【摘要】 任务管理和错误恢复是CFD网格应用平台的核心部分,它对运行在平台上的CFD程序进行管理,并提供错误恢复机制。为了更好地管理CFD任务,平台通过建立CFD程序抽象模型,对任务管理和错误恢复模块进行设计上的优化。因此该模块采用了双层架构,上层实现了对服务的管理,下层负责对并行程序的管理。同时该模块还提供了守护进程CFD-Daemon来实现错误恢复,以及应用开发包供CFD程序员使用。更多还原

【Abstract】 Job management and fault recovering is the kernel of the CFD application platform,managing the CFD programs running on platform,and providing the fault recovering mechanism to them.To manage the CFD programs much better,by building the CFD program abstract model,the platform optimizes the design of job management and fault recovering.Thus the module adopts the two-level architecture:high level for managing the services and low level for parallel programs.It also provides a Daemon program called CFD-Daemon to handle the fault recovering,and an application development package which can be used by CFD programmers.更多还原