summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--roles/os_zabbix/vars/template_openshift_master.yml33
1 files changed, 33 insertions, 0 deletions
diff --git a/roles/os_zabbix/vars/template_openshift_master.yml b/roles/os_zabbix/vars/template_openshift_master.yml
index e36f23a2b..45f2ecf07 100644
--- a/roles/os_zabbix/vars/template_openshift_master.yml
+++ b/roles/os_zabbix/vars/template_openshift_master.yml
@@ -6,6 +6,24 @@ 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"
+ type: int
+ applications:
+ - Openshift Master
+
+ - key: openshift.master.app.create.time
+ description: "check the time it takes app create with a build process"
+ type: int
+ applications:
+ - Openshift Master
+
+ - key: openshift.master.app.build.time
+ description: "check the time it takes app build"
+ type: int
+ applications:
+ - Openshift Master
- key: openshift.master.process.count
description: Shows number of master processes running
@@ -295,6 +313,13 @@ 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 +328,14 @@ 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'