Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1403816

Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will fire soon

From Christian Borntraeger <borntraeger@de.ibm.com>
Newsgroups linux.kernel
Subject Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will fire soon
Date 2016-05-19 17:50 +0200
Message-ID <rAymZ-1DD-5@gated-at.bofh.it> (permalink)
References (1 earlier) <rAwEx-vI-23@gated-at.bofh.it> <rAxAC-16l-29@gated-at.bofh.it> <rAxAD-16l-41@gated-at.bofh.it> <rAxKi-1oW-13@gated-at.bofh.it> <rAxKi-1oW-11@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


On 05/19/2016 05:06 PM, Paolo Bonzini wrote:
> 
> 
> On 19/05/2016 17:03, Christian Borntraeger wrote:
>>>> Would this work too and be simpler?
>>>> Hmm, your patch does only fiddle with the grow/shrink logic (which might
>>>> be a good idea independently of this change), but the original patch 
>>>> actually takes into account that we have a guaranteed maximum time by a 
>>>> wakeup timer - IOW we know exactly what the maximum poll time is.
>>>
>>> Yes, it's different.  The question is whether a 10us poll (40,000 clock
>>> cycles) has an impact even if it's sometimes wrong.
>>
>> Valid question. As I said, this change might be something good independent from
>> the original patch. (it might make it unnecessary, though) On the other hand
>> I can handle ~30 guest entry/exit cycles of a simple exit like diag9c.
>> Needs measurement. 
> 
> Actually I'm okay with the original patch, and especially on s390 where
> the maximum poll time is small it may make a bigger difference.  Though
> I suppose the timer interrupt is not floating?

Right its cpu local. So a timer wakeup would be considered valid (if the timer
kicks in before the poll ends - the poll does also check if the timer expires and
maybe the hrtimer is a bit late.
> 
> Since it's not 4.7 material, I'll wait for your experiments and David's
> remarks.

I will try to get both patches scheduled but it might take a while.

Back to linux.kernel | Previous | NextPrevious in thread | Next in thread | Find similar | Unroll thread


Thread

[PATCH v2] KVM: halt-polling: poll if emulated lapic timer will fire soon Wanpeng Li <kernellwp@gmail.com> - 2016-05-19 15:30 +0200
  Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will  fire soon Christian Borntraeger <borntraeger@de.ibm.com> - 2016-05-19 15:50 +0200
  Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will  fire soon Paolo Bonzini <pbonzini@redhat.com> - 2016-05-19 16:00 +0200
    Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will  fire soon Christian Borntraeger <borntraeger@de.ibm.com> - 2016-05-19 17:00 +0200
      Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will  fire soon Paolo Bonzini <pbonzini@redhat.com> - 2016-05-19 17:00 +0200
        Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will  fire soon Paolo Bonzini <pbonzini@redhat.com> - 2016-05-19 17:10 +0200
          Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will  fire soon Christian Borntraeger <borntraeger@de.ibm.com> - 2016-05-19 17:50 +0200
        Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will  fire soon Christian Borntraeger <borntraeger@de.ibm.com> - 2016-05-19 17:10 +0200
    Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will  fire soon Wanpeng Li <kernellwp@gmail.com> - 2016-05-24 04:50 +0200
  Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will  fire soon David Matlack <dmatlack@google.com> - 2016-05-19 20:10 +0200
    Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will  fire soon David Matlack <dmatlack@google.com> - 2016-05-19 20:40 +0200
      Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will  fire soon Yang Zhang <yang.zhang.wz@gmail.com> - 2016-05-20 04:10 +0200
        Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will  fire soon Wanpeng Li <kernellwp@gmail.com> - 2016-05-20 08:00 +0200
        Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will  fire soon David Matlack <dmatlack@google.com> - 2016-05-20 20:40 +0200
          Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will  fire soon Yang Zhang <yang.zhang.wz@gmail.com> - 2016-05-23 03:30 +0200
            Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will  fire soon David Matlack <dmatlack@google.com> - 2016-05-23 20:10 +0200
              Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will  fire soon Yang Zhang <yang.zhang.wz@gmail.com> - 2016-05-24 03:20 +0200
                Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will  fire soon David Matlack <dmatlack@google.com> - 2016-05-24 03:20 +0200
                Re: [PATCH v2] KVM: halt-polling: poll if emulated lapic timer will  fire soon Yang Zhang <yang.zhang.wz@gmail.com> - 2016-05-24 05:00 +0200

csiph-web