Search

The last couple of years have seen a growing momentum toward using the Internet for conducting business. Web-based electronic commerce applications are one of the fastest growing segments of the Internet today. A key enabler for e-commerce applications is the ability to setup secure private channels over a public network. The Secure Sockets Layer protocol provides this capability and is the most widely used security protocol in the Internet. We take a close look at the working principles behind SSL with an eye on performance. We benchmark two of the popular Web servers in wide use in a number of large e-commerce sites. Our results show that the overheads due to SSL can make Web servers slower by a couple of orders of magnitude. We investigate the reason for this deficiency by instrumenting the SSL protocol stack with a detailed profiling of the protocol processing components. In light of our observations, we outline architectural guidelines for large e-commerce sites.

In this paper, we consider the change management process for enterprise IT services with the goal of improving the efficiency of this process, i.e., minimizing change completion time and maximizing the "change capacity". The change management process handles critical updates in the system that must be implemented by a set of executing personnel. In presence of such timing constraints and scheduling conflicts between change classes, we argue that addressing the application change management question optimally involves computing solutions to NP-hard problems. Using appropriate simulation models, we evaluate various batched scheduling alternatives to understand the effect of simple process re-engineering on the change completion time, and the change capacity of the system. In addition, we examine the benefit of executor cross-training and degree of conflicts on the performance of the system. Our results indicate that a simple longest queue based scheduling approach works well in a wide range of practical scenarios. Based on these results, we recommend process re-engineering based on longest queue based scheduling with a small degree of executor cross-training.

As more business applications have become web enabled, the web server architecture has evolved to provide performance isolation, service differentiation, and QoS guarantees. Various server mechanisms that provide QoS extensions, however, rely on external administrators to set the right parameter values for their desirable performance. Due to the complexity of handling varying workloads and bursty traffic, configuring such parameters optimally becomes a challenge. In this paper, we describe an observation-based approach for self-managing web servers that can adapt to changing workloads while maintaining the QoS requirements of different classes. In this approach, the system state is monitored continuously and parameter values of various system resources-primarily the accept queue and the CPU-are adjusted to maintain the system-wide QoS goals. We implement our techniques using the Apache web server and the Linux operating system. We first demonstrate the need to manage different resources in the system depending on the workload characteristics. We then experimentally demonstrate that our observation-based system monitors such as workload changes and adjusts the resource parameters of the accept queue and CPU schedulers in order to maintain the QoS requirements of the different classes.

Suez is a high-performance real-time packet router that supports fast best-effort packet routing and scalable QoS-guaranteed packet scheduling, and is built on a hardware platform consisting of a cluster of commodity PCs connected by a gigabit/sec system area network. The major goal of the Suez project is to demonstrate that the PC cluster architecture can be as cost-effective a platform for high-performance network packet routing as for parallel computing. Suez features a cache-conscious routing-table search algorithm that exploits CPU caching hardware for fast lookup by treating IP addresses directly as virtual addresses. To scale the number of real-time connections supportable with the link speed, Suez implements a fixed-granularity fluid fair queuing (FGFFQ) algorithm that completely eliminates the per-packet sorting overhead associated with conventional weighted fair queuing algorithms. This paper presents the architectural features of Suez, and reports the performance measurements of the Linux-based Suez prototype, which is built on four Pentium-II 400 MHz machines and Myrinet.

Server providers that support e-commerce applications as a service for multiple e-commerce Web sites traditionally use a tiered server architecture. This architecture includes an application tier to process requests for dynamically generated content. How this tier is provisioned can significantly impact a provider's profit margin. In this article we study methods to provision servers in the application serving tier that increase a server provider's profits. First, we examine actual traces of request arrivals to the application tier of an e-commerce site, and show that the arrival process is effectively Poisson. Next, we construct an optimization problem in the context of a set of application servers modeled as M / G /1/ PS queueing systems, and derive three simple methods that approximate the allocation that maximizes profits. Simulation results demonstrate that our approximation methods achieve profits that are close to optimal, and are significantly higher than those achieved via simple heuristics.