Solution of a problem in concurrent programming control
Communications of the ACM
A Distributed Solution to the k-out of-M Resources Allocation Problem
ICCI '91 Proceedings of the International Conference on Computing and Information: Advances in Computing and Information
Distributed Resource Allocation Algorithms (Extended Abstract)
WDAG '92 Proceedings of the 6th International Workshop on Distributed Algorithms
A distributed K-mutual exclusion algorithm
ICDCS '95 Proceedings of the 15th International Conference on Distributed Computing Systems
A fast distributed modular algorithm for resource allocation
ICDCS '95 Proceedings of the 15th International Conference on Distributed Computing Systems
(h-k)-arbiter for h-out of-k Mutual Exclusion Problem
ICDCS '99 Proceedings of the 19th IEEE International Conference on Distributed Computing Systems
Hi-index | 0.00 |
The distributed resource allocation problem is one of important problems in distributed environment. In some applications where a resource is required by many processes at a time, some kinds of resources, such as a memory, a disk, or a communication channel can be divided into many units, which can be allocated to more than one process in the same time according to their requested amounts for the resource. In this paper, in order to use such kind of resources efficiently, we propose a new method for allocating the resources, by employing a "unobstructed squeezing" technique. By this method, a process with lower priority may acquire requested units, before another process with higher priority, if this allocation to the latter will not be delayed. A simulation shows that the performance of our method will be about 30% better than the traditional method for h-out-of-k problem (without squeezing), when each resource has large number of units and the number of requests for the resource is large enough.