cancel
Showing results for 
Search instead for 
Did you mean: 

Processors

longcheung
Journeyman III

AMD 9004 running KVM autoreboot

Hello sir,

We have encountered some issues with AMD CPUs. We have been running KVM on the 3rd generation 7003 series CPUs, and it has been very stable. However, after switching to the 4th generation 9004 series CPUs six months ago, we have been experiencing frequent automatic restarts. We are using ROCKY LINUX, and after the automatic restart, we couldn't find any relevant logging in the system or IPMI.


Here are the methods we have tried:


1. Initially, we thought the issue might be overheating with the 9654 CPU. However, we also experienced the same problem with the 9634 CPU, and the temperatures were around 70 degrees Celsius.


2. We tried different versions of the kernel (4, 5, 6), but the issue persisted.


3. We originally used Gigabyte servers and later switched to ASUS, but the situation remained the same.


4. We disabled the following options in the BIOS:
• Power Supply Idle Control --> Typical Current Idle
• Global C-state control --> Disabled


5. We used the following kernel option:• processor.max_cstate=0


Do you have any suggestions for our next steps? We haven't been able to find a solution because the same KVM configuration runs without any issues on the 3rd generation CPUs.

0 Likes
1 Reply
BillyFeltrop
Challenger

Since the same KVM configuration runs smoothly on the 3rd generation CPUs, it suggests that the problem might be specific to the 4th generation CPUs or their compatibility with your setup.

Here are some additional steps you can consider:

  1. Firmware Updates: Ensure that you have the latest firmware/BIOS updates installed for your ASUS servers. Sometimes, firmware updates address known issues and improve compatibility.

  2. Contact Support: Reach out to AMD support or the server manufacturer's support team for assistance. They may be able to provide specific guidance or identify any known issues related to the 4th generation CPUs and KVM.

  3. Troubleshooting Logs: Check if you can enable additional logging options in the BIOS or the operating system to gather more information about the automatic restarts. Detailed logs might help pinpoint the root cause.

  4. Compatibility Testing: If possible, try running a different hypervisor or operating system on the 4th generation CPUs to see if the issue persists. This can help determine if it's a specific interaction between KVM and the CPUs.

  5. Community Forums: Explore forums or discussion boards related to ROCKY LINUX, KVM, or AMD CPUs. Other users or experts might have encountered similar issues and can provide insights or potential solutions.

It's important to note that diagnosing and resolving hardware compatibility issues can be complex, and it may require a combination of troubleshooting steps and expert assistance.

PC Hardware Specialist
0 Likes