Presented By
O’Reilly + Cloudera
Make Data Work
March 25-28, 2019
San Francisco, CA
Please log in

When SQL users run wild: Resource management features and techniques to tame Apache Impala

Tim Armstrong (Cloudera)
5:10pm–5:50pm Wednesday, March 27, 2019
Data Engineering & Architecture
 Location: 2004
Average rating: ****.
(4.80, 5 ratings)
Download slides (PDF)

Who is this presentation for?

  • Cluster and system admins and DBAs

Level

Intermediate

Prerequisite knowledge

  • Basic familiarity with Apache Impala, particularly its Admission Control feature

What you'll learn

  • Understand how Impala resource management works and how to utilize it to keep your cluster healthy
  • Explore concrete examples of how to configure Impala on a real cluster

Description

Apache Impala has offered fast SQL analytics over big data since its initial beta release in 2012. As the popularity and utilization of Impala deployments increases, clusters often become victims of their own success when demand for resources exceeds the supply.

Tim Armstrong dives into the latest resource management features in Impala to maintain high cluster availability and optimal performance and provides examples of how to configure them in your Impala deployment. Tim also discusses ongoing work on Impala’s admission control to make workload management simpler, more flexible, and automatic, including how the setup of Impala admission control was streamlined and efforts to make out-of-memory errors a thing of the past.

Photo of Tim Armstrong

Tim Armstrong

Cloudera

Tim Armstrong is an engineer at Cloudera, where he works on making Apache Impala faster and more robust via improvements to query execution and resource management. He holds a PhD focused on the intersection of high-performance computing and programming language implementation.