Messages in this thread | | | Subject | Re: [PATCH v2 2/6] KVM-HV: KVM Steal time implementation | From | Peter Zijlstra <> | Date | Mon, 31 Jan 2011 12:07:11 +0100 |
| |
On Fri, 2011-01-28 at 14:52 -0500, Glauber Costa wrote: > + u64 to = (get_kernel_ns() - vcpu->arch.this_time_out); > + /* > + * using nanoseconds introduces noise, which accumulates easily > + * leading to big steal time values. We want, however, to keep the > + * interface nanosecond-based for future-proofness. > + */ > + to /= NSEC_PER_USEC; > + to *= NSEC_PER_USEC;
This just doesn't make any sense at all, you use the most expensive and accurate kernel interface to get ns resolution timestamps (ktime_get), and then you truncate the stuff to usec for some totally weird and unexplained reason.
If ktime_get is wrong all our time-keeping is out the window.
| |