I have a Supermicro X9DR3-i/F running the latest BIOS with two Intel Xeon E5-2667 v2. The server is freezing but not restarting or shutting down. This seemed to only happen when the server had been on for about a month. I thought it was just OS instability, but today it happened again after only being up for four days. I investigated the IPMI event log and its showing “CPLD CATERR – Asserted”. Any ideas on what is causing this? I noticed in the IPMI after the error all the RAM slots were showing as not present in the sensor list, I am running a mem test now.
Memtest finished, no errors reported.
Possibly a ram error but may be cause d by connection the to CPU
Try reseating the CPUs first. If that doesn’t work you will need to eliminate one component at a time, namely drop to one CPU, half the ram, see what happens. If you workload can’t support a month of testing doing that then it is time for an upgrade.
I reseated the CPU’s and RAM, now we wait.
I think the CPU reseating may have fixed the issue. The server has been up for 51 days now, however I upgraded the hypervisor and did not re-enable IOMMU so next reboot I will enable that.
Congratulations. I suggest you mark the thread as solved so others can learn from your experience.
Good luck with the new setup.
This topic was automatically closed 273 days after the last reply. New replies are no longer allowed.