MetaCartSign in to MyCiteSeer

Include Citations | Advanced Search | Help

Include Citations | Advanced Search | Help

  Simatic A Decentralized and Efficient Algorithm for Load Sharing (1991) [2 citations — 0 self]

Download:
Download as a PDF | Download as a PS
by Guy Bernard, Michel Simatic
in Networks of Workstations Proc. EurOpen Spring 1991 Conf
http://casaturn.kaist.ac.kr/~sikang/course/CS642/BS91.ps.gz
Add To MetaCart

Abstract:

This paper presents the design and evaluation of a decentralized load sharing algorithm for networks of workstations, RADIO. With respect to general distributed computing environments, networks of workstations have some peculiarities. First, the global computing power is most of the time much underutilized. Second, users of workstations need occasionally a peek of computing power. Third, workstations are often diskless, so that running a process on one workstation or another does not add file migration overhead. Fourth, network interfaces often provide a broadcast capability, which may be used to reach several destinations in a single message. Last, workstations are often dedicated to an "owner", so that a workstation may only be used for running foreign processes only when the workstation's owner does not use it (or at least when running foreign processes would not increase the owner's programs response time by a significant amount). The first three points make load sharing very attractive for a network of workstations. The fourth point may be used for simplifying the design of load sharing algorithms, but broadcasting is expensive. The goal of RADIO is to provide the benefits of a decentralized load sharing algorithm while preserving the personal character of workstations and providing good performance results, in particular with respect to extensibility. The key feature of the RADIO load sharing algorithm is that it is decentralized but involves expensive broadcast messages only occasionally. The design choices for information policy, location policy and transfer policy are described and motivated. RADIO has been implemented on a network of Sun workstations, and runs entirely outside of the kernel. Experimental results show that the extensibility of RADIO is better than that of previous decentralized algorithms, based on broadcast messages. 1.

Citations

83 Finding Idle Machines in A Workstation-Based Distributed System – Theimer, Lantz - 1989
41 Profiling workstations' available capacity for remote execution, Performance '87 – Mutka, Livny - 1987
30 The design and implementation of a decentralized scheduling facility for a workstation cluster – Stumm - 1988
20 The diverse objectives of distributed scheduling policies – Krueger, Livny - 1987
19 The influence of workload on load balancing strategies – Cabrera - 1986
18 Process Server: Sharing Processing Power in a Workstation Environment, in preparation – Hagmann
17 an Intelligent Load Sharing Filter – History - 1990
11 Sharing Jobs Among Independently Owned Processors – Alonso, Cova - 1988
9 Multiprocessing in a Network of Workstations – Nichols - 1990
2 Distributed Processes in Loosely-Coupled Unix Multiprocessor Systems – Bonomi, Fleming, et al. - 1989