hey
Wanted some clarification on the way xen schedules vcpus on physical cpus.
- Lets assume there are 8 physical cpus.
If I set vcpu = 2, for a VM, can it use more that 2 physical cpu time ? i.e. does VM sees 2 more powerful processors ? Assuming that no-one else need it.
From the explanation of credit scheduler on the wiki, it seems that the guest kernel would not schedule more that 2 units for work at a time (as it sees 2 cpus). So it looks like the max it can consume is 200%... or max 2 physical cpu time.
Or the PV driver in the guest does better ?
Is there any difference between the PV guest and HVM guest in this regard ?
A related question is : Given the cpu utilization reported by xm top, can I infer cpu utilization within guest
(reported by top, or task manager ?).
Any significant changes in cpu scheduling approach between xen versions.. xen 3.1, 3.2, 3.3, 3.4 ?
Thanks.
/Jd
|
