-
Notifications
You must be signed in to change notification settings - Fork 63
/
mcelog.conf
196 lines (163 loc) · 7 KB
/
mcelog.conf
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
#
# Example config file for mcelog
# mcelog is the user space backend that decodes and process machine check events
# (cpu hardware errors) reported by the CPU to the kernel
#
# general format
#optionname = value
# white space is not allowed in value currently, except at the end where it is dropped
#
# In general all command line options that are not commands work here.
# See man mcelog or mcelog --help for a list.
# e.g. to enable the --no-syslog option use
#no-syslog = yes (or no to disable)
# when the option has a argument
#logfile = /tmp/logfile
# below are the options which are not command line options.
# Set CPU type for which mcelog decodes events:
#cpu = type
# For valid values for type please see mcelog --help.
# If this value is set incorrectly the decoded output will be likely incorrect.
# By default when this parameter is not set mcelog uses the CPU it is running on
# on very new kernels the mcelog events reported by the kernel also carry
# the CPU type which is used too when available and not overridden.
# Enable daemon mode:
#daemon = yes
# By default mcelog just processes the currently pending events and exits.
# In daemon mode it will keep running as a daemon in the background and poll
# the kernel for events and then decode them.
# Filter out known broken events by default.
filter = yes
# Don't log memory errors individually.
# They still get accounted if that is enabled.
#filter-memory-errors = yes
# output in undecoded raw format to be easier machine readable
# (default is decoded).
#raw = yes
# Set CPU Mhz to decode uptime from time stamp counter (output
# unreliable, not needed on new kernels which report the event time
# directly. A lot of systems don't have a linear time stamp clock
# and the output is wrong then.
# Normally mcelog tries to figure out if it the TSC is reliable
# and only uses the current frequency then.
# Setting a frequency forces timestamp decoding.
# This setting is obsolete with modern kernels which report the time
# directly.
#cpumhz = 1800.00
# log output options
# Log decoded machine checks in syslog (default stdout or syslog for daemon)
#syslog = yes
# Log decoded machine checks in syslog with error level
#syslog-error = yes
# Never log anything to syslog
#no-syslog = yes
# Append log output to logfile instead of stdout. Only when no syslog logging is active
#logfile = filename
# Use SMBIOS information to decode DIMMs (needs root).
# This function is not recommended to use right now and generally not needed.
# The exception is memdb prepopulation, which is configured separately below.
#dmi = no
# When in daemon mode run as this user after set up.
# Note that the triggers will run as this user too.
# Setting this to non root will mean that triggers cannot take some corrective
# action, like offlining objects.
#run-credentials-user = root
# group to run as daemon with
# default to the group of the run-credentials-user
#run-credentials-group = nobody
[server]
# user allowed to access client socket.
# when set to * match any
# root is always allowed to access.
# default: root only
client-user = root
# group allowed to access mcelog
# When no group is configured any group matches (but still user checking).
# when set to * match any
#client-group = root
# Path to the unix socket for client<->server communication.
# When no socket-path is configured the server will not start
#socket-path = /var/run/mcelog-client
# When mcelog starts it checks if a server is already running. This configures the timeout
# for this check.
#initial-ping-timeout = 2
#
[dimm]
# Is the in memory DIMM error tracking enabled?
# Only works on systems with integrated memory controller and
# which are supported.
# Only takes effect in daemon mode.
dimm-tracking-enabled = yes
# Use DMI information from the BIOS to prepopulate DIMM database.
# Note this might not work with all BIOS and requires mcelog to run as root.
# Alternative is to let mcelog create DIMM objects on demand.
dmi-prepopulate = yes
#
# Execute these triggers when the rate of corrected or uncorrected
# Errors per DIMM exceeds the threshold.
# Note when the hardware does not report DIMMs this might also
# be per channel.
# The default of 10/24h is reasonable for server quality
# DDR3 DIMMs as of 2009/10.
#uc-error-trigger = dimm-error-trigger
uc-error-threshold = 1 / 24h
#ce-error-trigger = dimm-error-trigger
ce-error-threshold = 10 / 24h
[socket]
# Enable memory error accounting per socket.
socket-tracking-enabled = yes
# Threshold and trigger for uncorrected memory errors on a socket.
# mem-uc-error-trigger = socket-memory-error-trigger
mem-uc-error-threshold = 100 / 24h
# Trigger script for corrected memory errors on a socket.
mem-ce-error-trigger = socket-memory-error-trigger
# Threshold on when to trigger a correct error for the socket.
mem-ce-error-threshold = 100 / 24h
# Log socket error threshold explicitly?
mem-ce-error-log = yes
# Trigger script for uncorrected bus error events
bus-uc-threshold-trigger = bus-error-trigger
# Trigger script for uncorrected IOMCA erors
iomca-threshold-trigger = iomca-error-trigger
# Trigger script for other uncategorized errors
unknown-threshold-trigger = unknown-error-trigger
[cache]
# Processing of cache error thresholds reported by Intel CPUs.
cache-threshold-trigger = cache-error-trigger
# Should cache threshold events be logged explicitly?
cache-threshold-log = yes
[page]
# Memory error accouting per 4K memory page.
# Threshold for the correct memory errors trigger script.
memory-ce-threshold = 2 / 24h
# Trigger script for corrected errors.
# memory-ce-trigger = page-error-trigger
# Memory error counter per 4K memory page.
# Threshold for the counter replacements trigger script.
memory-ce-counter-replacement-threshold = 20 / 24h
# Trigger script for counter replacements.
memory-ce-counter-replacement-trigger = page-error-counter-replacement-trigger
# Should page threshold events be logged explicitly?
memory-ce-log = yes
# specify the internal action in mcelog to exceeding a page error threshold
# this is done in addition to executing the trigger script if available
# off no action
# account only account errors
# soft try to soft-offline page without killing any processes
# This requires an uptodate kernel. Might not be successfull.
# hard try to hard-offline page by killing processes
# Requires an uptodate kernel. Might not be successfull.
# soft-then-hard First try to soft offline, then try hard offlining
#memory-ce-action = off|account|soft|hard|soft-then-hard
memory-ce-action = soft
# Trigger script before doing soft memory offline
# this trigger will scan and run all the scipts in the page-error-pre-soft-trigger.extern
memory-pre-sync-soft-ce-trigger = page-error-pre-sync-soft-trigger
# Trigger script after completing soft memory offline
# this trigger will scan and run all the scipts in the page-error-post-soft-trigger.extern
memory-post-sync-soft-ce-trigger = page-error-post-sync-soft-trigger
[trigger]
# Maximum number of running triggers
children-max = 2
# execute triggers in this directory
directory = /etc/mcelog