2016-09-10 0:38 GMT+08:00 Paolo Bonzini :
>
>
> On 09/09/2016 00:13, David Matlack wrote:
>> Hi Paolo,
>>
>> On Tue, Sep 6, 2016 at 3:29 PM, Paolo Bonzini wrote:
>>> Bad things happen if a guest using the TSC deadline timer is migrated.
>>> The guest
2016-09-10 0:38 GMT+08:00 Paolo Bonzini :
>
>
> On 09/09/2016 00:13, David Matlack wrote:
>> Hi Paolo,
>>
>> On Tue, Sep 6, 2016 at 3:29 PM, Paolo Bonzini wrote:
>>> Bad things happen if a guest using the TSC deadline timer is migrated.
>>> The guest doesn't re-calibrate the TSC after migration,
2016-09-16 17:06+0200, Paolo Bonzini:
> On 16/09/2016 16:59, Radim Krčmář wrote:
>> KVM_MSR_DEADLINE would be interface in kvmclock nanosecond values and
>> MSR_IA32_TSCDEADLINE in TSC values. KVM_MSR_DEADLINE would follow
>> similar rules as MSR_IA32_TSCDEADLINE -- the interrupt fires when
>>
2016-09-16 17:06+0200, Paolo Bonzini:
> On 16/09/2016 16:59, Radim Krčmář wrote:
>> KVM_MSR_DEADLINE would be interface in kvmclock nanosecond values and
>> MSR_IA32_TSCDEADLINE in TSC values. KVM_MSR_DEADLINE would follow
>> similar rules as MSR_IA32_TSCDEADLINE -- the interrupt fires when
>>
On 16/09/2016 16:59, Radim Krčmář wrote:
> KVM_MSR_DEADLINE would be interface in kvmclock nanosecond values and
> MSR_IA32_TSCDEADLINE in TSC values. KVM_MSR_DEADLINE would follow
> similar rules as MSR_IA32_TSCDEADLINE -- the interrupt fires when
> kvmclock reaches the value, you read what
On 16/09/2016 16:59, Radim Krčmář wrote:
> KVM_MSR_DEADLINE would be interface in kvmclock nanosecond values and
> MSR_IA32_TSCDEADLINE in TSC values. KVM_MSR_DEADLINE would follow
> similar rules as MSR_IA32_TSCDEADLINE -- the interrupt fires when
> kvmclock reaches the value, you read what
2016-09-15 23:02+0200, Paolo Bonzini:
> On 15/09/2016 21:59, Radim Krčmář wrote:
>> 2016-09-15 18:00+0200, Paolo Bonzini:
When we are already going the paravirtual route, we could add an
interface that accepts the deadline in kvmclock nanoseconds.
It would be much more maintanable
2016-09-15 23:02+0200, Paolo Bonzini:
> On 15/09/2016 21:59, Radim Krčmář wrote:
>> 2016-09-15 18:00+0200, Paolo Bonzini:
When we are already going the paravirtual route, we could add an
interface that accepts the deadline in kvmclock nanoseconds.
It would be much more maintanable
On 15/09/2016 21:59, Radim Krčmář wrote:
> 2016-09-15 18:00+0200, Paolo Bonzini:
>> So virtual_tsc_khz does change on migration, at least if your host
>> doesn't have TSC scaling (which is pretty much all Intel hosts in
>> existence).
>
> Ugh, I'd consider exposing constant TSC to the guest
On 15/09/2016 21:59, Radim Krčmář wrote:
> 2016-09-15 18:00+0200, Paolo Bonzini:
>> So virtual_tsc_khz does change on migration, at least if your host
>> doesn't have TSC scaling (which is pretty much all Intel hosts in
>> existence).
>
> Ugh, I'd consider exposing constant TSC to the guest
2016-09-15 18:00+0200, Paolo Bonzini:
> On 15/09/2016 17:09, Radim Krčmář wrote:
>> 2016-09-07 00:29+0200, Paolo Bonzini:
>>> Bad things happen if a guest using the TSC deadline timer is migrated.
>>> The guest doesn't re-calibrate the TSC after migration, and the
>>> TSC frequency can and will
2016-09-15 18:00+0200, Paolo Bonzini:
> On 15/09/2016 17:09, Radim Krčmář wrote:
>> 2016-09-07 00:29+0200, Paolo Bonzini:
>>> Bad things happen if a guest using the TSC deadline timer is migrated.
>>> The guest doesn't re-calibrate the TSC after migration, and the
>>> TSC frequency can and will
On 15/09/2016 17:09, Radim Krčmář wrote:
> 2016-09-07 00:29+0200, Paolo Bonzini:
>> Bad things happen if a guest using the TSC deadline timer is migrated.
>> The guest doesn't re-calibrate the TSC after migration, and the
>> TSC frequency can and will change unless your processor supports TSC
>>
On 15/09/2016 17:09, Radim Krčmář wrote:
> 2016-09-07 00:29+0200, Paolo Bonzini:
>> Bad things happen if a guest using the TSC deadline timer is migrated.
>> The guest doesn't re-calibrate the TSC after migration, and the
>> TSC frequency can and will change unless your processor supports TSC
>>
2016-09-07 00:29+0200, Paolo Bonzini:
> Bad things happen if a guest using the TSC deadline timer is migrated.
> The guest doesn't re-calibrate the TSC after migration, and the
> TSC frequency can and will change unless your processor supports TSC
> scaling (on Intel this is only Skylake) or your
2016-09-07 00:29+0200, Paolo Bonzini:
> Bad things happen if a guest using the TSC deadline timer is migrated.
> The guest doesn't re-calibrate the TSC after migration, and the
> TSC frequency can and will change unless your processor supports TSC
> scaling (on Intel this is only Skylake) or your
On Fri, Sep 9, 2016 at 9:38 AM, Paolo Bonzini wrote:
>
> On 09/09/2016 00:13, David Matlack wrote:
>> Hi Paolo,
>>
>> On Tue, Sep 6, 2016 at 3:29 PM, Paolo Bonzini wrote:
>>> Bad things happen if a guest using the TSC deadline timer is migrated.
>>> The
On Fri, Sep 9, 2016 at 9:38 AM, Paolo Bonzini wrote:
>
> On 09/09/2016 00:13, David Matlack wrote:
>> Hi Paolo,
>>
>> On Tue, Sep 6, 2016 at 3:29 PM, Paolo Bonzini wrote:
>>> Bad things happen if a guest using the TSC deadline timer is migrated.
>>> The guest doesn't re-calibrate the TSC after
On 09/09/2016 00:13, David Matlack wrote:
> Hi Paolo,
>
> On Tue, Sep 6, 2016 at 3:29 PM, Paolo Bonzini wrote:
>> Bad things happen if a guest using the TSC deadline timer is migrated.
>> The guest doesn't re-calibrate the TSC after migration, and the
>> TSC frequency can
On 09/09/2016 00:13, David Matlack wrote:
> Hi Paolo,
>
> On Tue, Sep 6, 2016 at 3:29 PM, Paolo Bonzini wrote:
>> Bad things happen if a guest using the TSC deadline timer is migrated.
>> The guest doesn't re-calibrate the TSC after migration, and the
>> TSC frequency can and will change
Hi Paolo,
On Tue, Sep 6, 2016 at 3:29 PM, Paolo Bonzini wrote:
> Bad things happen if a guest using the TSC deadline timer is migrated.
> The guest doesn't re-calibrate the TSC after migration, and the
> TSC frequency can and will change unless your processor supports TSC
>
Hi Paolo,
On Tue, Sep 6, 2016 at 3:29 PM, Paolo Bonzini wrote:
> Bad things happen if a guest using the TSC deadline timer is migrated.
> The guest doesn't re-calibrate the TSC after migration, and the
> TSC frequency can and will change unless your processor supports TSC
> scaling (on Intel
Bad things happen if a guest using the TSC deadline timer is migrated.
The guest doesn't re-calibrate the TSC after migration, and the
TSC frequency can and will change unless your processor supports TSC
scaling (on Intel this is only Skylake) or your data center is perfectly
homogeneous.
The
Bad things happen if a guest using the TSC deadline timer is migrated.
The guest doesn't re-calibrate the TSC after migration, and the
TSC frequency can and will change unless your processor supports TSC
scaling (on Intel this is only Skylake) or your data center is perfectly
homogeneous.
The
24 matches
Mail list logo