okd/roles/os_zabbix/vars/template_app_zabbix_server.yml

---
g_template_app_zabbix_server:
   name: Template App Zabbix Server
   zitems:
   - key: housekeeper_creates
     applications:
     - Zabbix server
     description: A simple count of the number of partition creates output by the housekeeper script.
     units: ''
     value_type: int
     zabbix_type: 5

   - key: housekeeper_drops
     applications:
     - Zabbix server
     description: A simple count of the number of partition drops output by the housekeeper script.
     units: ''
     value_type: int
     zabbix_type: 5

   - key: housekeeper_errors
     applications:
     - Zabbix server
     description: A simple count of the number of errors output by the housekeeper script.
     units: ''
     value_type: int
     zabbix_type: 5

   - key: housekeeper_total
     applications:
     - Zabbix server
     description: A simple count of the total number of lines output by the housekeeper
       script.
     units: ''
     value_type: int
     zabbix_type: 5

   - key: zabbix[process,alerter,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[process,configuration syncer,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[process,db watchdog,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[process,discoverer,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[process,escalator,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[process,history syncer,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[process,housekeeper,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[process,http poller,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[process,icmp pinger,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[process,ipmi poller,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[process,java poller,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[process,node watcher,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[process,poller,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[process,proxy poller,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[process,self-monitoring,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[process,snmp trapper,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[process,timer,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[process,trapper,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[process,unreachable poller,avg,busy]
     applications:
     - Zabbix server
     description: ''
     units: '%'
     value_type: float
     zabbix_type: 5

   - key: zabbix[queue,10m]
     applications:
     - Zabbix server
     description: ''
     units: ''
     value_type: int
     zabbix_type: 5
     interval: 600

   - key: zabbix[queue]
     applications:
     - Zabbix server
     description: ''
     units: ''
     value_type: int
     zabbix_type: 5
     interval: 600

   - key: zabbix[rcache,buffer,pfree]
     applications:
     - Zabbix server
     description: ''
     units: ''
     value_type: float
     zabbix_type: 5

   - key: zabbix[wcache,history,pfree]
     applications:
     - Zabbix server
     description: ''
     units: ''
     value_type: float
     zabbix_type: 5

   - key: zabbix[wcache,text,pfree]
     applications:
     - Zabbix server
     description: ''
     units: ''
     value_type: float
     zabbix_type: 5

   - key: zabbix[wcache,trend,pfree]
     applications:
     - Zabbix server
     description: ''
     units: ''
     value_type: float
     zabbix_type: 5

   - key: zabbix[wcache,values]
     applications:
     - Zabbix server
     description: ''
     units: ''
     value_type: float
     zabbix_type: 5
     delta: 1 # speed per second

   ztriggers:
   - description: "There has been unexpected output while running the housekeeping script\
       \ on the Zabbix. There are only three kinds of lines we expect to see in the output,\
       \ and we've gotten something enw.\r\n\r\nCheck the script's output in /var/lib/zabbix/state\
       \ for more details."
     expression: '{Template App Zabbix Server:housekeeper_errors.last(0)}+{Template App Zabbix Server:housekeeper_creates.last(0)}+{Template App Zabbix Server:housekeeper_drops.last(0)}<>{Template App Zabbix Server:housekeeper_total.last(0)}'
     name: Unexpected output in Zabbix DB Housekeeping
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_DB_Housekeeping.asciidoc

   - description: An error has occurred during running the housekeeping script on the Zabbix. Check the script's output in /var/lib/zabbix/state for more details.
     expression: '{Template App Zabbix Server:housekeeper_errors.last(0)}>0'
     name: Errors during Zabbix DB Housekeeping
     priority: high
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[process,alerter,avg,busy].min(600)}>75'
     name: Zabbix alerter processes more than 75% busy
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[process,configuration syncer,avg,busy].min(600)}>75'
     name: Zabbix configuration syncer processes more than 75% busy
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[process,db watchdog,avg,busy].min(600)}>75'
     name: Zabbix db watchdog processes more than 75% busy
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[process,discoverer,avg,busy].min(600)}>75'
     name: Zabbix discoverer processes more than 75% busy
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[process,escalator,avg,busy].min(600)}>75'
     name: Zabbix escalator processes more than 75% busy
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[process,history syncer,avg,busy].min(600)}>75'
     name: Zabbix history syncer processes more than 75% busy
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[process,housekeeper,avg,busy].min(1800)}>75'
     name: Zabbix housekeeper processes more than 75% busy
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[process,http poller,avg,busy].min(600)}>75'
     name: Zabbix http poller processes more than 75% busy
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[process,icmp pinger,avg,busy].min(600)}>75'
     name: Zabbix icmp pinger processes more than 75% busy
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[process,ipmi poller,avg,busy].min(600)}>75'
     name: Zabbix ipmi poller processes more than 75% busy
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[process,java poller,avg,busy].min(600)}>75'
     name: Zabbix java poller processes more than 75% busy
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[process,node watcher,avg,busy].min(600)}>75'
     name: Zabbix node watcher processes more than 75% busy
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[process,poller,avg,busy].min(600)}>75'
     name: Zabbix poller processes more than 75% busy
     priority: high
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[process,proxy poller,avg,busy].min(600)}>75'
     name: Zabbix proxy poller processes more than 75% busy
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[process,self-monitoring,avg,busy].min(600)}>75'
     name: Zabbix self-monitoring processes more than 75% busy
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[process,snmp trapper,avg,busy].min(600)}>75'
     name: Zabbix snmp trapper processes more than 75% busy
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: Timer processes usually are busy because they have to process time
       based trigger functions
     expression: '{Template App Zabbix Server:zabbix[process,timer,avg,busy].min(600)}>75'
     name: Zabbix timer processes more than 75% busy
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[process,trapper,avg,busy].min(600)}>75'
     name: Zabbix trapper processes more than 75% busy
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[process,unreachable poller,avg,busy].min(600)}>75'
     name: Zabbix unreachable poller processes more than 75% busy
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc

   - description: "This alert generally indicates a performance problem or a problem\
       \ with the zabbix-server or proxy.\r\n\r\nThe first place to check for issues\
       \ is Administration > Queue. Be sure to check the general view and the per-proxy\
       \ view."
     expression: '{Template App Zabbix Server:zabbix[queue,10m].min(600)}>1000'
     name: More than 1000 items having missing data for more than 10 minutes
     priority: high
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/data_lost_overview_plugin.asciidoc

   - description: Consider increasing CacheSize in the zabbix_server.conf configuration
       file
     expression: '{Template App Zabbix Server:zabbix[rcache,buffer,pfree].min(600)}<5'
     name: Less than 5% free in the configuration cache
     priority: info
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/check_cache.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[wcache,history,pfree].min(600)}<25'
     name: Less than 25% free in the history cache
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/check_cache.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[wcache,text,pfree].min(600)}<25'
     name: Less than 25% free in the text history cache
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/check_cache.asciidoc

   - description: ''
     expression: '{Template App Zabbix Server:zabbix[wcache,trend,pfree].min(600)}<25'
     name: Less than 25% free in the trends cache
     priority: avg
     url: https://github.com/openshift/ops-sop/blob/master/Alerts/check_cache.asciidoc