Lightweight job submission and file sharing schemes for a teaching ecosystem for parallel computing courses

Abstract

Parallel computing has been widely used in various industries. Many colleges and universities have launched courses on parallel computing and can build teaching ecosystems to serve these courses. Job submission and file sharing are two essential functionalities. This paper builds a teaching ecosystem for parallel computing courses and proposes lightweight job submission and file sharing schemes for the ecosystem. The job submission scheme supports Pthread, OpenMP, and MPI (message passing interface) jobs. It has five working modes: demonstration, experiment, examination, research, and maintenance. In particular, the examination mode can be applied for online examinations. For the fair use of resources, the job submission scheme not only limits the submission times of each student and the run time of each job but also designs a fair job scheduling algorithm. The ecosystem adopts Samba to supply file sharing services. To ensure the safety of the shared files, this paper proposes a lightweight attribute-based access control mechanism. This mechanism uses Python logical expressions to describe access rules; thus, it is not only easy to use but also able to describe complicated rules. In addition, the ecosystem has a well-structured module design that facilitates functionality expansion and modification. Experiments verify the feasibility and validity of the ecosystem.