Kubernetes v1.36 introduces major architectural improvements to workload-aware scheduling.
- •Workload and PodGroup APIs are separated: Workload acts as a static template while PodGroup manages runtime state
- •New PodGroup scheduling cycle enables atomic group evaluation, preventing scheduling deadlocks
- •Topology-aware scheduling co-locates Pods within specific physical or logical domains to reduce network latency
- •Gang scheduling ensures strict all-or-nothing placement of interdependent workloads
- •ResourceClaim support enables Dynamic Resource Allocation for PodGroups
This summary was automatically generated by AI based on the original article and may not be fully accurate.
Kubernetes
Google Cloud
Grafana