The world wide web has achieved immense popularity in the business world. Businesses are experiencing heavy bursts of traffic, causing a depreciation in revenues. It is thus essential to characterize the traffic behavior at these sites, a study that will facilitate the design and development of high-performance, reliable e-commerce servers. This thesis makes an effort in this direction.; Aggregated traffic arriving at a Business-to-Business (B2B) and a Business-to-Consumer (B2C) e-commerce site was collected and analyzed. High degree of self-similarity was found in the traffic (higher than that observed in web-environment). Heavy-tailed behavior of transfer times was established at both the sites. Traditionally this behavior has been attributed to the distribution of transfer sizes, which was not the case in B2C space. This implies that the heavy-tailed transfer times are actually caused by the behavior of back-end service time. An approach to reduce the burstiness in back-end service time was proposed, which splits the buffer cache to hold files with a maximum size restriction.; In B2B space, transfer-sizes were found to be heavy-tailed. Further study will be needed to split such a buffer cache with heavy-tailed arrivals. However, the effect of buffer cache on the service time was found to be negligible in B2B space, since a very high cache read hit ratio (99%) was seen. This workload characterization is a starting point for further studies. Inferences of this study can be further analyzed to aid in the design of high-performance e-commerce servers.
展开▼
