Joint affinity aware grouping and virtual machine placement

Abstract

The Non-Affinity Aware Grouping based resource Allocation (NAGA) method toward the General VMPlacement (GP) problem enables (1) some VMs to be co-located onto the same PM while the VMs are required to be placed onto distinct PMs; and (2) some VMs to be dispersedly placed onto distinct PMs while the VMs are required to be co-located onto the same PM, leading to a serious performance degradation of application running over multiple VMs in cloud computing. In this work we study an Affinity Aware VM Placement (AAP) problem and propose a Joint Affinity AwareGrouping and Bin Packing (JAGBP) method to remedy the deficiency of the NAGA method. We firstly introduce affinity of VMs to identify affinity relationships to VMs which are required to be placed with a special VM placement pattern, such as colocation or disperse placement, and formulate the AAP problem. Then, we propose an affinity aware resource scheduling framework, and provide methods to obtain and identify the affinity relationships between VMs, and the JAGBP method. Lastly, we present holistic evaluation experiments to validate the feasibility and evaluate the performance of the proposed methods. The results demonstrate the significance of introduced affinity and the effectiveness of JAGBP method.