内存控制器错误信息[备忘]

参考日志错误信息:

[root@hh-yun-compute-130125 ~]# cat /var/log/messages | grep -i error
Mar  1 04:58:05 hh-yun-compute-130125 kernel: sbridge: HANDLING MCE MEMORY ERROR
Mar  1 04:58:06 hh-yun-compute-130125 kernel: EDAC MC1: CE row 2, channel 0, label "CPU_SrcID#1_Channel#2_DIMM#0": 1 Unknown error(s): memory scrubbing on FATAL area : cpu=6 Err=0008:00c2 (ch=2), addr = 0x16113a9000 => socket=1, Channel=2(mask=4), rank=0
Mar  1 10:27:08 hh-yun-compute-130125 kernel: sbridge: HANDLING MCE MEMORY ERROR
Mar  1 10:27:09 hh-yun-compute-130125 kernel: EDAC MC1: CE row 2, channel 0, label "CPU_SrcID#1_Channel#2_DIMM#0": 1 Unknown error(s): memory scrubbing on FATAL area : cpu=6 Err=0008:00c2 (ch=2), addr = 0x15e1c49000 => socket=1, Channel=2(mask=4), rank=0
Mar  1 13:52:56 hh-yun-compute-130125 kernel: sbridge: HANDLING MCE MEMORY ERROR
Mar  1 13:52:57 hh-yun-compute-130125 kernel: EDAC MC1: CE row 2, channel 0, label "CPU_SrcID#1_Channel#2_DIMM#0": 1 Unknown error(s): memory scrubbing on FATAL area : cpu=6 Err=0008:00c2 (ch=2), addr = 0x160e949000 => socket=1, Channel=2(mask=4), rank=0
Mar  2 04:16:56 hh-yun-compute-130125 kernel: sbridge: HANDLING MCE MEMORY ERROR
Mar  2 04:16:56 hh-yun-compute-130125 kernel: sbridge: HANDLING MCE MEMORY ERROR
Mar  2 04:16:57 hh-yun-compute-130125 kernel: EDAC MC1: CE row 2, channel 0, label "CPU_SrcID#1_Channel#2_DIMM#0": 1 Unknown error(s): memory scrubbing on FATAL area : cpu=6 Err=0008:00c2 (ch=2), addr = 0x1613a61000 => socket=1, Channel=2(mask=4), rank=0
Mar  2 04:16:57 hh-yun-compute-130125 kernel: EDAC MC1: CE row 2, channel 0, label "CPU_SrcID#1_Channel#2_DIMM#0": 1 Unknown error(s): memory scrubbing on FATAL area : cpu=6 Err=0008:00c2 (ch=2), addr = 0x1613a79000 => socket=1, Channel=2(mask=4), rank=0

参考信息2:

[root@hh-yun-compute-130125 ~]# cat /sys/devices/system/edac/mc/mc?/ce*count
0
0
8
0
[root@hh-yun-compute-130125 ~]# cat /sys/devices/system/edac/mc/mc1/ce_count
8

模块信息

[root@hh-yun-compute-130125 ~]# modinfo sb_edac
filename:       /lib/modules/2.6.32-504.3.3.el6.x86_64/kernel/drivers/edac/sb_edac.ko
description:    MC Driver for Intel Sandy Bridge and Ivy Bridge memory controllers -  Ver: 1.1.0
author:         Red Hat Inc. (http://www.redhat.com)
author:         Mauro Carvalho Chehab <mchehab@redhat.com>
license:        GPL
srcversion:     01CFEEBE911D55B6FE660BE
alias:          pci:v00008086d00002FA0sv*sd*bc*sc*i*
alias:          pci:v00008086d00000EA8sv*sd*bc*sc*i*
alias:          pci:v00008086d00003CA8sv*sd*bc*sc*i*
depends:        edac_core
vermagic:       2.6.32-504.3.3.el6.x86_64 SMP mod_unload modversions
parm:           edac_op_state:EDAC Error Reporting state: 0=Poll,1=NMI (int)


[root@hh-yun-compute-130125 ~]# modinfo edac_core
filename:       /lib/modules/2.6.32-504.3.3.el6.x86_64/kernel/drivers/edac/edac_core.ko
description:    Core library routines for EDAC reporting
author:         Doug Thompson www.softwarebitmaker.com, et al
license:        GPL
srcversion:     C21E296292A2174839A086C
depends:
vermagic:       2.6.32-504.3.3.el6.x86_64 SMP mod_unload modversions
parm:           check_pci_errors:Check for PCI bus parity errors: 0=off 1=on (int)
parm:           edac_pci_panic_on_pe:Panic on PCI Bus Parity error: 0=off 1=on (int)
parm:           edac_mc_panic_on_ue:Panic on uncorrected error: 0=off 1=on (int)
parm:           edac_mc_log_ue:Log uncorrectable error to console: 0=off 1=on (int)
parm:           edac_mc_log_ce:Log correctable error to console: 0=off 1=on (int)
parm:           edac_mc_poll_msec:Polling period in milliseconds

官方解释:

Total Correctable Errors count attribute file:

	'ce_count'

	This attribute file displays the total count of correctable
	errors that have occurred on this csrow. This
	count is very important to examine. CEs provide early
	indications that a DIMM is beginning to fail. This count
	field should be monitored for non-zero values and report
	such information to the system administrator.

启用 mcelog

[root@hh-yun-compute-130125 ~]# service  mcelogd restart
Stopping mcelog                                     [确定]
Starting mcelog daemon                              [确定]
[root@hh-yun-compute-130125 ~]# mcelog
mcelog: Family 6 Model 3e CPU: only decoding architectural errors

查询日志

[root@hh-yun-compute-130125 ~]# tail /var/log/mcelog
mcelog: failed to prefill DIMM database from DMI data
mcelog: mcelog server already running

相关评估

This is a harmless warning message. The DIMM database prefill relies on a specific non-standard format of the DIMMs in the DMI BIOS tables. If this format is not used by the BIOS, mcelog will only discover DIMMs as they get their first error (if the CPU reports DIMMs in machine check errors). Please understand for the most part, mcelog should be ignored.