Machine Learning for Predictive Analytics of Compute Cluster Jobs
This addresses resource allocation inefficiencies in HPC clusters for users and administrators, but it appears incremental as it applies existing methods to a new dataset.
The paper tackles predicting job failures due to insufficient memory and CPU resources at submission time using supervised machine learning, with preliminary results showing that job failure probability is associated with information available at submission time.
We address the problem of predicting whether sufficient memory and CPU resources have been requested for jobs at submission time. For this purpose, we examine the task of training a supervised machine learning system to predict the outcome - whether the job will fail specifically due to insufficient resources - as a classification task. Sufficiently high accuracy, precision, and recall at this task facilitates more anticipatory decision support applications in the domain of HPC resource allocation. Our preliminary results using a new test bed show that the probability of failed jobs is associated with information freely available at job submission time and may thus be usable by a learning system for user modeling that gives personalized feedback to users.