Unexpected HPMC/TOC. Processor HPA 0xFFFBEC00

[Robert T. Lott]

My HP-PRC-HP H70 crashed with the following codes see be low: Could not run Q4 successfully nor does it has ts99:
** message edited to comply with forum guidelines **

20041215.044208 CRMSGI1M (1657)

-- n0124021 Wed Dec 15 04:30:32 EST 2004
-- (@&j2D&j10L
-- FLT CBF0&jC&j1D(@&j2D&j10L
-- FLT 2040&jC&j1D(@&j2D&j10L
-- FLT CBFB&jC&j1D
PM ******* Unexpected HPMC/TOC. Processor HPA 0xFFFBEC00 *******
-- GENERAL REGISTERS:
-- r00/07 00000000 000000AA 000ACCBC 000002E1 01EBEB00 0000000D FFFFFFFF 00479BD0
-- r08/15 00000003 00000000 00000102 0000005F 0000001F 00004FFF 00007FFF 00007C98
-- r16/23 00000000 00000066 00000000 020C8180 00000003 0000000B 00C83AD8 00000001
-- r24/31 0000000B 00000001 000000CC 0047BBD0 00000001 0000000D 7FFE67C0 01D90600
-- CONTROL REGISTERS:
-- sr0/7 00000000 0000165C 00006A34 00000000 00000000 00007BCE 00003609 00000000
-- pcq 00000000.000ACCDC 00000000.000ACCE0 isr = 00000000 ior = 00000001
-- pid1/4 0000 0000 0000 0000 ipsw = 0004010F iva = 00018000 sar = 18 ccr = C0
-- tr0/7 00C83AD8 0020D800 FFFFFFF0 00570140 00752F20 811B578E C1349C33 7B040AF8
-- rctr = 00000004 itmr = 84DB5AFC eiem = C6000000 eirr = 80000000 iir = 86E42082
-- cr1/7 00000000 00000000 00000000 00000000 00000000 00000000 00000000
-- MACHINE CHECK PARAMETERS:
-- Check Type = 80000000 CPU STATE = 9E000004 Cache Check = 40000000
-- TLB Check = 00000000 Bus Check = 00000000 PIM State = ? SIU Status = ????????
-- Detected by 00000000 Assists = 00000000 Processor = 00000000
-- Assist ID = 00000000 Slave Addr = 00000000 Master Addr = 00000000
nh trap type 1 (HPMC), pcsq.pcoq = 0.accdc, isr.ior = 0.1
-- @(#)9245XB HP-UX (B.10.20) #1: Sun Jun 9 06:31:19 PDT 1996
-- High-priority machine check: (display==0xd910, flags==0x0)
-- Processor 1 TOC: pcsq.pcoq = 0.14c9ac, isr.ior = 0.41d7a4
-- * CPU State 0x9e000004
-- * Detected By 0x0
-- * Cache Check 0x40000000
-- It was not possible for the kernel to find a process
-- that caused this crash.
-- Dumpsys() called
-- Attempting to dump 268435456 bytes of memory to disk device 0x1c004000
-- Disk write: mem addr 0x0, disk addr 0xCED8000, count 1048576.
-- Disk write: mem addr 0x100000, disk addr 0xCFD8000, count 1048576.
-- Disk write: mem addr 0x200000, disk addr 0xD0D8000, count 1048576.
-- Disk write: mem addr 0x300000, disk addr 0xD1D8000, count 1048576.
-- Disk write: mem addr 0x400000, disk addr 0xD2D8000, count 1048576.
-- Further "Disk write:" messages suppressed.
-- Successfully dumped 268435456 bytes to dev 0x1c004000, offset 211808 Kbytes
-- Processor Dependent Code (PDC) revision 2.2
-- Duplex Console IO Dependent Code (IODC) revision 1
-- Console path = 56.0.0.0.0.0.0 (dec)
-- 38.0.0.0.0.0.0 (hex)
-- Primary boot path = 52.4.0.0.0.0.0 (dec)
-- 34.4.0.0.0.0.0 (hex)
-- Alternate boot path = 52.6.0.0.0.0.0 (dec)
-- 34.6.0.0.0.0.0 (hex)
-- 256 MB of memory configured and tested.
-- Autosearch for boot path enabled
-- To override, press any key within 10 seconds.
-- 10 seconds expired.
-- Proceeding with autoboot.
-- Trying Primary Boot Path
-- ------------------------
-- Booting...


Core files:
n0124021:root pwd
/bto/sys/crash/core.3

[Cheryl Griffin]

Your posting history is full of messages regarding HPMCs. You must be a pro by now in troubleshooting them.

Please refrain from posting your email address in your messages as this is against forum guidelines.

[Robert T. Lott]

Well, part of the problem I monitor over a 1000 mid-range servers and when you have that many somethings is bound to happen most everyday another problem is a lot of my customers don't like loading these server up(eat up memory, space)with a lot of troubleshooting software so I have to rely on you guys for help... I mostly troubleshoot hardware very little firmware, patches.
Thx,
Oh, thx for the advise on the e-mail address I didn't know...

[Frauke Denker_2 · Accepted solution]

Hello,
a H70 is not able to write the hpmc data to the filesystem, if you want to see the HPMC data, boot the system to BCH and change to Service Menu and use the pim command to get that data. But as Cheryl said, you need to have a lot of knowledge to be able to analyse the data. But at least you will be able to tell, wether there has been an HPMC really to appove what the dump says.
Regards
Frauke

[melvyn burnard]

It would seem you have yet another hardware error.
Log a call with your HP Response Centre and have them analyze thuis and repair the system for you (Assuming you have a contract)

[Stefan Stechemesser]

Hi,

the CPU with the Hard Physical Address 0xFFFBEC00 (I think it is CPU #1, please check in stm information tool) had a cache error:

-- MACHINE CHECK PARAMETERS:
-- Check Type = 80000000 CPU STATE = 9E000004 Cache Check = 40000000
-- TLB Check = 00000000 Bus Check = 00000000 PIM State = ? SIU Status

Check Type 80000000 means cache error and Cache Check = 40000000 means data cache error.

Chassis Code FLT 2040 also means data chache error.

I would recomend to do nothing. Maybe it does not happen again. If the same error happens frequently, replace the bad CPU.

best regards

Stefan