In the Search for Optimal Concurrency
- 437 Downloads
It is common practice to use the epithet “highly concurrent” referring to data structures that are supposed to perform well in concurrent environments. But how do we measure the concurrency of a data structure in the first place? In this paper, we propose a way to do this, which allowed us to formalize the notion of a concurrency-optimal implementation.
The concurrency of a program is defined here as the program’s ability to accept concurrent schedules, i.e., interleavings of steps of its sequential implementation. To make the definition sound, we introduce a novel correctness criterion, LS-linearizability, that, in addition to classical linearizability, requires the interleavings of memory accesses to be locally indistinguishable from sequential executions. An implementation is then concurrency-optimal if it accepts all LS-linearizable schedules. We explore the concurrency properties of search data structures which can be represented in the form of directed acyclic graphs exporting insert, delete and search operations. We prove, for the first time, that pessimistic (e.g., based on conservative locking) and optimistic serializable (e.g., based on serializable transactional memory) implementations of search data-structures are incomparable in terms of concurrency. Thus, neither of these two implementation classes is concurrency-optimal, hence raising the question of the existence of concurrency-optimal programs.
KeywordsConcurrency Search data structures Lower bounds
This research was supported under Australian Research Council’s Discovery Projects funding scheme (project number 160104801) entitled “Data Structures for Multi-Core”. Vincent Gramoli is the recipient of the Australian Research Council Discovery International Award. Petr Kuznetsov was supported by the Agence Nationale de la Recherche, under grant agreement N ANR-14-CE35-0010-01, project DISCMAT. Srivatsan Ravi acknowledges support from the National Science Foundation (NSF) grant CNS-1117065.
- 2.Aguilera, M.K., Frølund, S., Hadzilacos, V., Horn, S.L., Toueg, S.: Abortable and query-abortable objects and their efficient implementation. In: PODC, pp. 23–32 (2007)Google Scholar
- 5.Dalessandro, L., Spear, M.F., Scott, M.L.: NOrec: streamlining STM by abolishing ownership records. In: PPOPP, pp. 67–78 (2010)Google Scholar
- 6.David, T., Guerraoui, R., Trigonakis, V.: Asynchronized concurrency: the secret to scaling concurrent search data structures. In: ASPLOS, pp. 631–644 (2015)Google Scholar
- 8.Felber, P., Fetzer, C., Riegel, T.: Dynamic performance tuning of word-based software transactional memory. In: PPoPP, pp. 237–246 (2008)Google Scholar
- 9.Gramoli, V.: More than you ever wanted to know about synchronization: synchrobench, measuring the impact of the synchronization on concurrent algorithms. In: PPoPP, pp. 1–10 (2015)Google Scholar
- 12.Gramoli, V., Kuznetsov, P., Ravi, S.: In the search of optimal concurrency. CoRR, abs/1603.01384 (2016)Google Scholar
- 13.Gramoli, V., Kuznetsov, P., Ravi, S., Shang, D.: Brief announcement: a concurrency-optimal list-based set. In: 29th International Symposium on Distributed Computing, DISC 2015, Tokyo, Japan, 7–9 October 2015. Technical report http://arxiv.org/abs/1502.01633
- 20.Herlihy, M., Moss, J.E.B.: Transactional memory: architectural support for lock-free data structures. In: ISCA, pp. 289–300 (1993)Google Scholar
- 21.Herlihy, M., Shavit, N.: The Art of Multiprocessor Programming. Morgan Kaufmann, San Francisco (2008)Google Scholar
- 24.Imbs, D., de Mendívil, J.R.G., Raynal, M.: Brief announcement: virtual world consistency: a new condition for STM systems. In: PODC, pp. 280–281 (2009)Google Scholar
- 25.Kung, H.T., Papadimitriou, C.H.: An optimality theory of concurrency control for databases. In: SIGMOD, pp. 116–126 (1979)Google Scholar
- 28.Shavit, N., Touitou, D.: Software transactional memory. In: PODC, pp. 204–213 (1995)Google Scholar
- 30.Weikum, G.: A theoretical foundation of multi-level concurrency control. In: PODS, pp. 31–43 (1986)Google Scholar
- 31.Weikum, G., Vossen, G.: Transactional Information Systems: Theory, Algorithms, and the Practice of Concurrency Control and Recovery. Morgan Kaufmann, San Francisco (2002)Google Scholar