Non-scalable locks are dangerous

Several operating systems rely on non-scalable spin locks for serialization. For example, the Linux kernel uses ticket spin locks, even though scalable locks have better theoretical properties. Using Linux on a 48-core machine, this paper shows that non-scalable locks can cause dramatic collapse in the performance of real workloads, even for very short critical sections. The nature and sudden onset of collapse are explained with a new Markovbased performance model. Replacing the offending nonscalable spin locks with scalable spin locks avoids the collapse and requires modest changes to source code.