Highly concurrent directory management in the Galaxy distributed system

Xiaohua Jia, Hirohiko Nakano, Kentaro Shimizu, Mamoru Maekawa

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

Abstract

An efficient method of consistency control of replicated directories is presented. By taking advantage of special characteristics of directories, the method achieves fast access to directories and high concurrency in updating directory replicas. The algorithm differs from conventional mechanisms for concurrency control of replicated data in two aspects: (1) It does not use global locks or global timestamp orderings. (2) Updating operations can proceed without being in synchronization. The algorithm can survive both node failure and network failure. The directory problem, design objectives and related works are described. The system model and consistency control requirements are defined, and the data structures and algorithm are presented. The fault tolerance and recovery mechanism of the approach are discussed, as is the applicability of the algorithm. The approach is evaluated and compared with other works. The detail algorithm and consistency proof are given.
Original languageEnglish
Title of host publicationProceedings - International Conference on Distributed Computing Systems
PublisherIEEE
Pages416-423
Publication statusPublished - 1990
Externally publishedYes
EventProceedings of the 10th International Conference on Distributed Computing Systems - ICDCS-10 - Paris, Fr
Duration: 28 May 19901 Jun 1990

Conference

ConferenceProceedings of the 10th International Conference on Distributed Computing Systems - ICDCS-10
CityParis, Fr
Period28/05/901/06/90

Fingerprint

Dive into the research topics of 'Highly concurrent directory management in the Galaxy distributed system'. Together they form a unique fingerprint.

Cite this