List of common Failure modes Internal/NodeFailureModes

Node Problems Log

Please keep track of any and all known problems with nodes here. If something is a quick fix (i.e. replace hard drive) please bold that entry. Once a node has been fixed to not delete it's entry, move it to fixed, along with a date stamp and what was fixed.

Issues

Grid

• 8-7: Bad HDD?
• 3-20: fails to check in during imaging
• 18-1: fails to check in during imaging

SB1

• Node 1 segfaults, check temperature issues

OLD

Known Bad

Please list all nodes that are known to fail imagining/inventory here along with suspected problems

• 19-1: Boots but segfaulted during run, then locked up. Possible memory or cpu overheating problems
• 19-3: No disk
• 19-4: Dead Disk
• 19-17: Likely a bad CM cable running to the back

Questionable

Fixed

List of Node Failures

1 = good, 0 = bad

Front Face #	Disk	Memory	CPU / Mother Board	Fan	Network	Solution / Notes
1	1	1	1	1	1	Dies in the middle of PXE: Additional Errors see here
2	1	1	0	1	0	Fails to pxe regardless of memory installed.
3	1	1	0	1	0	Fails to pxe regardless of memory installed.
4	1	1	0	1	0	Fails to pxe regardless of memory installed.