From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Subject: Re: [PATCH] use unfair spinlock when running on hypervisor. Date: Tue, 1 Jun 2010 18:38:07 +0200 Message-ID: <20100601163807.GA11880@basil.fritz.box> References: <20100601093515.GH24302@redhat.com> <87sk56ycka.fsf@basil.nowhere.org> <20100601162414.GA6191@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Andi Kleen , linux-kernel@vger.kernel.org, kvm@vger.kernel.org, avi@redhat.com, hpa@zytor.com, mingo@elte.hu, npiggin@suse.de, tglx@linutronix.de, mtosatti@redhat.com To: Gleb Natapov Return-path: Content-Disposition: inline In-Reply-To: <20100601162414.GA6191@redhat.com> Sender: linux-kernel-owner@vger.kernel.org List-Id: kvm.vger.kernel.org On Tue, Jun 01, 2010 at 07:24:14PM +0300, Gleb Natapov wrote: > On Tue, Jun 01, 2010 at 05:53:09PM +0200, Andi Kleen wrote: > > Gleb Natapov writes: > > > > > > The patch below allows to patch ticket spinlock code to behave similar to > > > old unfair spinlock when hypervisor is detected. After patching unlocked > > > > The question is what happens when you have a system with unfair > > memory and you run the hypervisor on that. There it could be much worse. > > > How much worse performance hit could be? It depends on the workload. Overall it means that a contended lock can have much higher latencies. If you want to study some examples see the locking problems the RT people have with their heavy weight mutex-spinlocks. But the main problem is that in the worst case you can see extremly long stalls (upto a second has been observed), which then turns in a correctness issue. > > > Your new code would starve again, right? > > > Yes, of course it may starve with unfair spinlock. Since vcpus are not > always running there is much smaller chance then vcpu on remote memory > node will starve forever. Old kernels with unfair spinlocks are running > fine in VMs on NUMA machines with various loads. Try it on a NUMA system with unfair memory. > > There's a reason the ticket spinlocks were added in the first place. > > > I understand that reason and do not propose to get back to old spinlock > on physical HW! But with virtualization performance hit is unbearable. Extreme unfairness can be unbearable too. -Andi -- ak@linux.intel.com -- Speaking for myself only.