计算机科学与探索 ›› 2014, Vol. 8 ›› Issue (11): 1304-1313.DOI: 10.3778/j.issn.1673-9418.1402039

• 学术研究 • 上一篇    下一篇

基于多任务下载的P2P-VoD系统的测量与分析

刘春阳1,张铁赢2,3+,陈国耀4,余智华2,3   

  1. 1. 国家计算机网络应急技术处理协调中心,北京 100031
    2. 中国科学院 计算技术研究所,北京 100190
    3. 中国科学院 网络数据科学与技术重点实验室,北京 100190
    4. 神华科学技术研究院,北京 102211
  • 出版日期:2014-11-01 发布日期:2014-11-04

Measurements and Analysis of Multi-Task P2P-VoD Systems

LIU Chunyang1, ZHANG Tieying2,3+, CHEN Guoyao4, YU Zhihua2,3   

  1. 1. National Computer Network Emergency Response Technical Team Coordination Center of China, Beijing 100031, China
    2. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
    3. Key Laboratory of Network Data Science and Technology, Chinese Academy of Sciences, Beijing 100190, China
    4. Shenhua Science and Technology Research Institute, Beijing 102211, China
  • Online:2014-11-01 Published:2014-11-04

摘要: 近些年,P2P点播系统(P2P-VoD)受到广泛关注,其大多研究工作基于理论性的传统假设,这些假设在真实的系统中是如何表现的不得而知。因此,在真实P2P-VoD系统中对传统假设进行全面的测量和验证就显得十分迫切。对实际运行的P2P-VoD系统CoolFish进行了大量的测量与分析,发现了一些不同于以往假设的结果:节点加入不是简单地服从泊松分布;观看时间和影片流行度不呈严格的正相关性;跳转频率和影片流行度不呈负相关。最后对这些结果进行了深入的分析和讨论。

关键词: peer-to-peer(P2P), 视频点播(VoD), 流媒体, P2P评价模型

Abstract: P2P-VoD systems have gained tremendous popularity in recent years. Existing research is mostly based on the traditional theoretical assumptions. However, what is the performance of these assumptions is not known in the real world. It is particularly valuable to understand how the real-world system works. This paper presents a comprehensive measurement and analysis on CoolFish, a real deployed P2P-VoD system, and proposes some statistical models different from the traditional observations on user behavior: the access pattern does not match Poisson distribution; session time does not have positive correlation with movie popularity; jump frequency does not have a negative correlation with movie popularity as assumed in previous studies. This paper analyzes the reasons for these results.

Key words: peer-to-peer (P2P), video-on-demand (VoD), streaming, P2P evaluation model