An approximate analytic performance model of object-based storage

Authors:
Qun Liu;Dan Feng
Affiliations:
Key Laboratory of Data Storage System, Ministry of Education, School of Computer, Huazhong University of Science and Technology, Wuhan, China;Key Laboratory of Data Storage System, Ministry of Education, School of Computer, Huazhong University of Science and Technology, Wuhan, China
Venue:
ICCSA'06 Proceedings of the 6th international conference on Computational Science and Its Applications - Volume Part I
Year:
2006

Citing 7
Cited 0

An analytic performance model of disk arrays

SIGMETRICS '93 Proceedings of the 1993 ACM SIGMETRICS conference on Measurement and modeling of computer systems
A decomposition approach for stochastic reward net models

Performance Evaluation
An analytic model of hierarchical mass storage systems with network-attached storage devices

Proceedings of the 1996 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Utilization of Disk Drives for RAID

APDC '97 Proceedings of the 1997 Advances in Parallel and Distributed Computing Conference (APDC '97)
Modeling and Performance Analysis of a Multiserver Multiqueue System on the Grid

FTDCS '03 Proceedings of the The Ninth IEEE Workshop on Future Trends of Distributed Computing Systems
A class of generalised stochastic petri nets for the performance evaluation of multiprocessor systems

SIGMETRICS '83 Proceedings of the 1983 ACM SIGMETRICS conference on Measurement and modeling of computer systems
Object-based storage

IEEE Communications Magazine

Quantified Score

Hi-index	0.00

Visualization

Abstract

The Object-based storage has emerged as an important new field, distinguished from traditional network storage architecture by its focus on large-scale storage resource sharing and high-performance orientation. This paper presents a Stochastic Petri Nets (SPN) model that can be used to evaluate the performance of the object-based storage. But the problem of state space’s explosion of SPN limits its ability to analyze complex and large-scale systems. An approximate analysis technique is proposed to replace the complexity model with the performance equivalence simplification model. This simplified model was used to validate the both well scalability and high performance of the OBS as the number of clients and OSD nodes increase.