2016-05-24 10:19 GMT+08:00 Wanpeng Li <kernellwp@xxxxxxxxx>:
> 2016-05-24 2:01 GMT+08:00 David Matlack <dmatlack@xxxxxxxxxx>:
>> On Sun, May 22, 2016 at 5:42 PM, Wanpeng Li <kernellwp@xxxxxxxxx> wrote:
>>> From: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>
>>
>> I'm ok with this patch, but I'd like to better understand the target
>> workloads. What type of workloads do you expect to benefit from this?
>
> dynticks guests I think is one of workloads which can get benefit,
> there are lots of upcoming fire timers captured by my feature. Even
> during TCP testing. And also the workload of Yang's.
>
>>
>>>
>>> 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
>>> KVM_REQ_PENDING_TIMER, and this flag will be check during busy poll.
>>> This can avoid context switch overhead and the latency which we wake
>>> up vCPU.
>>>
>>> This feature is slightly different from current advance expiration
>>> way. Advance expiration rely on the vCPU is running(do polling before
>>> vmentry). But in some cases, the timer interrupt may be blocked by
>>> other thread(i.e., IF bit is clear) and vCPU cannot be scheduled to
>>> run immediately. So even advance the timer early, vCPU may still see
>>> the latency. But polling is different, it ensures the vCPU to aware
>>> the timer expiration before schedule out.
>>>
>>> iperf TCP get ~6% bandwidth improvement.
>>
>> I think my question got lost in the previous thread :). Can you
>> explain why TCP bandwidth improves with this patch?
>
Please forget TCP stuff. I run lmbench ctx switch benchmark:
echo HRTICK > /sys/kernel/debug/sched_features in dynticks guests.
Context switching - times in microseconds - smaller is better
-------------------------------------------------------------------------
Host OS 2p/0K 2p/16K 2p/64K 8p/16K 8p/64K 16p/16K 16p/64K
ctxsw ctxsw ctxsw ctxsw ctxsw ctxsw ctxsw
--------- ------------- ------ ------ ------ ------ ------ ------- -------
kernel Linux 4.6.0+ 7.9800 11.0 10.8 14.6 9.4300 13.0
10.2 vanilla
kernel Linux 4.6.0+ 15.3 13.6 10.7 12.5 9.0000 12.8 7.38000 poll
Regards,
Wanpeng Li
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
