Understanding Customer Dissatisfaction with Underutilized Distributed File Servers

An important trend in the design of storage subsystems is a move toward direct network attachment. Network-attached storage offers the opportunity to off-load distributed file system functionality from dedicated file server machines and execute many requests directly at the storage devices. For this strategy to lead to better performance, as perceived by users, the response time of distributed operations must improve. In this paper we analyze measurements of an Andrew file system (AFS) server that we recently upgraded in an effort to improve client performance in our laboratory. While the original server's overall utilization was only about 3%, we show how burst loads were sufficiently intense to lead to period of poor response time significant enough to trigger customer dissatisfaction. In particular, we show how, after adjusting for network load and traffic to non-project servers, 50% of the variation in client response time was explained by variation in server central processing unit (CPU) use. That is, clients saw long response times in large part because the server was often over-utilized when it was used at all. Using these measures, we see that off-loading file server work in a network-attached storage architecture has to potential to benefit user response time. Computational power in such a system scales directly with storage capacity, so the slowdown during burst period should be reduced.