Linux Installation Guide

Linux Installation Guide (PDF)

NVIDIA DOCA Installation Guide for Linux

This document details the necessary steps to set up NVIDIA DOCA in your Linux environment.

There are two ways to install the NVIDIA® BlueField® DPU software:

1.1. Supported Platforms

DOCA is supported on the devices listed in the following subsections.

Note:

This is a special GA release for improved stability that supports BlueField-3 DPUs only.

1.1.1. Supported BlueField DPUs

The following NVIDIA® BlueField® DPUs are supported with DOCA:

NVIDIA SKU PSID Description
900-9D3B6-00CN-AB0 MT_0000000883 BlueField-3 B3240 P-Series Dual-slot FHHL DPU; 400GbE / NDR IB (default mode); Dual-port QSFP112; PCIe Gen5.0 x16 with x16 PCIe extension option; 16 Arm cores; 32GB on-board DDR; integrated BMC; Crypto Enabled
900-9D3B6-00CV-AA0 MT_0000000884 BlueField-3 B3220 P-Series FHHL DPU; 200GbE (default mode) / NDR200 IB; Dual-port QSFP112; PCIe Gen5.0 x16 with x16 PCIe extension option; 16 Arm cores; 32GB on-board DDR; integrated BMC; Crypto Enabled
900-9D3B6-00SN-AB0 MT_0000000964 BlueField-3 B3240 P-Series Dual-slot FHHL DPU; 400GbE / NDR IB (default mode); Dual-port QSFP112; PCIe Gen5.0 x16 with x16 PCIe extension option; 16 Arm cores; 32GB on-board DDR; integrated BMC; Crypto Disabled
900-9D3B6-00SV-AA0 MT_0000000965 BlueField-3 B3220 P-Series FHHL DPU; 200GbE (default mode) / NDR200 IB; Dual-port QSFP112; PCIe Gen5.0 x16 with x16 PCIe extension option; 16 Arm cores; 32GB on-board DDR; integrated BMC; Crypto Disabled
900-9D3B4-00EN-EA0 MT_0000001010 BlueField-3 B3140L E-Series FHHL DPU; 400GbE / NDR IB (default mode); Single-port QSFP112; PCIe Gen5.0 x16; 8 Arm cores; 16GB on-board DDR; integrated BMC; Crypto Enabled
900-9D3B4-00PN-EA0 MT_0000001011 BlueField-3 B3140L E-Series FHHL DPU; 400GbE / NDR IB (default mode); Single-port QSFP112; PCIe Gen5.0 x16; 8 Arm cores; 16GB on-board DDR; integrated BMC; Crypto Disabled
900-9D3B6-00CC-AA0 MT_0000001024 BlueField-3 B3210 P-Series FHHL DPU; 100GbE (default mode) / HDR100 IB; Dual-port QSFP112; PCIe Gen5.0 x16 with x16 PCIe extension option; 16 Arm cores; 32GB on-board DDR; integrated BMC; Crypto Enabled
900-9D3B6-00SC-AA0 MT_0000001025 BlueField-3 B3210 P-Series FHHL DPU; 100GbE (default mode) / HDR100 IB; Dual-port QSFP112; PCIe Gen5.0 x16 with x16 PCIe extension option; 16 Arm cores; 32GB on-board DDR; integrated BMC; Crypto Disabled
900-9D3D4-00EN-HA0 MT_0000001069 BlueField-3 B3140H E-series HHHL DPU; 400GbE(default mode)/NDR IB; Single-port QSFP112; PCIe Gen5.0 x16; 8 Arm cores; 16GB on board DDR; integrated BMC; Crypto Enabled
900-9D3D4-00NN-HA0 MT_0000001070 BlueField-3 B3140H E-series HHHL DPU; 400GbE(default mode)/NDR IB; Single-port QSFP112; PCIe Gen5.0 x16; 8 Arm cores; 16GB on board DDR; integrated BMC; Crypto Disabled

1.2. Hardware Prerequisites

This quick start guide assumes that an NVIDIA® BlueField® DPU has been installed in a server according to the instructions detailed in your DPU's hardware user guide.

1.3. DOCA Packages

Device Component Version Description

Host

DOCA SDK 2.2.1 Software development kit package for developing host software
DOCA Runtime 2.2.1 Runtime libraries required to run DOCA-based software applications on host
DOCA Tools 2.2.1 Tools for developers and administrators on host
DOCA Extra 2.2.1 Contains helper scripts (doca-info, doca-kernel-support)
DOCA OFED 2.2.1 Software stack which operates across all NVIDIA network adapter solutions

Arm emulated (QEMU) development container

4.2.2 Linux-based BlueField Arm emulated container for developers

Target BlueField DPU (Arm)

BlueField BSP 4.2.2 BlueField image and firmware
DOCA SDK 2.2.1 Software development kit packages for developing Arm software
DOCA Runtime 2.2.1 Runtime libraries requied to run DOCA-based software applications on Arm
DOCA Tools 2.2.1 Tools for developers and administrators for Arm target

1.4. Supported Operating System Distributions

The default operating system of the BlueField DPU (Arm) is Ubuntu 22.04.

The supported operating systems on the host machine are the following:
Note:

Only the following generic kernel versions are supported for DOCA local repo package for host installation (whether by SDKM or manually).

OS Kernel x86 aarch64
Alinux 3.2 5.10  
Debian 10.13

5.10.135

5.4.210

 
Debian 10.8 4.19.0  
Oracle Linux 8.7 5.10/5.15  
RHEL/CentOS 7.6 3.10  
RHEL/CentOS 8.2 4.18  
Ubuntu 18.04 4.15  
Ubuntu 20.04 5.4  
Ubuntu 22.04 5.15  
Windows DOCA support for Windows is on DOCA's roadmap. For Windows driver support, refer to WinOF-2 Release Notes.

NVIDIA SDK Manager (SDKM) supports DOCA installation, including software packages on the host and the BlueField target. The SDKM automates the process of DOCA installation and other related configuration of the system.

Note:

If installing DOCA using SDKM, please skip the remaining sections and follow the wizard instead.

Note:

SDKM installation requires Internet connection through out-of-band (OOB) port.

The following example uses the SDKM CLI to install DOCA without any additional SDKs:

Copy
Copied!
            

host# sdkmanager --cli install --logintype devzone --product DOCA --version 2.2.1 --targetos Linux --host --target BLUEFIELD2_DPU_TARGETS --flash all

This guide provides the minimal first-step instructions for setting up DOCA on a standard system.

3.1. Installation Files

DeviceComponentOS and ArchLink
HostThese files contain the following components suitable for their respective OS version.
  • DOCA SDK v2.2.1
  • DOCA Runtime v2.2.1
  • DOCA Tools v2.2.1
  • DOCA Extra v2.2.1
  • DOCA OFED v2.2.1
Alinux 3.2 on x86doca-host-repo-alinux32-2.2.1-0.0.3.2.2.1009.1.al8.23.07.0.5.0.0.x86_64.rpm
Debian 10.13 on x86doca-host-repo-debian1013_2.2.1-0.0.3.2.2.1009.1.23.07.0.5.0.0_amd64.deb
Debian 10.8 on x86doca-host-repo-debian108_2.2.1-0.0.3.2.2.1009.1.23.07.0.5.0.0_amd64.deb
Oracle Linux 8.7 on x86doca-host-repo-ol87-2.2.1-0.0.3.2.2.1009.1.el8.23.07.0.5.0.0.x86_64.rpm
RHEL/CentOS 7.6 on x86doca-host-repo-rhel76-2.2.1-0.0.3.2.2.1009.1.el7.23.07.0.5.0.0.x86_64.rpm
RHEL/CentOS 8.2 on x86doca-host-repo-rhel82-2.2.1-0.0.3.2.2.1009.1.el8.23.07.0.5.0.0.x86_64.rpm
Ubuntu 18.04 on x86doca-host-repo-ubuntu1804_2.2.1-0.0.3.2.2.1009.1.23.07.0.5.0.0_amd64.deb
Ubuntu 20.04 on x86doca-host-repo-ubuntu2004_2.2.1-0.0.3.2.2.1009.1.23.07.0.5.0.0_amd64.deb
Ubuntu 22.04 on x86doca-host-repo-ubuntu2204_2.2.1-0.0.3.2.2.1009.1.23.07.0.5.0.0_amd64.deb
Arm Emulated Development ContainerArm container v4.2.2 on aarch64doca_devel_ubuntu_20.04-inbox-5.5.tar
Target BlueField DPU (Arm)BlueField Software v4.2.2Ubuntu 22.04 on aarch64doca_2.2.1_bsp_4.2.2_ubuntu_22.04-13.23-09.prod.bfb
DOCA SDK v2.2.1Ubuntu 22.04 on aarch64doca-dpu-repo-ubuntu2204-local_2.2.1009-1.23.07.0.5.0.0.bf.4.2.2.12955.6.23_arm64.deb
DOCA Runtime v2.2.1
DOCA Tools v2.2.1

3.2. Uninstalling Software from Host

If an older DOCA software version is installed on your host, make sure to uninstall it before proceeding with the installation of the new version:

OS Commands
Ubuntu/Debian
Copy
Copied!
            

$ for f in $( dpkg --list | grep doca | awk '{print $2}' ); do echo $f ; apt remove --purge $f -y ; done $ sudo apt-get autoremove

CentOS/RHEL
Copy
Copied!
            

host# for f in $(rpm -qa |grep -i doca ) ; do yum -y remove $f; done host# yum autoremove host# yum makecache


3.3. Installing Prerequisites on Host for Target DPU

Install doca-tools to manage and flash the BlueField DPU.

OS Instructions
For Ubuntu/Debian
  1. Download the DOCA host repo package from the Installation Files section.
  2. Unpack the deb repo. Run:
    Copy
    Copied!
                

    host# sudo dpkg -i doca-host-repo-ubuntu<version>_amd64.deb

  3. Perform apt update. Run:
    Copy
    Copied!
                

    host# sudo apt-get update

  4. Run apt install for DOCA Tools:
    Copy
    Copied!
                

    host# sudo apt install doca-tools

For CentOS/RHEL 8.x/

Rocky 8.6

  1. Download the DOCA host repo package from the Installation Files section.
  2. Unpack the RPM repo. Run:
    Copy
    Copied!
                

    host# sudo rpm -Uvh doca-host-repo-rhel<version>.x86_64.rpm

  3. Enable new dnf repos. Run:
    Copy
    Copied!
                

    host# sudo dnf makecache

  4. Run yum install to install DOCA Tools:
    Copy
    Copied!
                

    host# sudo yum install doca-tools

For CentOS/RHEL 7.x
  1. Download the DOCA host repo package from the Installation Files section.
  2. Unpack the RPM repo. Run:
    Copy
    Copied!
                

    host# sudo rpm -Uvh doca-host-repo-rhel<version>.x86_64.rpm

  3. Enable new yum repos. Run:
    Copy
    Copied!
                

    host# sudo yum makecache

  4. Run dnf install to install DOCA Tools:
    Copy
    Copied!
                

    host# sudo dnf install doca-tools


3.4. Determining DPU Device ID

It is is important to learn your DPU's device-id for performing some of the software installations or upgrades in this guide. To determine the device ID of the DPUs on your setup, run:

Copy
Copied!
            

host# mst start host# mst status -v

Example output:

Copy
Copied!
            

MST modules: ------------ MST PCI module is not loaded MST PCI configuration module loaded PCI devices: ------------ DEVICE_TYPE MST PCI RDMA NET NUMA BlueField2(rev:1) /dev/mst/mt41686_pciconf0.1 3b:00.1 mlx5_1 net-ens1f1 0 BlueField2(rev:1) /dev/mst/mt41686_pciconf0 3b:00.0 mlx5_0 net-ens1f0 0 BlueField3(rev:1) /dev/mst/mt41692_pciconf0.1 e2:00.1 mlx5_1 net-ens7f1np1 4 BlueField3(rev:1) /dev/mst/mt41692_pciconf0 e2:00.0 mlx5_0 net-ens7f0np0 4

The device IDs for the BlueField-2 and BlueField-3 DPUs in this example are /dev/mst/mt41686_pciconf0 and /dev/mst/mt41692_pciconf0 respectively.


3.5. Installing Software on Host

Important:

Skip this section if you intend to update only the BlueField software (*.bfb).

  1. Follow the instructions under Installing Prerequisites on Host for Target DPU.
  2. Install DOCA local repo package for host.
    Note:

    The following table provides instructions for installing the DOCA host repo on your device depending on your OS and desired profile.

    OS Profile Device Instructions
    Ubuntu/Debian doca-all BlueField
    1. Download the DOCA host repo package from Installation Files for the host.
    2. Unpack the deb repo. Run:
      Copy
      Copied!
                  

      host# dpkg -i <repo_file>

    3. Perform apt update. Run:
      Copy
      Copied!
                  

      host# apt-get update

    4. If the kernel version on your host is not supported (not shown under Supported Operating System Distributions), refer to DOCA Extra Package.
    5. Run apt install for DOCA SDK, DOCA runtime, DOCA tools:
      Copy
      Copied!
                  

      host# sudo apt install -y doca-runtime doca-sdk doca-tools

    doca-cx ConnectX
    1. Download the DOCA host repo package from Installation Files for the host.
    2. Unpack the deb repo. Run:
      Copy
      Copied!
                  

      host# dpkg -i <repo_file>

    3. Perform apt update. Run:
      Copy
      Copied!
                  

      host# apt-get update

    4. If the kernel version on your host is not supported (not shown under Supported Operating System Distributions), refer to DOCA Extra Package.
    5. Run apt install for DOCA SDK, DOCA runtime, DOCA tools:
      Copy
      Copied!
                  

      host# sudo apt install -y doca-cx-runtime doca-cx-sdk doca-cx-tools

    doca-ofed All
    1. Download the DOCA host repo package from Installation Files for the host.
    2. Unpack the deb repo. Run:
      Copy
      Copied!
                  

      host# sudo dpkg -i doca-host-repo-ubuntu<version>_amd64.deb

    3. Perform apt update. Run:
      Copy
      Copied!
                  

      host# sudo apt-get update

    4. If the kernel version on your host is not supported (not shown under Supported Operating System Distributions), refer to DOCA Extra Package.
    5. Install doca-ofed. Run:
      Copy
      Copied!
                  

      host# sudo apt install -y doca-ofed

    CentOS/RHEL/Alinux/

    Rocky/Oracle Linux

    doca-all BlueField
    1. Install the following software dependencies:
      • For RedHat 8.x, run:
        Copy
        Copied!
                    

        host# yum -y install https://dl.fedoraproject.org/pub/epel/epel-release-latest-8.noarch.rpm

      • For Alinux 3.x, run:
        Copy
        Copied!
                    

        host# yum -y install https://dl.fedoraproject.org/pub/epel/epel-release-latest-8.noarch.rpm

      • For Rocky 8.x, run:
        Copy
        Copied!
                    

        host# sudo dnf makecache host# sudo dnf install epel-release host# sudo dnf install -y yum-utils host# sudo dnf config-manager --enable PowerTools host# sudo dnf clean dbcache

      • For CentOS 8.x, run:
        Copy
        Copied!
                    

        host# sudo dnf install epel-release host# sudo dnf config-manager --set-enabled PowerTools

      • For CentOS 7.x, run:
        Copy
        Copied!
                    

        host# sudo yum install -y https://dl.fedoraproject.org/pub/epel/epel-release-latest-7.noarch.rpm host# sudo yum-config-manager --add-repo http://mirror.centos.org/centos/7/os/x86_64 host# sudo rpm --import http://mirror.centos.org/centos/7/os/x86_64/RPM-GPG-KEY-CentOS-7 host# sudo yum-config-manager --add-repo http://mirror.centos.org/centos/7/extras/x86_64 host# sudo yum-config-manager --save --setopt=mirror.centos.org_centos_7_os_x86_64.exclude='pciutils* libnl3*' host# yum makecache

    2. Download the DOCA host repo package from Installation Files for the host.
    3. Unpack the rpm repo. Run:
      Copy
      Copied!
                  

      host# rpm -Uvh <repo_file>.rpm

    4. Perform yum update. Run:
      Copy
      Copied!
                  

      host# sudo yum makecache

    5. If the kernel version on your host is not supported (not shown under Supported Operating System Distributions), refer to DOCA Extra Package.
    6. Run yum install for DOCA SDK, DOCA runtime, DOCA tools:
      Copy
      Copied!
                  

      host# sudo yum install -y doca-runtime doca-sdk doca-tools

    doca-cx ConnectX

    RHEL users need a valid subscription to install packages.

    1. Install the following software dependencies. Run:
      • For RedHat 8.x, run:
        Copy
        Copied!
                    

        host# yum -y install https://dl.fedoraproject.org/pub/epel/epel-release-latest-8.noarch.rpm

      • For Alinux 3.x, run:
        Copy
        Copied!
                    

        host# yum -y install https://dl.fedoraproject.org/pub/epel/epel-release-latest-8.noarch.rpm

      • For Rocky 8.x, run:
        Copy
        Copied!
                    

        host# sudo dnf makecache host# sudo dnf install epel-release host# sudo dnf install -y yum-utils host# sudo dnf config-manager --enable PowerTools host# sudo dnf clean dbcache

      • For CentOS 8.x, run:
        Copy
        Copied!
                    

        host# sudo dnf install epel-release host# sudo dnf config-manager --set-enabled PowerTools

      • For CentOS 7.x, run:
        Copy
        Copied!
                    

        host# sudo yum install -y https://dl.fedoraproject.org/pub/epel/epel-release-latest-7.noarch.rpm host# sudo yum-config-manager --add-repo http://mirror.centos.org/centos/7/os/x86_64 host# sudo rpm --import http://mirror.centos.org/centos/7/os/x86_64/RPM-GPG-KEY-CentOS-7 host# sudo yum-config-manager --add-repo http://mirror.centos.org/centos/7/extras/x86_64 host# sudo yum-config-manager --save --setopt=mirror.centos.org_centos_7_os_x86_64.exclude='pciutils* libnl3*' host# yum makecache

      • For Oracle Linux 8.7, run:
        Copy
        Copied!
                    

        host# yum config-manager --set-enabled ol8_codeready_builder

    2. Download the DOCA host repo package from Installation Files for the host.
    3. Unpack the rpm repo. Run:
      Copy
      Copied!
                  

      host# rpm -Uvh <repo_file>.rpm

    4. Perform yum update. Run:
      Copy
      Copied!
                  

      host# sudo yum makecache

    5. If the kernel version on your host is not supported (not shown under Supported Operating System Distributions), refer to DOCA Extra Package.
    6. Run yum install for DOCA SDK, DOCA runtime, DOCA tools:
      Copy
      Copied!
                  

      host# sudo yum install -y doca-cx-runtime doca-cx-sdk doca-cx-tools

    doca-ofed All
    1. Download the DOCA host repo package from Installation Files for the host.
    2. Unpack the RPM repo. Run:
      Copy
      Copied!
                  

      host# sudo rpm -Uvh doca-host-repo-rhel<version>.x86_64.rpm

    3. Install doca-extra. Run:
      Copy
      Copied!
                  

      host# sudo yum/dnf install -y doca-extra

    4. If the kernel version on your host is not supported (not shown under Supported Operating System Distributions), refer to DOCA Extra Package.
    5. Install doca-ofed. Run:
      Copy
      Copied!
                  

      host# sudo yum install -y doca-ofed

  3. Initialize MST. Run:
    Copy
    Copied!
                

    host# sudo mst start

  4. Reset the nvconfig params to their default values:
    Copy
    Copied!
                

    host# sudo mlxconfig -d <device-id> -y reset Reset configuration for device <device-id>? (y/n) [n] : y Applying... Done! -I- Please reboot machine to load new configurations.

    Note:

    To learn the DPU's device ID, refer to Determining DPU Device ID.

  5. Skip this step if your BlueField DPU is Ethernet only. Please refer to Supported Platforms to learn your DPU type. If you have a VPI DPU, the default link type of the ports will be configured to IB. To verify your link type, run:
    Copy
    Copied!
                

    host# sudo mst start host# sudo mlxconfig -d <device-id> -e q | grep -i link_type Configurations: Default Current Next Boot * LINK_TYPE_P1 IB(1) ETH(2) IB(1) * LINK_TYPE_P2 IB(1) ETH(2) IB(1)

    Note:

    If your DPU is Ethernet capable only, then the sudo mlxconfig -d <device> command will not provide an output.

    If the current link type is set to IB, run the following command to change it to Ethernet:
    Copy
    Copied!
                

    host# sudo mlxconfig -d <device-id> s LINK_TYPE_P1=2 LINK_TYPE_P2=2


  6. Verify that RShim is active.
    Copy
    Copied!
                

    host# sudo systemctl status rshim

    This command is expected to display active (running). If RShim service does not launch automatically, run:
    Copy
    Copied!
                

    host# sudo systemctl enable rshim host# sudo systemctl start rshim

  7. Assign a dynamic IP to tmfifo_net0 interface (RShim host interface).
    Note:

    Skip this step if you are installing the DOCA image on multiple DPUs.

    Copy
    Copied!
                

    host# ifconfig tmfifo_net0 192.168.100.1 netmask 255.255.255.252 up


3.5.1. DOCA Extra Package

If the kernel version on on your host is not supported (not shown under "Supported Operating System Distributions"), two options are available:

  • Switch to a compatible kernel
  • Install doca-extra package
    1. Run:
      Copy
      Copied!
                  

      host# sudo apt install -y doca-extra

    2. Execute the doca-kernel-support script which downloads the appropriate missing packages from your kernel to support DOCA:
      Copy
      Copied!
                  

      host# sudo /opt/mellanox/doca/tools/doca-kernel-support

      Note:

      doca-kernel-support does not support customized or unofficial kernels.


3.6. Installing Software on DPU

Users have two options for installing DOCA on the DPU:

  • Upgrading the full DOCA image on the DPU (recommended) - this option overwrites the entire boot partition.
  • Upgrading DOCA local repo package on the DPU – this option upgrades DOCA components without overwriting the boot partition. Use this option to preserve configurations or files on the DPU itself.


3.6.1. Installing Full DOCA Image on DPU

Important:

This step overwrites the entire boot partition.

Note:

This installation sets up the OVS bridge.

Note:

If you are installing DOCA on multiple DPUs, skip to section Installing Full DOCA Image on Multiple DPUs.

3.6.1.1. Option 1 - No Pre-defined Password

Note:

To set the password in advance, proceed to Option 2.

BFB installation is executed as follows:

Copy
Copied!
            

host# sudo bfb-install --rshim <rshimN> --bfb <image_path.bfb>

Where rshimN is rshim0 if you only have one DPU. You may run the following command to verify:

Copy
Copied!
            

host# ls -la /dev/ | grep rshim


3.6.1.2. Option 2 - Set Pre-defined Password

Ubuntu users can provide a unique password that will be applied at the end of the BlueField software image installation. This password needs to be defined in a bf.cfg configuration file. To set the password for the "ubuntu" user:

  1. Create password hash. Run:
    Copy
    Copied!
                

    host# openssl passwd -1 Password: Verifying - Password: $1$3B0RIrfX$TlHry93NFUJzg3Nya00rE1

  2. Add the password hash in quotes to the bf.cfg file:

    Copy
    Copied!
                

    host# sudo vim bf.cfg ubuntu_PASSWORD='$1$3B0RIrfX$TlHry93NFUJzg3Nya00rE1'

    When running the installation command, use the --config flag to provide the file containing the password:

    Copy
    Copied!
                

    host# sudo bfb-install --rshim <rshimN> --bfb <image_path.bfb> --config bf.cfg

    Note:

    If --config is not used, then upon first login to the BlueField device, users will be asked to update their password.

    The following is an example of Ubuntu installation assuming the "pv" Linux tool has been installed (to view the installation progress).

    Copy
    Copied!
                

    host# sudo bfb-install --rshim rshim0 --bfb DOCA_<version>-aarch64.bfb --config bf.cfg Pushing bfb 1.08GiB 0:00:57 [19.5MiB/s] [ <=> ] Collecting BlueField booting status. Press Ctrl+C to stop… INFO[BL2]: start INFO[BL2]: DDR POST passed INFO[BL2]: UEFI loaded INFO[BL31]: start INFO[BL31]: runtime INFO[UEFI]: eMMC init INFO[UEFI]: eMMC probed INFO[UEFI]: PCIe enum start INFO[UEFI]: PCIe enum end INFO[MISC]: Ubuntu installation started INFO[MISC]: Installation finished INFO[MISC]: Rebooting...


3.6.2. Installing Full DOCA Image on Multiple DPUs

On a host with multiple DPUs, the BFB image can be installed on all of them using the multi-bfb-installscript.

Copy
Copied!
            

host# ./multi-bfb-install --bfb <bfb-file> --password <password>

This script detects the number of RShim devices and configures them statically.

  • For Ubuntu – the script creates a configuration file /etc/netplan/20-tmfifo.yaml
  • For CentOS/RHEL 7.6 – the script creates a configuration file /etc/sysconfig/network-scripts/ifcfg-br_tmfifo
  • For CentOS/RHEL 8.0 and 8.2 – the script installs bridge-utils package to use the command brctl, creates bridge tm-br and connects all RShim interfaces to it

After the installation is complete, the configuration of the bridge and each RShim interface can be observed using ifconfig. The expected result is to see the IP on the bridge tm-br configured to 192.168.100.1 with subnet 255.255.255.0.

Note:

To log into BlueField with rshim0, run:

Copy
Copied!
            

ssh ubuntu@192.168.100.2

For each RShim after that, add 1 to the fourth octet of the IP address (e.g., ubuntu@192.168.100.3 for rshim1, ubuntu@192.168.100.4 for rshim2, etc).

The script burns a new MAC address to each DPU and configures a new IP, 192.168.100.x, as described earlier.


3.6.3. Installing DOCA Local Repo Package on DPU

Note:

If you have already installed BlueField image, be aware that the DOCA SDK, Runtime, and Tools are already contained in the BFB, and this installation is not mandatory. If you have not installed the BlueField image and wish to update DOCA Local Repo package, proceed with the following procedure.

Note:

Before installing DOCA on the target DPU, make sure the out-of-band interface (mgmt) is connected to the Internet.

  1. Download the DOCA SDK, DOCA Runtime, and DOCA Tools package from section Installation Files.
  2. Copy deb repo package into BlueField. Run:
    Copy
    Copied!
                

    host# sudo scp -r doca-repo-aarch64-ubuntu2004-local_<version>_arm64.deb ubuntu@192.168.100.2:/tmp/

  3. Unpack the deb repo. Run:
    Copy
    Copied!
                

    dpu# sudo dpkg -i doca-dpu-repo-ubuntu2004-local_<version>_arm64.deb

  4. Run apt update:
    Copy
    Copied!
                

    dpu# sudo apt-get update

  5. Check for any DOCA package content upgrade. Run:
    Copy
    Copied!
                

    dpu# sudo apt install doca-runtime dpu# sudo apt install doca-tools dpu# sudo apt install doca-sdk


3.7. Upgrading Firmware

Note:

If multiple DPUs are installed, the following steps must be performed on all of them after BFB installation.

To upgrade firmware:

  1. SSH to your BlueField device via 192.168.100.2 (preconfigured).
    Note:

    If multiple DPUs are installed, the tmfifo IP interface does not have to be 192.168.100.2. The last octate changes and depends on the RShim number.

    The default credentials for Ubuntu are as follows:
    • Username: ubuntu
    • Password: ubuntu or a unique password that you set in bf.cfg

    For example:

    Copy
    Copied!
                

    host# ssh ubuntu@192.168.100.2 Password: <configured-password>

  2. Upgrade firmware in BlueField DPU. Run:
    Copy
    Copied!
                

    dpu# sudo /opt/mellanox/mlnx-fw-updater/mlnx_fw_updater.pl --force-fw-update

    Example output:
    Copy
    Copied!
                

    Device #1: ---------- Device Type: BlueField-2 [...] Versions: Current Available FW <Old_FW> <New_FW>


  3. Power cycle the host server for the firmware upgrade to take effect.
    Note:

    The entire DPU will experience reset.


3.8. Post-installation Procedure

  1. Restart the driver. Run:
    Copy
    Copied!
                

    host# sudo /etc/init.d/openibd restart Unloading HCA driver: [ OK ] Loading HCA driver and Access Layer: [ OK ]

  2. Configure the physical function (PF) interfaces.
    Copy
    Copied!
                

    host# sudo ifconfig <interface-1> <network-1/mask> up host# sudo ifconfig <interface-2> <network-2/mask> up

    For example:
    Copy
    Copied!
                

    host# sudo ifconfig p2p1 192.168.200.32/24 up host# sudo ifconfig p2p2 192.168.201.32/24 up

    Pings between the source and destination should now be operational.

Users wishing to build their own customized BlueField OS image can use the BFB build environment. Please refer to the bfb-build project in this GitHub webpage for more information.

Note:

For a customized BlueField OS image to boot on the UEFI secure-boot-enabled DPU (default DPU secure boot setting), the OS must be either signed with an existing key in the UEFI DB (e.g., the Microsoft key), or UEFI secure boot must be disabled. Please refer to the Secure Boot section and its subpages of the NVIDIA BlueField DPU Platform Operating System Documentation for more details.

For full instructions about setting up a development environment, refer to the NVIDIA DOCA Developer Guide.


6.1. Installing CUDA on NVIDIA Converged Accelerator

NVIDIA® CUDA® is a parallel computing platform and programming model developed by NVIDIA for general computing GPUs.

This section details the necessary steps to set up CUDA on your environment. This section assumes that a BFB image has already been installed on your environment. To install CUDA on your converged accelerator:

  1. Download and install the latest NVIDIA Data Center GPU driver.
  2. Download and install CUDA.
    Note:

    The CUDA version tested to work with DOCA SDK is 12.1.

Note:

Downloading CUDA includes the latest NVIDIA Data Center GPU driver and CUDA toolkit. For more information about CUDA and driver compatibility please refer to NVIDIA CUDA Toolkit Release Notes.


6.1.1. Configuring Operation Mode

There are two modes that the NVIDIA Converged Accelerator may operate in:

  • Standard mode (default) – the BlueField DPU and the GPU operate separately
  • BlueField-X mode – the GPU is exposed to the DPU and is no longer visible on the host

To verify which mode the system is operating in, run:

Copy
Copied!
            

host# sudo mst start host# sudo mlxconfig -d <device-id> q PCI_DOWNSTREAM_PORT_OWNER[4]

Note:

To learn the DPU's device ID, refer to Determining DPU Device ID.


  • Standard mode output:
    Copy
    Copied!
                

    Device #1: […] Configurations: Next Boot PCI_DOWNSTREAM_PORT_OWNER[4] DEVICE_DEFAULT(0)

  • BlueField-X mode output:
    Copy
    Copied!
                

    Device #1: […] Configurations: Next Boot PCI_DOWNSTREAM_PORT_OWNER[4] EMBEDDED_CPU(15)

To configure BlueField-X mode, run:

Copy
Copied!
            

host# mlxconfig -d <device-id> s PCI_DOWNSTREAM_PORT_OWNER[4]=0xF


To configure standard mode, run:

Copy
Copied!
            

host# mlxconfig -d <device-id> s PCI_DOWNSTREAM_PORT_OWNER[4]=0x0

Note:

To learn the DPU's device ID, refer to Determining DPU Device ID.


Power cycle is required for configuration to take effect. To power cycle the host run:

Copy
Copied!
            

host# ipmitool power cycle

6.1.2. Downloading and Installing CUDA Toolkit and Driver

This section details the necessary steps to set up CUDA on your environment. It assumes that a BFB image has already been installed on your environment.

  1. Install CUDA by visiting the CUDA Toolkit Downloads webpage.
    Note:

    Select the Linux distribution and version relevant for your environment.

    Note:

    This section shows the native compilation option either on x86 or aarch64 hosts.

  2. Test that the driver installation completed successfully. Run:
    Copy
    Copied!
                

    dpu# nvidia-smi Tue Apr 5 13:37:59 2022 +-----------------------------------------------------------------------------+ | NVIDIA-SMI 510.47.03 Driver Version: 510.47.03 CUDA Version: 11.8 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |===============================+======================+======================| | 0 NVIDIA BF A10 Off | 00000000:06:00.0 Off | 0 | | 0% 43C P0 N/A / 225W | 0MiB / 23028MiB | 0% Default | | | | N/A | +-------------------------------+----------------------+----------------------+ +-----------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=============================================================================| | No running processes found | +-----------------------------------------------------------------------------+

  3. Verify that the installation completed successfully.
    1. Download CUDA samples repo. Run:
      Copy
      Copied!
                  

      dpu# git clone https://github.com/NVIDIA/cuda-samples.git

    2. Build and run vectorAdd CUDA sample. Run:
      Copy
      Copied!
                  

      dpu# cd cuda-samples/Samples/0_Introduction/vectorAdd dpu# make dpu# ./vectorAdd

    Note:

    If the vectorAdd sample works as expected, it should output "Test Passed".

    Note:

    If it seems that the GPU is slow or stuck, stop execution and run:

    Copy
    Copied!
                

    dpu# sudo setpci -v -d ::0302 800.L=201 # CPL_VC0 = 32

6.1.3. GPUDirect RDMA

To enable CPU map GPU memory feature in DPDK's gpudev library, you need the gdrcopy library and driver to be installed on your system.

  1. Install the gdrcopy library. Run:
    Copy
    Copied!
                

    dpu# git clone https://github.com/NVIDIA/gdrcopy.git

  2. Install dependencies:
    • For RHEL/CentOS:
      Copy
      Copied!
                  

      # DKMs can be installed from epel-release. See https://fedoraproject.org/wiki/EPEL. dpu# sudo yum install dkms check check-devel subunit subunit-devel

    • For Ubuntu/Debian:
      Copy
      Copied!
                  

      dpu# sudo apt install check libsubunit0 libsubunit-dev

  3. Build the library and install the driver. Run:
    Copy
    Copied!
                

    dpu# cd gdrcopy dpu# make # Launch gdrdrv kernel module on the system dpu# ./insmod.sh

  4. Setup the path to gdrcopy. Run:
    Copy
    Copied!
                

    dpu# export GDRCOPY_PATH_L=/path/to/libgdrapi

    Note:

    In general, the path to libgdrapi is /path/to/gdrcopy/src/.

6.2. Installing Rivermax on DPU

NVIDIA Rivermax offers a unique IP-based solution for any media and data streaming use case.

This section provides the steps to install Rivermax assuming that a BFB image has already been installed on your environment.

6.2.1. Downloading Rivermax Driver

  1. Navigate to the NVIDIA Rivermax SDK product page.
  2. Register to be able to download the driver package using the JOIN button at the top of the page.
  3. Download the appropriate driver package according to your BFB under the "Linux" subsection. For example, for Ubuntu 22.04 BFB, download rivermax_ubuntu2204_<version>.tar.gz.

6.2.2. Installing Rivermax Driver

  1. Copy the .tgz file to the DPU:
    Copy
    Copied!
                

    host# sudo scp -r rivermax_ubuntu2204_<version>.tar.gz ubuntu@192.168.100.2:/tmp/

  2. Extract the Rivermax file:
    Copy
    Copied!
                

    dpu# sudo tar xzf rivermax_ubuntu2204_<version>.tar.gz

  3. Install the Rivermax driver package:
    Copy
    Copied!
                

    dpu# cd <rivermax-version>/Ubuntu.22.04/deb-dist/aarch64/ dpu# sudo dpkg -i rivermax_<version>.deb

6.2.3. Installing Rivermax Libraries from DOCA

Rivermax libraries are compatibles with DOCA components and can be found inside the doca-dpu-repo.

  1. Unpack the doca-dpu-repo:
    Copy
    Copied!
                

    dpu# sudo dpkg -i doca-dpu-repo-ubuntu2204-local_<version>_arm64.deb

  2. Run apt update:
    Copy
    Copied!
                

    dpu# sudo apt-get update

  3. Install the Rivermax libraries:
    Copy
    Copied!
                

    dpu# sudo apt install doca-rmax-libs dpu# sudo apt install libdoca-rmax-libs-dev

For additional details and guidelines, please visit the NVIDIA Rivermax SDK product page.

Notice

This document is provided for information purposes only and shall not be regarded as a warranty of a certain functionality, condition, or quality of a product. NVIDIA Corporation nor any of its direct or indirect subsidiaries and affiliates (collectively: “NVIDIA”) make no representations or warranties, expressed or implied, as to the accuracy or completeness of the information contained in this document and assume no responsibility for any errors contained herein. NVIDIA shall have no liability for the consequences or use of such information or for any infringement of patents or other rights of third parties that may result from its use. This document is not a commitment to develop, release, or deliver any Material (defined below), code, or functionality.

NVIDIA reserves the right to make corrections, modifications, enhancements, improvements, and any other changes to this document, at any time without notice.

Customer should obtain the latest relevant information before placing orders and should verify that such information is current and complete.

NVIDIA products are sold subject to the NVIDIA standard terms and conditions of sale supplied at the time of order acknowledgement, unless otherwise agreed in an individual sales agreement signed by authorized representatives of NVIDIA and customer (“Terms of Sale”). NVIDIA hereby expressly objects to applying any customer general terms and conditions with regards to the purchase of the NVIDIA product referenced in this document. No contractual obligations are formed either directly or indirectly by this document.

NVIDIA products are not designed, authorized, or warranted to be suitable for use in medical, military, aircraft, space, or life support equipment, nor in applications where failure or malfunction of the NVIDIA product can reasonably be expected to result in personal injury, death, or property or environmental damage. NVIDIA accepts no liability for inclusion and/or use of NVIDIA products in such equipment or applications and therefore such inclusion and/or use is at customer’s own risk.

NVIDIA makes no representation or warranty that products based on this document will be suitable for any specified use. Testing of all parameters of each product is not necessarily performed by NVIDIA. It is customer’s sole responsibility to evaluate and determine the applicability of any information contained in this document, ensure the product is suitable and fit for the application planned by customer, and perform the necessary testing for the application in order to avoid a default of the application or the product. Weaknesses in customer’s product designs may affect the quality and reliability of the NVIDIA product and may result in additional or different conditions and/or requirements beyond those contained in this document. NVIDIA accepts no liability related to any default, damage, costs, or problem which may be based on or attributable to: (i) the use of the NVIDIA product in any manner that is contrary to this document or (ii) customer product designs.

No license, either expressed or implied, is granted under any NVIDIA patent right, copyright, or other NVIDIA intellectual property right under this document. Information published by NVIDIA regarding third-party products or services does not constitute a license from NVIDIA to use such products or services or a warranty or endorsement thereof. Use of such information may require a license from a third party under the patents or other intellectual property rights of the third party, or a license from NVIDIA under the patents or other intellectual property rights of NVIDIA.

Reproduction of information in this document is permissible only if approved in advance by NVIDIA in writing, reproduced without alteration and in full compliance with all applicable export laws and regulations, and accompanied by all associated conditions, limitations, and notices.

THIS DOCUMENT AND ALL NVIDIA DESIGN SPECIFICATIONS, REFERENCE BOARDS, FILES, DRAWINGS, DIAGNOSTICS, LISTS, AND OTHER DOCUMENTS (TOGETHER AND SEPARATELY, “MATERIALS”) ARE BEING PROVIDED “AS IS.” NVIDIA MAKES NO WARRANTIES, EXPRESSED, IMPLIED, STATUTORY, OR OTHERWISE WITH RESPECT TO THE MATERIALS, AND EXPRESSLY DISCLAIMS ALL IMPLIED WARRANTIES OF NONINFRINGEMENT, MERCHANTABILITY, AND FITNESS FOR A PARTICULAR PURPOSE. TO THE EXTENT NOT PROHIBITED BY LAW, IN NO EVENT WILL NVIDIA BE LIABLE FOR ANY DAMAGES, INCLUDING WITHOUT LIMITATION ANY DIRECT, INDIRECT, SPECIAL, INCIDENTAL, PUNITIVE, OR CONSEQUENTIAL DAMAGES, HOWEVER CAUSED AND REGARDLESS OF THE THEORY OF LIABILITY, ARISING OUT OF ANY USE OF THIS DOCUMENT, EVEN IF NVIDIA HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. Notwithstanding any damages that customer might incur for any reason whatsoever, NVIDIA’s aggregate and cumulative liability towards customer for the products described herein shall be limited in accordance with the Terms of Sale for the product.

Trademarks

NVIDIA, the NVIDIA logo, and Mellanox are trademarks and/or registered trademarks of Mellanox Technologies Ltd. and/or NVIDIA Corporation in the U.S. and in other countries. The registered trademark Linux® is used pursuant to a sublicense from the Linux Foundation, the exclusive licensee of Linus Torvalds, owner of the mark on a world¬wide basis. Other company and product names may be trademarks of the respective companies with which they are associated.

Copyright

© 2023 NVIDIA Corporation & affiliates. All rights reserved.

© Copyright 2023, NVIDIA. Last updated on Jan 29, 2024.