proomt

Search

Search posts, papers, and topics

All posts

Kubernetes2 min readintermediate

Kubernetes v1.37: Pod-Level Resource Managers graduated to Beta

Read on kubernetes.io

Summary

Kubernetes v1.37 adds Pod‑Level Resource Managers to beta (off by default). The feature lets Kubelet’s Topology, CPU, and Memory managers consume pod‑level `.spec.resources` to reserve exclusive NUMA‑aligned CPUs/memory for primary containers while sidecars share a pod‑isolated pool. A new PodResources gRPC API now reports `cpu_ids` and `memory` per pod. Enable via the `PodLevelResourceManagers`…

  • Beta feature (feature‑gate `PodLevelResourceManagers`) enables hybrid allocation: exclusive NUMA‑aligned resources for main containers, shared pool for sidecars.
  • Kubelet’s Topology, CPU, and Memory managers now read pod‑level resource declarations directly.
  • PodResources gRPC service (`v1`) adds top‑level `cpu_ids` and `memory` fields, simplifying monitoring and device‑plugin queries.
  • Feature is disabled by default; enable via the feature gate and configure through the new docs/tutorials.

Sidecar containers (logging, telemetry, etc.) often don’t need dedicated cores, but traditional exclusive allocation forced operators to either waste cores or lose NUMA alignment. This feature improves performance isolation for latency‑critical workloads while increasing overall node utilization.

5/10
kubernetesresource managementcpu managermemory managertopology manager

Related reading

  1. Kubernetes 1.37 Released: Stable Metrics API and Rootless Kubelet in Beta

    Kubernetes 1.37 (Garhwal) ships GA Metrics API, beta rootless kubelet, GA resilient watchcache, GA pod certificates, and a suite of alpha/beta features (workload‑aware scheduling, pod checkpoint/restore, StatefulSet Recreate strategy). The release focuses on stability, security, and AI/ML cost‑optimisation.

    InfoQinfoq.com2 minrelease

  2. Monitor TAS and gang scheduling for AI training in Kubernetes

    Kubernetes’ default scheduler can’t satisfy AI training’s need for low‑latency GPU interconnects and simultaneous pod start‑up. The blog explains how the open‑source Kueue job queue adds topology‑aware placement (using node labels like `topology.kubernetes.io/rack`) and how the Coscheduling plugin adds a permit phase that only binds a gang of pods when the full set is ready, preventing idle GPU r…

    Datadogdatadoghq.com19 min

  3. Kubernetes v1.37: Hardening Container Storage with Bind Mount Options and EmptyDir Permissions

    Kubernetes v1.37 adds two alpha‑level storage hardening knobs: per‑volume `bindMountOptions` (e.g. noexec, nosuid, nodev) that affect the bind‑mount the runtime creates, and an `emptyDir` `mode` field to set Unix permission bits (including the sticky bit). Together they let you enforce least‑privilege policies on writable volumes without init‑containers or CSI tricks.

    Kuberneteskubernetes.io8 minHN3

  5. Kubernetes Multi-Cluster Project Karmada Reaches CNCF Graduation

    Karmada, a multi-cluster and multi-cloud Kubernetes orchestration project, has graduated to the highest maturity tier within the CNCF. It extends the standard Kubernetes API to manage workloads across diverse environments, enhancing multi-component scheduling for AI training jobs and promoting priority-based scheduling.

    InfoQinfoq.com3 minrelease

  6. Microsoft Open-Sources TauGrid to Simplify AI Workload Management on Kubernetes

    Microsoft open‑sourced TauGrid, a Helm‑installable platform that bundles Kueue, KubeRay and other components to schedule, monitor and checkpoint AI workloads on GPU‑enabled Kubernetes clusters. Engineers define jobs in a simple `tau.yaml`, and TauGrid handles queuing, health checks, and observability, simplifying AI workload management.

    InfoQinfoq.com2 min