Hi,
I have a Jetson Nano (production module) mounted on a Seed Studio carrier board J101.
Sometimes when I’m using the GPU on high load, it restarts.
I have found this by storing tegrastats and observing last thing it writes is a 99% frequency on GPU
RAM 3245/3964MB (lfb 107x4MB) SWAP 698/1982MB (cached 38MB) IRAM 0/252kB(lfb 252kB) CPU [11%@1326,35%@1326,13%@1326,11%@1326] EMC_FREQ 18%@1600 GR3D_FREQ 99%@921 VIC_FREQ 9%@192 APE 25 PLL@49C [email protected] PMIC@50C [email protected] AO@64C [email protected] POM_5V_IN 7274/3121 POM_5V_GPU 3570/557 POM_5V_CPU 894/463
I’m using the MAXN mode
sudo jetson_clocks --show
SOC family:tegra210 Machine:NVIDIA Jetson Nano Developer Kit
Online CPUs: 0-3
cpu0: Online=1 Governor=schedutil MinFreq=1200000 MaxFreq=1479000 CurrentFreq=1479000 IdleStates: WFI=1 c7=1
cpu1: Online=1 Governor=schedutil MinFreq=1200000 MaxFreq=1479000 CurrentFreq=1224000 IdleStates: WFI=1 c7=1
cpu2: Online=1 Governor=schedutil MinFreq=1200000 MaxFreq=1479000 CurrentFreq=1479000 IdleStates: WFI=1 c7=1
cpu3: Online=1 Governor=schedutil MinFreq=1200000 MaxFreq=1479000 CurrentFreq=1224000 IdleStates: WFI=1 c7=1
GPU MinFreq=76800000 MaxFreq=921600000 CurrentFreq=76800000
EMC MinFreq=204000000 MaxFreq=1600000000 CurrentFreq=1600000000 FreqOverride=0
Fan: PWM=80
NV Power Mode: MAXN
The power supply is the Raspberry 5 one (up to 27W) so power should not be a problem.
How can I find what is exactly happening? How can I prevent the machine to reboot on high loads?
Thanks