Abstract

The development of science encourages an increase of experimental data, which subject to analysis to generate new knowledge. The current volume of computations often exceeds the capacities of a cluster to calculate for a satisfactory time; hence, it is necessary to distribute the computation of such amounts of data using the GRID systems.For the load balancing in such systems, the special mechanisms - brokers – are used. They implement a policy, under which such a system allocates tasks among computing resources according to the workload of computational resources in the system or according to properties of a task.To implement the algorithm of balancing the broker must take into account enough factors to find the most appropriate resource that is able to perform the task with the lowest possible load, or in minimal time. At the same time, regular news sources of the software that serves GRID system and extras not included in the standard package of the software can be used.The aim of this work is to develop strategies and architectures for distributed broker in Nordugrid ARC 2.0 using advanced possibilities of this platform - web services that run on the basis of the software platform and extend the functionality of the cluster software. The strategies developed should be of general purpose, therefore, they should not rely only on a certain type of tasks distributed among the available resources.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.