selfhost-utils/healthcheck.cfg.example

[DEFAULT]

#### EMAIL NOTIFICATIONS

# Notify this email address(es) in case of alarm, multiple addresses separated by commas
MAILTO=root@localhost, user@localhost

# Sender address
MAILFROM=root@localhost

# Use a remote SMTP host (enable by removing comment)
#SMTPHOST=my.smtp.host:465

# SMTP credentials
#SMTPUSER=mysmtpuser
#SMTPPASS=mysmtppass

# Use SSL for SMTP
#SMTPSSL=True



#### HEALTH CHECKS ####
# Every health check is based on a command being executed, its result being parsed with a regexp
# to extract (as a single group) the numeric or string value, and the value being compared with
# a configured value. This checks are ready to be used, just enable the ones you need.
# You can add your own custom check declaring another section like this:
#
# [my_custom_check_name]
# DISABLED=False
# ALARM_STRING_EQUAL=Lorem ipsum
# ALARM_STRING_NOT_EQUAL=The lazy fox
# ALARM_VALUE_EQUAL=99
# ALARM_VALUE_NOT_EQUAL=76.365338
# ALARM_VALUE_MORE_THAN=1.0
# ALARM_VALUE_LESS_THAN=12
# COMMAND=/my/custom/binary --with parameters
# REGEXP=my regex to parse (awesome|disappointing) command output

[system_load_1min]
# The system load average in the last minute
DISABLED=True
ALARM_VALUE_MORE_THAN=1.0
COMMAND=uptime
REGEXP=.*load average: (\d+[,.]\d+), \d+[,.]\d+, \d+[,.]\d+

[system_load_5min]
# The system load average in the last 5 minutes
DISABLED=True
ALARM_VALUE_MORE_THAN=1.0
COMMAND=uptime
REGEXP=.*load average: \d+[,.]\d+, (\d+[,.]\d+), \d+[,.]\d+

[system_load_15min]
# The system load average in the last 15 minutes
DISABLED=True
ALARM_VALUE_MORE_THAN=1.0
COMMAND=uptime
REGEXP=.*load average: \d+[,.]\d+, \d+[,.]\d+, (\d+[,.]\d+)

[used_disk_space]
# Used disk space (in percent, i.e. ALARM_VALUE_MORE_THAN=75 -> alarm if disk is more than 75% full)
DISABLED=True
ALARM_VALUE_MORE_THAN=75
COMMAND=df -h /dev/sda1
REGEXP=(\d{1,3})%

[raid_status]
# Issues an alarm when the raid is corrupted
# Checks this part of the /proc/mdstat file:
#       243553280 blocks super 1.2 [2/2] [UU]
# If the content of the last [ ] contains only U (without _), the raid array is healty
# Otherwise, [U_] or [_U] is displayed (may contain more U or _ if the array is more disks)
DISABLED=True
ALARM_STRING_NOT_EQUAL=UU
COMMAND=cat /proc/mdstat
REGEXP=.*\] \[([U_]+)\]\n

[battery_level]
# Issues an alarm when battery is discharging below a certain level (long blackout, pulled power cord...)
# For laptops used as servers, apparently common among the self hosters. Requires acpi package installed.
# Value is in %
DISABLED=True
COMMAND=acpi -b
REGEXP=Battery \d: .*, (\d{1,3})%
ALARM_VALUE_LESS_THAN=90

[laptop_charger_disconnected]
# Issues an alarm when laptop charger is disconnected
# For laptops used as servers, apparently common among the self hosters. Requires acpi package installed.
DISABLED=True
COMMAND=acpi -a
REGEXP=Adapter \d: (.+)
ALARM_STRING_NOT_EQUAL=on-line

[free_ram]
# Free ram in %
# Shows another approach: does all the computation in the command and picks up
# all the output (by not declaring a regexp).
DISABLED=True
COMMAND=free | grep Mem | awk '{print int($4/$2 * 100.0)}'
ALARM_VALUE_LESS_THAN=20

[cpu_temperature]
# CPU Temperature alarm: requires lm-sensors installed and configured (check your distribution's guide)
# The regexp must be adapted to your configuration: run `sensors` in the command line
# to find the name of the temperature sensor in your system. In this case is `Core 0`,
# but may be called Tdie or a lot of different names, there is no standard.
DISABLED=True
ALARM_VALUE_MORE_THAN=80
COMMAND=sensors
REGEXP=Core 0: +\+?(-?\d{1,3}).\d°[CF]

[fan_speed]
# Fan speed alarm: requires lm-sensors installed and configured (check your distribution's guide)
# The regexp must be adapted to your configuration: run `sensors` in the command line
# to find the name of the fan speed sensor in your system.
DISABLED=True
ALARM_VALUE_LESS_THAN=300
COMMAND=sensors
REGEXP=cpu_fan: +(\d) RPM