Two-node configuration hangs at "UEFI starting" - System x3850 X5, x3950 X5

Resolving The Problem

Source

RETAIN tip: H202012

Symptom

After connecting two (2) System x3850 X5/ System x3950 X5 servers together using QuickPath Interconnect (QPI) scalability cables and powering up, the console screen hangs at the following message:

There may be no errors recorded in the System Event Logs (SEL) or Integrated Management Module (IMM) logs. There may also be no error Light Emitting Diodes (LEDs) on the Light Path Diagnostics (LPD); the QPI link LEDs show solid green (ok) LEDs.

Affected configurations

The system may be any of the following IBM servers:

• System x3850 X5, type 7145, any model
• System x3850 X5, type 7146, any model
• System x3950 X5, type 7145, any model

This tip is not software specific.

This tip is not option specific.

Workaround

1. Power off the servers and remove the AC power cables from both nodes.
2. Remove the QPI cables and check for any damage to the cable connectors.
3. Check the QPI connector pins for any damage.
4. If damage is found, then replace the affected component. If no damage is found, then reseat the QPI cables carefully. Make sure that the cables are firmly seated and the cable latch clicks into place.
   

Additional information

Unified Extensible Firmware Interface (UEFI) is attempting to initialize QPI and memory during this boot phase. If any QPI cable is not making proper connection with the processor board, then the boot processes cannot complete successfully and the system will hang.