Re: [PATCH 0/3] KVM: Improving vCPU halt_poll_ns grow behavior

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Sun, 27 Jan 2019 at 18:19, Nir Weiner <nir.weiner@xxxxxxxxxx> wrote:
>
> grow_halt_poll_ns() sets the halt_poll_ns value for a vCPU when growing - It has
> significant effect on how vCPU performs. On the standard case, higher value is
> better - we will spend more time in the polling busyloop, handle
> events & interrupts faster and result in better performance for the VM.
> But on outliers it puts us in a busy loop that does nothing.
>
> grow_halt_poll_ns() optimal algorithm changes between different workloads.
> The changes in this patch series fixes 2 weird behaviors and exposes hard-coded
> value which stands for the initial grow value in order to get a better
> fine-tunning control. See the individual patches for more details.

Please also post the performance number for your improvement.

Regards,
Wanpeng Li



[Index of Archives]     [KVM ARM]     [KVM ia64]     [KVM ppc]     [Virtualization Tools]     [Spice Development]     [Libvirt]     [Libvirt Users]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite Questions]     [Linux Kernel]     [Linux SCSI]     [XFree86]

  Powered by Linux