12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970 |
- ---
- g_template_openshift_node:
- name: Template Openshift Node
- zitems:
- - key: openshift.node.process.count
- description: Shows number of OpenShift Node processes running
- value_type: int
- applications:
- - Openshift Node
- - key: openshift.node.ovs.pids.count
- description: Shows number of ovs process ids running
- value_type: int
- applications:
- - Openshift Node
- - key: openshift.node.ovs.ports.count
- description: Shows number of OVS ports defined
- value_type: int
- applications:
- - Openshift Node
- - key: openshift.node.ovs.stray.rules
- description: Number of OVS stray rules found/removed
- value_type: int
- applications:
- - Openshift Node
- - key: openshift.node.registry-pods.healthy_pct
- description: Shows the percentage of healthy registries in the cluster
- value_type: int
- applications:
- - Openshift Node
- - key: openshift.node.registry.service.ping
- description: Ping docker-registry service from node
- value_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
|