Development of the distributed computing system for the MPD experiment at the NICA collider

Abstract

Experimental data processing and storing are topical issues in modern high energy physics experiments. Development of a distributed cluster based on the server farm of the Laboratory of high energy physics was started to accomplish these tasks in the MPD experiment at the NICA accelerator complex. This article describes the design approaches and methods of cluster development for storing and processing data obtained at the multipurpose detector. The current cluster scheme and structure are presented; software for building data storage and parallelization of the MPD event processing is noted. The article introduces two methods to parallelize data processing: using PROOF software tool of the ROOT environment and a scheduling system under development by the author.