A hierarchical adaptive distributed algorithm for load balancing

Load balancing/sharing exploits the communication facility between the servers of a distributed system, by using the exchanging of status information and jobs between any two servers of the system in order to improve the overall performance. We propose an adaptive distributed hierarchical scheme, the Virtual Tree Algorithm (VTA), which creates a virtual binary tree structure over the actual network topology. It uses the difference-initiated (DI) technique for load balancing, which needs remote information for the transfer policy and no additional information for the location policy. We demonstrate that the introduced virtual construction keeps the exchanged messages to relatively low levels. To evaluate the performance of our policy, we present both theoretical and simulation results. By using simulation, we compare our results with one of the most representative, adaptive, symmetrical and efficient algorithms, the Variable Threshold (V_THR) algorithm.

[1]  Sanglu Lu,et al.  A scalable loading balancing system for NOWs , 1998, OPSR.

[2]  Mukesh Singhal,et al.  Load distributing for locally distributed systems , 1992, Computer.

[3]  Ravishankar K. Iyer,et al.  Predictability of Process Resource Usage: A Measurement-Based Study on UNIX , 1989, IEEE Trans. Software Eng..

[4]  Stephen Taylor,et al.  A Practical Approach to Dynamic Load Balancing , 1998, IEEE Trans. Parallel Distributed Syst..

[5]  Edward D. Lazowska,et al.  Adaptive load sharing in homogeneous distributed systems , 1986, IEEE Transactions on Software Engineering.

[6]  Cheng-Zhong Xu,et al.  Iterative Dynamic Load Balancing in Multicomputers , 1994 .

[7]  Phillip Krueger,et al.  Two adaptive location policies for global scheduling algorithms , 1990, Proceedings.,10th International Conference on Distributed Computing Systems.

[8]  Pallab Dasgupta,et al.  V_THR: An Adaptive Load Balancing Algorithm , 1997, J. Parallel Distributed Comput..

[9]  Min-You Wu,et al.  On Runtime Parallel Scheduling for Processor Load Balancing , 1997, IEEE Trans. Parallel Distributed Syst..

[10]  Ravishankar K. Iyer,et al.  Prediction-Based Dynamic Load-Sharing Heuristics , 1993, IEEE Trans. Parallel Distributed Syst..

[11]  A. J. Harget,et al.  Load balancing algorithms in loosely-coupled distributed systems: a survey , 1990 .

[12]  T. Kunz.  The Innuence of Diierent Workload Descriptions on a Heuristic Load Balancing Scheme the Innuence of Diierent Workload Descriptions on a Heuristic Load Balancing Scheme , 2007 .

[13]  Sivarama P. Dandamudi.  The effect of scheduling discipline on dynamic load sharing in heterogeneous distributed systems , 1997, Proceedings Fifth International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems.

[14]  Yung-Terng Wang,et al.  Load Sharing in Distributed Systems , 1985, IEEE Transactions on Computers.

[15]  Gerassimos D. Barlas.  Collection-Aware Optimum Sequencing of Operations and Closed-Form Solutions for the Distribution of a Divisible Load on Arbitrary Processor Trees , 1998, IEEE Trans. Parallel Distributed Syst..

[16]  Paul G. Spirakis,et al.  A Competitive Symmetrical Transfer Policy for Load Sharing , 1998, Euro-Par.

[17]  V. DevarakondaM.,et al.  Predictability of Process Resource Usage , 1989 .

[18]  Jie Li,et al.  Optimal Load Balancing in Distributed Computer Systems , 1997 .

[19]  Sivarama P. Dandamudi.  Sensitivity evaluation of dynamic load sharing in distributed systems , 1998, IEEE Concurr..

[20]  Edward D. Lazowska,et al.  A Comparison of Receiver-Initiated and Sender-Initiated Adaptive Load Sharing , 1986, Perform. Evaluation.

[21]  Anna Hác,et al.  Dynamic Load Balancing in a Distributed System Using a Decentralized Algorithm , 1987, ICDCS.

[22]  Wentong Cai,et al.  How network topology affects dynamic loading balancing , 1996, IEEE Parallel Distributed Technol. Syst. Appl..

[23]  Xiaotie Deng,et al.  Competitive Analysis of Network Load Balancing , 1997, J. Parallel Distributed Comput..

[24]  S.P. Dandamudi,et al.  A hierarchical load sharing policy for distributed systems , 1997, Proceedings Fifth International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems.

[25]  Ellen W. Zegura,et al.  A quantitative comparison of graph-based models for Internet topology , 1997, TNET.

[26]  Walter H. Kohler,et al.  Models for Dynamic Load Balancing in a Heterogeneous Multiple Processor System , 1979, IEEE Transactions on Computers.

[27]  Satish K. Tripathi,et al.  SAHAYOG: A test bed for evaluating dynamic load‐sharing policies , 1989, Softw. Pract. Exp..

[28]  Lois M. L. Delcambre,et al.  Load balancing with network cooperation , 1991, [1991] Proceedings. 11th International Conference on Distributed Computing Systems.

[29]  Rajeev Motwani,et al.  Randomized algorithms , 1996, CSUR.

[30]  Samuel T. Chanson,et al.  Theoretical Analysis of the Heterogeneous Dynamic Load-Balancing Problem Using a Hydrodynamic Approach , 1997, J. Parallel Distributed Comput..

[31]  Sivarama P. Dandamudi.  Performance impact of scheduling discipline on adaptive load sharing in homogeneous distributed systems , 1995, Proceedings of 15th International Conference on Distributed Computing Systems.

[32]  Arif Ghafoor,et al.  Semi-Distributed Load Balancing For Massively Parallel Multicomputer Systems , 1991, IEEE Trans. Software Eng..