Skip to content
View in the app

A better way to browse. Learn more.

Unraid

A full-screen app on your home screen with push notifications, badges and more.

To install this app on iOS and iPadOS
  1. Tap the Share icon in Safari
  2. Scroll the menu and tap Add to Home Screen.
  3. Tap Add in the top-right corner.
To install this app on Android
  1. Tap the 3-dot menu (⋮) in the top-right corner of the browser.
  2. Tap Add to Home screen or Install app.
  3. Confirm by tapping Install.

Consant crashes on gpu usage with ryzen

Featured Replies

Hello!
Some time back ago i made a similar post to this one and that is my unraid server keeps crashing if gpu is being used. I.E i watch something on jellyfin or plex it might crash, the server does not crash if my gpu's aren't being used so it can stay up for days just fine, but as soon as someone uses my plex or jellyfin there is a chance it will crash, it can happen almost instantly from it being used or an hour in or so (i think depending on file type).
So i am once again asking if anyone can see something that is in my diagnostics (from the most recent crash, i watched a show and it crashed).
i have tried doing a memtest aswell and that is all fine. tried installing my p2000 and using that and it works great until server crashes.
Tried running unraid without plex or jellyfin (no crashes, i can run them fine by itself, as soon as someone waches something then theres an issue). i have tried different ram, only 1 drive, no gpu, safemode, different motherboard, different cpu (same type but different chip) and disabling c-type, set ram speed to 2933 and power setting in bios as was recommended for keeping ryzen servers stable. Ryzen seems to not be able to log "Machine Check Events detected on your server" as good as intel not sure why but i can't see anything except for the standard safe to ignore messages from MCE:
 

Quote

Jun 12 01:26:05 fatbeast kernel: mce: [Hardware Error]: Machine check events logged Jun 12 01:26:05 fatbeast kernel: mce: [Hardware Error]: CPU 17: Machine Check: 0 Bank 1: bc800800060c0859 Jun 12 01:26:05 fatbeast kernel: mce: [Hardware Error]: TSC 0 ADDR a69a80d40 MISC d012000000000000 IPID 100b000000000 Jun 12 01:26:05 fatbeast kernel: mce: [Hardware Error]: PROCESSOR 2:a20f12 TIME 1686525931 SOCKET 0 APIC b microcode a20120a

Jun 12 01:27:52 fatbeast kernel: md: recovery thread: check P ... Jun 12 01:36:06 fatbeast root: Fix Common Problems: Error: Machine Check Events detected on your server Jun 12 01:36:06 fatbeast root: mcelog: ERROR: AMD Processor family 25: mcelog does not support this processor. Please use the edac_mce_amd module instead.



Syslinux conf:
OS GUI
kernel /bzimage
append rcu_nocbs=0-23 initrd=/bzroot,/bzroot-gui video=efifb:off

OS
kernel /bzimage
append rcu_nocbs=0-23 initrd=/bzroot video=efifb:off

Server parts:
Motherboard: ASUS TUF GAMING B550-PRO
CPU: AMD Ryzen 9 5900X 12-Core 
RAM: 128 GiB DDR4 Multi-bit ECC
Storage: Seagate IronWolf PRO 3,5" NAS HDD 8TB x6
Cache: Kingston KC3000 M.2 2280 NVMe SSD 1TB
Encoding gpu: Quadro p2000
VM GPU: Geforce gtx 1080TI

If anyone has any ideas as to why this happends please do let me know, i will be forever thankful

fatbeast-diagnostics-20230612-0158.zip

Solved by AceBoyden

  • Author

Server crashed around 8 times within 24 hours, same as before, tried moving the p2000 to different pci slot and removed the 1080ti still same issue, even with just the 1080ti on another pci slot

  • Author
  • Solution

SOLVED.

Was a memory issue where it only used 0.5Gb of ram and overloaded and crashed.

May i ask if you could explain this further? I have somewhat of a similar problem with my server, See here.
Mine mostly crashes when using plex now but also seemingly random with no Log explanation whatsoever.

Edited by DAREKON
Typo

  • Author
1 minute ago, DAREKON said:

May i ask if you could explain this further? I have somewhat of a similar problem with my server, See here.
Mine mostly crashes when using plex now but also seemingly random with no Log explanation whatsoever.

For me it was that 1 of my vm’s and 1 of my docker container tried to use more ram that what was assigned so server just turned off.

 

you could try to disable your docker containers and see if the issue still persist when you install your vm. Also do install a plugin called fix common problems to see if that catches on anything. If you’re using something to download media try disabling it and then try everything 

5 minutes ago, AceBoyden said:

you could try to disable your docker containers and see if the issue still persist when you install your vm. Also do install a plugin called fix common problems to see if that catches on anything. If you’re using something to download media try disabling it and then try everything 

I did everything but install the Plugin. Will try that after reassembling it to its original state.

Still, thank you for your reply ^^

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Guest
Reply to this topic...

Account

Navigation

Search

Search

Configure browser push notifications

Chrome (Android)
  1. Tap the lock icon next to the address bar.
  2. Tap Permissions → Notifications.
  3. Adjust your preference.
Chrome (Desktop)
  1. Click the padlock icon in the address bar.
  2. Select Site settings.
  3. Find Notifications and adjust your preference.