Shared Storage Software Defined Data Centers: Analyzing VM Migration Based on Application Workloads
Sumitro Bhaumik, Rohit Dhangar, Gouranga Murari, Swapnil Kumar Bishnu, Sandip Chakraborty · 2018
Enterprise data center architectures have gone through a major change during the last couple of years with widespread developments of software defined platforms and virtualization technologies, in the form of storage virtualization and network virtualization. As a consequence, the industries are gradually being shifted towards a shared storage software defined data center (SDDC) platform, where all the resources like computing, storage and network are virtualized within a single box and managed by a single controller. However, with such kind of shared storage architecture, network can be a performance bottleneck, as the network also needs to carry the storage workload. Because of this reason, virtual machine (VM) migration over a started storage SDDC platform can be an issue in the presence of storage workload. In this paper, we provide a thorough performance study of VM migration performance over shared storage SDDC platform under various different types of workloads. We first discuss a methodology to develop a shared storage SDDC platform using open source softwares and tools, and then perform thorough experimentation of VM migration performance in terms of application quality of service (QoS) under various different workloads. We observe that VM migration with either network or storage workload may get affected due to shared storage data synchronization over the network. From this performance analysis, we conclude that although shared storage SDDC provides a flexible, cost-effective, energy-efficient and easy-manageable solution for data centers, there are multiple performance bottlenecks that need to be addressed for getting the best out of it.