Computing Seminar

Performance monitoring with AFFAIR

Tome Anticic, Rudjer Boskovic Institute, Zagreb

Abstract

It is becoming increasingly important to be able to efficently and easily monitor the system performance of a very large computing fabric, and also the applications running on it.

I present in this talk AFFAIR, the performance monitoring software developed by the ALICE Data Acquisition project. AFFAIR is largely based on open source code and is composed of the following components: data gathering, inter-node communication employing DIM, fast and temporary round robin database storage, and permanent storage and plot generation using ROOT. Real time data is monitored via a PHP generated web interface.

AFFAIR is successfully used during the ALICE Data Challenge. It is scalable to hundreds of nodes, robust, easy to maintain, flexible, and has low network and CPU requirements.

About the speaker: Tome Anticic earned his doctorate at the Johns Hopkins University in 1997, working at the L3 experiment. For the past two years he has been involved in the ALICE DAQ team, where he is leading the effort to develop a detailed simulation of the ALICE Data Acquisition and Trigger. He is also in charge of creating AFFAIR to monitor the ALICE Data Acquisition System.