Mlxlink - Bad signal integrity on Mellanox ConnectX-4 LX

I am using Ubuntu 18.04.6, Kernel 5.4.0-150-generic, x86_64 system. Below are the commands I used, results I got:

lspci -v | grep Mellanox

01:00.0 Ethernet controller: Mellanox Technologies MT27710 Family [ConnectX-4 Lx]
Subsystem: Mellanox Technologies Stand-up ConnectX-4 Lx EN, 25GbE dual-port SFP28, PCIe3.0 x8, MCX4121A-ACAT
01:00.1 Ethernet controller: Mellanox Technologies MT27710 Family [ConnectX-4 Lx]
Subsystem: Mellanox Technologies Stand-up ConnectX-4 Lx EN, 25GbE dual-port SFP28, PCIe3.0 x8, MCX4121A-ACAT

mst start

Starting MST (Mellanox Software Tools) driver set
Loading MST PCI module - Success
Loading MST PCI configuration module - Success
Create devices
Unloading MST PCI module (unused) - Success

mst status

MST modules:

MST PCI module is not loaded
MST PCI configuration module loaded

MST devices:

/dev/mst/mt4117_pciconf0 - PCI configuration cycles access.
domain:bus:dev.fn=0000:01:00.0 addr.reg=88 data.reg=92 cr_bar.gw_offset=-1
Chip revision is: 00

mlxlink -d /dev/mst/mt4117_pciconf0.1

Operational Info

State : Active
Physical state : LinkUp
Speed : 10GbE
Width : 1x
FEC : No FEC
Loopback Mode : No Loopback
Auto Negotiation : ON

Supported Info

Enabled Link Speed : 0x38007013 (25G,10G,1G)
Supported Cable Speed : 0x00001001 (10G,1G)

Troubleshooting Info

Status Opcode : 15
Group Opcode : PHY FW
Recommendation : Bad signal integrity

Tool Information

Firmware Version : 14.32.1010
MFT Version : mft 4.26.1-3

mlxlink -d /dev/mst/mt4117_pciconf0

Operational Info

State : Active
Physical state : LinkUp
Speed : 10GbE
Width : 1x
FEC : No FEC
Loopback Mode : No Loopback
Auto Negotiation : ON

Supported Info

Enabled Link Speed : 0x38007013 (25G,10G,1G)
Supported Cable Speed : 0x00001001 (10G,1G)

Troubleshooting Info

Status Opcode : 15
Group Opcode : PHY FW
Recommendation : Bad signal integrity

Tool Information

Firmware Version : 14.32.1010
MFT Version : mft 4.26.1-3

I have 2 ports on the NIC card, I used the 2 ports, both are showing same error message. The NIC cards were supposed to get data from FPGA through 10GbE DAC SFP+ Ethernet cable. I also changed the cable with a new one, still it is showing the same error.

Does anyone know on how to debug the errors shown by Mellanox cards? Also, can you provide the reference for mlx commands and its output meaning.

If need any additional info, please let me know.

Hello emb3,

Thank you for posting your inquiry on the NVIDIA Developer Forum - Infrastructure and Networking - Section.

Based on the info provided, please make sure you use a supported/validated cable based on the latest RN for the ConnectX-4 Lx → Firmware Compatible Products - NVIDIA Docs

The command reference for the mlxlink command you can find through the following link → mlxlink Utility - NVIDIA Docs

mlxlink is part of the MFT package.

Thank you and regards,
~NVIDIA Networking Technical Support

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.