INVESTIGADORES
MOCSKOS Esteban Eduardo
congresos y reuniones científicas
Título:
Clover: Efficient Monitoring of HPC Clusters
Autor/es:
DAMIÁN MONTALDO; ESTEBAN MOCSKOS; DIEGO FERNÁNDEZ SLEZAK
Lugar:
Mar del Plata
Reunión:
Simposio; HPCS 2009, 38th Argentine Conference on Informatics and Operational Research; 2009
Institución organizadora:
Sociedad Argentina de Investigación Operativa
Resumen:
As a consequence of the last decade evolution of computational power and the proliferation of clusters, i.e. collection of interconnected personal computers, system monitoring has become a critical and non-trivial task.Specialized protocols have been developed to provide cluster state information without degradation of performance and avoiding the consumption of computational power.Clover is a system monitoring tool designed on a plugin architecture based on the CluMon project, a tool developed at the NCSA.The main goal is to allow the verification of the cluster state at a glance.It includes a plugin implemented over the IPMI protocol to collect data with almost no CPU-cycle consumption.The aim of this paper is to show the clover current state of development.Furthermore, the benefits of using IPMI in monitoring activities are verified running the simulation of the heat equation as a test application in both shared and distributed memory architectures.The results obtained suggest that the use of specialized hardware protocols for sensoring and monitoring would save valuable CPU cycles.