diff options
Diffstat (limited to 'roles/os_zabbix')
| -rw-r--r-- | roles/os_zabbix/tasks/main.yml | 36 | ||||
| -rw-r--r-- | roles/os_zabbix/vars/template_app_zabbix_agent.yml | 23 | ||||
| -rw-r--r-- | roles/os_zabbix/vars/template_app_zabbix_server.yml | 412 | ||||
| -rw-r--r-- | roles/os_zabbix/vars/template_docker.yml | 5 | ||||
| -rw-r--r-- | roles/os_zabbix/vars/template_openshift_master.yml | 110 | ||||
| -rw-r--r-- | roles/os_zabbix/vars/template_openshift_node.yml | 28 | ||||
| -rw-r--r-- | roles/os_zabbix/vars/template_ops_tools.yml | 23 | ||||
| -rw-r--r-- | roles/os_zabbix/vars/template_os_linux.yml | 65 | ||||
| -rw-r--r-- | roles/os_zabbix/vars/template_performance_copilot.yml | 14 |
9 files changed, 681 insertions, 35 deletions
diff --git a/roles/os_zabbix/tasks/main.yml b/roles/os_zabbix/tasks/main.yml index 8347e9a61..82bf78b57 100644 --- a/roles/os_zabbix/tasks/main.yml +++ b/roles/os_zabbix/tasks/main.yml @@ -12,6 +12,10 @@ - include_vars: template_docker.yml - include_vars: template_openshift_master.yml - include_vars: template_openshift_node.yml +- include_vars: template_ops_tools.yml +- include_vars: template_app_zabbix_server.yml +- include_vars: template_app_zabbix_agent.yml +- include_vars: template_performance_copilot.yml - name: Include Template Heartbeat include: ../../lib_zabbix/tasks/create_template.yml @@ -52,3 +56,35 @@ server: "{{ ozb_server }}" user: "{{ ozb_user }}" password: "{{ ozb_password }}" + +- name: Include Template Ops Tools + include: ../../lib_zabbix/tasks/create_template.yml + vars: + template: "{{ g_template_ops_tools }}" + server: "{{ ozb_server }}" + user: "{{ ozb_user }}" + password: "{{ ozb_password }}" + +- name: Include Template App Zabbix Server + include: ../../lib_zabbix/tasks/create_template.yml + vars: + template: "{{ g_template_app_zabbix_server }}" + server: "{{ ozb_server }}" + user: "{{ ozb_user }}" + password: "{{ ozb_password }}" + +- name: Include Template App Zabbix Agent + include: ../../lib_zabbix/tasks/create_template.yml + vars: + template: "{{ g_template_app_zabbix_agent }}" + server: "{{ ozb_server }}" + user: "{{ ozb_user }}" + password: "{{ ozb_password }}" + +- name: Include Template Performance Copilot + include: ../../lib_zabbix/tasks/create_template.yml + vars: + template: "{{ g_template_performance_copilot }}" + server: "{{ ozb_server }}" + user: "{{ ozb_user }}" + password: "{{ ozb_password }}" diff --git a/roles/os_zabbix/vars/template_app_zabbix_agent.yml b/roles/os_zabbix/vars/template_app_zabbix_agent.yml new file mode 100644 index 000000000..d636d4822 --- /dev/null +++ b/roles/os_zabbix/vars/template_app_zabbix_agent.yml @@ -0,0 +1,23 @@ +--- +g_template_app_zabbix_agent: + name: Template App Zabbix Agent + zitems: + - key: agent.hostname + applications: + - Zabbix agent + value_type: character + zabbix_type: agent + + - key: agent.ping + applications: + - Zabbix agent + description: The agent always returns 1 for this item. It could be used in combination with nodata() for availability check. + value_type: int + zabbix_type: agent + + ztriggers: + - name: '[Reboot] Zabbix agent on {HOST.NAME} is unreachable for 15 minutes' + description: Zabbix agent is unreachable for 15 minutes. + expression: '{Template App Zabbix Agent:agent.ping.nodata(15m)}=1' + priority: high + url: https://github.com/openshift/ops-sop/blob/master/Alerts/check_ping.asciidoc diff --git a/roles/os_zabbix/vars/template_app_zabbix_server.yml b/roles/os_zabbix/vars/template_app_zabbix_server.yml new file mode 100644 index 000000000..43517113b --- /dev/null +++ b/roles/os_zabbix/vars/template_app_zabbix_server.yml @@ -0,0 +1,412 @@ +--- +g_template_app_zabbix_server: + name: Template App Zabbix Server + zitems: + - key: housekeeper_creates + applications: + - Zabbix server + description: A simple count of the number of partition creates output by the housekeeper script. + units: '' + value_type: int + zabbix_type: internal + + - key: housekeeper_drops + applications: + - Zabbix server + description: A simple count of the number of partition drops output by the housekeeper script. + units: '' + value_type: int + zabbix_type: internal + + - key: housekeeper_errors + applications: + - Zabbix server + description: A simple count of the number of errors output by the housekeeper script. + units: '' + value_type: int + zabbix_type: internal + + - key: housekeeper_total + applications: + - Zabbix server + description: A simple count of the total number of lines output by the housekeeper + script. + units: '' + value_type: int + zabbix_type: internal + + - key: zabbix[process,alerter,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[process,configuration syncer,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[process,db watchdog,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[process,discoverer,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[process,escalator,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[process,history syncer,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[process,housekeeper,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[process,http poller,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[process,icmp pinger,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[process,ipmi poller,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[process,java poller,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[process,node watcher,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[process,poller,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[process,proxy poller,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[process,self-monitoring,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[process,snmp trapper,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[process,timer,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[process,trapper,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[process,unreachable poller,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: internal + + - key: zabbix[queue,10m] + applications: + - Zabbix server + description: '' + units: '' + value_type: int + zabbix_type: internal + interval: 600 + + - key: zabbix[queue] + applications: + - Zabbix server + description: '' + units: '' + value_type: int + zabbix_type: internal + interval: 600 + + - key: zabbix[rcache,buffer,pfree] + applications: + - Zabbix server + description: '' + units: '' + value_type: float + zabbix_type: internal + + - key: zabbix[wcache,history,pfree] + applications: + - Zabbix server + description: '' + units: '' + value_type: float + zabbix_type: internal + + - key: zabbix[wcache,text,pfree] + applications: + - Zabbix server + description: '' + units: '' + value_type: float + zabbix_type: internal + + - key: zabbix[wcache,trend,pfree] + applications: + - Zabbix server + description: '' + units: '' + value_type: float + zabbix_type: internal + + - key: zabbix[wcache,values] + applications: + - Zabbix server + description: '' + units: '' + value_type: float + zabbix_type: internal + delta: 1 # speed per second + + ztriggers: + - description: "There has been unexpected output while running the housekeeping script\ + \ on the Zabbix. There are only three kinds of lines we expect to see in the output,\ + \ and we've gotten something enw.\r\n\r\nCheck the script's output in /var/lib/zabbix/state\ + \ for more details." + expression: '{Template App Zabbix Server:housekeeper_errors.last(0)}+{Template App Zabbix Server:housekeeper_creates.last(0)}+{Template App Zabbix Server:housekeeper_drops.last(0)}<>{Template App Zabbix Server:housekeeper_total.last(0)}' + name: Unexpected output in Zabbix DB Housekeeping + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_DB_Housekeeping.asciidoc + + - description: An error has occurred during running the housekeeping script on the Zabbix. Check the script's output in /var/lib/zabbix/state for more details. + expression: '{Template App Zabbix Server:housekeeper_errors.last(0)}>0' + name: Errors during Zabbix DB Housekeeping + priority: high + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[process,alerter,avg,busy].min(600)}>75' + name: Zabbix alerter processes more than 75% busy + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[process,configuration syncer,avg,busy].min(600)}>75' + name: Zabbix configuration syncer processes more than 75% busy + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[process,db watchdog,avg,busy].min(600)}>75' + name: Zabbix db watchdog processes more than 75% busy + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[process,discoverer,avg,busy].min(600)}>75' + name: Zabbix discoverer processes more than 75% busy + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[process,escalator,avg,busy].min(600)}>75' + name: Zabbix escalator processes more than 75% busy + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[process,history syncer,avg,busy].min(600)}>75' + name: Zabbix history syncer processes more than 75% busy + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[process,housekeeper,avg,busy].min(1800)}>75' + name: Zabbix housekeeper processes more than 75% busy + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[process,http poller,avg,busy].min(600)}>75' + name: Zabbix http poller processes more than 75% busy + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[process,icmp pinger,avg,busy].min(600)}>75' + name: Zabbix icmp pinger processes more than 75% busy + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[process,ipmi poller,avg,busy].min(600)}>75' + name: Zabbix ipmi poller processes more than 75% busy + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[process,java poller,avg,busy].min(600)}>75' + name: Zabbix java poller processes more than 75% busy + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[process,node watcher,avg,busy].min(600)}>75' + name: Zabbix node watcher processes more than 75% busy + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[process,poller,avg,busy].min(600)}>75' + name: Zabbix poller processes more than 75% busy + priority: high + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[process,proxy poller,avg,busy].min(600)}>75' + name: Zabbix proxy poller processes more than 75% busy + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[process,self-monitoring,avg,busy].min(600)}>75' + name: Zabbix self-monitoring processes more than 75% busy + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[process,snmp trapper,avg,busy].min(600)}>75' + name: Zabbix snmp trapper processes more than 75% busy + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: Timer processes usually are busy because they have to process time + based trigger functions + expression: '{Template App Zabbix Server:zabbix[process,timer,avg,busy].min(600)}>75' + name: Zabbix timer processes more than 75% busy + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[process,trapper,avg,busy].min(600)}>75' + name: Zabbix trapper processes more than 75% busy + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[process,unreachable poller,avg,busy].min(600)}>75' + name: Zabbix unreachable poller processes more than 75% busy + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc + + - description: "This alert generally indicates a performance problem or a problem\ + \ with the zabbix-server or proxy.\r\n\r\nThe first place to check for issues\ + \ is Administration > Queue. Be sure to check the general view and the per-proxy\ + \ view." + expression: '{Template App Zabbix Server:zabbix[queue,10m].min(600)}>1000' + name: More than 1000 items having missing data for more than 10 minutes + priority: high + url: https://github.com/openshift/ops-sop/blob/master/Alerts/data_lost_overview_plugin.asciidoc + + - description: Consider increasing CacheSize in the zabbix_server.conf configuration + file + expression: '{Template App Zabbix Server:zabbix[rcache,buffer,pfree].min(600)}<5' + name: Less than 5% free in the configuration cache + priority: info + url: https://github.com/openshift/ops-sop/blob/master/Alerts/check_cache.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[wcache,history,pfree].min(600)}<25' + name: Less than 25% free in the history cache + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/check_cache.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[wcache,text,pfree].min(600)}<25' + name: Less than 25% free in the text history cache + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/check_cache.asciidoc + + - description: '' + expression: '{Template App Zabbix Server:zabbix[wcache,trend,pfree].min(600)}<25' + name: Less than 25% free in the trends cache + priority: avg + url: https://github.com/openshift/ops-sop/blob/master/Alerts/check_cache.asciidoc diff --git a/roles/os_zabbix/vars/template_docker.yml b/roles/os_zabbix/vars/template_docker.yml index 395e054de..bfabf50c5 100644 --- a/roles/os_zabbix/vars/template_docker.yml +++ b/roles/os_zabbix/vars/template_docker.yml @@ -7,6 +7,11 @@ g_template_docker: - Docker Daemon value_type: int + - key: docker.info_elapsed_ms + applications: + - Docker Daemon + value_type: int + - key: docker.storage.is_loopback applications: - Docker Storage diff --git a/roles/os_zabbix/vars/template_openshift_master.yml b/roles/os_zabbix/vars/template_openshift_master.yml index c71e07910..cd702a814 100644 --- a/roles/os_zabbix/vars/template_openshift_master.yml +++ b/roles/os_zabbix/vars/template_openshift_master.yml @@ -13,6 +13,96 @@ g_template_openshift_master: applications: - Openshift Master + - key: openshift.master.user.count + description: Shows number of users in a cluster + type: int + applications: + - Openshift Master + + - key: openshift.master.pod.running.count + description: Shows number of pods running + type: int + applications: + - Openshift Master + + - key: openshift.project.counter + description: Shows number of projects on a cluster + type: int + applications: + - Openshift Master + + - key: openshift.master.etcd.create.success + description: Show number of successful create actions + type: int + applications: + - Openshift Master + + - key: openshift.master.etcd.create.fail + description: Show number of failed create actions + type: int + applications: + - Openshift Master + + - key: openshift.master.etcd.delete.success + description: Show number of successful delete actions + type: int + applications: + - Openshift Master + + - key: openshift.master.etcd.delete.fail + description: Show number of failed delete actions + type: int + applications: + - Openshift Master + + - key: openshift.master.etcd.get.success + description: Show number of successful get actions + type: int + applications: + - Openshift Master + + - key: openshift.master.etcd.get.fail + description: Show number of failed get actions + type: int + applications: + - Openshift Master + + - key: openshift.master.etcd.set.success + description: Show number of successful set actions + type: int + applications: + - Openshift Master + + - key: openshift.master.etcd.set.fail + description: Show number of failed set actions + type: int + applications: + - Openshift Master + + - key: openshift.master.etcd.update.success + description: Show number of successful update actions + type: int + applications: + - Openshift Master + + - key: openshift.master.etcd.update.fail + description: Show number of failed update actions + type: int + applications: + - Openshift Master + + - key: openshift.master.etcd.watchers + description: Show number of etcd watchers + type: int + applications: + - Openshift Master + + - key: openshift.master.etcd.ping + description: etcd ping + type: int + applications: + - Openshift Master + 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' @@ -28,3 +118,23 @@ g_template_openshift_master: expression: '{Template Openshift Master:openshift.master.process.count.min(#3)}>1' url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.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' + priority: info + + - name: 'There are no projects running on {HOST.NAME}' + expression: '{Template Openshift Master:openshift.project.counter.last()}=0' + 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' + 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 diff --git a/roles/os_zabbix/vars/template_openshift_node.yml b/roles/os_zabbix/vars/template_openshift_node.yml index 36f9cc4a3..ce28b1048 100644 --- a/roles/os_zabbix/vars/template_openshift_node.yml +++ b/roles/os_zabbix/vars/template_openshift_node.yml @@ -8,13 +8,37 @@ g_template_openshift_node: applications: - Openshift Node + - key: openshift.node.ovs.pids.count + description: Shows number of ovs process ids running + type: int + applications: + - Openshift Node + + - key: openshift.node.ovs.ports.count + description: Shows number of OVS ports defined + type: int + applications: + - Openshift Node + ztriggers: - 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/master/V3/Alerts/openshift_node.asciidoc' + url: 'https://github.com/openshift/ops-sop/blob/node/V3/Alerts/openshift_node.asciidoc' priority: high - name: 'Too many Openshift Node processes running on {HOST.NAME}' expression: '{Template Openshift Node:openshift.node.process.count.min(#3)}>1' - url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_node.asciidoc' + url: 'https://github.com/openshift/ops-sop/blob/node/V3/Alerts/openshift_node.asciidoc' + priority: high + + - name: 'OVS may not be running on {HOST.NAME}' + expression: '{Template Openshift Node:openshift.node.ovs.pids.count.last()}<>4' + url: 'https://github.com/openshift/ops-sop/blob/node/V3/Alerts/openshift_node.asciidoc' priority: high + + - name: 'Number of OVS ports is 0 on {HOST.NAME}' + expression: '{Template Openshift Node:openshift.node.ovs.ports.count.last()}=0' + url: 'https://github.com/openshift/ops-sop/blob/node/V3/Alerts/openshift_node.asciidoc' + priority: high + + 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..aeeec4b8d 100644 --- a/roles/os_zabbix/vars/template_os_linux.yml +++ b/roles/os_zabbix/vars/template_os_linux.yml @@ -188,28 +188,14 @@ g_template_os_linux: multiplier: 1024 units: B - # Disk items - - key: filesys.full.xvda2 - applications: - - Disk - value_type: float - - - key: filesys.full.xvda3 - applications: - - Disk - value_type: float - - zdiscoveryrules: - 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 @@ -217,38 +203,36 @@ g_template_os_linux: applications: - Disk - ztriggerprototypes: - - name: 'Filesystem: {#OSO_FILESYS} has less than 10% free on {HOST.NAME}' - expression: '{Template OS Linux:disc.filesys.full[{#OSO_FILESYS}].last()}>90' - url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc' - priority: warn - - - name: 'Filesystem: {#OSO_FILESYS} has less than 5% free on {HOST.NAME}' - expression: '{Template OS Linux:disc.filesys.full[{#OSO_FILESYS}].last()}>95' - url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc' - priority: high + - discoveryrule_key: disc.filesys + name: "Percentage of used inodes on {#OSO_FILESYS}" + key: "disc.filesys.inodes.pused[{#OSO_FILESYS}]" + value_type: float + description: "PCP derived value of percentage of used inodes on a filesystem." + applications: + - Disk - ztriggers: - - name: 'Filesystem: / has less than 10% free on {HOST.NAME}' - expression: '{Template OS Linux:filesys.full.xvda2.last()}>90' + ztriggerprototypes: + - name: 'Filesystem: {#OSO_FILESYS} has less than 15% free disk space on {HOST.NAME}' + expression: '{Template OS Linux:disc.filesys.full[{#OSO_FILESYS}].last()}>85' url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc' priority: warn - - name: 'Filesystem: / has less than 5% free on {HOST.NAME}' - expression: '{Template OS Linux:filesys.full.xvda2.last()}>95' + - name: 'Filesystem: {#OSO_FILESYS} has less than 10% free disk space on {HOST.NAME}' + expression: '{Template OS Linux:disc.filesys.full[{#OSO_FILESYS}].last()}>90' url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc' priority: high - - name: 'Filesystem: /var has less than 10% free on {HOST.NAME}' - expression: '{Template OS Linux:filesys.full.xvda3.last()}>90' + - name: 'Filesystem: {#OSO_FILESYS} has less than 10% free inodes on {HOST.NAME}' + expression: '{Template OS Linux:disc.filesys.inodes.pused[{#OSO_FILESYS}].last()}>90' url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc' priority: warn - - name: 'Filesystem: /var has less than 5% free on {HOST.NAME}' - expression: '{Template OS Linux:filesys.full.xvda3.last()}>95' + - name: 'Filesystem: {#OSO_FILESYS} has less than 5% free inodes on {HOST.NAME}' + expression: '{Template OS Linux:disc.filesys.inodes.pused[{#OSO_FILESYS}].last()}>95' url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc' priority: high + ztriggers: - name: 'Too many TOTAL processes on {HOST.NAME}' expression: '{Template OS Linux:proc.nprocs.last()}>5000' url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_proc.asciidoc' @@ -259,3 +243,18 @@ 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.max(#5)}<5' + url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_cpu_idle.asciidoc' + priority: average + description: 'CPU is less than 5% idle' + + - name: 'CPU idle less than 10% on {HOST.NAME}' + expression: '{Template OS Linux:kernel.all.cpu.idle.max(#5)}<10' + url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_cpu_idle.asciidoc' + priority: average + description: 'CPU is less than 10% idle' + dependencies: + - 'CPU idle less than 5% on {HOST.NAME}' diff --git a/roles/os_zabbix/vars/template_performance_copilot.yml b/roles/os_zabbix/vars/template_performance_copilot.yml new file mode 100644 index 000000000..b62fa0228 --- /dev/null +++ b/roles/os_zabbix/vars/template_performance_copilot.yml @@ -0,0 +1,14 @@ +--- +g_template_performance_copilot: + name: Template Performance Copilot + zitems: + - key: pcp.ping + applications: + - Performance Copilot + value_type: int + + ztriggers: + - name: 'pcp.ping failed on {HOST.NAME}' + expression: '{Template Performance Copilot:pcp.ping.max(#3)}<1' + url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_pcp_ping.asciidoc' + priority: average |