Performance Evaluation of Static VM Consolidation Algorithms for Cloud-Based Data Centers Considering Inter-VM Performance Interference

Energy efficiency in data centers is a very important issue and getting growing attention from researchers. One approach to reduce energy consumption is to allocate virtual machines (VMs) to physical machines (PMs) in such a way that the number of idle PMs is maximized. Approaches of this kind are called VM consolidation methods. Idle PMs can be put into an energy-saving sleep mode, in which PMs consume significantly lower energy than in the normal operation mode. But if too many VMs are packed into a single PM without considering their execution characteristics, the performance interference among VMs can cause significant slowdown to jobs. When a VM for a new job arrives at a cloud, this VM should be allocated to a PM and we consider this job allocation problem as a static VM consolidation algorithm. We introduce several static VM consolidation algorithms which not only increase number of idle servers and, therefore, reduce the total energy consumption on a cloud-based data center but also consider performance degradation on jobs due to inter-VM interference. We analyze introduced algorithms through simulation assuming more realistic data centers where each server consists of many cores and multiple types of resources including CPUs, memory, and IOs. We measure the idle server ratio and the total energy consumption in a cloud-based data center and the service level agreement violation ratio of executed jobs and compare these values with those of other existing algorithms.