ESXi 6.7/6.7 U1: NVIDIA ConnectX-4/ConnectX-5 NATIVE ESXi Driver for VMware vSphere User Manual v4.17.15.16
Linux Kernel Upstream Release Notes v6.5

Troubleshooting

You may be able to easily resolve the issues described in this section. If a problem persists and you are unable to resolve it yourself, please contact your Mellanox representative or Mellanox Support at support@mellanox.com.

Issue

Cause

Solution

The system panics when it is booted with a failed adapter installed

Malfunction hardware component

  1. Remove the failed adapter

  2. Reboot the system

Mellanox adapter is not identified as a PCI device

PCI slot or adapter PCI connector dysfunctionality

  1. Run lspci

  2. Reseat the adapter in its PCI slot or insert the adapter to a different PCI slot. If the PCI slot confirmed to be functional, the adapter should be replaced.

Mellanox adapters are not installed in the system

Misidentification of the Mellanox adapter installed

Run the command below to identify the Mellanox adapter installed

lspci | grep Mellanox'

Issue

Cause

Solution

No link

Mis-configuration of the switch port or using a cable not supporting link rate

  • Ensure the switch port is not down

  • Ensure the switch port rate is configured to the same rate as the adapter's port

No link with break-out cable

Misuse of the break-out cable or misconfiguration of the switch's split ports

  • Use supported ports on the switch with proper configuration. For further information, please refer to the MLNX_OS User Manual

  • Make sure the QSFP breakout cable side is connected to the SwitchX

Physical link fails to negotiate to maximum supported rate

The adapter is running an outdated firmware

Install the latest firmware on the adapter

Physical link fails to come up

The cable is not connected to the port or the port on the other end of the cable is disabled

Ensure that the cable is connected on both ends or use a known working cable

Issue

Cause

Solution

Driver installation fails.

The install script may fail for the following reasons:

  • Failed to uninstall the previous installation due to dependencies being used

  • The operating system is not supported

  • Uninstall the previous driver before installing the new one

  • Use a supported operating system and kernel

© Copyright 2023, NVIDIA. Last updated on Sep 8, 2023.