| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101 |
- ---
- g_template_openshift_node:
- name: Template Openshift Node
- zitems:
- - key: openshift.node.process.count
- description: Shows number of OpenShift Node processes running
- type: int
- applications:
- - Openshift Node
- - key: openshift.node.ovs.pids.count
- description: Shows number of ovs process ids running
- type: int
- applications:
- - Openshift Node
- - key: openshift.node.ovs.ports.count
- description: Shows number of OVS ports defined
- type: int
- applications:
- - Openshift Node
- - key: openshift.node.ovs.stray.rules
- description: Number of OVS stray rules found/removed
- type: int
- applications:
- - Openshift Node
- - key: openshift.node.registry-pods.healthy_pct
- description: Shows the percentage of healthy registries in the cluster
- type: int
- applications:
- - Openshift Node
- - key: openshift.node.registry.service.ping
- description: Ping docker-registry service from node
- type: int
- applications:
- - Openshift Node
- ztriggers:
- - name: 'One or more Docker Registries is unhealthy according to {HOST.NAME}'
- expression: '{Template Openshift Node:openshift.node.registry-pods.healthy_pct.last(#2)}<100 and {Template Openshift Node:openshift.node.registry-pods.healthy_pct.last(#1)}<100'
- url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_registry.asciidoc'
- priority: avg
- - name: 'Docker Registry service is unhealthy according to {HOST.NAME}'
- expression: '{Template Openshift Node:openshift.node.registry.service.ping.last(#2)}<1 and {Template Openshift Node:openshift.node.registry.service.ping.last(#1)}<1'
- url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_registry.asciidoc'
- priority: avg
- - name: 'Openshift Node process not running on {HOST.NAME}'
- expression: '{Template Openshift Node:openshift.node.process.count.max(#3)}<1'
- url: 'https://github.com/openshift/ops-sop/blob/node/V3/Alerts/openshift_node.asciidoc'
- priority: high
- - name: 'Too many Openshift Node processes running on {HOST.NAME}'
- expression: '{Template Openshift Node:openshift.node.process.count.min(#3)}>1'
- url: 'https://github.com/openshift/ops-sop/blob/node/V3/Alerts/openshift_node.asciidoc'
- priority: high
- - name: '[HEAL] OVS may not be running on {HOST.NAME}'
- expression: '{Template Openshift Node:openshift.node.ovs.pids.count.last(#1)}<>4 and {Template Openshift Node:openshift.node.ovs.pids.count.last(#2)}<>4'
- url: 'https://github.com/openshift/ops-sop/blob/node/V3/Alerts/openshift_node.asciidoc'
- priority: high
- - name: 'Number of OVS ports is 0 on {HOST.NAME}'
- expression: '{Template Openshift Node:openshift.node.ovs.ports.count.last()}=0'
- url: 'https://github.com/openshift/ops-sop/blob/node/V3/Alerts/openshift_node.asciidoc'
- priority: high
- zactions:
- - name: '[HEAL] OVS may not be running on {HOST.NAME}'
- status: disabled
- escalation_time: 60
- conditions_filter:
- calculation_type: "and/or"
- conditions:
- - conditiontype: maintenance status
- operator: not in
- - conditiontype: trigger name
- operator: like
- value: "[HEAL] OVS may not be running on"
- - conditiontype: trigger value
- operator: "="
- value: PROBLEM
- operations:
- - esc_step_from: 1
- esc_step_to: 1
- esc_period: 0
- operationtype: remote command
- opcommand:
- command: 'ssh -i /etc/openshift_tools/scriptrunner_id_rsa {{ ozb_scriptrunner_user }}@{{ ozb_scriptrunner_bastion_host }} remote-healer --host \"{HOST.NAME}\" --trigger \"{TRIGGER.NAME}\" --trigger-val \"{TRIGGER.VALUE}\"'
- execute_on: "zabbix server"
- type: 'custom script'
- target_hosts:
- - target_type: 'zabbix server'
- opconditions:
- - conditiontype: 'event acknowledged'
- operator: '='
- value: 'not acknowledged'
|
