CAREER: Broadcast Disks: Technique for Data in Management in Asymmetric Communication Environments

许多新兴的网络应用都具有节点间通信不对称的特性。通常，服务器可以和/或必须向客户端发送比客户端发送回服务器的数据多得多的数据。例如，具有移动客户端的无线网络、有线和直接卫星广播电视系统、信息传播和信息检索应用。广播盘技术通过将重复且循环地传输的广播数据流作为存储设备来利用这种环境的特性。这种方法的实质是在单个广播频道上叠加以不同速度旋转的多个广播节目(或磁盘)；实际上，创建了一个任意细粒度的内存层次结构。该技术还集成了客户端存储资源的使用，用于缓存和预取通过广播传送的数据。广播磁盘方法为非统一访问的数据提供了更高的性能，并提高了重要数据的可用性。该项目正在解决的挑战包括：广播节目生成、缓存和预取策略，以及适应不稳定的数据、不断变化的客户需求和通信错误。这项研究的结果将是这种新方法的技术、分析和原型实现，它有可能显著提高未来分布式计算系统的性能和可用性。该项目的教育部分旨在开发新的课程、软件工具和实验室，为各级学生在建立数据库系统和应用程序方面提供更直接的实践经验。

Many emerging networked applications have the property that communication among nodes is asymmetric. Typically, servers can and/or must send much more data to clients than clients send back to the servers. Examples include wireless networks with mobile clients, cable and direct satellite broadcast TV systems, information dispersal and information retrieval applications. Broadcast Disks technique exploits the characteristics of such environments, by treating a broadcast stream of data that are repeatedly and cyclicly transmitted as a storage device. The essence of this approach is to superimpose multiple broadcast programs (or `disks`) spinning at different speeds on a single broadcast channel; in effect, creating an arbitrarily fine-grained memory hierarchy. The technique also integrates the use of client storage resources for caching and prefetching data that is delivered over the broadcast. The Broadcast Disks approach provides improved performance for non-uniformly accessed data and increased availability of important data. The challenges being addressed in this project include: broadcast program generation, caching and prefetching strategies, and adapting to volatile data, changing client needs, and communication errors. The results of this research will be techniques, analyses, and prototype implementations of this novel approach, which has the potential to significantly improve the performance and availability of future distributed computing systems. The education portion of this project aims to develop new courses, software tools and laboratories that will provide students at all levels with more direct, hands-on experience in building database systems and applications.