* last_kernel_ns ?
@ 2010-10-04 16:50 Glauber Costa
2010-10-04 21:49 ` Zachary Amsden
0 siblings, 1 reply; 2+ messages in thread
From: Glauber Costa @ 2010-10-04 16:50 UTC (permalink / raw)
To: kvm; +Cc: zamsden, mtosatti, avi
Zach,
vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
vcpu->last_kernel_ns = kernel_ns; <===== (1)
vcpu->last_guest_tsc = tsc_timestamp;
vcpu->hv_clock.flags = 0;
If I understand your intention corretly, you should add kvmclock_offset to (1).
Am I misinterpreting something?
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: last_kernel_ns ?
2010-10-04 16:50 last_kernel_ns ? Glauber Costa
@ 2010-10-04 21:49 ` Zachary Amsden
0 siblings, 0 replies; 2+ messages in thread
From: Zachary Amsden @ 2010-10-04 21:49 UTC (permalink / raw)
To: Glauber Costa; +Cc: kvm, mtosatti, avi
On 10/04/2010 06:50 AM, Glauber Costa wrote:
> Zach,
>
> vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
> vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
> vcpu->last_kernel_ns = kernel_ns;<===== (1)
> vcpu->last_guest_tsc = tsc_timestamp;
> vcpu->hv_clock.flags = 0;
>
> If I understand your intention corretly, you should add kvmclock_offset to (1).
> Am I misinterpreting something?
>
No, last_kernel_ns is the last observed value of kernel_ns, not system
time. The kvmclock_offset may be modified since observation (unlikely,
yet possible), and should not be considered in this computation.
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2010-10-04 21:49 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2010-10-04 16:50 last_kernel_ns ? Glauber Costa
2010-10-04 21:49 ` Zachary Amsden
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.