Trying to Diagnose my Dual Xeon E5 Build - passed HCI memtest and Linx = no hardware issue?

[traderjay]

To help isolate issues in my dual XEON build, I tried the following troubleshooting procedures:

(CPU-Z Confirmed both CPUs are the same stepping)

- Running in single CPU mode
- Running in single RAM
- Tested all components on another X10DAX motherboard
- Tried different RAM model
- Tried different power supply
- Tried different GPU Model

Last night I was able to stabilize the system running in single CPU and updating the nvidia drivers to the latest version and setting performance mode to High. Adding the second CPU back to the motherboard resulted in BSOD again so I bought a copy of HCI Memtest pro and let it run and completed 100% coverage with no errors.

I also let Linx run for more than 12 errors without any errors or crashes. At this stage, can I rule out hardware issues?

UPDATE: ALL PROBLEM RESOLVED WOOOOHOOOOO!

Almost gave up and decided to plea for help online and an ex-lieutenant from the US Navy nuclear forces on anandtech saved my sorry butt. On a late Friday evening, he looked every every screenshot of my bios settings and told me to change two obscure XEON specific power saving features and it magically cleared up ALL my problems.

The following two are disabled on the BIOS:

- Disable C6 State Reporting
- Disable Spread Spectrum

 

[Terry Kennedy]

Adding the second CPU back to the motherboard resulted in BSOD again so I bought a copy of HCI Memtest pro and let it run and completed 100% coverage with no errors.

BSOD == Windows? Post the BSOD text (if running some version of Windows that still provides useful messages) and complete Windows version info. You can also go back to single CPU mode and boot Windows, then install / run something like WhoCrashed to see more details about the actual crash.

I also let Linx run for more than 12 errors without any errors or crashes. At this stage, can I rule out hardware issues?

Not necessarily - Windows could be doing something differently than Linux does, or even have a device driver for some part of the system that Linux either ignores or uses a generic driver for.

 

[CookiesLikeWhoa]

What version of Windows are you running? Non-Pro versions or 32bit versions can give some wonky results.

 

[lni]

not sure how you tested your linux run, I found the following open source stress test program pretty useful.

GitHub - stressapptest/stressapptest: Stressful Application Test - userspace memory and IO test

 

[traderjay]

What version of Windows are you running? Non-Pro versions or 32bit versions can give some wonky results.

Windows 10 Pro fresh install. I've been testing the system now in dual CPU config with two instances of Linx (problem size 61474, memory 31 GB) and its loading both CPU at 100% with 99% memory consumption. So far it just passed the 12 hours mark without problem.