Subject: need help understanding "system correctable error corrected by system" messages
To: NetBSD/alpha Discussion List <port-alpha@NetBSD.ORG>
From: Greg A. Woods <woods@weird.com>
List: port-alpha
Date: 08/02/2003 16:54:34
Are these three messages related? I.e. why are the second two reporting
a "physical address" of 0x0 (I see the bit about "B-Cache during D-Cache")?
Should I worry? (i.e. should I be on the lookout for new memory)?
(i.e. how often do these ECC warnings occur on older AS4x00 systems?)
The machine has been running "build.sh" for over three hours now. It
has a gigabyte of RAM and of course it has not paged at all during this
time so I doubt all of physical memory has yet been touched except
during the SRM POST.
kn300: CPU ID 0 system correctable error corrected by system
Machine Check Code 0x860000
Physical Address of Error 0xffffff000fb61f7f
Corrected ECC Error in Memory during D-Cache fill
EI Status = 0xfffffff0c1ffffff
Fill Syndrome = 0x0000000000002300
Interrupt Status Reg. = 0x0000000100000000
Whami Reg. = 0x0000000000000000
Sys. Env. Reg. = 0x0000000000000000
MCPCIA Regs. = 0x0000000000000000
PCI Rev. Reg. = 0x0000000000000000
MC_ERR0 Reg. = 0x0000000000000000
MC_ERR1 Reg. = 0x0000000000000000
CAP_ERR Reg. = 0x0000000000000000
MDPA_STAT Reg. = 0x0000000000000000
MDPA_SYN Reg. = 0x0000000000000000
MDPB_STAT Reg. = 0x0000000000000000
MDPB_SYN Reg. = 0x0000000000000000
kn300: CPU ID 0 system correctable error corrected by system
Machine Check Code 0x2040000
Physical Address of Error 0x0
Other Errorin B-Cache during D-Cache fill
EI Status = 0x0000000000000000
Fill Syndrome = 0x0000000000000000
Interrupt Status Reg. = 0x0000000000000000
Whami Reg. = 0x0000000000000000
Sys. Env. Reg. = 0x0000000000000000
MCPCIA Regs. = 0x000000f9e0000000
PCI Rev. Reg. = 0x0000000006008332
MC_ERR0 Reg. = 0x000000000fb61f40
MC_ERR1 Reg. = 0xffffffff800e9a00
CAP_ERR Reg. = 0xffffffff90000000
MDPA_STAT Reg. = 0x0000000000000000
MDPA_SYN Reg. = 0x0000000000000000
MDPB_STAT Reg. = 0x0000000000000000
MDPB_SYN Reg. = 0x0000000000000000
kn300: CPU ID 0 system correctable error corrected by system
Machine Check Code 0x2040000
Physical Address of Error 0x0
Other Errorin B-Cache during D-Cache fill
EI Status = 0x0000000000000000
Fill Syndrome = 0x0000000000000000
Interrupt Status Reg. = 0x0000000000000000
Whami Reg. = 0x0000000000000000
Sys. Env. Reg. = 0x0000000000000000
MCPCIA Regs. = 0x000000fbe0000000
PCI Rev. Reg. = 0x0000000006000332
MC_ERR0 Reg. = 0x000000000fb61f40
MC_ERR1 Reg. = 0xffffffff800e9a00
CAP_ERR Reg. = 0xffffffff90000000
MDPA_STAT Reg. = 0x0000000000000000
MDPA_SYN Reg. = 0x0000000000000000
MDPB_STAT Reg. = 0x0000000000000000
MDPB_SYN Reg. = 0x0000000000000000
--
Greg A. Woods
+1 416 218-0098 VE3TCP RoboHack <woods@robohack.ca>
Planix, Inc. <woods@planix.com> Secrets of the Weird <woods@weird.com>