论文部分内容阅读
近来计算机和通信技术的发展使得视频点播（ｖｉｄｅｏ－ｏｎ－ｄｅｍａｎｄ，简称ＶＯＤ）在技术和经济上成为可能．连续媒体的特性使得ＶＯＤ系统需要大规模的存储服务器．层次化存储体系是减少系统费用的合理方案．文章提出了一种层次化的存储模型和磁盘ｃａｃｈｅ的概念．根据这个模型，提出了基于访问频率的替换算法，并对算法的有效性进行了模拟和分析．结果表明，这种算法解决了ＬＦＵ（ｌｅａｓｔｆｒｅｑｕｅｎｔｌｙｕｓｅｄ）算法中的“ｃａｃｈｅ污染”（ｃａｃｈｅｐｏｌｕｔｉｏｎ）问题，能较好地适用于连续媒体数据应用．
Recently, the development of computer and communication technologies has made video-on-demand (VOD) technically and economically possible. The continuous media features make VOD systems require large-scale storage servers. Hierarchical storage system is a reasonable solution to reduce system costs. The article presents a hierarchical storage model and the concept of disk cache. According to this model, a replacement algorithm based on access frequency is proposed, and the validity of the algorithm is simulated and analyzed. The results show that this algorithm solves the problem of “cache pollution” in the least frequently used algorithm (LFU) and can be applied to continuous media data applications.