Messages in this thread | | | Date | Mon, 11 Aug 2008 09:02:15 -0700 | From | Jeremy Fitzhardinge <> | Subject | Re: Use of barriers in pvclock ABI |
| |
Glauber Costa wrote: > Okay for guest vcpu, but what about physical cpus? > > IIRC, the checks are there, and so strict, to account for the > possiblity of the vcpu to be migrated to another cpu in the middle of > the > clock reading. >
That's fine. As part of rescheduling a vcpu on a new pcpu, the clock record will be updated with the new cpu's parameters, but that update will be complete by the time the vcpu gets rescheduled. The version check and loop still needs to be there, but it will never see an inconsistent (partially updated) clock record.
J
| |