statscloud.io-ruby-plugin-system-monitor
To use this plugin with your StatsCloud client install this gem
gem install stats_cloud-plugin-system_monitor
and add plugins section configuration in .statscloud.yml file:
...
plugins:
- system-monitor
You can customize plugin settings as well:
...
plugins:
- name: system-monitor
settings:
collectIntervalInSeconds: 1 # interval to collect metrics in seconds, default value is 1
flushIntervalInSeconds: 60 # how often to capture the metric values, default value is specified in .statscloud.json on top level
retention: # how long to store metrics for and at which granularity, default value is specified in .statscloud.json on top level
- frequency: 1m
keep: 3d
intervals: # interval to count metrics during, default value is ["1m"]
- 1m
enableAlerts: false # you can enable or disable alerts, default value is false
admins: [] # list of admin names no notify about plugin alerts, default value is an empty array
channels: [] # list of channels to send notifications via, default value is an empty array
alertsRepeatInterval: 15m # how often to repeat the alerts, default value is "15m"
alertsUnhealthyDelay: 5m # how much time the metric is allowed to stay in unhealthy zone before alert is raised, default value is "5m"
alertsHealthyDelay: 2m # how much time the metric should stay in healthy zone before alert is removed, default value is "2m"
alerts: # you can specify settings for each alert
memory-percent-overlimit: # alert that raised when memory usage overruns limit
enabled: true # enable this alert, default value is taken from enableAlerts setting from top-level plugin configuration
threshold: 80 # max memory usage in percent, default value is 80
repeatInterval: 15m # how often to repeat the alerts, default value is taken from alertsRepeatInterval setting from top-level plugin configuration
unhealthyDelay: 5m # how much time the metric is allowed to stay in unhealthy zone before alert is raised, default value is taken from alertsUnhealthyDelay setting from top-level plugin configuration
healthyDelay: 2m # how much time the metric should stay in healthy zone before alert is removed, default value is taken from alertsHealthyDelay setting from top-level plugin configuration
admins: [] # list of admin names no notify about this alert, default value is taken from admins setting from top-level plugin configuration
channels: [] # list of channels to send notifications via, default value is taken from channels setting from top-level plugin configuration
cpu-percent-overlimit: # alert that raised when cpu usage overruns limit
enabled: true # enable this alert, default value is taken from enableAlerts setting from top-level plugin configuration
threshold: 70 # max cpu usage in percent, default value is 70
repeatInterval: 15m # how often to repeat the alerts, default value is taken from alertsRepeatInterval setting from top-level plugin configuration
unhealthyDelay: 5m # how much time the metric is allowed to stay in unhealthy zone before alert is raised, default value is taken from alertsUnhealthyDelay setting from top-level plugin configuration
healthyDelay: 2m # how much time the metric should stay in healthy zone before alert is removed, default value is taken from alertsHealthyDelay setting from top-level plugin configuration
admins: [] # list of admin names no notify about this alert, default value is taken from admins setting from top-level plugin configuration
channels: [] # list of channels to send notifications via, default value is taken from channels setting from top-level plugin configuration
disk-belowlimit: # alert that raised when disk free space is too low
enabled: true # enable this alert, default value is taken from enableAlerts setting from top-level plugin configuration
threshold: 1 # min disk free space in Gb, default value is 1
repeatInterval: 15m # how often to repeat the alerts, default value is taken from alertsRepeatInterval setting from top-level plugin configuration
unhealthyDelay: 5m # how much time the metric is allowed to stay in unhealthy zone before alert is raised, default value is taken from alertsUnhealthyDelay setting from top-level plugin configuration
healthyDelay: 2m # how much time the metric should stay in healthy zone before alert is removed, default value is taken from alertsHealthyDelay setting from top-level plugin configuration
admins: [] # list of admin names no notify about this alert, default value is taken from admins setting from top-level plugin configuration
channels: [] # list of channels to send notifications via, default value is taken from channels setting from top-level plugin configuration
disk-percent-overlimit: # alert that raised when disk usage overruns limit
enabled: true # enable this alert, default value is taken from enableAlerts setting from top-level plugin configuration
threshold: 90 # max disk usage in percent, default value is 90
repeatInterval: 15m # how often to repeat the alerts, default value is taken from alertsRepeatInterval setting from top-level plugin configuration
unhealthyDelay: 5m # how much time the metric is allowed to stay in unhealthy zone before alert is raised, default value is taken from alertsUnhealthyDelay setting from top-level plugin configuration
healthyDelay: 2m # how much time the metric should stay in healthy zone before alert is removed, default value is taken from alertsHealthyDelay setting from top-level plugin configuration
admins: [] # list of admin names no notify about this alert, default value is taken from admins setting from top-level plugin configuration
channels: [] # list of channels to send notifications via, default value is taken from channels setting from top-level plugin configuration
battery-belowlimit: # alert that raised when battery is too low
enabled: true # enable this alert, default value is taken from enableAlerts setting from top-level plugin configuration
threshold: 10 # min battery percent value, default value is 10
repeatInterval: 15m # how often to repeat the alerts, default value is taken from alertsRepeatInterval setting from top-level plugin configuration
unhealthyDelay: 5m # how much time the metric is allowed to stay in unhealthy zone before alert is raised, default value is taken from alertsUnhealthyDelay setting from top-level plugin configuration
healthyDelay: 2m # how much time the metric should stay in healthy zone before alert is removed, default value is taken from alertsHealthyDelay setting from top-level plugin configuration
admins: [] # list of admin names no notify about this alert, default value is taken from admins setting from top-level plugin configuration
channels: [] # list of channels to send notifications via, default value is taken from channels setting from top-level plugin configuration
system-load-overlimit: # alert that raised when system load overruns limit
enabled: true # enable this alert, default value is taken from enableAlerts setting from top-level plugin configuration
threshold: 2 # max system load, default value is 2
repeatInterval: 15m # how often to repeat the alerts, default value is taken from alertsRepeatInterval setting from top-level plugin configuration
unhealthyDelay: 5m # how much time the metric is allowed to stay in unhealthy zone before alert is raised, default value is taken from alertsUnhealthyDelay setting from top-level plugin configuration
healthyDelay: 2m # how much time the metric should stay in healthy zone before alert is removed, default value is taken from alertsHealthyDelay setting from top-level plugin configuration
admins: [] # list of admin names no notify about this alert, default value is taken from admins setting from top-level plugin configuration
channels: [] # list of channels to send notifications via, default value is taken from channels setting from top-level plugin configuration