Nvidia jetson orin nano reboots itself continuously. I checked, it is not thermal problem, it is not adapter problem ( I use 19V, 2.37A original adapter). When I checked logs, I found this:
jetson1@ubuntu:~$ last -x | head -20
jetson1 pts/2 172.16.1.116 Wed Apr 8 10:42 still logged in
jetson1 :1 :1 Tue Apr 7 16:54 still logged in
runlevel (to lvl 5) 5.15.185-tegra Tue Apr 7 16:11 still running
reboot system boot 5.15.185-tegra Tue Apr 7 16:11 still running
jetson1 :1 :1 Tue Apr 7 15:37 - crash (00:33)
runlevel (to lvl 5) 5.15.185-tegra Tue Apr 7 15:07 - 16:11 (01:04)
reboot system boot 5.15.185-tegra Tue Apr 7 15:07 still running
It crashed April 7, 15:37, but I cannot find the reason
*** Please note that this reply is generated by LLM automatically ***
Based on the provided logs, it appears that the Jetson Orin Nano is experiencing a crash and rebooting continuously. The logs indicate that the system crashed on April 7 at 15:37, but the reason for the crash is not explicitly stated.
Given that you have checked and ruled out thermal and adapter problems, the issue is likely related to a software or system configuration problem. Here are a few potential causes and steps to help you troubleshoot:
- System configuration issue: The logs show that the system is running in runlevel 5, which is the default runlevel for the Jetson Orin Nano. However, it’s possible that there is a configuration issue that is causing the system to crash. Check the system configuration files, such as
/etc/systemd/system.conf and /etc/systemd/user.conf, to ensure that they are set up correctly.
- Software issue: The crash may be related to a software issue, such as a bug in a system service or a problem with a user-space application. Check the system logs, such as
/var/log/syslog and /var/log/messages, to see if there are any error messages that may indicate the cause of the crash.
- Resource issue: The Jetson Orin Nano has limited resources, and it’s possible that the system is running out of resources, such as memory or CPU. Check the system resource usage using tools like
top or htop to see if there are any resource-intensive processes running.
- Kernel issue: The crash may be related to a kernel issue, such as a bug in the kernel or a problem with a kernel module. Check the kernel logs, such as
/var/log/kern.log, to see if there are any error messages that may indicate the cause of the crash.
To further troubleshoot the issue, you can try the following steps:
- Check the system logs: Check the system logs, such as
/var/log/syslog and /var/log/messages, to see if there are any error messages that may indicate the cause of the crash.
- Run a system diagnostic: Run a system diagnostic tool, such as
systemd-analyze, to see if there are any issues with the system configuration or resource usage.
- Check for software updates: Check for software updates using
apt-get update and apt-get upgrade to ensure that the system is running with the latest software.
- Try a different kernel: Try booting the system with a different kernel version to see if the issue is kernel-related.
In comparison to other Jetson Orin Nano issues, this problem appears to be related to a system configuration or software issue, rather than a thermal or adapter problem. The logs do not indicate any thermal issues, and the system is not shutting down due to overheating. The issue is more likely related to a software or system configuration problem, which can be troubleshooted using the steps outlined above.
In terms of similar issues, there are a few other Jetson Orin Nano issues that may be related to this problem, such as:
- Jetson Orin Nano restarts while running building text-generation-webui: This issue is related to a software problem, where the system is crashing while running a specific application.
- Nvidia JetSon Nano Developer Kit: Not able to Install or not run able to run EfficientViT: This issue is related to a software problem, where the system is unable to install or run a specific application.
- Container torch_tensorrt not working: This issue is related to a software problem, where a container is not working correctly.
These issues may be related to the problem you are experiencing, and troubleshooting steps may be similar. However, the specific cause of the issue will depend on the system configuration and software running on the Jetson Orin Nano.
*** Please give the thumbs up if you get answers you like. Or provide feedback to help us improve the answer. ***
Hi,
Please record the serial console log when issue occurred.
Thanks
I checked again, the device does not reboots itself while there is some code running inside it. It reboots only when it is idle. After some point, it randomly restarts. The reset reason reported by the PMC is BCCPLEXWDT, indicating the hardware watchdog triggered after a kernel panic.
Two separate kernel panics were captured from /sys/fs/pstore/:
Crash 1 (dmesg-ramoops-0):
Unable to handle kernel paging request at virtual address 00ffff00008a5dcc
ESR = 0x0000000096000004, EC = 0x25: DABT (current EL)
FSC = 0x04: level 0 translation fault
Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP
CPU: 0, PID: 451, Comm: kworker/0:2
Call trace:
process_one_work
worker_thread
kthread
ret_from_fork
Crash 2 (dmesg-ramoops-1):
Kernel panic - not syncing: Fatal exception in interrupt
Call trace:
percpu_ref_get_many
refill_obj_stock
obj_cgroup_uncharge
memcg_slab_free_hook
kmem_cache_free
__d_free
rcu_core
rcu_core_si
handle_softirqs
irq_exit
handle_domain_irq
gic_handle_irq
Observations:
- Both crashes occur at idle with no user workloads running.
- railgate_enable is already 0 (/sys/devices/platform/bus@0/17000000.gpu/railgate_enable).
- jetson_clocks is running at all times.
- All packages are up to date as of April 2026 (apt reports nothing upgradable).
- No OOM, thermal, or hardware errors found in logs prior to the panics.
How can I exactly fix this problem?