Skip to Main Content
The workload on a cluster system can be highly variable, increasing the difficulty of balancing the load across its nodes. And the general rule is that high variability leads to wrong load balancing decisions taken with out-of-date information and difficult to correct in real-time during applications execution.In this work the workload variability is studied from the perspective of the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. Two different robustness metrics are proposed to select the best distribution rule for the algorithm, remote execution or process migration. With the proposed solution only when a high variability causes an intolerable performance degradation the process migration is used to balance the load in the system.