diff options
Diffstat (limited to 'roles/os_zabbix')
-rw-r--r-- | roles/os_zabbix/vars/template_openshift_master.yml | 152 | ||||
-rw-r--r-- | roles/os_zabbix/vars/template_openshift_node.yml | 12 |
2 files changed, 116 insertions, 48 deletions
diff --git a/roles/os_zabbix/vars/template_openshift_master.yml b/roles/os_zabbix/vars/template_openshift_master.yml index e36f23a2b..a38db9f65 100644 --- a/roles/os_zabbix/vars/template_openshift_master.yml +++ b/roles/os_zabbix/vars/template_openshift_master.yml @@ -6,261 +6,314 @@ g_template_openshift_master: applications: - Openshift Master key: openshift.master.app.create + + - key: openshift.master.app.build.create + description: "check the app create with a build process" + value_type: int + applications: + - Openshift Master + + - key: openshift.master.app.create.time + description: "check the time it takes app create with a build process" + value_type: float + applications: + - Openshift Master + + - key: openshift.master.app.build.time + description: "check the time it takes app build" + value_type: float + applications: + - Openshift Master - key: openshift.master.process.count description: Shows number of master processes running - type: int + value_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 + value_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 + value_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 + value_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 + value_type: int data_type: bool applications: - Openshift Master - key: openshift.master.user.count description: Shows number of users in a cluster - type: int + value_type: int applications: - Openshift Master - key: openshift.master.pod.running.count description: Shows number of pods running - type: int + value_type: int applications: - Openshift Master - key: openshift.master.pod.user.running.count description: Shows number of user pods running (non infrastructure pods) - type: int + value_type: int applications: - Openshift Master - key: openshift.master.pod.total.count description: Shows total number of pods (running and non running) - type: int + value_type: int applications: - Openshift Master - key: openshift.master.node.count description: Shows the total number of nodes found in the Openshift Cluster - type: int + value_type: int applications: - Openshift Master - key: openshift.project.count description: Shows number of projects on a cluster - type: int + value_type: int + applications: + - Openshift Master + + - key: openshift.master.pv.space.total + description: Shows the total space of pv + value_type: int + applications: + - Openshift Master + + - key: openshift.master.pv.space.available + description: Shows the available space of pv + value_type: int applications: - Openshift Master - key: openshift.master.pv.total.count description: Total number of Persistent Volumes in the Openshift Cluster - type: int + value_type: int applications: - Openshift Master - key: openshift.master.pv.available.count description: Total number of Available Persistent Volumes in the Openshift Cluster - type: int + value_type: int applications: - Openshift Master - key: openshift.master.pv.released.count description: Total number of Released Persistent Volumes in the Openshift Cluster - type: int + value_type: int applications: - Openshift Master - key: openshift.master.pv.bound.count description: Total number of Bound Persistent Volumes in the Openshift Cluster - type: int + value_type: int applications: - Openshift Master - key: openshift.master.pv.failed.count description: Total number of Failed Persistent Volumes in the Openshift Cluster - type: int + value_type: int applications: - Openshift Master - key: openshift.master.skydns.port.open description: State of the SkyDNS port open and listening - type: int + value_type: int applications: - Openshift Master - key: openshift.master.skydns.query description: SkyDNS can be queried or not - type: int + value_type: int applications: - Openshift Master - key: openshift.master.etcd.create.success description: Show number of successful create actions - type: int + value_type: int applications: - Openshift Etcd - key: openshift.master.etcd.create.fail description: Show number of failed create actions - type: int + value_type: int applications: - Openshift Etcd - key: openshift.master.etcd.delete.success description: Show number of successful delete actions - type: int + value_type: int applications: - Openshift Etcd - key: openshift.master.etcd.delete.fail description: Show number of failed delete actions - type: int + value_type: int applications: - Openshift Etcd - key: openshift.master.etcd.get.success description: Show number of successful get actions - type: int + value_type: int applications: - Openshift Etcd - key: openshift.master.etcd.get.fail description: Show number of failed get actions - type: int + value_type: int applications: - Openshift Etcd - key: openshift.master.etcd.set.success description: Show number of successful set actions - type: int + value_type: int applications: - Openshift Etcd - key: openshift.master.etcd.set.fail description: Show number of failed set actions - type: int + value_type: int applications: - Openshift Etcd - key: openshift.master.etcd.update.success description: Show number of successful update actions - type: int + value_type: int applications: - Openshift Etcd - key: openshift.master.etcd.update.fail description: Show number of failed update actions - type: int + value_type: int applications: - Openshift Etcd - key: openshift.master.etcd.watchers description: Show number of etcd watchers - type: int + value_type: int applications: - Openshift Etcd - key: openshift.master.etcd.ping description: etcd ping - type: int + value_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 + value_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 + value_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 + value_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 + value_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 + value_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 + value_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 + value_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 + value_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 + value_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 + value_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 + value_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 + value_type: int applications: - Openshift Master Metrics + zdiscoveryrules: + - name: disc.pv + key: disc.pv + lifetime: 1 + description: "Dynamically register the Persistent Volumes" + + zitemprototypes: + - discoveryrule_key: disc.pv + name: "disc.pv.count.{#OSO_PV}" + key: "disc.pv.count[{#OSO_PV}]" + value_type: int + description: "Number of PV's of this size" + applications: + - Openshift Master + + - discoveryrule_key: disc.pv + name: "disc.pv.available.{#OSO_PV}" + key: "disc.pv.available[{#OSO_PV}]" + value_type: int + description: "Number of PV's of this size that are available" + applications: + - Openshift Master + ztriggers: - name: 'Openshift Master process not running on {HOST.NAME}' expression: '{Template Openshift Master:openshift.master.process.count.max(#3)}<1' @@ -295,6 +348,13 @@ g_template_openshift_master: - 'Openshift Master process not running on {HOST.NAME}' priority: avg + - name: 'Application creation with build has failed on {HOST.NAME}' + expression: '{Template Openshift Master:openshift.master.app.build.create.last(#1)}=1 and {Template Openshift Master:openshift.master.app.build.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' @@ -303,6 +363,14 @@ g_template_openshift_master: description: The application create loop has failed 4 or more times in the last hour priority: avg + - name: 'Application with build creation has failed multiple times in the last 2 hour on {HOST.NAME}' + expression: '{Template Openshift Master:openshift.master.app.build.create.sum(2h)}>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' diff --git a/roles/os_zabbix/vars/template_openshift_node.yml b/roles/os_zabbix/vars/template_openshift_node.yml index 66bd3a147..9f84a2cdf 100644 --- a/roles/os_zabbix/vars/template_openshift_node.yml +++ b/roles/os_zabbix/vars/template_openshift_node.yml @@ -4,37 +4,37 @@ g_template_openshift_node: zitems: - key: openshift.node.process.count description: Shows number of OpenShift Node processes running - type: int + value_type: int applications: - Openshift Node - key: openshift.node.ovs.pids.count description: Shows number of ovs process ids running - type: int + value_type: int applications: - Openshift Node - key: openshift.node.ovs.ports.count description: Shows number of OVS ports defined - type: int + value_type: int applications: - Openshift Node - key: openshift.node.ovs.stray.rules description: Number of OVS stray rules found/removed - type: int + value_type: int applications: - Openshift Node - key: openshift.node.registry-pods.healthy_pct description: Shows the percentage of healthy registries in the cluster - type: int + value_type: int applications: - Openshift Node - key: openshift.node.registry.service.ping description: Ping docker-registry service from node - type: int + value_type: int applications: - Openshift Node |