On Thu, Aug 12, 2021 at 9:08 AM Paolo Bonzini <pbonzini@xxxxxxxxxx> wrote: > > On 12/08/21 01:37, Jing Zhang wrote: > > A per VM stat dirty_pages is added to record the number of dirtied pages > > in the life cycle of a VM. > > The growth rate of this stat is a good indicator during the process of > > live migrations. The exact number of dirty pages at the moment doesn't > > matter. That's why we define dirty_pages as a cumulative counter instead > > of an instantaneous one. > > Why not make it a per-CPU stat? mark_page_dirty_in_slot can use > kvm_get_running_vcpu() and skip the logging in the rare case it's NULL. > > Paolo > Sure, I will make it a per-CPU one in the next version. Thanks, Jing