Messages in this thread | | | Date | Thu, 17 Jun 2010 11:43:15 +0300 | From | Avi Kivity <> | Subject | Re: [RFC][PATCH 4/9] create aggregate kvm_total_used_mmu_pages value |
| |
On 06/16/2010 06:06 PM, Dave Hansen wrote: > > >>> +static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr) >>> +{ >>> + kvm->arch.n_used_mmu_pages += nr; >>> + kvm_total_used_mmu_pages += nr; >>> >>> >> Needs an atomic operation, since there's no global lock here. To avoid >> bouncing this cacheline around, make the variable percpu and make >> readers take a sum across all cpus. Side benefit is that you no longer >> need an atomic but a local_t, which is considerably cheaper. >> > That's a good point. All of the modifications are done under locks, but > the fast path isn't any more. I'll fix it up. > >
Note, even before you moved the shrinker out of the lock, this was a problem. kvm_mod_used_mmu_pages() is called not just from the shrinker code, we zap pages for other reasons as well.
-- error compiling committee.c: too many arguments to function
| |