Storage Management in Virtualized Cloud Environment

Abstract

Abstract-With Cloud Computing gaining tremendous importance in the recent past, understanding low-level implications of the cloud infrastructure becomes necessary. One of the key technologies deployed in large Cloud infrastructures namely the Amazon EC2 for providing isolation and separate protection domains for multiple clients is virtualization. Therefore, identifying the performance bottlenecks in a virtualized setup and understanding the implications of workload combinations and resource configurations on the overall I/O performance helps both the cloud providers in managing their infrastructure efficiently and also their customers by means of better performance.In this paper we present the measurement results of detailed experiments conducted on a virtualized setup focusing on the storage I/O performance. We categorize our experimental evaluation into four components, each of which presenting some significant factors that affect storage I/O performance. Our experimental results can be useful for cloud application developers to tune their applications for better I/O performance and for the cloud service providers to make more effective decisions on resource provisioning and workload scheduling.

Impact of memory intensive applications on performance of cloud virtual machine

“…evaluating the impact of input output block size, workload interference that is choosing the right workload for right machine etc. [9].Wang et al has studied the impact of different virtual network configurations on three types of workloads that is CPU intensive (tightly and loosely coupled both) and network intensive workload [10]. They have proved that to prevent poor performance regions the total number of virtual CPUs has to be larger than the number of processors (e.g., twice), and the total virtual memory allocated to VMs has to be less than physical memory.…”

Performance Analysis of Network I/O Workloads in Virtualized Data Centers

“…For example, some work has focused on I/O performance improvement by tuning I/O related parameter [11], [13], [17], [25], [26], [32], [39], such as TCP Segmentation Offload (TSO), network bridging. Recently, some study showed that performance interference exists among multiple virtual machines running on the same physical host due to the shared use of computing resources [5], [23], [36], [37] and the implicit resource scheduling of different virtual machines done by VMM in the privileged driver domain [19]. For example, in current Xen implementation, all the I/O requests have to be processed by the driver domain, and Xen does not explicitly differentiate the Dom 0 CPU usage caused by I/O operations for each guest domain.…”

“…However, several studies have documented that current implementation of VMMs does not provide sufficient performance isolation to guarantee the effectiveness of resource sharing, especially when the applications running on multiple VMs of the same physical machine are competing for computing and communication resources [2], [19], [23], [36], [37]. As a result, both cloud consumers and cloud providers may suffer from unexpected performance degradation in terms of efficiency and effectiveness of application execution or server consolidation.…”

A Cost-Effective Intelligent Configuration Model in Cloud Computing

“…The storage I/O performance has been measured based on the virtualized setup experiments of Amazon EC2. The performance bottlenecks in a virtual setup can be identified, the workload combination can be understood and resource configurations on the I/O performance can be used to manage the infrastructure efficiently [10]. The new performance measuring method for IaaS takes into account the type of service running in a virtual machine.…”