Presented by
Alex Pierce, Pepperdata Field Engineer
Monitoring Spark on Kubernetes: Key Performance Metrics
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:
- Core concepts and setup of Spark on Kubernetes
- Spark on Kubernetes architecture
- Monitoring Spark on Kubernetes best practices
- Why Prometheus alone is not enough for Kubernetes monitoring
- Observability and optimization
- Configuration tips for performance and efficient resource sharing
- End-to-end visibility for Spark on Kubernetes
Pepperdata
6421 subscribers3 talks
Real-time, automated cloud cost optimization with no manual tuning
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.