Mining for misconfigured machines in grid systems

Grid systems are proving increasingly useful for managing the batch computing jobs of organizations. One well known example for that is Intel which uses an internally developed system called NetBatch to manage tens of thousands of machines. The size, heterogeneity, and complexity of grid systems are extreme. Therefore, these systems are very difficult to configure. This often results in part of the machines being inadequately set-up. Such misconfigured machines can have adverse effects on the entire system. We investigate a distributed data mining approach for detection of misconfigured machines. Our Grid Monitoring System (GMS) non-intrusively collects data from all available sources (log files, system services, etc.) available throughout the grid system. It converts raw data to data with ontological meaning and stores the resulting data on the machine it was obtained from; thus, limiting incurred overhead and allowing scalability. Following, when analysis is requested, a distributed...

• Type: Conference
• Year: 2006
• Where: KDD
• Authors: Noam Palatin, Arie Leizarowitz, Assaf Schuster, Ran Wolff
• Keywords: Data Mining, Grid Systems, KDD 2006, Large Grid Systems, Such Misconfigured Machines