A Service for Reliable Execution of Grid Applications
A Service for Reliable Execution of Grid Applications
复制标题
用于可靠执行网格应用程序的服务
DOI：
10.1007/978-0-387-72812-4_14
复制
发表时间：
2006
期刊：
影响因子：
--
通讯作者：
Rosa M. Badia
中科院分区：
文献类型：
--
作者：
Elzbieta Krepska;T. Kielmann;R. Sirvent;Rosa M. Badia
在网格环境中，由于应用程序执行涉及大量组件（硬件和软件），这些组件中至少一个（暂时）无法正常工作的总体概率正在迅速增加。在传统操作系统中，此类故障被标记为致命故障，应用程序将被停止，并在问题解决后重新启动。在大型网格系统中，这不是一种可行的方法，因为故障发生得太频繁，而错误诊断可能根本不可能。这种情况要求采用不同的应用程序执行方法，其中错误条件的检测和规避成为不可或缺的一部分。我们提供了一项跟踪应用程序生命周期的服务，从用户提交到成功完成其执行。在案例研究中，我们描述了 GRID 超标量（一种网格应用程序编程环境）如何从我们的服务中受益。
In grid environments, with the large number of components (both hardware and software) that are involved in application execution, the overall probability that at least one of these components is (temporarily) non-functional is increasing rapidly. In traditional operating systems, such failures are flagged as fatal and the application will be stopped, relying on a re-start after the problem will have been fixed. In a large grid system, this is not a feasible approach as failures happen too frequently while error diagnostics might not be possible at all.This scenario is asking for a different approach to application execution, where detection and circumvention of error conditions become an integral part. We present a service that is keeping track of an application’s life cycle, from submission by the user to successful completion of its execution. In a case study, we describe how GRID superscalar, a grid application programming environment, can benefit from our service.