Vincent Gramoli
Emmanuelle Anceaume
ABSTRACT
Internet-scale applications require more and more resources to satisfy the unpredictable clients needs. Specifically, such applications must ensure quality of service despite bursts of load. Distributed dynamic self-organized systems present an inherent adaptiveness that can face unpredictable bursts of load. Nevertheless quality of service, and more particularly data consistency, remains hardly achievable in such systems since participants (i.e., nodes) can crash, leave, and join the system at arbitrary time. Atomic consistency guarantees that any read operation returns the last written value of a data and is generalizable to data composition. To guarantee atomic consistency in message-passing model, mutually intersecting sets (a.k.a. quorums) of nodes are used. The solution presented here, namely Square, uses self-adaptiveness and load-balancing to provide atomic consistency in large-scale dynamic distributed systems. This paper presents the Square algorithm and uses extensive simulation to show it achieves its desirable properties.
- eBay. http://www.ebay.com/.Google Scholar
- I. Abraham and D. Malkhi. Probabilistic quorums for dynamic systems. Distrib. Computing, 18(2):113--124, 2005. Google ScholarDigital Library
- E. Anceaume, M. Gradinariu, V. Gramoli, and A. Virgillito. P2P architecture for self* atomic memory. In Proc. of 8th Intl Symposium on Parallel Architectures, Algorithms and Networks, pages 214--219, 2005. Google ScholarDigital Library
- E. Anceaume, V. Gramoli, and A. Virgillito. SQUARE: Scalable quorum-based atomic memory with local reconfiguration. Technical Report 1805, IRISA Campus de Beaulieu, Rennes, France, 2006.Google Scholar
- H. Attiya, A. Bar-Noy, and D. Dolev. Sharing memory robustly in message-passing systems. Journal of the ACM, 42(1): 124--142, 1995. Google ScholarDigital Library
- B. Awerbuch and P. Vitanyi. Atomic shared register access by asynchronous hardware. In Proc. of 27th IEEE Symposium on Foundations of Computer Science (FOCS), pages 233--243, 1986.Google Scholar
- R. Baldoni, R. Jimnez-Peris, M. Patio-Martinez, L. Querzoni, and A. Virgillito. Dynamic Quorums for DHT-based P2P Networks. In Proceedings of the 4th IEEE International Symposium on Network Computing and Applications (NCA05), Cambridge, MA, USA, 2005. Google ScholarDigital Library
- G. Chockler, S. Gilbert, V. Gramoli, P. M. Musial, and A. A. Shvartsman. Reconfigurable distributed storage for dynamic networks. In Proc. of 9th Intl Conference on Principles of Distributed Systems (OPODIS), 2005. Google ScholarDigital Library
- S. Dolev, S. Gilbert, N. Lynch, A. Shvartsman, and J. Welch. GeoQuorums: Implementing atomic memory in ad hoc networks. In Proc. of 17th Intl Symposium on Distributed Computing (DISC), pages 306--320, 2003.Google ScholarCross Ref
- M. P. Herlihy. Dynamic quorum adjustment for partitioned data. ACM Trans. on Database Systems, 12(2): 170--194, 1987. Google ScholarDigital Library
- M. P. Herlihy and J. M. Wing. Linearizability: a correctness condition for concurrent objects. ACM Trans, on Programming Languages and Systems (TOPLAS), 12(3):463--492, 1990. Google ScholarDigital Library
- L. Lamport. On interprocess communication. Distributed Computing, 1(2):77--101, 1986.Google ScholarCross Ref
- N. Lynch and A. Shvartsman. RAMBO: A reconfigurable atomic memory service for dynamic networks. In Proc. of 16th Intl Symposium on Distributed Computing (DISC), pages 173--190, 2002. Google ScholarDigital Library
- N. A. Lynch. Distributed Algorithms. Morgan Kaufmann Publishers, 1996. Google ScholarDigital Library
- M. Maekawa. A √N algorithm for mutual exclusion in decentralized systems. ACM Trans. on Computer Systems (TOCS), 3(2): 145--159, 1985. Google ScholarDigital Library
- U. Nadav and M. Naor. Fault-tolerant storage in a dynamic environment. In Proc. of he 18th Annual Conference on Distributed Computing (DISC), 2004.Google ScholarCross Ref
- M. Naor and U. Wieder. Scalable and dynamic quorum systems. In Proc. of the 22th annual symposium on Principles of distributed computing (PODC), pages 114--122. ACM Press, 2003. Google ScholarDigital Library
- S. Ratnasamy, P. Francis, M. Handley, R. Karp, and S. Shenker. A scalable content-addressable network. In Proc. of the ACM SIGCOMM, pages 161--172, 2001. Google ScholarDigital Library
- B. Silaghi, P. Keleher, and B. Bhattacharjee. Multi-dimensional quorum sets for read-few write-many replica control protocols. In Proc. of the 4th CCGRID/GP2PC, 2004. Google ScholarDigital Library
Index Terms
- SQUARE: scalable quorum-based atomic memory with local reconfiguration
Recommendations
Scalable service-oriented replication with flexible consistency guarantee in the cloud
Replication techniques are widely applied in and for cloud to improve scalability and availability. In such context, the well-understood problem is how to guarantee consistency amongst different replicas and govern the trade-off between consistency and ...
Scalable consistency in Scatter
SOSP '11: Proceedings of the Twenty-Third ACM Symposium on Operating Systems PrinciplesDistributed storage systems often trade off strong semantics for improved scalability. This paper describes the design, implementation, and evaluation of Scatter, a scalable and consistent distributed key-value storage system. Scatter adopts the highly ...
ALOHA-KV: high performance read-only and write-only distributed transactions
SoCC '17: Proceedings of the 2017 Symposium on Cloud ComputingThere is a trend in recent database research to pursue coordination avoidance and weaker transaction isolation under a long-standing assumption: concurrent serializable transactions under read-write or write-write conflicts require costly ...
Comments