Toward understanding soft faults in high performance cluster networks

Fault management in high performance cluster networks has been focused on the notion of hard faults (i.e., link or node failures). Network degradations that negatively impact performance but do not result in failures often go unnoticed. In this paper, we classify such degradations as soft faults. In addition, we identify consistent performance as an important requirement in cluster networks. Using this service requirement, we describe a comprehensive strategy for cluster fault management.