discuss.kubernetes.io · May 2, 2026 04:23 PM UTC

How to solve "Remote Memory Access" latency on 128-core EPYC nodes?

Summary

Hi all! We are running a heavy HPC-style workload (CFD simulations) on a bare-metal K8s cluster with 128-core EPYC nodes. Even with CPU Manager (static policy),...

Original reporting

Open original source

AFBytes is a read-only aggregator. Use the original source for full context and complete reporting.

How to solve "Remote Memory Access" latency on 128-core EPYC nodes?

Summary

Original reporting

Related coverage

I Hope ‘Mortal Kombat II’ Knows What It’s Doing

The Best Star Wars Game Ever Made Is $2.29 for 72 Hours

GitHub - mikwielgus/undoredo: Undo-redo in Rust using deltas, snapshots or commands with convenience implementations for many standard and third-party types.

AI Intelligence Layer

C3

oss-sec: Re: CVE-2026-31431: CopyFail: linux local privilege scalation