summaryrefslogtreecommitdiffstats
path: root/roles/os_zabbix
diff options
context:
space:
mode:
Diffstat (limited to 'roles/os_zabbix')
-rw-r--r--roles/os_zabbix/vars/template_openshift_master.yml25
-rw-r--r--roles/os_zabbix/vars/template_openshift_node.yml22
2 files changed, 22 insertions, 25 deletions
diff --git a/roles/os_zabbix/vars/template_openshift_master.yml b/roles/os_zabbix/vars/template_openshift_master.yml
index 1824d7881..e36f23a2b 100644
--- a/roles/os_zabbix/vars/template_openshift_master.yml
+++ b/roles/os_zabbix/vars/template_openshift_master.yml
@@ -7,12 +7,6 @@ g_template_openshift_master:
- 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
@@ -278,11 +272,6 @@ 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'
@@ -345,20 +334,6 @@ g_template_openshift_master:
- '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'
diff --git a/roles/os_zabbix/vars/template_openshift_node.yml b/roles/os_zabbix/vars/template_openshift_node.yml
index b0488656d..c36c593df 100644
--- a/roles/os_zabbix/vars/template_openshift_node.yml
+++ b/roles/os_zabbix/vars/template_openshift_node.yml
@@ -26,7 +26,29 @@ g_template_openshift_node:
applications:
- Openshift Node
+ - key: openshift.node.registry-pods.healthy_pct
+ description: Shows the percentage of healthy registries in the cluster
+ type: int
+ applications:
+ - Openshift Node
+
+ - key: openshift.node.registry.service.ping
+ description: Ping docker-registry service from node
+ type: int
+ applications:
+ - Openshift Node
+
ztriggers:
+ - name: 'One or more Docker Registries is unhealthy according to {HOST.NAME}'
+ expression: '{Template Openshift Node:openshift.node.registry-pods.healthy_pct.last(#2)}<100 and {Template Openshift Node:openshift.node.registry-pods.healthy_pct.last(#1)}<100'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_registry.asciidoc'
+ priority: avg
+
+ - name: 'Docker Registry service is unhealthy according to {HOST.NAME}'
+ expression: '{Template Openshift Node:openshift.node.registry.service.ping.last(#2)}<1 and {Template Openshift Node:openshift.node.registry.service.ping.last(#1)}<1'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_registry.asciidoc'
+ priority: avg
+
- name: 'Openshift Node process not running on {HOST.NAME}'
expression: '{Template Openshift Node:openshift.node.process.count.max(#3)}<1'
url: 'https://github.com/openshift/ops-sop/blob/node/V3/Alerts/openshift_node.asciidoc'