Red Hat Enterprise Linux (RHEL) 8.8 Driver Documentation

Known Inbox-Related Issues

The following table describes known issues in this release and possible workarounds.

Internal Ref.

Bugzilla Ref.

Description

2482177

-

Description: RDMA device name for VFs may change after resetting all VFs at once.

Workaround: Either reset interfaces one by one with a delay in between, or use a network interface naming scheme with predictable interface names, such as NAME_PCI or NAME_GUID:

copy /lib/udev/rules.d/60-rdma-persistent-naming.rules to /etc/udev/rules.d/ and edit the last line accordingly.

Note that this will change interface names.

-

-

Description: RPM package kernel-modules-extra is required for supporting various OVS Hardware Offloads.

To use OVS Hardware Offloads, make sure to install the kernel-modules-extra RPM package which provides various kernel modules that are required for supporting this functionality.

1816660

Description: When the NUM_OF_VFS parameter configured in the Firmware (using the mstconfig tool) is higher than 64, VF LAG mode will not be supported while deploying OVS offload.

Workaround: N/A

Keywords: ConnectX-5, VF LAG, ASAP 2, SwitchDev

1816660

Description: An internal firmware error occurs either when attempting to disable single-root input/output virtualization or when unbinding PF using a function (such as ifdown and ip link) under the following condition:

VF LAG mode in an OVS offload deployment, where at least one VF of any PF is still bound on the host or attached to a VM.

Workaround: Unbind or detach VFs before you perform these actions as follows.

  1. Shutdown and detach any VMs.

  2. Remove VF LAG bond interface from OVS.

  3. Unbind VFs, perform for each configured VF:

# echo <VF PCIe BDF> > /sys/bus/pci/drivers/mlx5_core/unbind

  1. Disable SR-IOV, perform for each PF:

# echo 0 > /sys/class/net/<PF>/device/sriov_numvfs

Keywords: ConnectX-5, VF LAG, ASAP2, SwitchDev

1284047

-

Description: Bandwidth degradations due to PTI (Page Table Isolation) in Intel's CPU security fix.

Keywords: Performance

1610281

-

Description: Setting speed to 56GbE on ConnectX-4 causes firmware syndrome (0x1a303e).

Workaround: N/A

Keywords: ConnectX-4, syndrome

1609804

-

Description: Kernel panic during MTU change under stress traffic.

Workaround: N/A

Keywords: Panic, MTU

© Copyright 2023, NVIDIA. Last updated on Feb 4, 2024.