On Mon, Jul 27, 2015 at 03:48:19PM -0400, Bandan Das wrote: > Eyal Moscovici <EYALMO@xxxxxxxxxx> writes: > > > Hi, > > > > The test showed the same relative numbers as we got in our internal > > testing. I was wondering about the configuration in regards to NUMA. From > Thanks for confirming. > > > our testing we saw that if the VMs are spread across 2 NUMA nodes then > > having a shared vhost thread per node performs better then having the two > > threads in the same core. > > IIUC, this is similar to my test setup and observations i.e > > 14* 1173.8 1216.9 > > In this case, there's a shared vhost thread on CPU 14 for numa node 0 > and another on CPU 15 for numa node 1. Guests running on CPUs 0,2,4,6,8,10,12 > are serviced by vhost-0 that runs on CPU 14 and guests running on CPUs 1,3,5,7,9,11,13 > get serviced by vhost-1 (Numa node 1). I tried some other configurations but > this configuration gave me the best results. > > > Eyal, I think it makes sense to add polling on top of these patches and > get numbers for them too. Thoughts ? > > Bandan So simple polling by vhost is kind of ok for some guests, but I think to really make it work for a reasonably wide selection of guests/workloads you need to combine it with 1. polling the NIC - it makes no sense to me to only poll one side of the equation; and probably 2. - polling in guest. -- 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
