On 10/21/2018 09:06 AM, Paolo Bonzini wrote: > > I should be really close now to sending the dirty page ring buffer > series, which I think is incompatible with PTE-based dirty logging and > basically removes the cost of ioctls almost entirely, making them > O(#dirtied_pages). Do you think it's worthwhile to have PTE-based dirty > logging on !PML hosts, even at the cost of disabling the ring buffer? > The reduced performance for write protection is relatively small, less > than 10%, and without the ring buffer we sometimes have to resort to > vCPU stunning because the VM is _still_ running too fast for migration > to converge. > Yes, this would be incompatible with a ring buffer based dirty logging API. But I think that it might still be potentially worthwhile to have this available. At least during my testing, the cost of the IOCTLs themselves had generally been less of a problem for the brownout phase, but more for blackout. And at least for some workloads, the performance reduction of write-protection can be higher e.g. I had seen 50%+ performance reduction in some (admittedly extreme) benchmarks. Perhaps we could extend the dynamic mode switching mechanism in the last couple of patches to also switch between the two flavors of the dirty logging API? Then we might be able to get the best of both worlds: Dirty-bit based logging using the existing API during most of brownout and Write Protection based logging using the ring buffer API during the last stages of brownout and for blackout. Thanks, Junaid
