okd/roles/os_zabbix/vars/template_openshift_master.yml

---
g_template_openshift_master:
  name: Template Openshift Master
  zitems:
  - name: openshift.master.app.create
    applications:
    - Openshift Master
    key: openshift.master.app.create

  - key: openshift.master.registry.healthy_pct
    description: "Shows the percentage of healthy registries in the cluster"
    type: int
    applications:
    - Openshift Master

  - key: openshift.master.process.count
    description: Shows number of master processes running
    type: int
    applications:
    - Openshift Master

  - key: openshift.master.api.ping
    description: "Verify that the Openshift API is up (uses the cluster API URL)"
    type: int
    applications:
    - Openshift Master

  - key: openshift.master.local.api.ping
    description: "Verify that the Openshift API is up on the host (uses the API URL as the https://127.0.0.1)"
    type: int
    applications:
    - Openshift Master

  - key: openshift.master.api.healthz
    description: "Checks the healthz check of the master's api: https://<cluster_api_url>/healthz"
    type: int
    data_type: bool
    applications:
    - Openshift Master

  - key: openshift.master.local.api.healthz
    description: "Checks the healthz check of the master's api: https://127.0.0.1/healthz"
    type: int
    data_type: bool
    applications:
    - Openshift Master

  - key: openshift.master.user.count
    description: Shows number of users in a cluster
    type: int
    applications:
    - Openshift Master

  - key: openshift.master.pod.running.count
    description: Shows number of pods running
    type: int
    applications:
    - Openshift Master

  - key: openshift.master.pod.user.running.count
    description: Shows number of user pods running (non infrastructure pods)
    type: int
    applications:
    - Openshift Master

  - key: openshift.master.pod.total.count
    description: Shows total number of pods (running and non running)
    type: int
    applications:
    - Openshift Master

  - key: openshift.master.node.count
    description: Shows the total number of nodes found in the Openshift Cluster
    type: int
    applications:
    - Openshift Master

  - key: openshift.project.count
    description: Shows number of projects on a cluster
    type: int
    applications:
    - Openshift Master

  - key: openshift.master.pv.total.count
    description: Total number of Persistent Volumes in the Openshift Cluster
    type: int
    applications:
    - Openshift Master

  - key: openshift.master.pv.available.count
    description: Total number of Available Persistent Volumes in the Openshift Cluster
    type: int
    applications:
    - Openshift Master

  - key: openshift.master.pv.released.count
    description: Total number of Released Persistent Volumes in the Openshift Cluster
    type: int
    applications:
    - Openshift Master

  - key: openshift.master.pv.bound.count
    description: Total number of Bound Persistent Volumes in the Openshift Cluster
    type: int
    applications:
    - Openshift Master

  - key: openshift.master.pv.failed.count
    description: Total number of Failed Persistent Volumes in the Openshift Cluster
    type: int
    applications:
    - Openshift Master

  - key: openshift.master.skydns.port.open
    description: State of the SkyDNS port open and listening
    type: int
    applications:
    - Openshift Master

  - key: openshift.master.skydns.query
    description: SkyDNS can be queried or not
    type: int
    applications:
    - Openshift Master

  - key: openshift.master.etcd.create.success
    description: Show number of successful create actions
    type: int
    applications:
    - Openshift Etcd

  - key: openshift.master.etcd.create.fail
    description: Show number of failed create actions
    type: int
    applications:
    - Openshift Etcd

  - key: openshift.master.etcd.delete.success
    description: Show number of successful delete actions
    type: int
    applications:
    - Openshift Etcd

  - key: openshift.master.etcd.delete.fail
    description: Show number of failed delete actions
    type: int
    applications:
    - Openshift Etcd

  - key: openshift.master.etcd.get.success
    description: Show number of successful get actions
    type: int
    applications:
    - Openshift Etcd

  - key: openshift.master.etcd.get.fail
    description: Show number of failed get actions
    type: int
    applications:
    - Openshift Etcd

  - key: openshift.master.etcd.set.success
    description: Show number of successful set actions
    type: int
    applications:
    - Openshift Etcd

  - key: openshift.master.etcd.set.fail
    description: Show number of failed set actions
    type: int
    applications:
    - Openshift Etcd

  - key: openshift.master.etcd.update.success
    description: Show number of successful update actions
    type: int
    applications:
    - Openshift Etcd

  - key: openshift.master.etcd.update.fail
    description: Show number of failed update actions
    type: int
    applications:
    - Openshift Etcd

  - key: openshift.master.etcd.watchers
    description: Show number of etcd watchers
    type: int
    applications:
    - Openshift Etcd

  - key: openshift.master.etcd.ping
    description: etcd ping
    type: int
    applications:
    - Openshift Etcd

  - key: openshift.master.metric.ping
    description: "This check verifies that the https://master/metrics check is alive and communicating properly."
    type: int
    applications:
    - Openshift Master Metrics

  - key: openshift.master.nodesnotready.count
    description: "This check shows how many nodes in a cluster are in NotReady state."
    type: int
    applications: 
    - Openshift Master

  - key: openshift.master.nodesnotschedulable.count
    description: "This check shows how many nodes in a cluster are not schedulable."
    type: int
    applications:
    - Openshift Master

  - key: openshift.master.apiserver.latency.summary.pods.quantile.list.5
    description: "Value from https://master/metrics.  This is the time, in miliseconds, that 50% of the pod operations have taken to completed."
    type: int
    applications:
    - Openshift Master Metrics

  - key: openshift.master.apiserver.latency.summary.pods.quantile.list.9
    description: "Value from https://master/metrics.  This is the time, in miliseconds, that 90% of the pod operations have taken to completed."
    type: int
    applications:
    - Openshift Master Metrics

  - key: openshift.master.apiserver.latency.summary.pods.quantile.list.99
    description: "Value from https://master/metrics.  This is the time, in miliseconds, that 99% of the pod operations have taken to completed."
    type: int
    applications:
    - Openshift Master Metrics

  - key: openshift.master.apiserver.latency.summary.pods.quantile.watchlist.5
    description: "Value from https://master/metrics.  This is the time, in miliseconds, that 50% of the pod operations have taken to completed."
    type: int
    applications:
    - Openshift Master Metrics

  - key: openshift.master.apiserver.latency.summary.pods.quantile.watchlist.9
    description: "Value from https://master/metrics.  This is the time, in miliseconds, that 90% of the pod operations have taken to completed."
    type: int
    applications:
    - Openshift Master Metrics

  - key: openshift.master.apiserver.latency.summary.pods.quantile.watchlist.99
    description: "Value from https://master/metrics.  This is the time, in miliseconds, that 99% of the pod operations have taken to completed."
    type: int
    applications:
    - Openshift Master Metrics

  - key: openshift.master.scheduler.e2e.scheduling.latency.quantile.5
    description: "Value from https://master/metrics.  This is the time, in miliseconds, that 50% of the end to end scheduling operations have taken to completed."
    type: int
    applications:
    - Openshift Master Metrics

  - key: openshift.master.scheduler.e2e.scheduling.latency.quantile.9
    description: "Value from https://master/metrics.  This is the time, in miliseconds, that 90% of the end to end scheduling operations have taken to completed."
    type: int
    applications:
    - Openshift Master Metrics

  - key: openshift.master.scheduler.e2e.scheduling.latency.quantile.99
    description: "Value from https://master/metrics.  This is the time, in miliseconds, that 99% of the end to end scheduling operations have taken to completed."
    type: int
    applications:
    - Openshift Master Metrics

  ztriggers:
  - name: 'Openshift Master process not running on {HOST.NAME}'
    expression: '{Template Openshift Master:openshift.master.process.count.max(#3)}<1'
    url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
    priority: high

  - name: 'Too many Openshift Master processes running on {HOST.NAME}'
    expression: '{Template Openshift Master:openshift.master.process.count.min(#3)}>1'
    url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
    priority: high

  - name: 'Low number of etcd watchers on {HOST.NAME}'
    expression: '{Template Openshift Master:openshift.master.etcd.watchers.last(#1)}<10 and {Template Openshift Master:openshift.master.etcd.watchers.last(#2)}<10'
    url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_etcd.asciidoc'
    priority: avg

  - name: 'Etcd ping failed on {HOST.NAME}'
    expression: '{Template Openshift Master:openshift.master.etcd.ping.last(#1)}=0 and {Template Openshift Master:openshift.master.etcd.ping.last(#2)}=0'
    url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_etcd.asciidoc'
    priority: high

  - name: 'Number of users for Openshift Master on {HOST.NAME}'
    expression: '{Template Openshift Master:openshift.master.user.count.last()}=0'
    url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
    priority: info

  - name: 'There are no projects running on {HOST.NAME}'
    expression: '{Template Openshift Master:openshift.project.count.last()}=0'
    url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
    priority: info

  # Put triggers that depend on other triggers here (deps must be created first)
  - name: 'Application creation has failed on {HOST.NAME}'
    expression: '{Template Openshift Master:openshift.master.app.create.last(#1)}=1 and {Template Openshift Master:openshift.master.app.create.last(#2)}=1'
    url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_create_app.asciidoc'
    dependencies:
    - 'Openshift Master process not running on {HOST.NAME}'
    priority: avg

  - name: 'Application creation has failed multiple times in the last hour on {HOST.NAME}'
    expression: '{Template Openshift Master:openshift.master.app.create.sum(1h)}>3'
    url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_create_app.asciidoc'
    dependencies:
    - 'Openshift Master process not running on {HOST.NAME}'
    description: The application create loop has failed 4 or more times in the last hour
    priority: avg

  - name: 'Openshift Master API health check is failing on {HOST.NAME}'
    expression: '{Template Openshift Master:openshift.master.api.healthz.max(#3)}<1'
    url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
    priority: high

  - name: 'Openshift Master Local API health check is failing on {HOST.NAME}'
    expression: '{Template Openshift Master:openshift.master.local.api.healthz.max(#3)}<1'
    url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
    dependencies:
    - 'Openshift Master process not running on {HOST.NAME}'
    priority: high

  - name: 'Openshift Master API PING check is failing on {HOST.NAME}'
    expression: '{Template Openshift Master:openshift.master.api.ping.max(#3)}<1'
    url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
    priority: high

  - name: 'Openshift Master Local API PING check is failing on {HOST.NAME}'
    expression: '{Template Openshift Master:openshift.master.local.api.ping.max(#3)}<1'
    url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
    dependencies:
    - 'Openshift Master process not running on {HOST.NAME}'
    priority: high

  - name: 'Openshift Master metric PING check is failing on {HOST.NAME}'
    expression: '{Template Openshift Master:openshift.master.metric.ping.max(#3)}<1'
    url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
    dependencies:
    - 'Openshift Master process not running on {HOST.NAME}'
    priority: avg

  - name: 'One or more Docker Registries is unhealthy according to {HOST.NAME}'
    expression: '{Template Openshift Master:openshift.master.registry.healthy_pct.last(#2)}<100 and {Template Openshift Master:openshift.master.registry.healthy_pct.max(#2)}>50'
    url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_registry.asciidoc'
    dependencies:
    - 'Openshift Master process not running on {HOST.NAME}'
    priority: avg

  - name: 'Multiple Docker Registries are unhealthy according to {HOST.NAME}'
    expression: '{Template Openshift Master:openshift.master.registry.healthy_pct.last(#2)}<51'
    url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_registry.asciidoc'
    dependencies:
    - 'Openshift Master process not running on {HOST.NAME}'
    priority: high

  - name: 'SkyDNS port not listening on {HOST.NAME}'
    expression: '{Template Openshift Master:openshift.master.skydns.port.open.max(#3)}<1'
    url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
    dependencies:
    - 'Openshift Master process not running on {HOST.NAME}'
    priority: high

  - name: 'SkyDNS query failed on {HOST.NAME}'
    expression: '{Template Openshift Master:openshift.master.skydns.query.max(#3)}<1'
    url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
    dependencies:
    - 'Openshift Master API health check is failing on {HOST.NAME}'
    priority: high

  - name: 'Hosts not ready according to {HOST.NAME}'
    expression: '{Template Openshift Master:openshift.master.nodesnotready.count.last(#2)}>0'
    url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_node.asciidoc'
    dependencies: 
    - 'Openshift Master process not running on {HOST.NAME}'
    priority: high

  zgraphs:
  - name: Openshift Master API Server Latency Pods LIST Quantiles
    width: 900
    height: 200
    graph_items:
    - item_name: openshift.master.apiserver.latency.summary.pods.quantile.list.5
      color: red
    - item_name: openshift.master.apiserver.latency.summary.pods.quantile.list.9
      color: blue
    - item_name: openshift.master.apiserver.latency.summary.pods.quantile.list.99
      color: orange

  - name: Openshift Master API Server Latency Pods WATCHLIST Quantiles
    width: 900
    height: 200
    graph_items:
    - item_name: openshift.master.apiserver.latency.summary.pods.quantile.watchlist.5
      color: red
    - item_name: openshift.master.apiserver.latency.summary.pods.quantile.watchlist.9
      color: blue
    - item_name: openshift.master.apiserver.latency.summary.pods.quantile.watchlist.99
      color: orange

  - name: Openshift Master Scheduler End to End Latency Quantiles
    width: 900
    height: 200
    graph_items:
    - item_name: openshift.master.scheduler.e2e.scheduling.latency.quantile.5
      color: red
    - item_name: openshift.master.scheduler.e2e.scheduling.latency.quantile.9
      color: blue
    - item_name: openshift.master.scheduler.e2e.scheduling.latency.quantile.99
      color: orange