PUSH THE BOTTLENECK OF STREAMING MEDIA SYSTEM FROM STREAMING MEDIA SERVER TO NETWORK

Author:

DENG YUHUI12,WANG FRANK1,ZHANG JIANGLING2,FENG DAN2,WANG FANG2,JIANG HONG3

Affiliation:

1. Center for Grid Computing, Cambridge-Cranfield, High Performance Computing Facilities (CCHPCF), Cranfield University Campus, Bedfordshire MK430AL, United Kingdom

2. School of Computer Science, Huazhong University of Science and Technology, Wuhan 430074, PRC

3. Department of Computer Science and Engineering, University of Nebraska-Lincoln, Lincoln, Nebraska, USA

Abstract

Streaming media is pervasive on the Internet now and it continues to grow rapidly. Most streaming media systems have adopted a typical system architecture in which the storage devices are attached privately to the streaming media server. Unfortunately, with the steady growth of Internet subscribers, the streaming media server quickly becomes a system bottleneck. This paper proposes an innovative, high performance streaming media system architecture (HPSMS) based on the logical separation in the streaming media transport protocol. The architecture avoids expensive store-and-forward data copying between the streaming media server and storage devices. The most salient feature of HPSMS is that the architecture eliminates the streaming media server bottleneck, while dynamically increasing system bandwidth with the expansion of storage system capacity. The system performance of the proposed HPSMS is evaluated through a prototype implementation.

Publisher

World Scientific Pub Co Pte Lt

Subject

Computer Graphics and Computer-Aided Design,Computer Science Applications,Computer Vision and Pattern Recognition

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Deconstructing Network Attached Storage systems;Journal of Network and Computer Applications;2009-09

2. Exploring the performance impact of stripe size on network attached storage systems;Journal of Systems Architecture;2008-08

3. A heterogeneous storage grid enabled by grid service;ACM SIGOPS Operating Systems Review;2007-01

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3