Uploaded image for project: 'OpenShift Request For Enhancement'
  1. OpenShift Request For Enhancement
  2. RFE-8397

LLC Cache Alignment Strict Policy

XMLWordPrintable

    • Icon: Feature Request Feature Request
    • Resolution: Unresolved
    • Icon: Undefined Undefined
    • None
    • None
    • Node
    • None
    • None
    • Product / Portfolio Work
    • None
    • False
    • Hide

      None

      Show
      None
    • None
    • None
    • None
    • None
    • None
    • None
    • None
    • None

      Proposed title of this feature request: LLC Cache Alignment Strict Policy

      What is the nature and description of the request?

      Partner request that we add a flag/option to have a strict policy to use for workloads requiring LLC alignment for performance reasons.

      Currently we can have a case where NUMA0 is almost full, but can fit the deploying pod which has the uncore annotations, and will still deploy the pod in the NUMA0 node instead of the NUMA1 node that would have enough space for LLC alignment.

      Expansion of https://github.com/kubernetes/enhancements/blob/master/keps/sig-node/4800-cpumanager-split-uncorecache/README.md

       

      Why does the customer need this? (List the business requirements here)

      Performance enhancement for CNF workloads.

       

      List any affected packages or components.

      CPU Manager

              gausingh@redhat.com Gaurav Singh
              rhn-support-mmethot Marc Methot
              None
              Votes:
              1 Vote for this issue
              Watchers:
              8 Start watching this issue

                Created:
                Updated:
                None
                None