On the Impact of Serializing Contention Management on STM Performance
Transactional memory (TM) is an emerging concurrent programming abstraction. Numerous software-based transactional memory (STM) implementations have been developed in recent years. STM implementations must guarantee transaction atomicity and isolation. In order to ensure progress, an STM implementation must resolve transaction collisions by consulting a contention manager (CM).
Recent work established that serializing contention management - a technique in which the execution of colliding transactions is serialized for eliminating repeat-collisions - can dramatically improve STM performance in high-contention workloads. In low-contention and highly-parallel workloads, however, excessive serialization of memory transactions may limit concurrency too much and hurt performance. It is therefore important to better understand how the impact of serialization on STM performance varies as a function of workload characteristics.
We investigate how serializing CM influences the performance of STM systems. Specifically, we study serialization’s influence on STM throughput (number of committed transactions per time unit) and efficiency (ratio between the extent of “useful” work done by the STM and work “wasted” by aborts) as the workload’s level of contention varies. Towards this goal, we implement CBench - a synthetic benchmark that generates workloads in which transactions have (parameter) pre-determined length and probability of being aborted in the lack of contention reduction mechanisms. CBench facilitates evaluating the efficiency of contention management algorithms across the full spectrum of contention levels.
The characteristics of TM workloads generated by real applications may vary over time. To achieve good performance, CM algorithms need to monitor these characteristics and change their behavior accordingly. We implement adaptive algorithms that control the activation of serialization CM according to measured contention level, based on a novel low-overhead serialization algorithm. We then evaluate our new algorithms on CBench-generated workloads and on additional well-known STM benchmark applications. We believe our results shed light on the manner in which serializing CM should be used by STM systems.
KeywordsAdaptive Algorithm Transactional Memory Contention Level Software Transactional Memory Synthetic Benchmark
Unable to display preview. Download preview PDF.
- 1.Ansari, M., Luján, M., Kotselidis, C., Jarvis, K., Kirkham, C.C., Watson, I.: Steal-on-abort: Improving transactional memory performance through dynamic transaction reordering. In: HiPEAC, pp. 4–18 (2009)Google Scholar
- 2.Attiya, H., Epstein, L., Shachnai, H., Tamir, T.: Transactional contention management as a non-clairvoyant scheduling problem. In: PODC, pp. 308–315 (2006)Google Scholar
- 3.Dolev, S., Hendler, D., Suissa, A.: CAR-STM: scheduling-based collision avoidance and resolution for software transactional memory. In: PODC, pp. 125–134 (2008)Google Scholar
- 4.Dragojevic, A., Guerraoui, R., Singh, A.V., Singh, V.: Preventing versus curing: avoiding conflicts in transactional memories. In: PODC, pp. 7–16 (2009)Google Scholar
- 5.Fedorova, A., Felber, P., Hendler, D., Lawall, J., Maldonado, W., Marlier, P., Muller, G., Suissa, A.: Scheduling support for transactional memory contention management. In: PPoPP (to appear, 2010)Google Scholar
- 6.Felber, P., Riegel, T., Fetzer, C.: Dynamic performance tuning of word-based software transactional memory. In: PPOPP, pp. 237–246 (February 2008)Google Scholar
- 7.Fraser, K.: Practical lock-freedom. Ph. D. dissertation, UCAM-CL-TR-579, Computer Laboratory, University of Cambridge (2004)Google Scholar
- 9.Guerraoui, R., Herlihy, M., Pochon, B.: Towards a theory of transactional contention managers. In: PODC, pp. 316–317 (2006)Google Scholar
- 11.Harris, T., Fraser, K.: Language support for lightweight transactions. In: OOPSLA, pp. 388–402 (2003)Google Scholar
- 12.Herlihy, M.: SXM software transactional memory package for C#, http://www.cs.brown.edu/~mph
- 13.Herlihy, M., Luchangco, V., Moir, M., Scherer III, W.N.: Software transactional memory for dynamic-sized data structures. In: PODC, pp. 92–101 (2003)Google Scholar
- 14.Herlihy, M., Moss, J.E.B.: Transactional memory: Architectural support for lock-free data structures. In: ISCA, pp. 289–300 (1993)Google Scholar
- 16.Marathe, V.J., Spear, M.F., Heriot, C., Acharya, A., Eisenstat, D., Scherer, I.W.N., Scott, M.L.: Lowering the overhead of nonblocking software transactional memory. In: Workshop on Languages, Compilers, and Hardware Support for Transactional Computing (TRANSACT 2006) (2006)Google Scholar
- 17.Moore, K.E., Bobba, J., Moravan, M.J., Hill, M.D., Wood, D.A.: Logtm: Log-based transactional memory. In: Proceedings of the 12th International Conference on High Performance Computer Architecture, pp. 254–265 (2006)Google Scholar
- 18.Saha, B., Adl-Tabatabai, A.-R., Hudson, R.L., Minh, C.C., Hertzberg, B.: Mcrt-stm: a high performance software transactional memory system for a multi-core runtime. In: PPOPP, pp. 187–197 (2006)Google Scholar
- 19.Scott, M.L., Scherer III, W.N.: Advanced contention management for dynamic software transactional memory. In: PODC, pp. 240–248 (2005)Google Scholar
- 21.Spear, M.F., Silverman, M., Dalessandro, L., Michael, M.M., Scott, M.L.: Implementing and exploiting inevitability in software transactional memory. In: ICPP, pp. 59–66 (2008)Google Scholar
- 22.Vossen, G., Weikum, G.: Transactional information systems. Morgan Kaufmann, San Francisco (2001)Google Scholar
- 23.Yoo, R.M., Lee, H.-H.S.: Adaptive transaction scheduling for transactional memory systems. In: SPAA, pp. 169–178 (2008)Google Scholar