diff options
Diffstat (limited to 'roles/os_zabbix/vars')
| -rw-r--r-- | roles/os_zabbix/vars/main.yml | 1 | ||||
| -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 | 89 | ||||
| -rw-r--r-- | roles/os_zabbix/vars/template_heartbeat.yml | 13 | ||||
| -rw-r--r-- | roles/os_zabbix/vars/template_openshift_master.yml | 58 | ||||
| -rw-r--r-- | roles/os_zabbix/vars/template_openshift_node.yml | 44 | ||||
| -rw-r--r-- | roles/os_zabbix/vars/template_ops_tools.yml | 23 | ||||
| -rw-r--r-- | roles/os_zabbix/vars/template_os_linux.yml | 260 |
9 files changed, 923 insertions, 0 deletions
diff --git a/roles/os_zabbix/vars/main.yml b/roles/os_zabbix/vars/main.yml new file mode 100644 index 000000000..ed97d539c --- /dev/null +++ b/roles/os_zabbix/vars/main.yml @@ -0,0 +1 @@ +--- 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..6349b6384 --- /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: 0 + + - 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: 0 + + 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..aeec16254 --- /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: 5 + + - 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: 5 + + - 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: 5 + + - 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: 5 + + - key: zabbix[process,alerter,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[process,configuration syncer,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[process,db watchdog,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[process,discoverer,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[process,escalator,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[process,history syncer,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[process,housekeeper,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[process,http poller,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[process,icmp pinger,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[process,ipmi poller,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[process,java poller,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[process,node watcher,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[process,poller,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[process,proxy poller,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[process,self-monitoring,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[process,snmp trapper,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[process,timer,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[process,trapper,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[process,unreachable poller,avg,busy] + applications: + - Zabbix server + description: '' + units: '%' + value_type: float + zabbix_type: 5 + + - key: zabbix[queue,10m] + applications: + - Zabbix server + description: '' + units: '' + value_type: int + zabbix_type: 5 + interval: 600 + + - key: zabbix[queue] + applications: + - Zabbix server + description: '' + units: '' + value_type: int + zabbix_type: 5 + interval: 600 + + - key: zabbix[rcache,buffer,pfree] + applications: + - Zabbix server + description: '' + units: '' + value_type: float + zabbix_type: 5 + + - key: zabbix[wcache,history,pfree] + applications: + - Zabbix server + description: '' + units: '' + value_type: float + zabbix_type: 5 + + - key: zabbix[wcache,text,pfree] + applications: + - Zabbix server + description: '' + units: '' + value_type: float + zabbix_type: 5 + + - key: zabbix[wcache,trend,pfree] + applications: + - Zabbix server + description: '' + units: '' + value_type: float + zabbix_type: 5 + + - key: zabbix[wcache,values] + applications: + - Zabbix server + description: '' + units: '' + value_type: float + zabbix_type: 5 + 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 new file mode 100644 index 000000000..395e054de --- /dev/null +++ b/roles/os_zabbix/vars/template_docker.yml @@ -0,0 +1,89 @@ +--- +g_template_docker: + name: Template Docker + zitems: + - key: docker.ping + applications: + - Docker Daemon + value_type: int + + - key: docker.storage.is_loopback + applications: + - Docker Storage + value_type: int + + - key: docker.storage.data.space.total + applications: + - Docker Storage + value_type: float + + - key: docker.storage.data.space.used + applications: + - Docker Storage + value_type: float + + - key: docker.storage.data.space.available + applications: + - Docker Storage + value_type: float + + - key: docker.storage.data.space.percent_available + applications: + - Docker Storage + value_type: float + + - key: docker.storage.metadata.space.total + applications: + - Docker Storage + value_type: float + + - key: docker.storage.metadata.space.used + applications: + - Docker Storage + value_type: float + + - key: docker.storage.metadata.space.available + applications: + - Docker Storage + value_type: float + + - key: docker.storage.metadata.space.percent_available + applications: + - Docker Storage + value_type: float + ztriggers: + - name: 'docker.ping failed on {HOST.NAME}' + expression: '{Template Docker:docker.ping.max(#3)}<1' + url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_docker_ping.asciidoc' + priority: high + + - name: 'Docker storage is using LOOPBACK on {HOST.NAME}' + expression: '{Template Docker:docker.storage.is_loopback.last()}<>0' + url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_docker_loopback.asciidoc' + priority: high + + - name: 'Critically low docker storage data space on {HOST.NAME}' + expression: '{Template Docker:docker.storage.data.space.percent_available.max(#3)}<5 or {Template Docker:docker.storage.data.space.available.max(#3)}<5' # < 5% or < 5GB + url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_docker_storage.asciidoc' + priority: high + + - name: 'Critically low docker storage metadata space on {HOST.NAME}' + expression: '{Template Docker:docker.storage.metadata.space.percent_available.max(#3)}<5 or {Template Docker:docker.storage.metadata.space.available.max(#3)}<0.005' # < 5% or < 5MB + url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_docker_storage.asciidoc' + priority: high + + # Put triggers that depend on other triggers here (deps must be created first) + - name: 'Low docker storage data space on {HOST.NAME}' + expression: '{Template Docker:docker.storage.data.space.percent_available.max(#3)}<10 or {Template Docker:docker.storage.data.space.available.max(#3)}<10' # < 10% or < 10GB + url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_docker_storage.asciidoc' + dependencies: + - 'Critically low docker storage data space on {HOST.NAME}' + priority: average + + - name: 'Low docker storage metadata space on {HOST.NAME}' + expression: '{Template Docker:docker.storage.metadata.space.percent_available.max(#3)}<10 or {Template Docker:docker.storage.metadata.space.available.max(#3)}<0.01' # < 10% or < 10MB + url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_docker_storage.asciidoc' + dependencies: + - 'Critically low docker storage metadata space on {HOST.NAME}' + priority: average + diff --git a/roles/os_zabbix/vars/template_heartbeat.yml b/roles/os_zabbix/vars/template_heartbeat.yml new file mode 100644 index 000000000..8dbe0d0d6 --- /dev/null +++ b/roles/os_zabbix/vars/template_heartbeat.yml @@ -0,0 +1,13 @@ +--- +g_template_heartbeat: + name: Template Heartbeat + zitems: + - name: Heartbeat Ping + applications: + - Heartbeat + key: heartbeat.ping + ztriggers: + - name: 'Heartbeat.ping has failed on {HOST.NAME}' + expression: '{Template Heartbeat:heartbeat.ping.nodata(20m)}=1' + priority: avg + url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_node_heartbeat.asciidoc' diff --git a/roles/os_zabbix/vars/template_openshift_master.yml b/roles/os_zabbix/vars/template_openshift_master.yml new file mode 100644 index 000000000..1de4fefbb --- /dev/null +++ b/roles/os_zabbix/vars/template_openshift_master.yml @@ -0,0 +1,58 @@ +--- +g_template_openshift_master: + name: Template Openshift Master + zitems: + - name: create_app + applications: + - Openshift Master + key: create_app + + - key: openshift.master.process.count + description: Shows number of master processes running + type: int + 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 + + 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' + url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_create_app.asciidoc' + priority: avg + + - 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' + priority: high + + - name: 'Too many Openshift Master processes running on {HOST.NAME}' + 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 diff --git a/roles/os_zabbix/vars/template_openshift_node.yml b/roles/os_zabbix/vars/template_openshift_node.yml new file mode 100644 index 000000000..ce28b1048 --- /dev/null +++ b/roles/os_zabbix/vars/template_openshift_node.yml @@ -0,0 +1,44 @@ +--- +g_template_openshift_node: + name: Template Openshift Node + zitems: + - key: openshift.node.process.count + description: Shows number of OpenShift Node processes running + type: int + 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/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/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 new file mode 100644 index 000000000..3ae1500bc --- /dev/null +++ b/roles/os_zabbix/vars/template_os_linux.yml @@ -0,0 +1,260 @@ +--- +g_template_os_linux: + name: Template OS Linux + zitems: + - key: kernel.uname.sysname + applications: + - Kernel + value_type: string + + - key: kernel.all.cpu.wait.total + applications: + - Kernel + value_type: float + units: '%' + + - key: kernel.all.cpu.irq.hard + applications: + - Kernel + value_type: float + units: '%' + + - key: kernel.all.cpu.idle + applications: + - Kernel + value_type: float + units: '%' + + - key: kernel.uname.distro + applications: + - Kernel + value_type: string + + - key: kernel.uname.nodename + applications: + - Kernel + value_type: string + + - key: kernel.all.cpu.irq.soft + applications: + - Kernel + value_type: float + units: '%' + + - key: kernel.all.load.15_minute + applications: + - Kernel + value_type: float + + - key: kernel.all.cpu.sys + applications: + - Kernel + value_type: float + units: '%' + + - key: kernel.all.load.5_minute + applications: + - Kernel + value_type: float + + - key: kernel.all.cpu.nice + applications: + - Kernel + value_type: float + units: '%' + + - key: kernel.all.load.1_minute + applications: + - Kernel + value_type: float + + - key: kernel.uname.version + applications: + - Kernel + value_type: string + + - key: kernel.all.uptime + applications: + - Kernel + value_type: int + + - key: kernel.all.cpu.user + applications: + - Kernel + value_type: float + units: '%' + + - key: kernel.uname.machine + applications: + - Kernel + value_type: string + + - key: hinv.ncpu + applications: + - Kernel + value_type: int + + - key: kernel.all.cpu.steal + applications: + - Kernel + value_type: float + units: '%' + + - key: kernel.all.pswitch + applications: + - Kernel + value_type: int + + - key: kernel.uname.release + applications: + - Kernel + value_type: string + + - key: proc.nprocs + applications: + - Kernel + value_type: int + + # Memory Items + - key: mem.freemem + applications: + - Memory + value_type: int + description: "PCP: free system memory metric from /proc/meminfo" + multiplier: 1024 + units: B + + - key: mem.util.bufmem + applications: + - Memory + value_type: int + description: "PCP: Memory allocated for buffer_heads.; I/O buffers metric from /proc/meminfo" + multiplier: 1024 + units: B + + - key: swap.used + applications: + - Memory + value_type: int + description: "PCP: swap used metric from /proc/meminfo" + multiplier: 1024 + units: B + + - key: swap.length + applications: + - Memory + value_type: int + description: "PCP: total swap available metric from /proc/meminfo" + multiplier: 1024 + units: B + + - key: mem.physmem + applications: + - Memory + value_type: int + description: "PCP: The value of this metric corresponds to the \"MemTotal\" field reported by /proc/meminfo. Note that this does not necessarily correspond to actual installed physical memory - there may be areas of the physical address space mapped as ROM in various peripheral devices and the bios may be mirroring certain ROMs in RAM." + multiplier: 1024 + units: B + + - key: swap.free + applications: + - Memory + value_type: int + description: "PCP: swap free metric from /proc/meminfo" + multiplier: 1024 + units: B + + - key: mem.util.available + applications: + - Memory + value_type: int + description: "PCP: The amount of memory that is available for a new workload, without pushing the system into swap. Estimated from MemFree, Active(file), Inactive(file), and SReclaimable, as well as the \"low\" watermarks from /proc/zoneinfo.; available memory from /proc/meminfo" + multiplier: 1024 + units: B + + - key: mem.util.used + applications: + - Memory + value_type: int + description: "PCP: Used memory is the difference between mem.physmem and mem.freemem; used memory metric from /proc/meminfo" + multiplier: 1024 + units: B + + - key: mem.util.cached + applications: + - Memory + value_type: int + description: "PCP: Memory used by the page cache, including buffered file data. This is in-memory cache for files read from the disk (the pagecache) but doesn't include SwapCached.; page cache metric from /proc/meminfo" + multiplier: 1024 + units: B + + zdiscoveryrules: + - name: disc.filesys + key: disc.filesys + lifetime: 1 + description: "Dynamically register the filesystems" + + zitemprototypes: + - discoveryrule_key: disc.filesys + name: "disc.filesys.full.{#OSO_FILESYS}" + key: "disc.filesys.full[{#OSO_FILESYS}]" + value_type: float + description: "PCP filesys.full option. This is the percent full returned from pcp filesys.full" + applications: + - Disk + + - 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 + + 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: {#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: {#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: {#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' + priority: warn + + - name: 'Lack of available memory on {HOST.NAME}' + expression: '{Template OS Linux:mem.freemem.last()}<30720000' + 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: 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.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}' |