No abstract

The resource discovery management unit (RD) in distributed Exascale systems needs to be able to manage the occurrence of dynamic and interactive events in the requesting process when running activities related to RD. The occurrence of dynamic and interactive events in the requesting process causes some challenges in the execution trend of activities related to RD. The trend of execution activities related to RD will fail if there is no management and control on the occurrence of dynamic and interactive events. This paper first explores and describes the concept of dynamic and interactive nature in distributed Exascale systems. In addition, it attempts to show the influences of occurrence the dynamic and interactive events in the computing elements requesting the resource as well as on RD functionality. In addition, this paper aims at describing the challenges of RD to be used in distributed Exascale systems. To achieve this, changes need to be made in the generating space and RD functionality. Taking into account the solutions presented in this paper, RD has the potential to be used in distributed Exascale systems by remaining compatible with traditional computing systems.

Resource discovery in distributed Exascale computing systems, in addition to managing events resulting in failures due to not finding the resource, as well as failure to perform resource discovery activities at the acceptable time, needs to be able to manage events resulting in failures due to dynamic and interactive nature as well. While investigating the concept of dynamic and interactive nature and its impact on RD functionality, this paper introduces a mathematical model of events resulting in RD failure in this type of computing systems based on descriptive spaces of RD activities. This mathematical model helps to analyze this issue that in what situations the dynamic and interactive nature would lead to the failure of RD and what capabilities RD should have to prevent the failure.

No abstract

No abstract