Re: [PATCH 2/2] KVM: x86: optimize delivery of TSC deadline timer interrupt

2015-02-10 Thread Marcelo Tosatti
On Sat, Feb 07, 2015 at 09:33:09PM +0100, Paolo Bonzini wrote: > > Can remove another 300 cycles from do_div when programming LAPIC > > tscdeadline timer. > > Do you mean using something like lib/reciprocal_div.c? Yes. > Good idea, > though that's not latency, it's just being slow. :) It adds

Re: [PATCH 2/2] KVM: x86: optimize delivery of TSC deadline timer interrupt

2015-02-07 Thread Paolo Bonzini
On 06/02/2015 21:51, Marcelo Tosatti wrote: > On Fri, Feb 06, 2015 at 01:16:59PM +0100, Paolo Bonzini wrote: >> The newly-added tracepoint shows the following results on >> the tscdeadline_latency test: >> >> qemu-kvm-8387 [002] 6425.558974: kvm_vcpu_wakeup: poll time >> 10407 ns

Re: [PATCH 2/2] KVM: x86: optimize delivery of TSC deadline timer interrupt

2015-02-06 Thread Marcelo Tosatti
On Fri, Feb 06, 2015 at 01:16:59PM +0100, Paolo Bonzini wrote: > The newly-added tracepoint shows the following results on > the tscdeadline_latency test: > > qemu-kvm-8387 [002] 6425.558974: kvm_vcpu_wakeup: poll time > 10407 ns > qemu-kvm-8387 [002] 6425.558984: kvm_vcp

[PATCH 2/2] KVM: x86: optimize delivery of TSC deadline timer interrupt

2015-02-06 Thread Paolo Bonzini
The newly-added tracepoint shows the following results on the tscdeadline_latency test: qemu-kvm-8387 [002] 6425.558974: kvm_vcpu_wakeup: poll time 10407 ns qemu-kvm-8387 [002] 6425.558984: kvm_vcpu_wakeup: poll time 0 ns qemu-kvm-8387 [002] 6425.561242: kv