The greedy load sharing algorithm

doi:10.1016/0743-7315(90)90117-8

Journal of Parallel and Distributed Computing

Volume 9, Issue 1, May 1990, Pages 93-99

https://doi.org/10.1016/0743-7315(90)90117-8 Get rights and content

Abstract

Adaptive load sharing algorithms improve the performance of a distributed system considerably. In this paper we propose an algorithm, the Greedy algorithm, that yields good performance using minimal information about the system. An algorithm known as the Threshold algorithm also yields good performance using as much system information as the Greedy algorithm. We present the results of statistical experiments comparing the Greedy algorithm with the Threshold algorithm and conclude that the Greedy algorithm is an attractive alternative to the Threshold algorithm.

References (20)

D.L. Eager et al.
A comparison of receiver-initiated and sender-initiated adaptive load sharing
Performance Evaluation
(Mar. 1986)
A.V. Aho et al.
Data Structures and Algorithms
A. Barak et al.
A distributed load balancing policy for a multicomputer
Software-Practice and Experience
(Sept. 1985)
S.H. Bokhari
Dual processor scheduling with dynamic reassignment
IEEE Trans. Software Engrg.
(July 1979)
D.L. Eager et al.
Adaptive load sharing in homogeneous distributed systems
IEEE Trans. Software Engrg.
(May 1986)
Hac' A. and Jin X. Dynamic load balancing in a distributed system using a sender-initiated algorithm. Tech. Rep....
A. Hac' et al.
A study of dynamic load balancing in a distributed system
K. Hwang et al.
A Unix-based local computer network with load balancing
Computer
(Apr. 1982)
P. Krueger et al.
An adaptive load balancing algorithm for a multicomputer
P. Krueger et al.
When is the best load sharing algorithm a load balancing algorithm?

There are more references available in the full text version of this article.

Cited by (20)

Decentralized management of bi-modal network resources in a distributed stream processing platform
2011, Journal of Parallel and Distributed Computing
Citation Excerpt :
In both cases, the main problem is to allocate the node resources where certain processing need to be performed along with the network bandwidths that will carry the data stream through these nodes. In general, resource management problems in distributed system are tackled in centralized [31], distributed [11,15] or semi-distributed [2] manner. In a centralized scheme, the state of the whole network is collected at a single node and the resource management operation such as allocation or load balancing are performed in that node over the aggregated data.
This paper presents resource management techniques for allocating communication and computational resources in a distributed stream processing platform. The platform is designed to exploit the synergy of two classes of network connections—dedicated and opportunistic. Previous studies we conducted have demonstrated the benefits of such bi-modal resource organization that combines small pools of dedicated computers with a very large pool of opportunistic computing capacities of idle computers to serve high throughput computing applications. This paper extends the idea of bi-modal resource organization into the management of communication resources. Since distributed stream processing applications demand large volume of data transmission between processing sites at a consistent rate, adequate control over the network resources is important to ensure a steady flow of processing. The system model used in this paper is a platform where stream processing servers at distributed sites are interconnected with a combination of dedicated and opportunistic communication links. Two pertinent resource allocation problems are analyzed in detail and solved using decentralized algorithms. One is mapping of the processing and the communication tasks of the stream processing workload on the processing and the communication resources of the platform. The other is the dynamic re-allocation of the communication links due to variations in the capacity of the opportunistic communication links. Overall optimization goal of the allocations is higher task throughput and better utilization of the expensive dedicated links without deviating much from the timely completion of the tasks. The algorithms are evaluated through extensive simulation with a model based on realistic observations. The results demonstrate that the algorithms are able to exploit the synergy of bi-modal communication links towards achieving the optimization goals.
Toward Performance-Driven System Support for Distributed Computing in Clustered Environments
1999, Journal of Parallel and Distributed Computing
With the proliferation of workstation clusters connected by high-speed networks, providing efficient system support for concurrent applications engaging in nontrivial interaction has become an important problem. Two principal barriers to harnessing parallelism are: (1) efficient mechanisms that achieve transparent dependency maintenance while preserving semantic correctness and (2) scheduling algorithms that match coupled processes to distributed resources while explicitly incorporating their communication costs. This paper describes a set of performance features and their properties and implementation in a system support environment called DUNES that achieves transparent dependency maintenance—IPC, file access, memory access, process creation/termination, process relationships—under dynamic load balancing. The two principal performance features are push/pull-based active and passive end-point caching and communication-sensitive load balancing. Collectively, they mitigate the overhead introduced by the transparent dependency maintenance mechanisms. Communication-sensitive load balancing, in addition, affects the scheduling of distributed resources to application processes where both communication and computation costs are explicitly taken into account. DUNES' architecture endows commodity operating systems with distributed operating system functionality while achieving transparency with respect to their existing application base. DUNES also preserves semantic correctness with respect to single processor semantics. We show performance measurements of a UNIX-based implementation on Sparc and x86 architectures over high-speed LAN environments. We show that significant performance gains in terms of system throughput and parallel application speedup are achievable.
A partially asynchronous and iterative algorithm for distributed load balancing
1994, Parallel Computing
Defining task as independent entities with identical execution time and the workload of a processor as the number of tasks, load balancing is to distribute tasks among processors of a network so that the resulting workload of every processor will be as close to the average over all the workloads as possible. We propose in this paper a partially asynchronous and iterative algorithm for distributed load balancing, show its properties, and report its simulation results. The algorithm converges geometrically as assured by a theorem for balancing continuous workload. We prove that the algorithm can achieve the maximum load imbalance of no more than $⌈ d 2 ⌉$ tasks, where d is the diameter of a network. Our simulation not only validated the properties but also showed that the algorithm could produce much smaller load imbalances for hypercubes. The obtained imbalances for hypercubes of order up to ten were no more than two tasks and 56% of the sample runs produced only one task difference, as opposed to the theoretical maximum of six tasks.
Analysis of the generalized dimension exchange method for dynamic load balancing
1992, Journal of Parallel and Distributed Computing
The dimension exchange method is a distributed load balancing method for point-to-point networks. We add a parameter, called the exchange parameter, to the method to control the splitting of load between a pair of directly connected processors, and call this parameterized version the generalized dimension exchange (GDE) method. The rationale for the introduction of this parameter is that splitting the workload into equal halves does not necessarily lead to an optimal result (in terms of the convergence rate) for certain structures. We carry out an analysis of this new method, emphasizing its termination aspects and potential efficiency. Given a specific structure, one needs to determine a value to use for the exchange parameter that would lead to an optimal result. To this end, we first derive a sufficient and necessary condition for the termination of the method. We then show that equal splitting, proposed originally by others as a heuristic strategy, indeed yields optimal efficiency in hypercube structures. For chains, rings, meshes, and tori, however, optimal choices of the exchange parameter are found to be closely related to the scales of these structures. Finally, to further investigate the potential of the GDE method, we extend it to allow exchange parameters of different values to be used over the set of edges, and based on this extension, we compare the GDE method with the diffusion method.
Performance analysis of load balancing algorithms for cloud computing
2019, International Journal of Recent Technology and Engineering
TSSA: A two step scheduling algorithm for the event-driven clusters
2018, International Conference on Advanced Communication Technology, ICACT

View all citing articles on Scopus

^☆: This research is sponsored in part by the Air Force Office of Scientific Research, Air Force System Command, USAF, under Grant AFOSR-84-0072 and in part by the National Science Foundation under Grant NSF MCS-8320138.

View full text

Research noteThe greedy load sharing algorithm☆

Abstract

Performance Evaluation

Data Structures and Algorithms

A distributed load balancing policy for a multicomputer

Software-Practice and Experience

Dual processor scheduling with dynamic reassignment

IEEE Trans. Software Engrg.

Adaptive load sharing in homogeneous distributed systems

IEEE Trans. Software Engrg.

A study of dynamic load balancing in a distributed system

A Unix-based local computer network with load balancing

Computer

An adaptive load balancing algorithm for a multicomputer

When is the best load sharing algorithm a load balancing algorithm?

Research note
The greedy load sharing algorithm☆