killeriq

Family 6 Model 92 CPU: only decoding architectural errors

15 posts in this topic

Hello,

 

In "Fix Common Problems" ive got notice:

Machine Check Events detected on your server

Your server has detected hardware errors. You should install mcelog via the NerdPack plugin, post your diagnostics and ask for assistance on the unRaid forums. The output of mcelog (if installed) has been logged

 

 

 

So ive run : 
mcelog: Family 6 Model 92 CPU: only decoding architectural errors 

 

----

I have ASrock J4205-ITX mainboard

What's next? :)

 

thanks

0

Share this post


Link to post
Share on other sites

Post a diagnostics.  It may be mcelog does not support that processor, but need more info from syslog to verify.

0

Share this post


Link to post
Share on other sites

Posted (edited)

Quote

May  4 21:35:03 unRAIDTower mcelog: Running trigger `unknown-error-trigger'
May  4 21:35:03 unRAIDTower mcelog: CPU 0 on socket 0 received unknown error
May  4 21:35:03 unRAIDTower mcelog: Location: CPU 0 on socket 0

Quote


May  4 21:35:04 unRAIDTower root: Uncorrected error

 

A hardware failure did trigger the machine check event.  But mce doesn't have it classified 

Quote

The unknown-error-trigger runs on any errors not otherwise categorized.

 

If the mce doesn't re-occur (reset your server to clear out the already existing log), then I'd chalk it up to the stars just weren't aligned properly.

 

But, if it does reoccur, then its going to wind up being on of the following

 

- Power Supply

- CPU

- Motherboard (in particular the voltage regulation on the board)

 

Unfortunately, only if the problem is reoccuring can you diagnose what is actually causing it...  And of course we don't know if anything was actually affected by the uncorrected error or not.

Edited by Squid
0

Share this post


Link to post
Share on other sites

Not sure if mcelog is running as daemon with this plugin, can try from console/telnet/SSH, enter

mcelog --client > mcelog.txt

and post the txt file if it contains anything, preferably after unRAID has been running for several hours/days.

 

Beyond that I can only suggest rebooting and running the memtest from the boot menu at least overnight to see if you get memory errors.  If none and the server is not locking up then I'd say ignore it.

0

Share this post


Link to post
Share on other sites

This is what ive got:

root@unRAIDTower:/mnt/user/Appz# mcelog                                                                                                    
mcelog: Family 6 Model 92 CPU: only decoding architectural errors                                                                          
root@unRAIDTower:/mnt/user/Appz# mcelog --client > mcelog.txt
mcelog: client connect: No such file or directory                                                                                          
mcelog: client command write: Transport endpoint is not connected                                                                          
mcelog: client read: Invalid argument                                                                                                      
mcelog: client connect: No such file or directory                                                                                          
mcelog: client command write: Transport endpoint is not connected                                                                          
mcelog: client read: Invalid argument 

 

unraidtower-diagnostics-20170516-0121.zip

0

Share this post


Link to post
Share on other sites

Did you run the memtest overnight?

0

Share this post


Link to post
Share on other sites

did the test for the whole night cca 8h and no issue , RAM are new did test also before i build the server.

But now server was if some failed state, not sure if you can see the error in diag, so i made screenshot as well.

 

I didnt had those issues before, strange - ive changed USD flash drive before i bought the product, but as far i understand it just load it once during the boot and thats it...

unraidtower-diagnostics-20170519-1405.zip

C360_2017-05-19-13-59-24-255.jpg

0

Share this post


Link to post
Share on other sites

Noticed the clocksource doing dance between tsc and hpet.  Perhaps Apollo Lake support in 4.9 Kernel not quite fully ready?  Someone with more Kernel experience will need to chime in or get the attention of Limetech.

0

Share this post


Link to post
Share on other sites

no clue :( hope someone from Limetech could have a look - or i might try to mail them, if no reply within few days

 

thanks anyway!

0

Share this post


Link to post
Share on other sites

Tsc was final clocksource and had switched to it from hpet. I had a loop in my search and didn't catch it and assumed it switched from tsc back to hpet, but it didn't for the duration of the log that was posted. If keep having issues post another diagnostic before rebooting, if possible.

 

Sent from my ASUS_Z00AD using Tapatalk

 

 

 

 

0

Share this post


Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!


Register a new account

Sign in

Already have an account? Sign in here.


Sign In Now

Copyright © 2005-2017 Lime Technology, Inc. unRAID® is a registered trademark of Lime Technology, Inc.