Re: [PATCH v5] KVM: halt-polling: poll for the upcoming fire timers

On Fri, 27 May 2016 11:49:26 +0200 Paolo Bonzini wrote: > > > On 26/05/2016 22:33, yunhong jiang wrote: > > On Thu, 26 May 2016 12:26:27 +0200 > > Paolo Bonzini wrote: > > > >> > >> > >> On 25/05/2016 04:47, Wanpeng Li wrote: > >>> From: Wanpeng Li

Re: [PATCH v5] KVM: halt-polling: poll for the upcoming fire timers

On Fri, 27 May 2016 11:49:26 +0200 Paolo Bonzini wrote: > > > On 26/05/2016 22:33, yunhong jiang wrote: > > On Thu, 26 May 2016 12:26:27 +0200 > > Paolo Bonzini wrote: > > > >> > >> > >> On 25/05/2016 04:47, Wanpeng Li wrote: > >>> From: Wanpeng Li > >>> > >>> If an emulated lapic timer

Re: [PATCH v5] KVM: halt-polling: poll for the upcoming fire timers

On 26/05/2016 22:33, yunhong jiang wrote: > On Thu, 26 May 2016 12:26:27 +0200 > Paolo Bonzini wrote: > >> >> >> On 25/05/2016 04:47, Wanpeng Li wrote: >>> From: Wanpeng Li >>> >>> If an emulated lapic timer will fire soon(in the scope of 10us the

Re: [PATCH v5] KVM: halt-polling: poll for the upcoming fire timers

On 26/05/2016 22:33, yunhong jiang wrote: > On Thu, 26 May 2016 12:26:27 +0200 > Paolo Bonzini wrote: > >> >> >> On 25/05/2016 04:47, Wanpeng Li wrote: >>> From: Wanpeng Li >>> >>> If an emulated lapic timer will fire soon(in the scope of 10us the >>> base of dynamic halt-polling, lower-end

Re: [PATCH v5] KVM: halt-polling: poll for the upcoming fire timers

On Thu, 26 May 2016 12:26:27 +0200 Paolo Bonzini wrote: > > > On 25/05/2016 04:47, Wanpeng Li wrote: > > From: Wanpeng Li > > > > If an emulated lapic timer will fire soon(in the scope of 10us the > > base of dynamic halt-polling, lower-end of

Re: [PATCH v5] KVM: halt-polling: poll for the upcoming fire timers

On Thu, 26 May 2016 12:26:27 +0200 Paolo Bonzini wrote: > > > On 25/05/2016 04:47, Wanpeng Li wrote: > > From: Wanpeng Li > > > > If an emulated lapic timer will fire soon(in the scope of 10us the > > base of dynamic halt-polling, lower-end of message passing workload > > latency TCP_RR's

Re: [PATCH v5] KVM: halt-polling: poll for the upcoming fire timers

2016-05-26 18:30 GMT+08:00 Paolo Bonzini : > > > On 26/05/2016 12:26, Paolo Bonzini wrote: >> As discussed on IRC, I would like to understand why the adaptive >> adjustment of halt_poll_ns is failing. It seems like you have so few >> halts that you don't get halt_poll_ns>0.

Re: [PATCH v5] KVM: halt-polling: poll for the upcoming fire timers

2016-05-26 18:30 GMT+08:00 Paolo Bonzini : > > > On 26/05/2016 12:26, Paolo Bonzini wrote: >> As discussed on IRC, I would like to understand why the adaptive >> adjustment of halt_poll_ns is failing. It seems like you have so few >> halts that you don't get halt_poll_ns>0. Yet, when the VM

Re: [PATCH v5] KVM: halt-polling: poll for the upcoming fire timers

On 26/05/2016 12:26, Paolo Bonzini wrote: > As discussed on IRC, I would like to understand why the adaptive > adjustment of halt_poll_ns is failing. It seems like you have so few > halts that you don't get halt_poll_ns>0. Yet, when the VM halts, it's > very close to the timer tick---often

Re: [PATCH v5] KVM: halt-polling: poll for the upcoming fire timers

On 26/05/2016 12:26, Paolo Bonzini wrote: > As discussed on IRC, I would like to understand why the adaptive > adjustment of halt_poll_ns is failing. It seems like you have so few > halts that you don't get halt_poll_ns>0. Yet, when the VM halts, it's > very close to the timer tick---often

Re: [PATCH v5] KVM: halt-polling: poll for the upcoming fire timers

On 25/05/2016 04:47, Wanpeng Li wrote: > From: Wanpeng Li > > If an emulated lapic timer will fire soon(in the scope of 10us the > base of dynamic halt-polling, lower-end of message passing workload > latency TCP_RR's poll time < 10us) we can treat it as a short halt, >

Re: [PATCH v5] KVM: halt-polling: poll for the upcoming fire timers

On 25/05/2016 04:47, Wanpeng Li wrote: > From: Wanpeng Li > > If an emulated lapic timer will fire soon(in the scope of 10us the > base of dynamic halt-polling, lower-end of message passing workload > latency TCP_RR's poll time < 10us) we can treat it as a short halt, > and poll to wait it

[PATCH v5] KVM: halt-polling: poll for the upcoming fire timers

From: Wanpeng Li If an emulated lapic timer will fire soon(in the scope of 10us the base of dynamic halt-polling, lower-end of message passing workload latency TCP_RR's poll time < 10us) we can treat it as a short halt, and poll to wait it fire, the fire callback

[PATCH v5] KVM: halt-polling: poll for the upcoming fire timers

From: Wanpeng Li If an emulated lapic timer will fire soon(in the scope of 10us the base of dynamic halt-polling, lower-end of message passing workload latency TCP_RR's poll time < 10us) we can treat it as a short halt, and poll to wait it fire, the fire callback apic_timer_fn() will set