Monitoring Spark on Kubernetes: Key Performance Metrics

Logo
Presented by

Alex Pierce, Pepperdata Field Engineer

About this talk

Spark on Kubernetes is growing in popularity due to improved isolation, better resource sharing, and the ability to leverage homogeneous and cloud-native infrastructure for the entire stack. However, running Spark on Kubernetes in a stable, performant, cost-efficient, and secure manner still presents complex challenges. In this webinar, Alex Pierce discusses the key performance metrics to focus on when monitoring and optimizing Spark performance on Kubernetes. Topics include: - Automation and observability for lowering costs and improving performance - Deploying, managing, monitoring, and simplifying Spark on Kubernetes: big data application monitoring, platform monitoring, and dynamic optimization - Configuring for performance and efficiency - Spark app-level dynamic allocation and cluster level autoscaling - The fastest way to improve Spark on Kubernetes performance
Related topics:

More from this channel

Upcoming talks (0)
On-demand talks (117)
Subscribers (6416)
Pepperdata Capacity Optimizer delivers 30-47% greater cost savings for data-intensive workloads, eliminating the need for manual tuning by optimizing CPU and memory in real time with no application changes. Pepperdata pays for itself, immediately decreasing instance hours/waste, increasing utilization, and freeing developers from manual tuning to focus on innovation.