hotplug event you are losing
> the state information for the device, do I have that right?
>
> Looking over the QAT drivers it doesn't seem like any of them support
> the suspend/resume PM calls.  I would imagine it makes it difficult
> for a system with a QAT card in it to be able to drop the system to a
> low power state.  You might want to try enabling suspend/resume
> support for the devices on bare metal before you attempt to take on
> migration as it would provide you with a good testing framework to see
> what needs to be saved/restored within the device and in what order
> before you attempt to do the same while migrating from one system to
> another.

Sure. The suspend/resume job is under way.
Actually, we have enabled QAT work for migration internally. Doing more 
test and fixing bugs.

>
> - Alex
>

  reply	other threads:[~2015-12-10  3:16 UTC|newest]

Thread overview: 142+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-11-24 13:35 [RFC PATCH V2 00/10] Qemu: Add live migration support for SRIOV NIC Lan Tianyu
2015-11-24 13:35 ` [Qemu-devel] " Lan Tianyu
2015-11-24 13:35 ` [RFC PATCH V2 01/10] Qemu/VFIO: Create head file pci.h to share data struct Lan Tianyu
2015-11-24 13:35   ` [Qemu-devel] " Lan Tianyu
2015-11-24 13:35 ` [RFC PATCH V2 02/10] Qemu/VFIO: Add new VFIO_GET_PCI_CAP_INFO ioctl cmd definition Lan Tianyu
2015-11-24 13:35   ` [Qemu-devel] " Lan Tianyu
2015-12-02 22:25   ` Alex Williamson
2015-12-02 22:25     ` [Qemu-devel] " Alex Williamson
2015-12-03  8:40     ` Lan, Tianyu
2015-12-03  8:40       ` [Qemu-devel] " Lan, Tianyu
2015-12-03 15:26       ` Alex Williamson
2015-12-03 15:26         ` [Qemu-devel] " Alex Williamson
2015-11-24 13:35 ` [RFC PATCH V2 03/10] Qemu/VFIO: Rework vfio_std_cap_max_size() function Lan Tianyu
2015-11-24 13:35   ` [Qemu-devel] " Lan Tianyu
2015-11-24 13:35 ` [RFC PATCH V2 04/10] Qemu/VFIO: Add vfio_find_free_cfg_reg() to find free PCI config space regs Lan Tianyu
2015-11-24 13:35   ` [Qemu-devel] " Lan Tianyu
2015-11-24 13:35 ` [RFC PATCH V2 05/10] Qemu/VFIO: Expose PCI config space read/write and msix functions Lan Tianyu
2015-11-24 13:35   ` [Qemu-devel] " Lan Tianyu
2015-11-24 13:35 ` [RFC PATCH V2 06/10] Qemu/PCI: Add macros for faked PCI migration capability Lan Tianyu
2015-11-24 13:35   ` [Qemu-devel] " Lan Tianyu
2015-12-02 22:25   ` Alex Williamson
2015-12-02 22:25     ` [Qemu-devel] " Alex Williamson
2015-12-03  8:57     ` Lan, Tianyu
2015-12-03  8:57       ` [Qemu-devel] " Lan, Tianyu
2015-11-24 13:35 ` [RFC PATCH V2 07/10] Qemu: Add post_load_state() to run after restoring CPU state Lan Tianyu
2015-11-24 13:35   ` [Qemu-devel] " Lan Tianyu
2015-11-24 13:35 ` [RFC PATCH V2 08/10] Qemu: Add save_before_stop callback to run just before stopping VCPU during migration Lan Tianyu
2015-11-24 13:35   ` [Qemu-devel] " Lan Tianyu
2015-11-24 13:35 ` [RFC PATCH V2 09/10] Qemu/VFIO: Add SRIOV VF migration support Lan Tianyu
2015-11-24 13:35   ` [Qemu-devel] " Lan Tianyu
2015-11-24 21:03   ` Michael S. Tsirkin
2015-11-24 21:03     ` [Qemu-devel] " Michael S. Tsirkin
2015-11-25 15:32     ` Lan, Tianyu
2015-11-25 15:32       ` [Qemu-devel] " Lan, Tianyu
2015-11-25 15:44       ` Michael S. Tsirkin
2015-11-25 15:44         ` [Qemu-devel] " Michael S. Tsirkin
2015-12-02 22:25   ` Alex Williamson
2015-12-02 22:25     ` [Qemu-devel] " Alex Williamson
2015-12-03  8:56     ` Lan, Tianyu
2015-12-03  8:56       ` [Qemu-devel] " Lan, Tianyu
2015-11-24 13:35 ` [RFC PATCH V2 10/10] Qemu/VFIO: Misc change for enable migration with VFIO Lan Tianyu
2015-11-24 13:35   ` [Qemu-devel] " Lan Tianyu
2015-11-30  8:01 ` [RFC PATCH V2 00/10] Qemu: Add live migration support for SRIOV NIC Michael S. Tsirkin
2015-11-30  8:01   ` [Qemu-devel] " Michael S. Tsirkin
2015-12-01  6:26   ` Lan, Tianyu
2015-12-01  6:26     ` [Qemu-devel] " Lan, Tianyu
2015-12-01 15:02     ` Michael S. Tsirkin
2015-12-01 15:02       ` [Qemu-devel] " Michael S. Tsirkin
2015-12-02 14:08       ` Lan, Tianyu
2015-12-02 14:08         ` [Qemu-devel] " Lan, Tianyu
2015-12-02 14:31         ` Michael S. Tsirkin
2015-12-02 14:31           ` [Qemu-devel] " Michael S. Tsirkin
2015-12-03 14:53           ` Lan, Tianyu
2015-12-03 14:53             ` [Qemu-devel] " Lan, Tianyu
2015-12-04  6:42           ` Lan, Tianyu
2015-12-04  6:42             ` [Qemu-devel] " Lan, Tianyu
2015-12-04  8:05             ` Michael S. Tsirkin
2015-12-04  8:05               ` [Qemu-devel] " Michael S. Tsirkin
2015-12-04 12:11               ` Lan, Tianyu
2015-12-04 12:11                 ` [Qemu-devel] " Lan, Tianyu
2015-12-03 18:32         ` Alexander Duyck
2015-12-03 18:32           ` [Qemu-devel] " Alexander Duyck
2015-12-07 16:50 ` live migration vs device assignment (was Re: [RFC PATCH V2 00/10] Qemu: Add live migration support for SRIOV NIC) Michael S. Tsirkin
2015-12-07 16:50   ` [Qemu-devel] " Michael S. Tsirkin
2015-12-09 16:26   ` live migration vs device assignment (motivation) Lan, Tianyu
2015-12-09 16:26     ` [Qemu-devel] " Lan, Tianyu
2015-12-09 17:14     ` Alexander Duyck
2015-12-09 17:14       ` [Qemu-devel] " Alexander Duyck
2015-12-10  3:15       ` Lan, Tianyu [this message]
2015-12-10  3:15         ` Lan, Tianyu
2015-12-09 20:07     ` Michael S. Tsirkin
2015-12-09 20:07       ` [Qemu-devel] " Michael S. Tsirkin
2015-12-10  3:04       ` Lan, Tianyu
2015-12-10  3:04         ` [Qemu-devel] " Lan, Tianyu
2015-12-10  8:38         ` Michael S. Tsirkin
2015-12-10  8:38           ` [Qemu-devel] " Michael S. Tsirkin
2015-12-10 14:23           ` Lan, Tianyu
2015-12-10 14:23             ` [Qemu-devel] " Lan, Tianyu
2015-12-10 10:18     ` Dr. David Alan Gilbert
2015-12-10 10:18       ` Dr. David Alan Gilbert
2015-12-10 11:28       ` Yang Zhang
2015-12-10 11:28         ` Yang Zhang
2015-12-10 11:41         ` Dr. David Alan Gilbert
2015-12-10 11:41           ` Dr. David Alan Gilbert
2015-12-10 13:07           ` Yang Zhang
2015-12-10 13:07             ` Yang Zhang
2015-12-10 14:38           ` Lan, Tianyu
2015-12-10 14:38             ` [Qemu-devel] " Lan, Tianyu
2015-12-10 16:11             ` Michael S. Tsirkin
2015-12-10 16:11               ` Michael S. Tsirkin
2015-12-10 19:17               ` Alexander Duyck
2015-12-10 19:17                 ` Alexander Duyck
2015-12-11  7:32               ` Lan, Tianyu
2015-12-11  7:32                 ` Lan, Tianyu
2015-12-14  9:12                 ` Michael S. Tsirkin
2015-12-14  9:12                   ` Michael S. Tsirkin
2015-12-10 16:23             ` Dr. David Alan Gilbert
2015-12-10 16:23               ` Dr. David Alan Gilbert
2015-12-10 17:16             ` Alexander Duyck
2015-12-10 17:16               ` Alexander Duyck
2015-12-13 15:47               ` Lan, Tianyu
2015-12-13 15:47                 ` Lan, Tianyu
2015-12-13 19:30                 ` Alexander Duyck
2015-12-13 19:30                   ` Alexander Duyck
2015-12-25  7:03                   ` Lan Tianyu
2015-12-25  7:03                     ` [Qemu-devel] " Lan Tianyu
2015-12-25 12:11                     ` Michael S. Tsirkin
2015-12-25 12:11                       ` Michael S. Tsirkin
2015-12-28 17:42                       ` Lan, Tianyu
2015-12-28 17:42                         ` Lan, Tianyu
2015-12-29 16:46                         ` Michael S. Tsirkin
2015-12-29 16:46                           ` Michael S. Tsirkin
2015-12-29 17:04                           ` Alexander Duyck
2015-12-29 17:04                             ` Alexander Duyck
2015-12-29 17:15                             ` Michael S. Tsirkin
2015-12-29 17:15                               ` [Qemu-devel] " Michael S. Tsirkin
2015-12-29 18:04                               ` Alexander Duyck
2015-12-29 18:04                                 ` Alexander Duyck
2016-01-04  2:15                           ` Lan Tianyu
2016-01-04  2:15                             ` Lan Tianyu
2015-12-25 22:31                     ` Alexander Duyck
2015-12-25 22:31                       ` Alexander Duyck
2015-12-27  9:21                       ` Michael S. Tsirkin
2015-12-27  9:21                         ` [Qemu-devel] " Michael S. Tsirkin
2015-12-27 21:45                         ` Alexander Duyck
2015-12-27 21:45                           ` Alexander Duyck
2015-12-28  8:51                           ` Michael S. Tsirkin
2015-12-28  8:51                             ` Michael S. Tsirkin
2015-12-28  3:20                       ` Dong, Eddie
2015-12-28  3:20                         ` Dong, Eddie
2015-12-28  4:26                         ` Alexander Duyck
2015-12-28  4:26                           ` [Qemu-devel] " Alexander Duyck
2015-12-28 11:50                         ` Michael S. Tsirkin
2015-12-28 11:50                           ` Michael S. Tsirkin
2015-12-14  9:26                 ` Michael S. Tsirkin
2015-12-14  9:26                   ` Michael S. Tsirkin
2015-12-28  8:52                   ` Pavel Fedin
2015-12-28  8:52                     ` Pavel Fedin
2015-12-28 11:51                     ` Michael S. Tsirkin
2015-12-28 11:51                       ` Michael S. Tsirkin
2016-03-17  9:15 ` [Qemu-devel] [RFC PATCH V2 00/10] Qemu: Add live migration support for SRIOV NIC Wei Yang
2016-03-17  9:15   ` Wei Yang

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=5668EE6F.90200@intel.com \
    --to=tianyu.lan@intel.com \
    --cc=agraf@suse.de \
    --cc=aik@ozlabs.ru \
    --cc=alex.williamson@redhat.com \
    --cc=alexander.duyck@gmail.com \
    --cc=amit.shah@redhat.com \
    --cc=anthony@codemonkey.ws \
    --cc=ard.biesheuvel@linaro.org \
    --cc=blauwirbel@gmail.com \
    --cc=cornelia.huck@de.ibm.com \
    --cc=donald.c.skidmore@intel.com \
    --cc=eddie.dong@intel.com \
    --cc=emil.s.tantilov@intel.com \
    --cc=gerlitz.or@gmail.com \
    --cc=kraxel@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=lcapitulino@redhat.com \
    --cc=mark.d.rustad@intel.com \
    --cc=mst@redhat.com \
    --cc=nrupal.jani@intel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.