On 2020/2/21 下午11:28, Peter Zijlstra wrote: > On Mon, Feb 17, 2020 at 09:23:52PM +0800, 王贇 wrote: >> FYI, by monitoring locality, we found that the kvm vcpu thread is not >> covered by NUMA Balancing, whatever how many maximum period passed, the >> counters are not increasing, or very slowly, although inside guest we are >> copying memory. >> >> Later we found such task rarely exit to user space to trigger task >> work callbacks, and NUMA Balancing scan depends on that, which help us >> realize the importance to enable NUMA Balancing inside guest, with the >> correct NUMA topo, a big performance risk I'll say :-P > > That's a bug in KVM, see: > > https://lkml.kernel.org/r/20190801143657.785902257@xxxxxxxxxxxxx > https://lkml.kernel.org/r/20190801143657.887648487@xxxxxxxxxxxxx > > ISTR there being newer versions of that patch-set, but I can't seem to > find them in a hurry. Aha, that's exactly the problem we saw, will check~ Regards, Michael Wang >
