Re: [PATCH 0/7 -v2] KVM: Alleviate mmu_lock hold time when we start dirty logging

2013-01-14 Thread Gleb Natapov
On Tue, Jan 08, 2013 at 07:42:38PM +0900, Takuya Yoshikawa wrote: > Changelog v1->v2: > The condition in patch 1 was changed like this: > npages && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) > > This patch set makes kvm_mmu_slot_remove_write_access() rmap based and > adds conditional

Re: [PATCH 0/7 -v2] KVM: Alleviate mmu_lock hold time when we start dirty logging

2013-01-14 Thread Gleb Natapov
On Tue, Jan 08, 2013 at 07:42:38PM +0900, Takuya Yoshikawa wrote: Changelog v1-v2: The condition in patch 1 was changed like this: npages (mem-flags KVM_MEM_LOG_DIRTY_PAGES) This patch set makes kvm_mmu_slot_remove_write_access() rmap based and adds conditional rescheduling to it.

Re: [PATCH 0/7 -v2] KVM: Alleviate mmu_lock hold time when we start dirty logging

2013-01-10 Thread Marcelo Tosatti
On Tue, Jan 08, 2013 at 07:42:38PM +0900, Takuya Yoshikawa wrote: > Changelog v1->v2: > The condition in patch 1 was changed like this: > npages && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) > > This patch set makes kvm_mmu_slot_remove_write_access() rmap based and > adds conditional

Re: [PATCH 0/7 -v2] KVM: Alleviate mmu_lock hold time when we start dirty logging

2013-01-10 Thread Marcelo Tosatti
On Tue, Jan 08, 2013 at 07:42:38PM +0900, Takuya Yoshikawa wrote: Changelog v1-v2: The condition in patch 1 was changed like this: npages (mem-flags KVM_MEM_LOG_DIRTY_PAGES) This patch set makes kvm_mmu_slot_remove_write_access() rmap based and adds conditional rescheduling to it.

[PATCH 0/7 -v2] KVM: Alleviate mmu_lock hold time when we start dirty logging

2013-01-08 Thread Takuya Yoshikawa
Changelog v1->v2: The condition in patch 1 was changed like this: npages && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) This patch set makes kvm_mmu_slot_remove_write_access() rmap based and adds conditional rescheduling to it. The motivation for this change is of course to reduce the mmu_lock

[PATCH 0/7 -v2] KVM: Alleviate mmu_lock hold time when we start dirty logging

2013-01-08 Thread Takuya Yoshikawa
Changelog v1-v2: The condition in patch 1 was changed like this: npages (mem-flags KVM_MEM_LOG_DIRTY_PAGES) This patch set makes kvm_mmu_slot_remove_write_access() rmap based and adds conditional rescheduling to it. The motivation for this change is of course to reduce the mmu_lock hold