Prioritized Token-Based Mutual Exclusion for Distributed Systems
IPPS '98 Proceedings of the 12th. International Parallel Processing Symposium on International Parallel Processing Symposium
| Hi-index | 0.00 |
A number of solutions have been proposed for the problem of mutual excIusion in distributed systems. Some of these approaches have since been extended to a prioritized environment suitable for real-time applications but impose a higher message passing overhead than our approach. We present a new protocol for prioritized mutual exclusion in a distributed environment. Our approach uses a token-based model working on a logical tree structure, which is dynamically modified. In addition, we utilize a set of local queues whose union would resemble a single global queue. The prioritized algorithm has an average overhead of O(log(n)) messages per request for mutual exclusion with a worst-case overhead of O(n), where n represents the number of nodes in the system. Thus, our prioritized algorithm matches the message complexity of the best non-prioritized algorithms while previous prioritized algorithms have a higher message complexity, to our knowledge. Furthermore, the concept of local queues can be incorporated into arbitrary token-based protocols with or without priority support to reduce the amount of messages.