Adapting Distributed Commit Protocol for Dynamic Metacomputing Frameworks
نویسندگان
چکیده
With increasing interest in applications which benefit from distributed computing paradigm and require at the same time to operate on data from heterogeneous data sources there is an increasing desire for commit protocols which can suit such systems. Well known two-phase commit protocol and three-phase commit protocol or its modifications do not provide flexibility which is desired for wide area of potential applications. In this paper we present an adaptation of three-phase commit protocol for dynamic distributed systems. The protocol is not only resistant to nodes/network failures, but also provides good scalability. Our protocol offers users a set of parameters which can be tuned and, depending on specific requirements of the system, guarantee consistency at desired level for the best
منابع مشابه
The Harness Metacomputing Framework
Metacomputing frameworks have received renewed attention of late, fueled both by advances in hardware and networking, and by novel concepts such as computational grids. However these frameworks are often inflexible, and force the application into a fixed environment rather than trying to adapt to the application’s needs. Harness is an experimental metacomputing framework based upon the principl...
متن کاملHierarchical Coordinated Checkpointing Protocol
Coordinated checkpointing protocol is a simple and useful protocol, used for fault tolerance in distributed system on LAN. However, checkpoint overhead of the protocol is bottlenecked by the link speed. Checkpoint overhead of the protocol increases even if only one link in the network is of low-speed. In a metacomputing environment, where distributed application communicates over low speed WAN,...
متن کاملAdapting Commit Protocols for Large-Scale and Dynamic Distributed Applications
The continued advances in distributed data intensive applications have formed an increasing demand for distributed commit protocols that are adaptive to large scale and dynamic nature of the applications to guarantee data consistency and integrity. Well known two-phase commit protocol and three-phase commit protocol and their variants do not provide scalability and flexibility desired for a wid...
متن کاملUsing Reflection for Incorporating Fault-Tolerance Techniques into Distributed Applications
As part of the Legion metacomputing project, we have developed a reflective model, the Reflective Graph & Event (RGE) model, for incorporating functionality into applications. In this paper we apply the RGE model to the problem of making applications more robust to failures. RGE encourages system developers to express fault-tolerance algorithms in terms of transformations on the data structures...
متن کاملBehavioral Objects and Layered Services: The Aplication Programming Style in the Harness Metacomputing System
Recent advances in hardware and networking have fueled the interest in distributed computing in general and in metacomputing frameworks in particular. Harness is an experimental metacomputing system based upon the principle of dynamic reconfigurability both in terms of the computers and networks that comprise the virtual machine, and in the services offered by the virtual machine itself. In thi...
متن کامل