The BOOT_MODE of my bluefield2 is 3? The normal situation is 1. So I can't install the bfb on it. Ask for help!

[ziji.chen]

cat /dev/rshim0/misc
DISPLAY_LEVEL 2 (0:basic, 1:advanced, 2:log)
BOOT_MODE 3 (0:rshim, 1:emmc, 2:emmc-boot-swap)
BOOT_TIMEOUT 150 (seconds)
DROP_MODE 0 (0:normal, 1:drop)
SW_RESET 0 (1: reset)
DEV_NAME pcie-0000:61:00.2
DEV_INFO BlueField-2(Rev 1)
OPN_STR N/A

---

bfb-install --rshim /dev/rshim0 --bfb DOCA_2.5.0_BSP_4.5.0_Ubuntu_22.04-1.23-10.prod.bfb
Pushing bfb
1.10GiB 0:12:36 [1.49MiB/s] [ <=> ]
Collecting BlueField booting status. Press Ctrl+C to stop…
^C

[ziji.chen]

mst status -v
MST modules:

MST PCI module is not loaded
MST PCI configuration module loaded

PCI devices:

DEVICE_TYPE MST PCI RDMA NET NUMA
NA /dev/mst/mt41686_pciconf0.1 61:00.1 -1

NA /dev/mst/mt41686_pciconf0 61:00.0 -1

ConnectX6DX(rev:0) /dev/mst/mt4125_pciconf0.1 01:00.1 mlx5_3 net-enp1s0f1np1 -1

ConnectX6DX(rev:0) /dev/mst/mt4125_pciconf0 01:00.0 mlx5_2 net-enp1s0f0np0 -1

[jtal]

Hello,

Please try to run the following command to change the boot mode:
echo 'BOOT_MODE 1' > /dev/rshim0/misc
And then try to install the .bfb again.

If this still doesn’t solve the issue, please open a case at: enterprisesupport@nvidia.com, and it will be handled according to entitlement.

Best Regards,
Jonathan.

[ziji.chen]

Thank you, I got some errors in ‘dmesg’.

[cs.lev]

I don’t know what your card is doing, but maybe a firmware upgrade (not the bfb-install), and playing around with the BIOS of the Bluefield can help. I have written a post about this when I thought my Bluefield was bricked:

https://medium.com/codex/how-did-i-unbrick-an-nvidia-bluefield-2-dpu-smartnic-89ecaa757ff1

[ziji.chen]

Thank you! It does help but can’t solve the problem completely. The final solution is to install new cooling fans.

[yavtuk]

@ziji.chen hello, do you use only 1 DPU or there are another PCI devices (nic, dpu, gpu) also? I had the same log for xFusion v5 server but I used several connect-x5 NICs additionally. I removed NICs from server and this error was gone.