Constructing Shared Objects That Are Both Robust and High-Throughput
Shared counters are among the most basic coordination structures in distributed computing. Known implementations of shared counters are either blocking, non-linearizable, or have a sequential bottleneck. We present the first counter algorithm that is both linearizable, nonblocking, and can provably achieve high throughput in semisynchronous executions. The algorithm is based on a novel variation of the software combining paradigm that we call bounded-wait combining. It can thus be used to obtain implementations, possessing the same properties, of any object that supports combinable operations, such as stack or queue. Unlike previous combining algorithms where processes may have to wait for each other indefinitely, in the bounded-wait combining algorithm a process only waits for other processes for a bounded period of time and then ‘takes destiny in its own hands’.
In order to reason rigorously about the parallelism attainable by our algorithm, we define a novel metric for measuring the throughput of shared objects which we believe is interesting in its own right. We use this metric to prove that our algorithm can achieve throughput of Ω(N / logN) in executions where process speeds vary only by a constant factor, where N is the number of processes that can participate in the algorithm.
We also introduce and use pseduo-transactions – a technique for concurrent execution that may prove useful for other algorithms.
KeywordsLeaf Node Base Object Shared Object High Parallelism Asynchronous Mode
Unable to display preview. Download preview PDF.
- 3.Attiya, H., Welch, J.L.: Distributed Computing: Fundamentals, Simulations and Advanced Topics, 2nd edn. Wiley, Chichester (2004)Google Scholar
- 4.Fich, F.E., Hendler, D., Shavit, N.: Linear lower bounds on real-world implementations of concurrent objects. In: FOCS 2005, pp. 165–173 (2005)Google Scholar
- 5.Goodman, J.R., Vernon, M.K., Woest, P.J.: Efficent synchronization primitives for large-scale cache-coherent multiprocessors. In: ASPLOS, pp. 64–75 (1989)Google Scholar
- 6.Gottlieb, A., Grishman, R., Kruskal, C.P., McAuliffe, K.P., Rudolph, L., Snir, M.: The nyu ultracomputer designing a mimd, shared-memory parallel machine. In: ISCA 1998: 25 years of the international symposia on Computer architecture (selected papers), pp. 239–254. ACM Press, New York (1998)CrossRefGoogle Scholar
- 7.Greenwald, M.: Two-handed emulation: How to build non-blocking implementations of complex data-structures using dcas. In: PODC 2002, pp. 260–269 (2002)Google Scholar
- 8.Ha, P.H., Papatriantafilou, M., Tsigas, P.: Self-tuning reactive distributed trees for counting and balancingGoogle Scholar
- 12.Herlihy, M., Luchango, V., Moir, M.: Obstruction-free synchronization: Double-ended queues as an example. In: ICDCS 2003, pp. 522–529 (2003)Google Scholar
- 16.Lynch, N.A., Shavit, N.: Timing-based mutual exclusion. In: IEEE Real-Time Systems Symposium, pp. 2–11 (1992)Google Scholar
- 17.Moir, M., Nussbaum, D., Shalev, O., Shavit, N.: Using elimination to implement scalable and lock-free fifo queues. In: SPAA 2005, New York, pp. 253–262 (2005)Google Scholar