The Impact of Workload Variability on Load Balancing Algorithms

The workload on a cluster system can be highly variable, increasing the difficulty of balancing the load across its nodes. The general rule is that high variability leads to wrong load balancing decisions taken with out-of-date information and difficult to correct in real-time during applications execution. In this work the workload variability is studied from the perspective of the load balancing performance, focusing on the design of algorithms capable of dealing with this variability. In this paper an exhaustive analysis is presented to help users and administrators to understand if their load balancing mechanisms are sensitive to variability and to what degree. Furthermore, solutions to deal with variability in load balancing algorithms are proposed and their utilization is exemplified on a real load balancing algorithm.

[1]  Marta Beltrán,et al.  Dealing with Heterogeneity in Load Balancing Algorithms , 2006, 2006 Fifth International Symposium on Parallel and Distributed Computing.

[2]  Kevin Jeffay,et al.  Variability in TCP round-trip times , 2003, IMC '03.

[3]  Richard John Anthony,et al.  Self-Configuration in Parallel Processing , 2005, 16th International Workshop on Database and Expert Systems Applications (DEXA'05).

[4]  Rohit Jain,et al.  Variability in the execution of multimedia applications and implications for architecture , 2001, ISCA 2001.

[5]  Rajkumar Buyya,et al.  High Performance Cluster Computing: Architectures and Systems , 1999 .

[6]  Chun-Ying Huang,et al.  The Impact of Network Variabilities on TCP Clocking Schemes , 2005, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.

[7]  Marta Beltrán,et al.  Initiating Load Balancing Operations , 2005, Euro-Par.

[8]  David A. Patterson,et al.  Computer Architecture: A Quantitative Approach , 1969 .

[9]  Anthony A. Maciejewski,et al.  The robustness of resource allocation in parallel and distributed computing systems , 2004, Third International Symposium on Parallel and Distributed Computing/Third International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Networks.

[10]  Mark Carpenter,et al.  The New Statistical Analysis of Data , 2000, Technometrics.

[11]  Rajkumar Buyya,et al.  High Performance Cluster Computing , 1999 .

[12]  C. Murray Woodside,et al.  Evaluating the scalability of distributed systems , 1998, Proceedings of the Thirty-First Hawaii International Conference on System Sciences.

[13]  Richard Wolski,et al.  Predicting the CPU availability of time‐shared Unix systems on the computational grid , 2004, Cluster Computing.

[14]  Marta Beltrán,et al.  Estimating a workstation CPU assignment with the DYPAP monitor , 2004, Third International Symposium on Parallel and Distributed Computing/Third International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Networks.

[15]  Donald F. Towsley,et al.  Analysis of the Effects of Delays on Load Sharing , 1989, IEEE Trans. Computers.

[16]  Francis C. M. Lau,et al.  Load balancing in parallel computers - theory and practice , 1996, The Kluwer international series in engineering and computer science.

[17]  Riccardo Gusella,et al.  Characterizing the Variability of Arrival Processes with Indexes of Dispersion , 1991, IEEE J. Sel. Areas Commun..

[18]  Dejan S. Milojicic,et al.  Process migration , 1999, ACM Comput. Surv..