TCP retransmissions poor throughput and rx_no_buffer errors increasing on ibmveth NIC

Solution In Progress - Updated -

Issue

  • When TCP connections and TCP traffic load increases at a certain point the network is flooded with retransmissions due to packet drop which results in very poor network performance.

Environment

  • PPC64 LPAR
    • ibmveth NIC
    • Database application
    • multiple CPU cores allocated to LPAR
    • 1000s of TCP connection.

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