MAXN does not appear after install on SD or NVMe

Robotics & Edge Computing Jetson & Embedded Systems Jetson Orin Nano
1

I was able to successfully flash my jetson nano board.

After this, I used an SD card to install. This worked but I couldn’t get MAXN to show up in the power part.

I also went ahead and switched to burn the image to the NVME. I added the boot param with the PARTUUID and it boots off nvme now - but it’s the same problem.

I created the image from the downloaded image from the nvidia instructions.

I followed the directions to have MAXN show up, but everytime I delete and reboot, it still does not show up.

2

This could help:

tl;dr I had this working one time, but the sdkmanager installed via sd card and worked only one time and didn’t install any supporting software. So I re-ran sdkmanager again to include the software and it didn’t work. However, flashing it manually and using the image did work - but now I can not see the MAXN setting.

Yesterday I installed the software through sdkmanager on the sd card. When I did that I did not install the SDK software, and this did work for that time.

After the flash worked, I tried to re-install via nvme and re-flash was selected on sdkmanager, this failed multiple times so I flashed it successfully by running flash.sh manually.

The difference here is that I used the image that I was supposed to download as my initial image and not the one from the sdkmanager. Not sure if that made a difference?

However, it is not showing up now either way…

4

Could you share the result of this file? and its content.

ll /etc/nvpmodel.conf

5

/etc/nvpmodel.conf → /etc/nvpmodel/nvpmodel_p3767_0003.conf

#
# Copyright (c) 2021-2023, NVIDIA CORPORATION.  All rights reserved.
#
# NVIDIA CORPORATION and its licensors retain all intellectual property
# and proprietary rights in and to this software, related documentation
# and any modifications thereto.  Any use, reproduction, disclosure or
# distribution of this software and related documentation without an express
# license agreement from NVIDIA CORPORATION is strictly prohibited.
#
# FORMAT:
# < PARAM TYPE=PARAM_TYPE NAME=PARAM_NAME >
# ARG1_NAME ARG1_PATH_VAL
# ARG2_NAME ARG2_PATH_VAL
# ...
# This starts a section of PARAM definitions, in which each line
# has the syntax below:
# ARG_NAME ARG_PATH_VAL
# ARG_NAME is a macro name for argument value ARG_PATH_VAL.
# PARAM_TYPE can be FILE, or CLOCK.
#
# < POWER_MODEL ID=id_num NAME=mode_name >
# PARAM1_NAME ARG11_NAME ARG11_VAL
# PARAM1_NAME ARG12_NAME ARG12_VAL
# PARAM2_NAME ARG21_NAME ARG21_VAL
# ...
# This starts a section of POWER_MODEL configurations, followed by
# lines with parameter settings as the format below:
# PARAM_NAME ARG_NAME ARG_VAL
# PARAM_NAME and ARG_NAME are defined in PARAM definition sections.
# ARG_VAL is an integer for PARAM_TYPE of CLOCK, and -1 is taken
# as INT_MAX. ARG_VAL is a string for PARAM_TYPE of FILE.
# This file must contain at least one POWER_MODEL section.
#
# < PM_CONFIG DEFAULT=default_mode >
# This is a mandatory section to specify one of the defined power
# model as the default.

###########################
#                         #
# PARAM DEFINITIONS       #
#                         #
###########################

< PARAM TYPE=FILE NAME=CPU_ONLINE >
CORE_0 /sys/devices/system/cpu/cpu0/online
CORE_1 /sys/devices/system/cpu/cpu1/online
CORE_2 /sys/devices/system/cpu/cpu2/online
CORE_3 /sys/devices/system/cpu/cpu3/online
CORE_4 /sys/devices/system/cpu/cpu4/online
CORE_5 /sys/devices/system/cpu/cpu5/online

< PARAM TYPE=FILE NAME=FBP_POWER_GATING >
FBP_PG_MASK /sys/devices/gpu.0/fbp_pg_mask
FBP_PG_MASK_KNEXT /sys/devices/platform/gpu.0/fbp_pg_mask

< PARAM TYPE=FILE NAME=TPC_POWER_GATING >
TPC_PG_MASK /sys/devices/gpu.0/tpc_pg_mask
TPC_PG_MASK_KNEXT /sys/devices/platform/gpu.0/tpc_pg_mask

< PARAM TYPE=FILE NAME=GPU_POWER_CONTROL_ENABLE >
GPU_PWR_CNTL_EN /sys/devices/gpu.0/power/control
GPU_PWR_CNTL_EN_KNEXT /sys/devices/platform/gpu.0/power/control

< PARAM TYPE=FILE NAME=GPU_POWER_CONTROL_DISABLE >
GPU_PWR_CNTL_DIS /sys/devices/gpu.0/power/control
GPU_PWR_CNTL_DIS_KNEXT /sys/devices/platform/gpu.0/power/control

< PARAM TYPE=CLOCK NAME=CPU_A78_0 >
FREQ_TABLE /sys/devices/system/cpu/cpu0/cpufreq/scaling_available_frequencies
MAX_FREQ /sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq
MIN_FREQ /sys/devices/system/cpu/cpu0/cpufreq/scaling_min_freq
FREQ_TABLE_KNEXT /sys/devices/system/cpu/cpu0/cpufreq/scaling_available_frequencies
MAX_FREQ_KNEXT /sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq
MIN_FREQ_KNEXT /sys/devices/system/cpu/cpu0/cpufreq/scaling_min_freq

< PARAM TYPE=CLOCK NAME=CPU_A78_1 >
FREQ_TABLE /sys/devices/system/cpu/cpu4/cpufreq/scaling_available_frequencies
MAX_FREQ /sys/devices/system/cpu/cpu4/cpufreq/scaling_max_freq
MIN_FREQ /sys/devices/system/cpu/cpu4/cpufreq/scaling_min_freq
FREQ_TABLE_KNEXT /sys/devices/system/cpu/cpu4/cpufreq/scaling_available_frequencies
MAX_FREQ_KNEXT /sys/devices/system/cpu/cpu4/cpufreq/scaling_max_freq
MIN_FREQ_KNEXT /sys/devices/system/cpu/cpu4/cpufreq/scaling_min_freq

< PARAM TYPE=CLOCK NAME=GPU >
FREQ_TABLE /sys/devices/17000000.ga10b/devfreq/17000000.ga10b/available_frequencies
MAX_FREQ /sys/devices/17000000.ga10b/devfreq/17000000.ga10b/max_freq
MIN_FREQ /sys/devices/17000000.ga10b/devfreq/17000000.ga10b/min_freq
FREQ_TABLE_KNEXT /sys/devices/platform/17000000.gpu/devfreq_dev/available_frequencies
MAX_FREQ_KNEXT /sys/devices/platform/17000000.gpu/devfreq_dev/max_freq
MIN_FREQ_KNEXT /sys/devices/platform/17000000.gpu/devfreq_dev/min_freq

<PARAM TYPE=CLOCK NAME=EMC >
MAX_FREQ /sys/kernel/nvpmodel_emc_cap/emc_iso_cap
MAX_FREQ_KNEXT /sys/kernel/nvpmodel_clk_cap/emc

###########################
#                         #
# POWER_MODEL DEFINITIONS #
#                         #
###########################

< POWER_MODEL ID=0 NAME=15W >
CPU_ONLINE CORE_0 1
CPU_ONLINE CORE_1 1
CPU_ONLINE CORE_2 1
CPU_ONLINE CORE_3 1
CPU_ONLINE CORE_4 1
CPU_ONLINE CORE_5 1
FBP_POWER_GATING FBP_PG_MASK 2
TPC_POWER_GATING TPC_PG_MASK 240
GPU_POWER_CONTROL_ENABLE GPU_PWR_CNTL_EN on
CPU_A78_0 MIN_FREQ 729600
CPU_A78_0 MAX_FREQ -1
CPU_A78_1 MIN_FREQ 729600
CPU_A78_1 MAX_FREQ -1
GPU MIN_FREQ 0
GPU MAX_FREQ -1
GPU_POWER_CONTROL_DISABLE GPU_PWR_CNTL_DIS auto
EMC MAX_FREQ -1

< POWER_MODEL ID=1 NAME=7W >
CPU_ONLINE CORE_0 1
CPU_ONLINE CORE_1 1
CPU_ONLINE CORE_2 1
CPU_ONLINE CORE_3 1
CPU_ONLINE CORE_4 0
CPU_ONLINE CORE_5 0
FBP_POWER_GATING FBP_PG_MASK 2
TPC_POWER_GATING TPC_PG_MASK 252
GPU_POWER_CONTROL_ENABLE GPU_PWR_CNTL_EN on
CPU_A78_0 MIN_FREQ 729600
CPU_A78_0 MAX_FREQ 960000
GPU MIN_FREQ 0
GPU MAX_FREQ 408000000
GPU_POWER_CONTROL_DISABLE GPU_PWR_CNTL_DIS auto
EMC MAX_FREQ 2133000000

# mandatory section to configure the default power mode

So it looks like I should have it point to one of the _super conf files? I suppose if I delete it, there is supposed to be a process that tries to detect what I have, and it’s detecting the wrong one?

6

Also:

$ ls -alh /etc/nvpmodel
total 240K
drwxr-xr-x   2 root root 4.0K Dec 13 11:38 .
drwxr-xr-x 149 root root  12K Jan  2 22:54 ..
-rw-r--r--   1 root root 6.8K Dec 12 19:07 nvpmodel_igx_orin.conf
-rw-r--r--   1 root root 6.8K Dec 12 19:07 nvpmodel_igx_orin_safety.conf
-rw-r--r--   1 root root 9.0K Dec 12 19:07 nvpmodel_p3701_0000.conf
-rw-r--r--   1 root root 6.7K Dec 12 19:07 nvpmodel_p3701_0002.conf
-rw-r--r--   1 root root 8.1K Dec 12 19:07 nvpmodel_p3701_0004.conf
-rw-r--r--   1 root root 9.0K Dec 12 19:07 nvpmodel_p3701_0008.conf
-rw-r--r--   1 root root 8.1K Dec 12 19:07 nvpmodel_p3767_0000.conf
-rw-r--r--   1 root root 7.9K Dec 12 19:07 nvpmodel_p3767_0001.conf
-rw-r--r--   1 root root 5.1K Dec 12 19:07 nvpmodel_p3767_0003.conf
-rw-r--r--   1 root root 7.9K Dec 12 19:07 nvpmodel_p3767_0003_super.conf
-rw-r--r--   1 root root 5.5K Dec 12 19:07 nvpmodel_p3767_0004.conf
-rw-r--r--   1 root root 8.4K Dec 12 19:07 nvpmodel_p3767_0004_super.conf
-rw-r--r--   1 root root  12K Dec 12 19:07 nvpmodel_t194_8gb.conf
-rw-r--r--   1 root root  13K Dec 12 19:07 nvpmodel_t194_agxi.conf
-rw-r--r--   1 root root  15K Dec 12 19:07 nvpmodel_t194.conf
-rw-r--r--   1 root root 7.1K Dec 12 19:07 nvpmodel_t194_e3900_dGPU.conf
-rw-r--r--   1 root root  15K Dec 12 19:07 nvpmodel_t194_e3900_iGPU.conf
-rw-r--r--   1 root root  19K Dec 12 19:07 nvpmodel_t194_p3668.conf
-rw-r--r--   1 root root  18K Dec 12 19:07 nvpmodel_t194_p3668_emul.conf

So I went ahead and did this:

   32  sudo rm -rf /etc/nvpmodel.conf
   33  sudo ln -s /etc/nvpmodel/nvpmodel_p3767_0003_super.conf /etc/nvpmodel.conf
   34  sudo shutdown -r now

And now it’s showing up. Should I use the 004_super.conf file instead? Regardless, this one seems to work… I can go on to testing some of the cuda apps I want to test now

7

Not sure if it’s related - but I thought the max mhz was supposed to be 1700 mhz, but the current config doesn’t reflect this:

$ lscpu
Architecture:            aarch64
  CPU op-mode(s):        32-bit, 64-bit
  Byte Order:            Little Endian
CPU(s):                  6
  On-line CPU(s) list:   0-5
Vendor ID:               ARM
  Model name:            Cortex-A78AE
    Model:               1
    Thread(s) per core:  1
    Core(s) per cluster: 3
    Socket(s):           -
    Cluster(s):          2
    Stepping:            r0p1
    CPU max MHz:         1510.4000
    CPU min MHz:         115.2000
    BogoMIPS:            62.50
    Flags:               fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp
                          asimdhp cpuid asimdrdm lrcpc dcpop asimddp uscat ilrcp
                         c flagm paca pacg
Caches (sum of all):
8

let me put your board info in this post too.

9

sudo ln -s /etc/nvpmodel/nvpmodel_p3767_0003_super.conf /etc/nvpmodel.conf

What you did here is correct.

Could you run

sudo nvpmodel -m 2

sudo jetson_clocks

sudo tegrastats

and share the tegrastats result?

10 
 sudo tegrastats
01-02-2025 23:18:43 RAM 2194/7619MB (lfb 4x4MB) SWAP 0/3810MB (cached 0MB) CPU [0%@1510,0%@1510,2%@1510,0%@1510,0%@1510,0%@1510] EMC_FREQ 1%@2133 GR3D_FREQ 0%@[624] NVDEC off NVJPG off NVJPG1 off VIC off OFA off APE 200 cpu@49.656C soc2@48.625C soc0@47.718C gpu@50.031C tj@50.312C soc1@50.312C VDD_IN 6348mW/6348mW VDD_CPU_GPU_CV 1030mW/1030mW VDD_SOC 1861mW/1861mW
01-02-2025 23:18:45 RAM 2194/7619MB (lfb 4x4MB) SWAP 0/3810MB (cached 0MB) CPU [1%@1510,0%@1510,2%@1510,0%@1510,0%@1510,0%@1510] EMC_FREQ 1%@2133 GR3D_FREQ 0%@[624] NVDEC off NVJPG off NVJPG1 off VIC off OFA off APE 200 cpu@50C soc2@48.562C soc0@47.906C gpu@49.625C tj@50.406C soc1@50.406C VDD_IN 6348mW/6348mW VDD_CPU_GPU_CV 1030mW/1030mW VDD_SOC 1861mW/1861mW
01-02-2025 23:18:46 RAM 2194/7619MB (lfb 4x4MB) SWAP 0/3810MB (cached 0MB) CPU [2%@1510,2%@1510,1%@1510,0%@1510,0%@1510,0%@1510] EMC_FREQ 1%@2133 GR3D_FREQ 0%@[624] NVDEC off NVJPG off NVJPG1 off VIC off OFA off APE 200 cpu@49.75C soc2@48.656C soc0@47.656C gpu@49.656C tj@50.312C soc1@50.312C VDD_IN 6428mW/6375mW VDD_CPU_GPU_CV 1109mW/1056mW VDD_SOC 1861mW/1861mW
01-02-2025 23:18:47 RAM 2194/7619MB (lfb 4x4MB) SWAP 0/3810MB (cached 0MB) CPU [0%@1510,0%@1510,0%@1510,1%@1510,0%@1510,0%@1510] EMC_FREQ 1%@2133 GR3D_FREQ 0%@[624] NVDEC off NVJPG off NVJPG1 off VIC off OFA off APE 200 cpu@50.031C soc2@48.593C soc0@47.593C gpu@49.968C tj@50.312C soc1@50.312C VDD_IN 6348mW/6368mW VDD_CPU_GPU_CV 1030mW/1050mW VDD_SOC 1822mW/1851mW

And I ran it in this order per the instructions:

38  sudo nvpmodel -m 2
   39  sudo jetson_clocks
   40  sudo tegrastats
11

What is the result of nvpmodel -q ?

12 
~$ sudo nvmpdel -q
sudo: nvmpdel: command not found
13

sorry, my typo. nvpmodel

14 
$ sudo nvpmodel -q
NV Power Mode: MAXN
2
15

Sorry that I need to check more info here. It looks like software is only “partially” configured correctly.

Could you do below and attach the final file here?

sudo -s
cd /sys/kernel/debug/bpmp/debug/
cat dt > ~/bpmp.dts

Please attach that bpmp.dts in this post.

16

bpmp.dts.txt (21.3 KB)

17

This content is still the old one for common orin nano module. Not super setting.

Thus, I guess there are still some problem during flash. How did you flash your board?

18

I mean what option did you choose in sdkmanager?

19

I have a linux machine with ubuntu.

I first tried doing this through sdk manager, but it kept failing - over and over. It was during the flash process. So then I ran:

./nvidia/nvidia_sdk/JetPack_6.1_Linux_JETSON_ORIN_NANO_8GB_DEVKIT/Linux_for_Tegra/flash.sh jetson-orin-nano-devkit internal

Using an SD Card (it would not work if it was a nvme drive). This said the process finished successfully.

Then I took the image from the website for the dev kit and booted with that. The instructions on the “get started” seemed to be the only way I can get this running.

20

OK - on it!

21

The method you tried to flash will not fully work with super mode. It might be too complicated to explain the reason here due to some boot flow knowledge is required.

I would like to check what is going on with your sdkmanager, please use it to flash again (choose the devkit option).

Once it failed, there is a “EXPORT LOGS” button in the GUI, click it and attach the full zip file here for me to check log.