Preemptable ticket spinlocks: improving consolidated performance in the cloud
Proceedings of the 9th ACM SIGPLAN/SIGOPS international conference on Virtual execution environments
The Journal of Supercomputing
| Hi-index | 0.00 |
Multiprocessor (MP) virtual machines (VMs) are widely used in cloud environments. However, MP VMs suffer from lock holder preemption (LHP) issue. This causes a tremendous waste of CPU cycles, leading to deteriorated synchronization latency and a significant degradation in system performance. Previous works have addressed the problem with software co-scheduling or lock waiter yielding. However, co-scheduling suffers from CPU utility fragmentation, priority inversion and loss of the flexibility of hyper visor scheduler, which causes inefficiency in CPU usage. Lock waiter yielding, another solution, suffers from a large impact on hyper visor scheduler and issues with response latency. In this paper, we propose Lock-visor, an efficient transitory co-scheduling algorithm, to bypass the guest spin lock loop effectively. Our protocol has little to no impact on the flexibility of hyper visor scheduler, and achieves better system performance. Multiple policies are explored on top of transitory co-scheduling to maximize the efficiency of Lock-visor, i.e. instant transitory, selective instant transitory and deferred transitory co-scheduling. Comprehensive experiments are conducted using CPU-intensive, I/O-intensive and lock-intensive workloads. Our experimental results show that Lock-visor can significantly improve system performance (e.g. Lock-visor has up to 341.3% performance advantage over original Linux kernel 2.6.38 in Sys Bench 4-VM case), while at the same time improve system latency with little to no effect on scheduling fairness.