Title :
Performance Analyzing and Predicting of Network I/O in Xen System
Author :
Jianhua Che ; Wei Yao ; Shougang Ren ; Haoyun Wang
Author_Institution :
Coll. of Inf. Sci. & Technol., Nanjing Agric. Univ., Nanjing, China
Abstract :
The network I/O operations of a guest domain spend Domain0´s processor resource as well as its own processor resource. If no control is placed on the network I/O operations of guest domains, Xen system will likely overload when executing network I/O-intensive workload. To resolve this problem, the allowable network I/O request number of Xen system should be firstly figured out. This paper illuminated the characteristic of Xen system in handling the network I/O operations of guest domains with two experimental results, and established several performance analyzing and predicting models by studying the network I/O procedure and the processor resource consumption distribution of Xen system. These models can compute the allowable number of guest domains with fixed network I/O request number or the allowable network I/O request number of each guest domain based on all idle processor resource of Xen system, and prevent Xen system from overloading. Finally, the applicability of these models is preliminarily analyzed.
Keywords :
input-output programs; resource allocation; software performance evaluation; virtual machines; Xen system; allowable network I/O request number; guest domains; idle processor resource; network I/O operations; network I/O performance analysis; network I/O prediction model; processor resource consumption distribution; Analytical models; Computational modeling; Educational institutions; Equations; Mathematical model; Predictive models; Virtualization; Xen; availability; performance model; virtualization;
Conference_Titel :
Dependable, Autonomic and Secure Computing (DASC), 2013 IEEE 11th International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4799-3380-8
DOI :
10.1109/DASC.2013.139