Session

Hands-Off Rightsizing: How We Tuned Spark Resource Requests Automatically

Rokt automated resource optimization across 1,000+ daily Spark jobs running on Amazon EKS. The talk covers the JVM visibility gap that makes Spark uniquely difficult to rightsize, Rokt's graduated rollout approach using ScaleOps, and the real-world results: 30–35% reduction in CPU and memory requests. Hear from a hands-on experience our practical gotchas around policy segmentation, data skew, and Spot instance compounding.

Slide Deck: https://docs.google.com/presentation/d/1xYAY9T7roBzejfxc9bbGVz6QBRggguCvOypwFzPaJX0

Meetup Link: https://luma.com/p18cq1vz

Bruno Chauvet

Compute Platform Lead at Rokt

New York City, New York, United States

Actions

Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.

Jump to top