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

Re: [vfio-users] cpu usage in guest != cpu usage in host, even with exclusive pinning



Okay wow, Alex.  That made a huge difference immediately.  That dropped me from 90% to 33% on the main thread, and all the children are below 10%.

On Sun, Apr 3, 2016 at 8:07 PM, Alex Williamson <alex l williamson gmail com> wrote:
If this is the issue I think it is, the unraid folks bisected this and found the culprit as:

aca6ff2 KVM: dynamic halt-polling

(https://github.com/torvalds/linux/commit/aca6ff29c4063a8d467cdee241e6b3bf7dc4a171)

It seems to be a poor interaction of the halt polling interval vs the timer ticks on win10.  You can pick a different polling interval with the kvm module option halt_poll_ns.  The default is 500000.  It seemed that setting this to 400000 or lower resolves the issue.  You can do this via a modprobe entry, 'options kvm halt_poll_ns=400000' or on the kernel command line with kvm.halt_poll_ns=400000.  You can also change it dynamically via 'echo 400000 > /sys/module/kvm/parameters/halt_poll_ns'

_______________________________________________
vfio-users mailing list
vfio-users redhat com
https://www.redhat.com/mailman/listinfo/vfio-users



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