Very slow POD to POD throughput via vxlan when the Hypervisor has bnx2x_en NIC(s)

Solution Unverified - Updated -

Issue

  • On our OCP cluster, communication between pods running on different worker nodes is extremely slow. The cluster is installed on 25 GB Ethernet, yet inter pod communication has throughput only in 8-9 Mbit range.

Environment

  • Red Hat Enterprise Virtualization
  • Openshift
  • Broadcom network interface using bnxt_en driver, eg:
    • HPE 10/25Gb 2p 631FLR-SFP28 Adaptor
    • Broadcom BCM57414 NetXtreme-E 10Gb/25Gb RDMA Ethernet Controller

Subscriber exclusive content

A Red Hat subscription provides unlimited access to our knowledgebase, tools, and much more.

Current Customers and Partners

Log in for full access

Log In

New to Red Hat?

Learn more about Red Hat subscriptions

Using a Red Hat product through a public cloud?

How to access this content