vSpec： workload-adaptive operating system specialization for virtual machines in cloud computing

• Published in: Science China. Information sciences 2016-09, Vol.59 (9), p.43-58, Article 92105
• Main Authors: Zhao, Xinkui, Yin, Jianwei, Chen, Zuoning, He, Sheng
• Format: Article
• Language: English
• Subjects: Adaptive systems; Cloud computing; Computer Science; Configurations; Information Systems and Communication Service; Kernel functions; Operating systems; Performance evaluation; Research Paper; Virtual environments; Workload; Workloads; 专业化; 工作负载; 应用程序; 操作系统; 系统调用; 自适应模型; 虚拟机; 计算平台
• ISSN: 1674-733X; 1869-1919
• DOI: 10.1007/s11432-015-5387-6

In general, operating systems（OSs） are designed to mediate access to device hardware by applications. They process different kinds of system calls using an indiscriminate kernel with the same configuration.Applications in cloud computing platforms are constructed from service components. Each of the service components is assigned separately to an individual virtual machine（VM）, which leads to homogeneous system calls on each VM. In addition, the requirements for kernel function and configuration of system parameters from different VMs are different. Therefore, the suit-to-all design incurs an unnecessary performance overhead and restricts the OS＇s processing capacity in cloud computing. In this paper, we propose an adaptive model for cloud computing to resolve the conflict between generality and performance. Our model adaptively specializes the OS of a VM according to the resource-consuming characteristics of workloads on the VM. We implement a prototype of the adaptive model, v Spec. There are five classes of VM： CPU-intensive, memory-intensive, I/O-intensive, networkintensive and compound, according to the resource-consuming characteristics of the workloads running on the VMs. v Spec specializes the OS of a VM according to the VM class. We perform comprehensive experiments to evaluate the effectiveness of v Spec on benchmarks and real-world applications.