diff options
Diffstat (limited to 'roles/os_zabbix/vars/template_openshift_master.yml')
-rw-r--r-- | roles/os_zabbix/vars/template_openshift_master.yml | 101 |
1 files changed, 75 insertions, 26 deletions
diff --git a/roles/os_zabbix/vars/template_openshift_master.yml b/roles/os_zabbix/vars/template_openshift_master.yml index 6972ac877..a0ba8d104 100644 --- a/roles/os_zabbix/vars/template_openshift_master.yml +++ b/roles/os_zabbix/vars/template_openshift_master.yml @@ -68,6 +68,36 @@ g_template_openshift_master: 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.etcd.create.success description: Show number of successful create actions type: int @@ -201,26 +231,6 @@ g_template_openshift_master: - Openshift Master Metrics ztriggers: - - name: 'Application creation has failed on {HOST.NAME}' - expression: '{Template Openshift Master:create_app.last(#1)}=1 and {Template Openshift Master:create_app.last(#2)}=1' - url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_create_app.asciidoc' - 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 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 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' - priority: avg - - 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' @@ -231,6 +241,16 @@ g_template_openshift_master: 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' @@ -241,19 +261,48 @@ g_template_openshift_master: url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc' priority: info - - 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' + # 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:create_app.last(#1)}=1 and {Template Openshift Master:create_app.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: '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' + - name: 'Application creation has failed multiple times in the last hour on {HOST.NAME}' + expression: '{Template Openshift Master:create_app.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' + 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' + 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: 'Docker Registry check failed on {HOST.NAME}' expression: '{Template Openshift Master:openshift.master.registry.healthz.max(#2)}<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 zgraphs: |