Locating And Servicing - IBM Power Systems S822LC Technical Overview And Introduction

(SEL). There is also an eSEL that contains extra First Failure Data Capture (FFDC) from the
Host Boot, OCC, and OPAL subsystems that are associated with each SEL. For system
checkstop errors, OCC collects FIR data to PNOR, and Host Boot central electrical complex
diagnostic tests creates a SEL based on the FIR data in PNOR.
When the system can be successfully restarted either manually or automatically, or if the
system continues to operate, the host Linux OS can monitor the SELs on the service
processor through IPMI tool. Hardware and software failures are recorded in the SELs and
can be retrieved through IPMI interface. There is a plan to report SELs in the system log of
the operating system.
The system can report errors that are associated with PCIe adapters/devices.
For some example SEL events, see Example 2-2.
Example 2-2 Example of SEL events
31 | 09/04/2015 | 15:11:40 | Power Unit #0x1c | Power off/down | Asserted
32 | 09/04/2015 | 15:11:40 | Power Supply #0xcd | Presence detected | Deasserted
33 | 09/04/2015 | 15:11:40 | Power Supply #0xce | Presence detected | Deasserted
34 | 09/04/2015 | 15:11:43 | Power Supply #0xcd | Presence detected | Asserted
35 | 09/04/2015 | 15:11:43 | Power Supply #0xce | Presence detected | Asserted
36 | 09/04/2015 | 15:11:47 | System Firmware Progress #0x05 | Motherboard initialization | Asserted
37 | 09/04/2015 | 15:12:11 | Fan #0xd4 | Upper Non-critical going high | Asserted
38 | 09/04/2015 | 15:12:11 | Fan #0xd4 | Upper Critical going high | Asserted
39 | 09/04/2015 | 15:12:11 | Fan #0xd4 | Upper Non-recoverable going high | Asserted
3a | 09/04/2015 | 15:12:12 | Fan #0xd5 | Upper Non-critical going high | Asserted
3b | 09/04/2015 | 15:12:12 | Fan #0xd5 | Upper Critical going high | Asserted
3c | 09/04/2015 | 15:12:12 | Fan #0xd5 | Upper Non-recoverable going high | Asserted
3d | 09/04/2015 | 15:12:12 | Fan #0xd6 | Upper Non-critical going high | Asserted
3e | 09/04/2015 | 15:12:13 | Fan #0xd6 | Upper Critical going high | Asserted
3f | 09/04/2015 | 15:12:13 | Fan #0xd6 | Upper Non-recoverable going high | Asserted
40 | 09/04/2015 | 15:12:13 | Fan #0xd7 | Upper Non-critical going high | Asserted
41 | 09/04/2015 | 15:12:13 | Fan #0xd7 | Upper Critical going high | Asserted
42 | 09/04/2015 | 15:12:13 | Fan #0xd7 | Upper Non-recoverable going high | Asserted
43 | 09/04/2015 | 15:12:13 | Fan #0xd4 | Upper Non-recoverable going high | Deasserted
44 | 09/04/2015 | 15:12:13 | Fan #0xd4 | Upper Critical going high | Deasserted
45 | 09/04/2015 | 15:12:13 | Fan #0xd4 | Upper Non-critical going high | Deasserted
46 | 09/04/2015 | 15:12:13 | Fan #0xd5 | Upper Non-recoverable going high | Deasserted
47 | 09/04/2015 | 15:12:13 | Fan #0xd5 | Upper Critical going high | Deasserted
48 | 09/04/2015 | 15:12:14 | Fan #0xd5 | Upper Non-critical going high | Deasserted
To service a Linux system end to end, Linux service and productivity tools must be installed.
You can find them at the following website:
http://www.ibm.com/support/customercare/sas/f/lopdiags/home.html
The tools are automatically loaded if IBM manufacturing installs the Linux image or IBM
Installation Toolkit. PowerPack is the preferred way to install required service packages from
the website. The Linux call home feature is also supported in a stand-alone system
configuration to report serviceable events.

Locating and servicing

The final component of a comprehensive design for serviceability is the ability to locate and
replace effectively parts requiring service. POWER processor-based systems use a
combination of visual cues and guided maintenance procedures to ensure that the identified
part is replaced correctly every time.
40
IBM Power Systems S822LC for High Performance Computing