wiki:Internal/NodeFailureModes

Version 11 (modified by ssugrim, 15 years ago) ( diff )

List of Node Failures

Node Failure Mode Solution / Notes
[1,5] Pxe Halt - Locks up during execution of PXE code Multiple resets (more than 1)
may be required
Might require node Change
[1,5] Dead Node ID box top LED (the blinking one) Power cycle Fixed it
Rabbit Issue?
[3,8] First Power on Halt Locks during the first attempt
Post after reset
[17,4] First Power on Halt Locks during the first attempt
no serial console output
[1,14] First Power on Halt Locks during the first attempt
Reset Fixes it
has new disk
[20,19] Disk Failure Kernel Throws errors during imageing
Disk Changed
[12,9] Disk Controller Failure Disk controller was having issues, disks were being incorrectly recognised
[3,18] Disk Failure Disk Write errors
Disk replaced
[5,11] Disk Failure Disk Write errors
Disk replaced
[14,11] Disk Failure Disk Write errors
Disk replaced
[13,5] Lock Up Rabbit and Node were halted
Power cycled
[4,11] Disk Failure Disk Write errors
Disk replaced
[5,9] Disk Failure Disk Write errors
Disk replaced
[9,11] Disk Failure Disk Write errors
Disk replaced
[3,19] Bad Node Mother board Failure, refused to boot
Replaced
Note: See TracWiki for help on using the wiki.