DPDK: Application causing ixgbe transmit hang

Solution In Progress - Updated -

Issue

  • Openstack platform shows the VM "running" state on the compute node. Libvirt logs did not show any symptom of the instance rebooting at hypervisor level.
  • On the Hypervisor after the application hangs we see:
kernel: ixgbe 0000:0a:00.0 enpX: VF Reset msg received from vf 15  

and:

[ ] Detected Tx Unit Hang
[]   Tx Queue             <0>
[]   TDH, TDT             <0>, <2>
[]   next_to_use          <2>
[]   next_to_clean        <0>
[] tx_buffer_info[next_to_clean]
[ ]   next_to_watch         <ffff880b860b8010>
[ ]   eop_desc->wb.status  <168080>
[]   time_stamp           <fffb97a8>
[]   jiffies              <fffb97aa>
[] Detected Tx Unit Hang
[]   Tx Queue             <0>
[]   TDH, TDT             <0>, <2>
[]   next_to_use          <2>
[]   next_to_clean        <0>
[] tx_buffer_info[next_to_clean]

Environment

  • Red Hat Enterprise Linux 7
    • kernel-3.10.0-514.21.1.el7
  • Openstack
    • Debian Instance
      • DPDK version 16.07
  • Ixgbe driver
    • 4.4.0-k-rh7.3
    • ixgbevf

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