To Schedule or to Execute: Decision Support and Performance Implications

This paper addresses a fundamental trade-off in dynamic scheduling between the cost of scheduling and the quality of the resulting schedules. The time allocated to scheduling must be controlled explicitly, in order to obtain good-quality schedules in reasonable times. As task constraints are relaxed, the algorithms proposed in this paper increase scheduling complexity to optimize longer and obtain high-quality schedules. When task constraints are tightened, the algorithms adjust scheduling complexity to reduce the adverse effect of long scheduling times on the schedule quality. We show that taking into account the scheduling time is crucial for honoring the deadlines of scheduled tasks. We investigate the performance of our algorithms in two scheduling models: one that allows idle-time intervals to exist in the schedule and another that does not. The model with idle-time intervals has important implications for dynamic scheduling which are discussed in the paper. Experimental evaluation of the proposed algorithms shows that our algorithms outperform other candidate algorithms in several parameter configurations.     

Computer science research in India

The computer industry is playing an increasingly important role in India's economy. However, for a number of reasons, many researchers are not doing high-quality work. Computer science research in India takes place at academic, government-sponsored, and industry-sponsored institutions. These major institutions can conduct effective research because they have sufficient funding, high-quality programs, good equipment, and an effective infrastructure. This is not the case at India's many other institutions. Many local observers say that Indian computer scientists make advances in existing areas of research but rarely do cutting-edge work. This occurs, in part, because many Indian computer scientists receive little direction and have few co-workers in their fields, which means they work in relative isolation     

Accelerating dynamic Web content generation

As a middle-tier, server-side caching engine, the dynamic content accelerator reduces dynamic page-generation processing delays by caching fragments of dynamically generated Web pages. This fragment-level solution, combined with intelligent cache management strategies, can significantly reduce the processing load on the Web application server, letting it handle higher user loads and thus significantly outperforming existing middle-tier caching solutions.     

Guest Editors' Introduction: Dynamic Information Dissemination

Dissemination and delivery of rapidly changing information to large user communities remains a challenge on the Web. Consequently, we need techniques to disseminate such data as efficiently as possible. To this end, researchers are focusing on new approaches to building efficient, resilient, and scalable content-distribution networks.     

A local area network architecture for communication in distributed real-time systems

Distributed real-time systems of the future will require specialized network architectures that incorporate new classes of services and protocols in order to support time-constrained communication. In this paper, we propose a new local area network architecture for such systems. This four-layered architecture is characterized by new classes of connection-oriented and connectionless services that take into account the timing constraints of messages. We describe various aspects of the logical link control layer of the architecture and various real-time protocols that may be employed at the medium access control layer in order to support the new classes of services. We also describe a homogeneous approach to the implementation of medium access control protocols to support both connection-oriented and connectionless services, based on a uniform window splitting paradigm.     

关于实时数据库事务

实时数据库事务显示了与传统数据库事务的很大不同．这些不同主要表现在事务的复杂结构、定时特性、相关性和正确性方面．本文先分析了实时数据库事务的应用特征与需求，并给出了一个复杂事务结构的框架，然后着重讨论实时事务间的相关性：结构相关、数据相关、行为相关，以及实时事务的结果、结构、行为及时间正确性．     

ReDAL: An Efficient and Practical Request Distribution Technique for Application Server Clusters

Modern Web-based application infrastructures are based on clustered multitiered architectures, where request distribution occurs in two sequential stages: over a cluster of Web servers and over a cluster of application servers. Much work has focused on strategies for distributing requests across a Web server cluster in order to improve the overall throughput across the cluster. The strategies applied at the application layer are the same as those at the Web server layer because it is assumed that they transfer directly. In this paper, we argue that the problem of distributing requests across an application server cluster is fundamentally different from the Web server request distribution problem due to core differences in request processing in Web and application servers. We devise an approach for distributing requests across a cluster of application servers such that the overall system throughput is enhanced, and load across the application servers is balanced.     

Mobile user recovery in the context of Internet transactions

With the expansion of Web sites to include business functions, a user interfaces with e-businesses through an interactive and multistep process, which is often time-consuming. For mobile users accessing the Web over digital cellular networks, the failure of the wireless link, a frequent occurrence, can result in the loss of work accomplished prior to the disruption. This work must then be repeated upon subsequent reconnection - often at significant cost in time and computation. This "disconnection-reconnection-repeat work" cycle may cause mobile clients to incur substantial monetary as well as resource (such as battery power) costs. In this paper, we propose a protocol for "recovering" a user to an appropriate recent interaction state after such a failure. The objective is to minimize the amount of work that needs to be redone upon restart after failure. Whereas classical database recovery focuses on recovering the system, i.e., all transactions, our work considers the problem of recovering a particular user interaction with the system. This recovery problem encompasses several interesting subproblems: (1) modeling user interaction in a way that is useful for recovery, (2) characterizing a user's "recovery state", (3) determining the state to which a user should be recovered, and (4) defining a recovery mechanism. We describe the user interaction with one or more Web sites using intuitive and familiar concepts from database transactions. We call this interaction an Internet transaction (iTX), distinguish this notion from extant transaction models, and develop a model for it, as well as for a user's state on a Web site. Based on the twin foundations of our iTX and state models, we finally describe an effective protocol for recovering users to valid states in Internet interactions.     

What is predictability for real-time systems?

Conclusion In summary, predictability in real-time systems has been defined in many ways. For static real-time systems we can predict the overall system performance over large time frames (even over the life of the system) as well as predict the performance of individual tasks. If the prediction is that 100% of all tasks over the entire life of the system will meet their deadlines, then the system is predictable without resorting to any stochastic evaluation. In dynamic real-time systems we must resort to a stochastic evaluation for part of the performance evaluation. Predictability for these systems should mean that we are able to satisfy the timing requirements of critical tasks with 100% guarantee over the life of the system, be able to assess overall system performance over various time frames (a stochastic evaluation), and be able to assess individual task and task group performance at different times and as a function of the current system state. If all these assessments meet the timing requirements, then the system is predictable with respect to its timing requirements.This work was supported by ONR under contract N00014-85-K-0389 and NSF under grants DCR-8500332 and IRI-8908693.