Theoretical Results of QoS-Guaranteed Resource Scaling for Cloud-Based MapReduce

Quality of Service (QoS) is a new issue in cloud-based MapReduce, which is a popular computation model for parallel and distributed processing of big data. QoS guarantee is challenging in a dynamical computation environment due to the fact that a fixed resource allocation may become under-provisioning, which leads to QoS violation, or over-provisioning, which increases unnecessary resource cost. This requires runtime resource scaling to adapt environmental changes for QoS guarantee. Aiming to guarantee the QoS, which is referred as to hard deadline in this work, this paper develops a theory to determine how and when resource is scaled up/down for cloud-based MapReduce. The theory employs a nonlinear transformation to define the problem in a reverse resource space, simplifying the theoretical analysis significantly. Then, theoretical results are presented in three theorems on sufficient conditions for guaranteeing the QoS of cloud-based MapReduce. The superiority and applications of the theory are demonstrated through case studies.