Re: [vfio-users] Best pinning strategy for latency / performance trade-off

2017-02-08 Thread Thomas Lindroth
On 02/06/2017 11:08 PM, Abdulla Bubshait wrote: > Hey Thomas, > > Great analysis, thanks for sharing it all. But I had a question. You > mention setting realtime pri on the VM threads, and how it works with > NO_HZ_FULL. And I was wondering wouldn't you be able to to just use > isolcpus in cmd lin

Re: [vfio-users] Best pinning strategy for latency / performance trade-off

2017-02-06 Thread Abdulla Bubshait
Hey Thomas, Great analysis, thanks for sharing it all. But I had a question. You mention setting realtime pri on the VM threads, and how it works with NO_HZ_FULL. And I was wondering wouldn't you be able to to just use isolcpus in cmd line to leave the VM cores to the VM as an alternative? ___

Re: [vfio-users] Best pinning strategy for latency / performance trade-off

2017-02-02 Thread Zachary Boley
I have 2 Xeon 5540s (4 physical and 4 logical per CPU) currently one entire CPU is dedicated to the vm (basically what it says in numa 0 in lscpu) I didn't quite get the guide, what would be the best setup to get the most out of the vm for gaming? Or is that the best configuration I have atm On Fe

Re: [vfio-users] Best pinning strategy for latency / performance trade-off

2017-02-02 Thread Jan Wiele
Hi Thomas, awesome work! I've changed my (gaming-)setup (2x Xeon E5-2670 (8 real cores per CPU)) to the following: VM1 and VM2: Each gets 4 real cores on CPU0; Emulator-Thread is pinned to the respective Hyper-Threading cores. VM3: 6 real cores on CPU1; Emulator-Thread is pinned to the resp

[vfio-users] Best pinning strategy for latency / performance trade-off

2017-02-01 Thread Thomas Lindroth
A while ago there was a conversation on the #vfio-users irc channel about how to use cpuset/pinning to get the best latency and performance. I said I would run some tests and eventually did. Writing up the result took a lot of time and there are some more test I want to run to verify the results bu