The Bancomat problem: an example of resource allocation in a partitionable asynchronous system

A partition-aware application is an application that can make progress in multiple connected components. In this paper, we examine a particular partition-aware application to evaluate the properties provided by different partitionable group membership protocols. The application we examine is a simple resource allocation problem that we call the Bancomat problem. We define a metric specific to this application, which we call the cushion, that captures the effects of the uncertainty of the global state caused from partitioning. We solve the Bancomat problem using four different approaches for building partition-aware applications. We compare the approaches in terms of their cushions and discuss how well different group membership protocols support the different approaches.

[1]  Fred B. Schneider,et al.  Implementing fault-tolerant services using the state machine approach: a tutorial , 1990, CSUR.

[2]  Nancy A. Lynch,et al.  Specifying and using a partitionable group communication service , 1997, PODC '97.

[3]  Allan Borodin,et al.  Online computation and competitive analysis , 1998 .

[4]  Sam Toueg,et al.  Fault-tolerant broadcasts and related problems , 1993 .

[5]  Leslie Lamport,et al.  Time, clocks, and the ordering of events in a distributed system , 1978, CACM.

[6]  Roy Friedman,et al.  Strong and weak virtual synchrony in Horus , 1996, Proceedings 15th Symposium on Reliable Distributed Systems.

[7]  Bernadette Charron-Bost,et al.  On the impossibility of group membership , 1996, PODC '96.

[8]  Louise E. Moser,et al.  The Totem single-ring ordering and membership protocol , 1995, TOCS.

[9]  André Schiper,et al.  Primary Partition "Virtually-Synchronous Communication" harder than Consensus , 1994, WDAG.

[10]  Matti A. Hiltunen,et al.  Properties of membership services , 1995, Proceedings ISADS 95. Second International Symposium on Autonomous Decentralized Systems.

[11]  Frank B. Schmuck,et al.  Agreeing on Processor Group Membership in Timed Asynchronous Distributed Systems , 1995 .

[12]  Danny Dolev,et al.  The Transis approach to high availability cluster communication , 1996, CACM.

[13]  Brian Randell,et al.  Operating Systems, An Advanced Course , 1978 .

[14]  Jim Gray,et al.  Notes on Data Base Operating Systems , 1978, Advanced Course: Operating Systems.

[15]  Piotr Berman,et al.  Adaptability and the Usefulness of Hints (Extended Abstract) , 1998, ESA.

[16]  Kenneth P. Birman,et al.  Consistent Failure Reporting in Reliable Communication Systems , 1993 .

[17]  Robbert van Renesse,et al.  Horus: a flexible group communication system , 1996, CACM.

[18]  Keith Marzullo,et al.  Group communication services versus wide-area networks , 1999 .

[19]  F. Cristian,et al.  A fail-aware membership service , 1997, Proceedings of SRDS'97: 16th IEEE Symposium on Reliable Distributed Systems.

[20]  Susan B. Davidson,et al.  Optimism and consistency in partitioned distributed database systems , 1984, TODS.

[21]  Alberto Montresor,et al.  System support for partition-aware network applications , 1998, Proceedings. 18th International Conference on Distributed Computing Systems (Cat. No.98CB36183).

[22]  Alberto Montresor,et al.  Group membership and view synchrony in partitionable asynchronous distributed systems: specifications , 1997, OPSR.

[23]  Kenneth P. Birman,et al.  Using process groups to implement failure detection in asynchronous environments , 1991, PODC '91.

[24]  P. Berman,et al.  Adaptability and the usefulness of hints , 1998 .

[25]  Keith Marzullo,et al.  The Bancomat problem: an example of resource allocation in a partitionable asynchronous system , 2003, Theoretical Computer Science.

[26]  Louise E. Moser,et al.  Extended virtual synchrony , 1994, 14th International Conference on Distributed Computing Systems.