Abstract
A good replica consistency algorithm can complete the overall management of replicas. An effective solution to the problem of replica consistency can significantly improve the performance and scalability of cloud computing environment, and reduce job execution time. This paper proposes an activity-based multi-phase replica consistency algorithm (AMRCA). Firstly, the algorithm divides the replicas into two categories according to their active degree, one is “active” replica and the other is “inactive” replica. For those “active” replicas, we use a strong consistency algorithm, requiring all replicas in the system to be consistent, and any updates must be propagated to all replicas. For those “inactive” replicas, we use the weak consistency algorithm. The advantage of this method is that it avoids the increase of system overhead caused by using strong consistency algorithm for all replicas, and ensures that all replicas with high “activity” in the system are up-to-date and consistent. Secondly, the algorithm divides the process of data updating into several stages, each stage works together to ensure data consistency among all valid replicas, and at the same time, it minimizes the failure interval of replicas in the updating process, thus providing more reliable data access services for upper application.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ion, S., et al.: Chord: a scalable peer-to-peer lookup protocol for internet applications. IEEE/ACM Trans. Netw. 11(1), 17–32 (2003)
Ranjita, B., Stefan, S., Geoffrey, V.: Replication strategies for highly available peer-to-peer storage systems. Technical report, CS2002-0726, UCSD (2002)
Lv, Q., Cao, P., Cohen, E., Li, K., Shenker, S.: Search and replication in unstructured peer-to-peer networks. In: Proceedings of the 16th ACM International Conference on Supercomputing, pp. 84–95 (2002)
Wang, Q.B., Dai, Y.F., Tian, J., Zhao, T., Li, X.M.: An infrastructure for attribute addressable P2P network (in Chinese with English abstract). J. Softw. 14(8), 1481–1488 (2003)
Chen, X., Ren, S.S., Wang, H.N., Zhang, X.D.: SCOPE: scalable consistency maintenance in structured P2P systems. In: Proceedings of the IEEE Infocom 2005, pp. 1502–1513. IEEE Computer Society, Washington, D.C. (2005)
Wiesmann, M., Pedone, F., Schiper, A., Kemme, B., Alonso, G.: Understanding replication in databases and distributed systems. In: Proceedings of the 20th International Conference on Distributed Computing Systems (ICDCS 2000), p. 464 (2000)
Jurk, S., Neiling, M.: Client-side dynamic preprocessing of transactions. In: Kalinichenko, L., Manthey, R., Thalheim, B., Wloka, U. (eds.) ADBIS 2003. LNCS, vol. 2798, pp. 103–117. Springer, Heidelberg (2003). https://doi.org/10.1007/978-3-540-39403-7_10
Ripeanu, M.: Peer-to-peer architecture case study: Gnutella network. In: Proceedings of International Conference on Peer-to-Peer Computing Sweden, pp. 99–101. IEEE Computer Press (2001)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, G., Xu, H., Yang, S. (2020). Multi-stage Replica Consistency Algorithm Based on Activity. In: Shen, J., Chang, YC., Su, YS., Ogata, H. (eds) Cognitive Cities. IC3 2019. Communications in Computer and Information Science, vol 1227. Springer, Singapore. https://doi.org/10.1007/978-981-15-6113-9_11
Download citation
DOI: https://doi.org/10.1007/978-981-15-6113-9_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-6112-2
Online ISBN: 978-981-15-6113-9
eBook Packages: Computer ScienceComputer Science (R0)