在2009-04-22，"Daniel P. Berrange" <berrange@xxxxxxxxxx> 写道：
>Although the standard scheduler tunables are per thread, it is possible
>to put each QEMU process into a separate CGroup, and use the cpu_shares
>tunable to control scheduling priority of the guest as a whole, instead
>of individual threads. Not sure it this is sufficient for what you
>want, but it is one possible option for guest scheduling..
>
>Daniel
>--
Sorry if this email is duplicated. My email server keeps on sending
html-formated emails.
do you mean control all the guests as a whole, with no difference?
I guess a computing cloud provider are not satisfied either.
I guest they want the following function:
VM1 should has 30% cpu time
VM2 should has 50% cpu time
VM3 should has 20% cpu time
the extended scheduler I mentioned can provide this capacity.
And the meaning is more than this: in the future, you can
co-scheduling a set of virtual machines to make them cooperate with
each other more efficiently, only with the help of a few use level
tools.
Regards,
alex.
-------------------------
The Following is added by the ISP.
Please ignore them!
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
