东篱科研大数据发现系统（DRDS）

位置：成果数据库 > 期刊 > 期刊详情页

一种IA-64架构下的大规模流媒体服务器缓存调度算法

期刊名称：计算机研究与发展, 43(4):729-737, 2006.4
时间：0
分类：TP338.8[自动化与计算机技术—计算机系统结构;自动化与计算机技术—计算机科学与技术] TP37[自动化与计算机技术—计算机系统结构;自动化与计算机技术—计算机科学与技术]
作者机构：[1]清华大学计算机科学与技术系,北京100084, [2]北京世纪鼎点软件有限公司,北京100084
相关基金：国家自然科学基金项目（60433040）This paper is supported by the Natural Science Foundation of China under grant No. 60433040. The main purpose of the research is to improve the capacity of video streaming services to support more simultaneous users. It has three main parts. The first one is to understand the user behavior in large-scale video-on-demand services by analyzing the user log in real commercial system. The second is to improve the single server capacity of video services. The last one is to use state-of-art decentralized architecture like peer-to-peer to improve the performance of a whole video-on-demand system, Among these serial studies, technique like buffer management plays a very important role in it. Up to now, we have designed a two-level P2P architecture which is composed of some super peers and many common peers for video-on-demand services. The super peers can be regarded as a kind of media servers, They provide a high quality service to common peers, and responsible for other issues such as common peer management, and information exchanges. The common peers include all client machines. They require the media they need in the system, and broadcast them to other suitable peers. Strategies like multi-server cooperation, fault-tolerant, and QoS ensuring are being studied. With the cooperation with one of the leading video streaming software providers in China, Powerinfo, all results will be applied and tested in real commercial system too.
相关项目：对等计算及广域网虚拟平台

关键词：流媒体, 缓存管理, IA-64, video streaming, buffer management, IA-64

中文摘要：

在大规模流媒体服务中，缓存管理是非常关键的问题．特别是随着IA-64架构的出现，物理内存的大小可大大得到增加，缓存管理策略正变得越来越重要．目前已经有很多缓存管理算法，其中间隔缓存策略通常被认为是比较有效的一个．但是以往的各种基于间隔的算法大多没有考虑媒体对象的流行程度，致使缓存的利用率受到了影响．通过对媒体对象的流行程度的特点进行研究，并考虑到利用IA-64系统中的大内存的思想，提出了一种基于流行程度的间隔缓存策略．同时，为了分析该算法的性能，引入了一个算法的性能分析模型．分析结果显示该算法比传统的间隔缓存策略具有更好的性能.

英文摘要：

Buffer management is a very critical problem in large-scale video streaming servers. Especially with the appearance of IA-64, the physical memory size has increased up to 16 exabytes, so the buffer management becomes more and more important. There are already many caching policies, among which interval caching policy has been proposed as an effective one. But most of the previous interval-based policies don＇t consider the popularity of video objects, and the use of huge memories provided by IA-64 systems. The memory utilization is troubled by this. A popularity-based interval caching policy （PIC） is presented to solve the problem. It makes use of the huge memory in IA-64 systems and pays attention to the popularity of video objects. To study the performance of this policy, a static analytical model is given, and large amount of simulations are conducted. The results show that the PIC policy outperforms the traditional interval caching policy.

同期刊论文项目