Extracting message types from BlueGene/l’s logs

Abstract—In this paper we present the results on extracting message types from the BlueGene/L supercomputer logs using the IPLoM (Iterative Partitioning Log Mining) algorithm. Previous work using IPLoM indicates that IPLoM shows promise as message type extraction algorithm. We compared the results of IPLoM against manually produced message types produced on the BlueGene/L data. To provide a baseline of performance we also perform similar experiments using SLCT (Simple Log File Clustering Tool). The results show that IPLoM improves the performance of SLCT by finding the infrequent patterns in the data and is also able to achieve an F-Measure result of 91% based on micro-average classification accuracy. I