Operators of big data clusters face the problem of understanding the types of applications that run on these clusters in order to better predict runtimes, tune resource utilization, and increase efficiency. Unfortunately, application developers seldom provide meaningful information to accomplish this task. They may provide a descriptive name but leave the rest for the operators to discern.
Ash Munshi outlines a technique for labeling applications using runtime measurements of CPU, memory, and network I/O along with a deep neural network. This labeling groups the applications into buckets that have understandable characteristics, which can then be used to reason about the cluster and its performance. For example, members of a single group can be studied to understand variability in runtime, effects of different queue assignments, effects of the underlying system hardware architecture, and even the effects of start times for periodic applications.
The machine learning techniques presented are new and represent the first approach to classify multivariate time series. The data for the models comes from observing over 22,000 servers and all of their task metrics every five seconds for months.
Ash Munshi is CEO of Pepperdata. Previously, Ash was executive chairman for deep learning startup Marianas Labs (acquired by Askin in 2015); CEO of big data storage startup Graphite Systems (acquired by EMC DSSD in 2015); CTO of Yahoo; and CEO of a number of other public and private companies. He serves on the board of several technology startups.
For exhibition and sponsorship opportunities, email strataconf@oreilly.com
For information on trade opportunities with O'Reilly conferences, email partners@oreilly.com
View a complete list of Strata Data Conference contacts
©2018, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • confreg@oreilly.com