summaryrefslogtreecommitdiffstats
path: root/roles/os_zabbix
diff options
context:
space:
mode:
authorMatt Woodson <mwoodson@gmail.com>2015-11-17 09:15:21 -0500
committerMatt Woodson <mwoodson@gmail.com>2015-11-17 09:15:21 -0500
commit426aa0a1613bdfc5547abde43ab1130ba027126e (patch)
tree7aaf43cc0c4152e933207d61e8a1ef2e884c5d38 /roles/os_zabbix
parent56bfd1e0cd39c0cc5b3bd52113e634f3588eb14f (diff)
parent9abce4c8c8f40fa6b4bfdea6b5cffc6442249435 (diff)
downloadopenshift-426aa0a1613bdfc5547abde43ab1130ba027126e.tar.gz
openshift-426aa0a1613bdfc5547abde43ab1130ba027126e.tar.bz2
openshift-426aa0a1613bdfc5547abde43ab1130ba027126e.tar.xz
openshift-426aa0a1613bdfc5547abde43ab1130ba027126e.zip
Merge pull request #910 from mwoodson/master_checks
added healthz check and more pod count checks
Diffstat (limited to 'roles/os_zabbix')
-rw-r--r--roles/os_zabbix/vars/template_openshift_master.yml25
1 files changed, 24 insertions, 1 deletions
diff --git a/roles/os_zabbix/vars/template_openshift_master.yml b/roles/os_zabbix/vars/template_openshift_master.yml
index 6defc4989..aaf5b9445 100644
--- a/roles/os_zabbix/vars/template_openshift_master.yml
+++ b/roles/os_zabbix/vars/template_openshift_master.yml
@@ -13,6 +13,12 @@ g_template_openshift_master:
applications:
- Openshift Master
+ - key: openshift.master.api.healthz
+ description: "Checks the healthz check of the master's api: https://master_host/healthz"
+ type: bool
+ applications:
+ - Openshift Master
+
- key: openshift.master.user.count
description: Shows number of users in a cluster
type: int
@@ -24,7 +30,19 @@ g_template_openshift_master:
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.project.counter
description: Shows number of projects on a cluster
type: int
@@ -109,6 +127,11 @@ g_template_openshift_master:
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 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'