Repeated Machine Check Events on new X15 / MW34-SP0 / i7-14700 — looking for guidance

Hardware
1

I have a brand-new X15 system and recently had the Unraid Fix Common Problems plugin alert with:

Machine Check Events detected on your server

I am trying to determine whether this is something others have seen on similar hardware, whether it may be firmware/kernel related, or whether I should be treating it as an early hardware issue.

System details

Server: 45Homelab / 45Drives X15
Motherboard: Gigabyte MW34-SP0 rev 1.1
CPU: Intel Core i7-14700
RAM: ECC UDIMM, 64 GB
OS: Unraid 7.3.1
Kernel: 6.18.33-Unraid
CPU microcode: 0x133
BMC/IPMI SEL: no matching hardware events logged

Kernel MCE history

The kernel has logged repeated generic MCE notifications since boot:

[Wed Jul  1 02:23:46 2026] mce: [Hardware Error]: Machine check events logged
[Wed Jul  1 03:08:54 2026] mce: [Hardware Error]: Machine check events logged
[Thu Jul  2 04:49:11 2026] mce: [Hardware Error]: Machine check events logged
[Thu Jul  2 18:50:03 2026] mce: [Hardware Error]: Machine check events logged
[Thu Jul  2 21:27:54 2026] mce: [Hardware Error]: Machine check events logged
[Fri Jul  3 00:10:19 2026] mce: [Hardware Error]: Machine check events logged
[Fri Jul  3 00:12:09 2026] mce: [Hardware Error]: Machine check events logged
[Fri Jul  3 05:29:56 2026] mce: [Hardware Error]: Machine check events logged
[Fri Jul  3 12:23:03 2026] mce: [Hardware Error]: Machine check events logged

Fix Common Problems also logged:

Jul  3 12:05:01 x15 root: Fix Common Problems: Error: Machine Check Events detected on your server
Jul  4 04:40:05 x15 root: Fix Common Problems: Error: Machine Check Events detected on your server

After opening Fix Common Problems and rescanning, the plugin currently shows no active errors or warnings, but the MCE history is still present in dmesg/syslog.

What I checked so far

mcelog:
- /usr/sbin/mcelog exists
- /dev/mcelog exists
- mcelog --client returned no decoded records
- direct read from /dev/mcelog returned no queued records
- I briefly started the mcelog daemon, but it did not recover historical detail

rasdaemon:
- not installed / not available on this Unraid install

IPMI/BMC:
- no matching entries in the SEL / event log

PCIe AER:
- AER is enabled
- no corrected/uncorrected/fatal PCIe AER errors were shown in dmesg

EDAC:
- EDAC modules are present
- igen6_edac loads
- edac_core loads
- but no memory controller is registered
- /sys/devices/system/edac/mc has no mc0

CPU / kernel output

Linux x15 6.18.33-Unraid #1 SMP PREEMPT_DYNAMIC Mon May 25 10:59:51 PDT 2026 x86_64 Intel(R) Core(TM) i7-14700 GenuineIntel GNU/Linux

model name      : Intel(R) Core(TM) i7-14700
microcode       : 0x133

EDAC check

Loaded modules after modprobe:
skx_edac_common
igen6_edac
edac_core

/sys/devices/system/edac/mc:
no mc0 present

Current interpretation

At this point I only have the generic kernel MCE notifications, with no decoded bank/status/source. The system has not crashed or rebooted. IPMI/BMC SEL is clean, PCIe AER is clean, and EDAC does not expose usable memory-controller counters.

I do not have enough detail to say whether this is corrected memory-related, CPU/cache/interconnect-related, firmware/microcode-related, or something else.

Questions

  1. Has anyone seen repeated generic MCEs like this on the X15 / MW34-SP0 / Intel 14th-gen platform?
  2. Is there a recommended BIOS/BMC version or BIOS setting set for this platform?
  3. Is this likely to be a known firmware/kernel/microcode reporting issue, or should I treat it as probable hardware instability?
  4. Is there a preferred way to capture decoded MCE detail on Unraid for this platform, given that mcelog did not recover anything and EDAC does not expose mc0?
  5. Would you recommend running MemTest86 / firmware updates first, or opening a support ticket directly with 45Drives?

Any suggestions on next diagnostic steps would be appreciated.

2

Thanks to @Valtazarr. Additional finding: I checked DIMM population with dmidecode and found both 32 GB ECC UDIMMs were installed in the A-channel slots: DIMM_P0_A0 and DIMM_P0_A1. The MW34-SP0 manual labels the preferred 2-DIMM dual-channel layout as DIMM_A1 + DIMM_B1, so this likely maps to the two black slots rather than adjacent A1/A2. I plan to move the second DIMM from A2 to B1, then retest to see whether the MCEs recur. I am not assuming this explains the MCEs yet, but it seems worth correcting before further hardware diagnosis.

1 Like
3

Update: MCEs recurred after RAM swap

I swapped the RAM and rebooted on Jul 6 at approximately 03:32.

Initially the system showed 0 MCEs after the reboot, but the issue has now recurred:

system boot  2026-07-06 03:32

MCE count this boot: 2

[Tue Jul  7 03:34:32 2026] mce: [Hardware Error]: Machine check events logged
[Tue Jul  7 06:00:25 2026] mce: [Hardware Error]: Machine check events logged

So the RAM swap did not resolve it. The first post-swap MCE occurred about 24 hours after reboot, and the second occurred about 2h 26m later.

At this point I do not think this can be attributed only to the original RAM. It may still be memory-path related, but I am now also considering motherboard/DIMM slot, CPU memory controller, BIOS/memory training, firmware/microcode, CPU/cache/interconnect, or platform power behavior.

I captured fresh Unraid diagnostics and a post-swap MCE log,

4

I have posted to Unraid general support forums as well.

5

Hey, can you reach out to support@45homelab.com so one of our support members can assist you with the isuse your having