A Dynamic Resource Allocation Method for Load-Balance Scheduling Over Big Data Platforms
Wenda Tang, Xiang Liu, Wajid Rafique, Wanchun Dou · 2018
Currently, cloud computing scheme provides a model of utility computing, which usually implemented in the form of big data centers. There is an increasing number of high-performance computing (HPC) applications which are executed in data centers. As HPC application are usually resource-intensive, how to allocate resource to the applications under performance constraints and give a balanced workload among the data centers remains to be addressed appropriately. To address this challenge, we propose a Dynamic Resource Allocation method, named DRA in this paper, for load-balance task scheduling. Technically, the method is consisted of four steps that are enacted in a hierarchical control framework. The proposed method has been validated its feasibility and efficiency by extensive experiments comparing with the other two outstanding methods.