summaryrefslogtreecommitdiffstats
path: root/roles/os_zabbix/vars
diff options
context:
space:
mode:
Diffstat (limited to 'roles/os_zabbix/vars')
-rw-r--r--roles/os_zabbix/vars/template_ops_tools.yml23
-rw-r--r--roles/os_zabbix/vars/template_os_linux.yml17
2 files changed, 38 insertions, 2 deletions
diff --git a/roles/os_zabbix/vars/template_ops_tools.yml b/roles/os_zabbix/vars/template_ops_tools.yml
new file mode 100644
index 000000000..d1b8a2514
--- /dev/null
+++ b/roles/os_zabbix/vars/template_ops_tools.yml
@@ -0,0 +1,23 @@
+---
+g_template_ops_tools:
+ name: Template Operations Tools
+ zdiscoveryrules:
+ - name: disc.ops.runner
+ key: disc.ops.runner
+ lifetime: 1
+ description: "Dynamically register operations runner items"
+
+ zitemprototypes:
+ - discoveryrule_key: disc.ops.runner
+ name: "Exit code of ops-runner[{#OSO_COMMAND}]"
+ key: "disc.ops.runner.command.exitcode[{#OSO_COMMAND}]"
+ value_type: int
+ description: "The exit code of the command run from ops-runner"
+ applications:
+ - Ops Runner
+
+ ztriggerprototypes:
+ - name: 'ops-runner[{#OSO_COMMAND}]: non-zero exit code on {HOST.NAME}'
+ expression: '{Template Operations Tools:disc.ops.runner.command.exitcode[{#OSO_COMMAND}].last()}<>0'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_ops_runner_command.asciidoc'
+ priority: average
diff --git a/roles/os_zabbix/vars/template_os_linux.yml b/roles/os_zabbix/vars/template_os_linux.yml
index 36c890da9..70c3809bd 100644
--- a/roles/os_zabbix/vars/template_os_linux.yml
+++ b/roles/os_zabbix/vars/template_os_linux.yml
@@ -204,12 +204,10 @@ g_template_os_linux:
- name: disc.filesys
key: disc.filesys
lifetime: 1
- template_name: Template OS Linux
description: "Dynamically register the filesystems"
zitemprototypes:
- discoveryrule_key: disc.filesys
- template_name: Template OS Linux
name: "disc.filesys.full.{#OSO_FILESYS}"
key: "disc.filesys.full[{#OSO_FILESYS}]"
value_type: float
@@ -259,3 +257,18 @@ g_template_os_linux:
url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_memory.asciidoc'
priority: warn
description: 'Alert on less than 30MegaBytes. This is 30 Million Bytes. 30000 KB x 1024'
+
+ # CPU Utilization #
+ - name: 'CPU idle less than 5% on {HOST.NAME}'
+ expression: '{Template OS Linux:kernel.all.cpu.idle.last()}<5 and {Template OS Linux:kernel.all.cpu.idle.last(#2)}<5'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_cpu_idle.asciidoc'
+ priority: high
+ description: 'CPU is less than 5% idle'
+
+ - name: 'CPU idle less than 10% on {HOST.NAME}'
+ expression: '{Template OS Linux:kernel.all.cpu.idle.last()}<10 and {Template OS Linux:kernel.all.cpu.idle.last(#2)}<10'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_cpu_idle.asciidoc'
+ priority: warn
+ description: 'CPU is less than 10% idle'
+ dependencies:
+ - 'CPU idle less than 5% on {HOST.NAME}'