RoCE

Use the UI or CLI to monitor RDMA over Converged Ethernet (RoCE) for Spectrum switches and BlueField DPUs.

RoCE Commands

The following commands display your network’s RoCE configuration, RoCE counters and counter pools, and RoCE-related events. See the command line reference for additional options, definitions, and examples.

netq show roce-config 
netq show roce-counters (dpu | nic)
netq show roce-counters pool
netq show events message_type tca_roce
netq show events message_type roceconfig

The netq check roce command checks for consistent RoCE and QoS configurations across all nodes in your network fabric.

netq check roce

View RoCE Counters Networkwide in the UI

1. Select the Menu.

2. Under the RoCE counters heading, select either RoCE switches or RoCE DPUs.

The RoCE switches tab displays transmit (TX) and receive (RX) counters as well as counter pools for all switches running RoCE in your network.

The RoCE DPUs tab displays physical port, priority port, RoCE extended, RoCE, and peripheral component interconnect (PCI) information for all DPUs running RoCE in your network.

View RoCE Counters for a Given Switch

You can view the following RoCE counters for a given switch:

• Receive and transmit counters
• General, CNP, and RoCE-specific counters
• Counter pools
• Port-specific counters

To view RoCE counters on a switch, navigate to the header and select Devices, then click Open a device card. Select a switch that is running RoCE and open the large card on your workbench. Click the RoCE icon at the top of the card to view RoCE counters and their associated ports:

Expand the card to the largest size, then select RoCE counters from the side menu. Use the controls above the table to view, filter, or export counter statistics by Rx, Tx, or Pool.

Disable RoCE Monitoring

To disable RoCE monitoring:

1. Edit /etc/netq/commands/cl4-netq-commands.yml and comment out the following lines:

    cumulus@netq-ts:~$ sudo nano /etc/netq/commands/cl4-netq-commands.yml
   
    #- period: "60"
    #  key: "roce"
    #  isactive: true
    #  command: "/usr/lib/cumulus/mlxcmd --json roce counters"
    #  parser: "local"
   

2. Delete the /var/run/netq/netq_commands.yml file:

    cumulus@netq-ts:~$ sudo rm /var/run/netq/netq_commands.yml
   

3. Restart the NetQ Agent:

   cumulus@netq-ts:~$ netq config agent restart
   

Related Information

• RoCE threshold-crossing events reference
• RoCE and Cumulus Linux