Re: [Qemu-devel] about NPIV with qemu-kvm.

[ya su]

hi, hannes

      I really appreciate your clarify of my daze.

      as to improve vm's storage io perfomance as nearly hardware's,
it seems the only way is something like sr-iov by hba card.  NPIV can
not achieve this goal.

      I remember that LSI released some kind SAS controller(IR 2008?)
which support sr-iov , but there is not any document which describes
the steps to config. I wonder if your have any clues to help? thanks.

Regards.

Suya.

2011/10/26, Hannes Reinecke <address@hidden>:
> On 10/26/2011 06:40 AM, ya su wrote:
>> hi, hannes:
>>
>>     I want to use NPIV with qemu-kvm, I issued the following command:
>>
>>     echo '1111222233334444:5555666677778888' >
>> /sys/class/fc_host/host0/vport_create
>>
>>     and it will produce a new host6 and one vport succesfully, but it
>> does not create any virtual hba pci device. so I don't know how to
>> assign the virtual host to qemu-kvm.
>>
> Well, you can't. There is no mechanism for. When using NPIV you need
> to pass in the individual LUNs via eg virtio-blk.
>
>>     from your this mail, does array will first need to assign a lun to
>> this vport? and through this new created disk, like device /dev/sdf,
>> then I add qemu-kvm with -drive file=/dev/sdf,if=virtio... arguments?
>>
> Yes. That's what you need to do.
>
> Cheers,
>
> Hannes
> --
> Dr. Hannes Reinecke              zSeries & Storage
> address@hidden                  +49 911 74053 688
> SUSE LINUX Products GmbH, Maxfeldstr. 5, 90409 Nürnberg
> GF: Markus Rex, HRB 16746 (AG Nürnberg)
>