Characterizing temporal locality and its impact on web server performance
Characterizing temporal locality and its impact on web server performance
复制标题
DOI：
10.1109/icccn.2000.885525
复制
发表时间：
2000-10
期刊：
影响因子：
--
通讯作者：
L. Cherkasova;Gianfranco Ciardo
中科院分区：
文献类型：
--
作者：
L. Cherkasova;Gianfranco Ciardo
网络痕迹中的时间局部性的存在早已被认识到。但是，跟踪中对同一文件的请求非常接近可以归因于两个正交的原因：长期流行性和短期相关性。前者反映了这样一个事实，即对流行文档的请求出现“频繁”，因此它们在绝对意义上可能是“接近”的。后者反映了这样一个事实，即由于各种原因，如截止日期或用户兴趣激增，对给定文档的请求可能集中在跟踪中的特定点，因此它侧重于“相对”接近度。我们引入了一个新的时间局部性的措施，缩放堆栈距离，这是不敏感的流行和捕捉，而不是短期相关性的影响，并使用它来参数化的合成跟踪生成器。然后，我们通过比较对应于原始或合成轨迹的文件和字节未命中率来验证此量的适当性。
The presence of temporal locality in web traces has long been recognized. However, the close proximity of requests for the same file in a trace can be attributed to two orthogonal reasons: long-term popularity and short-term correlation. The former reflects the fact that requests for a popular document appear "frequently" thus they are likely to be "close" in an absolute sense. The latter reflects the fact that requests for a given document might concentrate around particular points in the trace due to a variety of reasons, such as deadlines or surges in user interests, hence it focuses on "relative" closeness. We introduce a new measure of temporal locality, the scaled stack distance, which is insensitive to popularity and captures instead the impact of short-term correlation, and use it to parameterize a synthetic trace generator. Then, we validate the appropriateness of this quantity by comparing the file and byte miss ratios corresponding to either the original or the synthetic traces.