Unexpected HPMC. Processor HPA FFFFFFFF'FFFA2000 ***

[Robert T. Lott]

Pls, someone I need help really fast on this one. My HP-PRC-HP K580 crashed yesterday and I still haven't figured out what's wrong with it. Can someone take a look at the attached files and give me some good feedback... Server is down users unable to work.

Attached is my TS99
Pls, also see my camcs Chassis FLT Codes at time of Crash listed below...:
20041106.102217 CRENDI7T (426)

-- n0125020 Thu Nov 4 18:15:55 EST 2004
-- n0125020 Thu Nov 4 18:31:08 EST 2004
-- n0125020 Thu Nov 4 18:45:11 EST 2004
-- n0125020 Thu Nov 4 19:01:13 EST 2004
-- n0125020 Thu Nov 4 19:15:18 EST 2004
-- n0125020 Thu Nov 4 19:30:30 EST 2004
-- &j2D&j10L
-- FLT CBF0&jC&j1D&j2D&j10L
-- FLT 5207&jC&j1D&j2D&j10L
-- FLT 5108&jC&j1D&j2D&j10L
-- FLT 5708&jC&j1D&j2D&j10L
-- FLT 7D03&jC&j1D&j2D&j10L
-- FLT 5308&jC&j1D&j2D&j10L
-- FLT 7D03&jC&j1D&j2D&j10L
-- FLT 5608&jC&j1D&j2D&j10L
-- FLT 5402&jC&j1D&j2D&j10L
-- FLT 5008&jC&j1D&j2D&j10L
-- FLT 5402&jC&j1D&j2D&j10L
-- FLT 7D03&jC&j1D&j2D&j10L
-- FLT 5402&jC&j1D&j2D&j10L
-- FLT 7D03&jC&j1D&j2D&j10L
-- FLT 5508&jC&j1D&j2D&j10L
-- FLT 7D03&jC&j1D&j2D&j10L
-- FLT 5508&jC&j1D&j2D&j10L
-- FLT 5402&jC&j1D&j2D&j10L
-- FLT 5508&jC&j1D&j2D&j10L
-- FLT 5402&jC&j1D&j2D&j10L
-- FLT CBFB&jC&j1D&j2D&j10L
-- FLT 5508&jC&j1D&j2D&j10L
-- FLT CBFB&jC&j1D&j2D&j10L
-- FLT 5508&jC&j1D&j2D&j10L
-- FLT CBFB&jC&j1D
PM ******* Unexpected HPMC. Processor HPA FFFFFFFF'FFFA2000 *******
-- GENERAL REGISTERS:
-- r00/03 00000000'00000000 00000000'00C13290 00000000'00000000 00000000'00000001
-- r04/07 00000000'00000000 00000000'027F13C8 00000000'027F1D78 00000000'00A4DA90
-- r08/11 00000000'00000000 00000000'00F254E8 00000000'00C10290 00000000'00C11290
-- r12/15 00000000'00C13290 00000000'00C13290 00000000'00C11290 00000000'00C15A90
-- r16/19 00000000'027F4630 00000000'00000000 00000000'00000000 00000000'00000005
-- r20/23 00000000'00000000 00000000'00000000 00000000'00000000 00000000'00000001
-- r24/27 00000000'00000000 00000000'00000000 00000000'0DB03530 00000000'00C15A90
-- r28/31 00000000'00000000 00000000'0D3CA290 00000000'0D3CA2C0 00000000'0F77822F
-- CONTROL REGISTERS:
-- sr0/3 00000000'0EBFA000 00000000'02A88400 00000000'0E3D9400 00000000'00000000
-- sr4/7 00000000'00000000 00000000'FFFFFFFF 00000000'0C044000 00000000'00000000
-- pcq = 00000000'00000000.00000000'00181730 00000000'00000000.00000000'00181734
-- isr = 00000000'10340009 ior = 00000000'FC7F15A0 iir = 92402000 rctr = 7E922C6A
-- pid reg cr8/cr9 00000000'0000E4AF 00000000'0000F6E4
-- pid reg cr12/cr13 00000000'00000000 00000000'00000000
-- ipsw = 000000FF'0804FF1F iva = 00000000'0002A000 sar = 01 ccr = C0
-- tr0/3 00000000'027F13C8 00000000'000377F0 00000000'00000000 00000000'400342F8
-- tr4/7 00000000'00000019 000236BB'B5C475BE 00000000'00176BD0 00000000'0D3CA2C0
-- eiem = FFFFFFF0'FFFFFFFF eirr = 80000000'00000000 itmr = 000236BB'B60033B4
-- 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 = 9E000004 Cache Check = 00000000
-- TLB Check = 00000000 Bus Check = 0030000D PIM State = ? SIU Status = ????????
-- Assists = 00000000 Processor = 00000000
-- Slave Addr = FFFFFFFF'FFFA2000 Master Addr = FFFFFFFF'FFFA0000
nh HPMC, pcsq.pcoq = 0'0.0'181730 , isr.ior = 0'10340009.0'fc7f15a0
-- @(#) $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 $Hig
-- heck: (display
-- ==0xd910, flags==0x0)
-- Processor 1 TOC: pcsq.pcoq = 0'ebfa0f0.f0'f0016698
-- isr.ior = 0'9227c3c0.c0000000'4210808c
-- Processor 3 TOC: pcsq.pcoq = 0'f0.f0'f0016698
-- isr.ior = 0'9227c3c0.c0000000'4290ae8c
-- Processor 4 TOC: pcsq.pcoq = 0'f0.f0'f0016698
-- isr.ior = 0'9227c3c0.c0000000'4310c58c
-- Processor 5 TOC: pcsq.pcoq = 0'f0.f0'f0016698
-- isr.ior = 0'9227c3c0.c0000000'4350dc8c
-- Processor 6 TOC: pcsq.pcoq = 0'f0.f0'f0016698
-- isr.ior = 0'9227c3c0.c0000000'43d0f38c
-- * CPU State 0x9e000004
-- * Bus Check 0x30000d
-- * Slave Address 0xffffffff'0xfffa2000
-- * Master Address 0xffffffff'0xfffa0000
-- &j2D&j10L
-- WARN E000&jC&j1D&j2D&j10L
-- WARN E000
-- *** A system crash has occurred. (See the above messages for details.)
-- *** The system is now preparing to dump physical memory to disk, for use
-- *** in debugging the crash.
-- *** The dump will be a SELECTIVE dump: 1055 of 3584 megabytes.
-- *** To change this dump type, press any key within 10 seconds.
-- *** Proceeding with selective dump.
-- *** The dump may be aborted at any time by pressing ESC.
-- *** Dumping: 0% complete (0 of 1055 MB) (device 64:0x2) *** Dumping: 0% complete (8 of 1055 MB) (device 64:0x2) *** Dumping: 1% complete (16 of 1055 MB) (device 64:0x2) *** Dumping: 2% comple
-- device 64:0x2)
-- *** Dumping: 3% complete (32 of 1055 MB) (device 64:0x2) *** Dumping: 3% complete (40 of 1055 MB) (device 64:0x2) *** Dumping: 4% complete (48 of 1055 MB) (device 64:0x2) *** Dumping:
-- 1055 MB) (devi
-- ce 64:0x2) *** Dumping: 6% complete (64 of 1055 MB) (device 64:0x2) *** Dumping: 6% complete (72 of 1055 MB) (device 64:0x2) *** Dumping: 7% complete (80 of 1055 MB) (device 64:0x2) ***
-- te (88 of 1055
-- MB) (device 64:0x2) *** Dumping: 9% complete (96 of 1055 MB) (device 64:0x2) *** Dumping: 9% complete (104 of 1055 MB) (device 64:0x2) *** Dumping: 10% complete (112 of 1055 MB) (device 64:0x2)
-- 11% complete
-- (120 of 1055 MB) (device 64:0x2) *** Dumping: 12% complete (128 of 1055 MB) (device 64:0x2) *** Dumping: 12% complete (136 of 1055 MB) (device 64:0x2) *** Dumping: 13% complete (144 of 1055 MB) (
Thx Robert Lott

P.S. This thread has been moved from General to HP 9000. - Hp Forum Moderator

[Sanjay_6 · Accepted solution]

Hi Robert,

Looks like the problem is with the 3rd CPU (CPU / Processor 2 since you start with 0).

The code 0x5207 --> Refers to direted error on the 2nd processor. The doc that i have suggets you to call your hardware support. Maybe a cpu board replacement would help.

Hope this helps.

Regds

[Robert T. Lott]

Thanks so much for your help you were right on the money if I could I'd give you a raise... Again thx, my users are very very happy now thanks to you...

Wish I could have given you more than just 10 points for this one...

[Steven E. Protter]

HPMC
High Priority Machine Check

Normally the result of a piece of hardware causing a Group 1 Interupt an HPMC. A Group 1 interrupt is th hightest priority interupt a system can generate. Such an interrupt crashes the system.

Though its seems that on a multi processor machine the OS should keep running thats not what happens in this case.

In the future any timeyou get a HPMC you should contact hardware support immediately. The assumption when you get this message is that its a hardware failure.

Some material in this post was paraphrased from HP-UX CSE by Charles Keenan.
http://www.amazon.com/exec/obidos/tg/detail/-/0131463969/qid=1099793805/sr=1-1/ref=sr_1_1/002-3828023-2392044?v=glance&s=books

You may never wish to take the CSE test, but since I started studying for the exam, this book has proved very helpful for day to day events in systems administration.

SEP