Unlocking the Power of CEL for Advanced Multi-Cluster Scheduling

on YouTube ↗23m

" summary

Explains how the Common Expression Language (CEL) can be used to express granular, extensible scheduling rules across multiple clusters, including matching on labels (e.g., version), CRD fields, and metrics. Describes Open Cluster Management (OCM) using CEL with the ClusterProfile API to meet complex multi-cluster scheduling needs and demonstrates applying CEL-powered policies to improve GPU bin-packing for AI workloads.

AI-written summary · about

" related talks

• 33mA Field Guide To Integrating CEL in the Kubernetes CodebaseSreeram Venkitesh, Priyanka Saggu · CNCF Maintainer Summit Europe 2025
• 28mBeyond Match & Pattern: Mastering Kyverno with CELKoray Oksay · KyvernoCon Europe 2026
• 34mWorking your Cluster: Smarter Scheduling Decisions for Your Work...Madalina Lazar, Denisio Togashi · KubeCon + CloudNativeCon Europe 2022
• 05mProject Lightning Talk: Scheduling AI Workload Among Multiple ClustersJosh Packer · KubeCon + CloudNativeCon Europe 2025
• 30mScore-Driven Multi-Cluster Management: An Evaluation Framework for…K. Takeuchi, J. Banerjee · KubeCon + CloudNativeCon Japan 2026
• 29mMulticluster Kubernetes Management Made Easy With Open Cluster ManagementJoshua Packer · KubeCon + CloudNativeCon North America 2022
• 01h 12mBuilding scalable and flexible cluster managers using declarative programmingLalith Suresh · Hydra 2021
• 41mHow the SIG-Multicluster API Specifications Are Used for Real World Multicluster ManagementAugust Simonelli, Ryan Zhang · KubeCon + CloudNativeCon Europe 2025