Fujitsu Supercomputer PRIMEHPC FX700, Руководство по модернизации и обслуживанию

Страница: 30 / 105

UNITID=[ machine ID ],[ level ]:[ 1st suspected FRU ]([SerialNo]):[ 2nd
suspected FRU
]([SerialNo]):[
1st suspected FRUE
]:[
message text
]
[code1] [code2] [code3] [code4] [code5] [code6] [code7] [code8]
Chapter 3 Basic Hardware Procedures
This chapter describes the use of diagnostic information as well as hardware handling procedures.
3.1 Using Diagnostic Information
The BMC sends a failure notification via an SNMP trap in the following notification format when a hardware
failure occurs.
SNMP Trap Notification Format
Perform the following diagnostic procedure to identify the faulty FX700 main unit and parts.
3.1.1 Identifying the FX700 Main Unit
Identify the faulty FX700 main unit from the machine ID in the SNMP trap notification.
If working in a data center environment or server room, make the ID lamp blink so that you can easily
identify the FX700 main unit or blade.
Use the BMC Web GUI to make the identification LED blink, or use an IPMI command to turn on the LED.
After successfully completing the maintenance work, be sure to turn off the identification LED.
3.1.2 Determining the Error Level
You can determine the error level from [level] in the format of the SNMP trap notification. Using the Web
GUI, you can also identify the error level from the [FRU information] screen.
For details on how to log in, see "3.1.1 FRU Information" in the FUJITSU Supercomputer PRIMEHPC
FX700 BMC User's Guide
(C120-0091EN).
3.1.3 Identifying a Faulty Part
- You can identify the faulty part from [suspected FRU] in the format of the SNMP trap notification.
- You can identify the faulty part from the CMU/FAN/PSU alarm LED.
For details, see "1.2 Buttons and LEDs on the FX700 Main Unit" in the FUJITSU Supercomputer
PRIMEHPC FX700 Operating Manual
(C120-0089EN).
- You can identify the faulty part from the [FRU Information] screen by using the Web GUI.
For details, see "3.1.1 FRU Information" in the FUJITSU Supercomputer PRIMEHPC FX700 BMC
User's Guide (C120-0091EN).
Chapter 3 Basic Hardware Procedures
C120-0090-04EN
3.1 Using Diagnostic Information
9