bug: system update introduced gliteches.

[aleeusgr]

after nixos-rebuild switch gnome started to freeze.
some things point to nouveau; so I changed the driver: 2df8c8c, which helped.

Closing tmux tabs while playing music via youtube on brave I experienced a glitch for a few seconds, X server crashed and pushed me back to the login page.

I recall my Bluetooth speaker starting to glitch a while ago.

K900 says 6.8.3 may fix it

[aleeusgr]

thanks to propagandalf at nix discord.

{pkgs, ...}: {
  # Workaround for GNOME autologin: https://github.com/NixOS/nixpkgs/issues/103746#issuecomment-945091229
  systemd.services."getty@tty1".enable = false;
  systemd.services."autovt@tty1".enable = false;

  services.xserver.desktopManager.gnome.enable = true;
  services.udev.packages = with pkgs; [gnome.gnome-settings-daemon];
  environment.systemPackages = with pkgs; [gnomeExtensions.appindicator];
  environment.gnome.excludePackages =
    (with pkgs; [gnome-photos gnome-connections gnome-tour])
    ++ (with pkgs.gnome; [
      cheese # photo booth
      eog # image viewer
      epiphany # web browser
      gedit # text editor
      totem # video player
      yelp # help viewer
      file-roller # archive manager
      geary # email client
      gnome-calculator
      gnome-characters
      gnome-contacts
      gnome-maps
      gnome-music
      gnome-weather
    ]);
}

<@930457726323138570>

[aleeusgr]

try to set up proper driver:
https://nixos.org/manual/nixos/stable/#sec-x11-graphics-cards-nvidia

[aleeusgr]

yet just now again I had a glitch, although much milder than before.

[ 1604.795946] asus_wmi: Unknown key code 0xcf                                                                         
[ 3869.560324] BUG: kernel NULL pointer dereference, address: 000000000000001a                                         
[ 3869.560332] #PF: supervisor read access in kernel mode                                                              
[ 3869.560335] #PF: error_code(0x0000) - not-present page

researching the error I found:
NixOS/nixpkgs#300547

This should be fixed in 6.8.3; how do I get 6.8.3?

[aleeusgr]

try disabling Bluetooth as a workaround.

[aleeusgr]

To troubleshoot and find the reason for your Linux system crashes, follow these steps:

1. System Logs: Analyze the system logs to identify potential issues. You can view logs using commands like dmesg (kernel messages), syslog (system events), or journalctl (system journal, available in newer Linux distributions). Look for error messages or patterns that might indicate the cause of the crash.

2. Kernel Messages: Focus on kernel-related errors, as they often provide valuable information about hardware issues or software conflicts. You can filter kernel messages by using tools like dmesg | grep <modulename> or dmesg | grep <errorcode>.

3. System Check: Run a system check using tools like memtest86+ (memory testing) or smartctl (hard drive health checking). This will help you identify potential issues with memory or storage.

4. Recent Changes: Review any recent changes to your system, such as new software installations, kernel updates, or configuration changes. This can help you isolate the cause of the crash.

5. System State: Before the crash, note the system's state, including any running applications, open files, and system load. This information can be useful when trying to reproduce the issue.

6. Reproduction: Try to reproduce the crash by replicating the system state and activities leading up to the crash. This can help you identify a specific cause.

7. Debugging: If the issue persists, enable kernel debugging (if available) or use a debugging tool like strace or gdb to capture more detailed information about the system's state and behavior.

8. Consult Documentation: Refer to your Linux distribution's documentation and online resources for specific troubleshooting guides and known issues related to your system configuration.

9. Update and Upgrade: Ensure your system is up-to-date with the latest security updates and kernel patches. This might resolve issues caused by outdated software.

10. Professional Assistance: If none of the above steps help you identify the cause or resolve the issue, consider seeking professional assistance from a Linux administrator or developer.

Remember to always back up your data before attempting to troubleshoot or modify your system.

[aleeusgr]

$ dmesg

...

[    3.461249] ACPI BIOS Error (bug): Could not resolve symbol [\CTDP], AE_NOT_FOUND (20230628/psargs-330)             
[    3.461729] ACPI Error: Aborting method \_SB.IETM.IDSP due to previous error (AE_NOT_FOUND) (20230628/psparse-529)  
[    3.462230] ACPI Warning: \_SB.IETM._TRT: Return Package has no elements (empty) (20230628/nsprepkg-94)             
[    3.464055] intel_pmc_core INT33A1:00:  initialized                                                                 
[    3.466282] Consider using thermal netlink events interface                                                         
[    3.484031] ACPI BIOS Error (bug): Could not resolve symbol [\_SB.PC00.LPCB.EC0.SEN1._CRT.S1CT], AE_NOT_FOUND (20230
628/psargs-330)                                                                                                        
[    3.484376] ACPI Error: Aborting method \_SB.PC00.LPCB.EC0.SEN1._CRT due to previous error (AE_NOT_FOUND) (20230628/
psparse-529)                                                                                                           
[    3.485063] ACPI BIOS Error (bug): Could not resolve symbol [\_SB.PC00.LPCB.EC0.SEN1._HOT.S1HT], AE_NOT_FOUND (20230
628/psargs-330) 

[aleeusgr]

$ journalctl -p 3 -x | cut -d ':' -f 2- | sort -u

...
54:29 nixos gdm-password][1855]: gkr-pam: unable to locate daemon control file                                         
54:31 nixos kernel:                                                                                                    
54:31 nixos kernel: ACPI BIOS Error (bug): Could not resolve symbol [\CTDP], AE_NOT_FOUND (20230628/psargs-330)

59:31 nixos pulseaudio[2555]: org.bluez.BatteryProviderManager1.UnregisterBatteryProvider() Failed: org.freedesktop.DBu
s.Error.NoReply:Message recipient disconnected from message bus without replying                                       
-- Boot 03736ad6f53949aa95e97b7b6e2e3941 --                                                                            
-- Boot 03b4225e5795494cb05800e1ad719811 --

[aleeusgr]

Kernel panic - not syncing, fatal exception in interrupt.

Based on the provided search results, a kernel panic - not syncing, fatal exception in interrupt is a critical error that occurs when the kernel detects a fatal exception during an interrupt handling process. This error can be caused by various factors, including:

Hardware issues: Problems with the CPU, memory, or other hardware components can trigger a kernel panic.
Driver bugs: Faulty or incompatible device drivers can cause interrupt-related errors.
Software conflicts: Incompatible or buggy software, such as kernel modules or firmware, can lead to kernel panics.
Configuration issues: Incorrect system configuration, including BIOS settings or kernel parameters, can contribute to kernel panics.

Troubleshooting Steps

To resolve a kernel panic - not syncing, fatal exception in interrupt, follow these steps:

1. Check system logs: Review the system logs for any relevant error messages or clues about the cause of the panic.
2. Verify hardware: Ensure that all hardware components are functioning correctly and are properly configured.
3. Update drivers and firmware: Ensure that all device drivers and firmware are up-to-date and compatible with the system.
4. Disable unnecessary modules: Disable any unnecessary kernel modules to reduce the likelihood of conflicts.
5. Revert to a previous kernel: If possible, revert to a previous kernel version to isolate the issue.
6. Perform a memory test: Run a memory test (e.g., memtest86+) to identify any potential memory issues.
7. Consult documentation and forums: Refer to system documentation and online forums for specific guidance on resolving kernel panics related to the HiFive Unmatched board or other similar systems.

Conclusion

A kernel panic - not syncing, fatal exception in interrupt is a serious error that requires thorough investigation and troubleshooting. By following these steps and analyzing the search results, you can identify and potentially resolve the underlying cause of the issue.