HammerCloud at CERN

I was a 2015 CERN Summer Student, working with CERN’s supercomputers to manage infrastructure for the LHCb experiment. The project I worked on, HammerCloud, tracks server statistics and system health for the WLCG (Worldwide Large Hadron Collider Computing Grid), the largest supercomputer grid in the world. The software acts as a distributed analysis testing system, sending test jobs to each of the supercomputer sites and ensuring that disk access and the job queue are functioning as desired. HammerCloud can help diagnose and resolve both intermittent and systemic failures.