Help with HMPC diagnosis RP7420

[Jimmie Mayfield]

Any suggestions about what this is trying to tell me would be greatly appreciated:

******* Unexpected HPMC. Processor HPA FFFFFFFF'FC0F8000 *******
GENERAL REGISTERS:
r00/03 00000000'00000000 00000000'00CCD800 00000000'003DEAF4 400003FF'FFFF1E08
r04/07 00000000'00000000 400003FF'FFFF1E08 00000000'49C19060 00000000'00000003
r08/11 00000000'00000003 00000000'00000001 00000000'00CCF800 00000000'00000003
r12/15 400003FF'FFFF03A0 00000000'4000A730 00000000'00BD5828 00000000'00948B24
r16/19 00000000'00BD6908 00000000'00000004 00000000'40002558 00000000'01111E90
r20/23 00000000'00001000 00000000'00001000 00000000'00001000 00000000'00000000
r24/27 00000000'00000004 FFFFFF81'017F0000 00000000'011111B0 00000000'00CD6000
r28/31 FFFFFF81'017F1000 00000000'0000000A 400003FF'FFFF1FA8 00000000'00000004
CONTROL REGISTERS:
sr0/3 00000000'00000000 00000000'07253000 00000000'00000000 00000000'00000000
sr4/7 00000000'00000000 00000000'0E0DB400 00000000'0F158800 00000000'00000000
pcq = 00000000'00000000.00000000'003E1FF4 00000000'00000000.00000000'003E1FF8
isr = 00000000'A6260405 ior = C0000000'FC7E0000 iir = 4B9C0000 rctr = 63F940AD

pid reg cr8/cr9 00000000'0000ACBF 00000000'0000C32C
pid reg cr12/cr13 00000000'00000000 0000B1F7'00000000
ipsw = 00000000'0804001F iva = 00000000'0002A000 sar = 35 ccr = C0
tr0/3 00000000'01524790 00000000'000377F0 00000000'00000003 00000000'01524790
tr4/7 00000000'00BD6908 00000000'00000004 00000000'00170E50 00000000'00000001
eiem = FFFFFFF0'FFFFFFFF eirr = 00000008'00000000 itmr = 00003105'04CD26F7
cr1/4 00000000'00000000 00000000'00000000 00000000'00000000 00000000'00000000
cr5/7 00000000'00000000 00000000'00000000 00000000'00000000
MACHINE CHECK PARAMETERS:
Check Type = 20000000 CPU STATE = 9E000000 Cache Check = 00000000
TLB Check = 00000000 Bus Check = 00000000 PIM State = ? SIU Status = ????????
Assists = 00000000 Processor = 00000000
Slave Addr = 00000000'00000000 Master Addr = 00000000'00000000


HPMC, pcsq.pcoq = 0'0.0'3e1ff4 , isr.ior = 0'a6260405.c0000000'fc7e0000
@(#) $Revision: vmunix: vw: -proj selectors: CUPI80_BL2000_1108 -c 'Vw for CUPI80_BL2000_1108 build' -- cupi80_bl2000_1108 'CUPI80_BL2000_1108' Wed Nov 8 19:24:56 PST 2000 $High-priority machine check: (display==0xd910, flags==0x0)
Processor 1 TOC: pcsq.pcoq = 0'0.0'17cc24
isr.ior = 0'10340005.0'4791f1d8
Processor 2 TOC: pcsq.pcoq = 0'0.0'17cc3c
isr.ior = 0'10340005.0'485205a0
Processor 4 TOC: pcsq.pcoq = 0'3fffffff.ffffffff'ffc9c044
isr.ior = 0'9a07fffc.c0000000'a82ac8d
* CPU State 0x9e000000
* Bus Check 0x0

[Tobias Hartlieb]

Hi,

this needs to be analyzed by HP. You probably still have at least Warranty on your RP7420... Get in contact with your local HP support and provide the most recent files of /var/tombstones/ ...

Regards.

Tobias

[Sameer_Nirmal]

Hi,

The error could be described as
An unexpected High Priority Machine Check ( HPMC ) has occured and encounterd by processor 3 ( FFFFFFFF'FC0F8000 ) . The HPMC on this processor has caused other processors ( 1,2,4) to perform TOC
( Transfer of Control ).
Most of the time the cause of HPMC turns out to be a hardware malfunctioning , but it may be caused by software ( rare though ) . To know the cause of the HPMC , the tombstones located at /var/tombstones/ts99 need to be analysed. This can only be done by HP. Raise a h/w call to HP and provide them this file, errors logged in syslog, console, MP -> SL -> E etc.

I suspect the problem could be with CPU 3 on the cell board. This should have caused a reboot. Check the processors status with MP -> CM -> PS . Check in the OS OE as well through # ioscan -fnC processor
# sar -uM 5 5

[Tonya Underwood]

Please attach the following file:

/var/tombstones/ts99