Showing papers by "Derrick Kondo published in 2014"
TL;DR: A novel prediction method with Bayes model is designed to predict a load fluctuation pattern over a long-term interval, in the context of Google data centers, and an exponentially segmented pattern model for the hostload prediction is devised.
54 citations
TL;DR: A model that can simulate Google jobs/tasks and dynamic events, in accordance with Google trace is built and experiments show that the tasks simulated based on the model exhibit fairly analogous features with those in Google trace.
Abstract: In this paper, we characterize and model Google applications and jobs, based on a 1-month Google trace from a large-scale Google data center. We address four contributions: (1) we compute the valuable statistics about task events and resource utilization for Google applications, based on various types of resources and execution types; (2) we analyze the classification of applications via a K-means clustering algorithm with optimized number of sets, based on task events and resource usage; (3) we study the correlation of Google application properties and running features (e.g., job priority and scheduling class); (4) we finally build a model that can simulate Google jobs/tasks and dynamic events, in accordance with Google trace. Experiments show that the tasks simulated based on our model exhibit fairly analogous features with those in Google trace. 95+ % of tasks' simulation errors are $$<$$ < 20 %, confirming a high accuracy of our simulation model.
48 citations
TL;DR: This work determines whether one can optimize both makespan and reliability simultaneously, or whether one metric must be degraded in order to improve the other, and devise scheduling algorithms for achieving (approximately) optimal makespan or reliability.
6 citations