[libvirt] [PATCH] qemu: Support multiple queue virtio-scsi
Eric Blake
eblake at redhat.com
Mon Apr 1 16:43:11 UTC 2013
On 04/01/2013 10:31 AM, Osier Yang wrote:
> No, multiple queue is not enabled by default. For "what happens if it
> doesn't match the number of vcpus", honestly, I'm not sure about it,
> my understanding is it doesn't have to match. But matching will have
> the best performance, and with this thought I think an attribute allows
> the user to specify the number makes sense instead of a boolean
> attribute. @paolo, can you confirm or deny this?
Then maybe all we need is just a recommendation that matching the number
of vcpus tends to give best performance, but not stating that it is
mandatory to match.
>
>>
>>> <code>model</code>, which is one of "piix3-uhci",
>>> "piix4-uhci", "ehci",
>>> - "ich9-ehci1", "ich9-uhci1", "ich9-uhci2", "ich9-uhci3",
>>> - "vt82c686b-uhci", "pci-ohci" or "nec-xhci". Additionally,
>>> + "ich9-ehci1", "ich9-uhci1", "ich9-uhci2", "ich9-uhci3",
>>> "vt82c686b-uhci",
>>> + "pci-ohci" or "nec-xhci". Additionally,
>> Any reason you reformatted these lines?
>
> I tended to make it more beautiful, but apprently it's not true. :-)
It doesn't affect the html output; so all it affects is the source file
legibility. But it is unrelated to the patch at hand, and since it
makes no semantic difference, I was merely questioning why you did it.
It's not wrong to leave it in, but it also doesn't add any value so
leaving it unchanged makes for a smaller diff.
--
Eric Blake eblake redhat com +1-919-301-3266
Libvirt virtualization library http://libvirt.org
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 621 bytes
Desc: OpenPGP digital signature
URL: <http://listman.redhat.com/archives/libvir-list/attachments/20130401/e7be2d5a/attachment-0001.sig>
More information about the libvir-list
mailing list