Utilizing PAPI Features for Resource Requirement Prediction in Grid Environment

M. Sarkar, S. Roy, and N. Mukherjee (India)

Keywords

Grid, job modeling, resource allocation, PAPI.

Abstract

Grid is a distributed, dynamic, heterogeneous environment. Selection of appropriate resources for jobs in such an environment is complicated and challenging task. In order to support proper resource selection and high performance job execution, resource management is essential. Resource management identifies job modeling to be a very important part of it. A proper job modeling can be helpful to allocate jobs into their most suitable resource providers in Grid. Consequently, it assists to manage the execution of jobs as well as helps to achieve the desired level of high performance. This paper presents technical implementation details of job modeling technique which is based on execution history. Proposed job modeling technique utilizes PAPI features to gather hardware performance monitoring data of a job, which are later used for analyzing that job. Job modeling technique describes the process required to identify the most suitable resource provider for a particular job.

Important Links:



Go Back