End-to-end field guides for running data frameworks on Kubernetes and EKS — architecture decisions, storage trade-offs, autoscaling, graceful upgrades, and the production gotchas no documentation tells you.
Executor sizing, DRA, Spark Operator on EKS
Stateful pipelines, checkpointing, HA on Kubernetes
Strimzi operator, tiered storage, rebalancing
Multi-tenant clusters, spill, fault-tolerant execution
Shared-data mode, CN autoscaling, ingestion