diff options
Diffstat (limited to 'roles/os_zabbix')
-rw-r--r-- | roles/os_zabbix/tasks/main.yml | 18 | ||||
-rw-r--r-- | roles/os_zabbix/vars/template_app_zabbix_server.yml | 408 | ||||
-rw-r--r-- | roles/os_zabbix/vars/template_ops_tools.yml | 23 | ||||
-rw-r--r-- | roles/os_zabbix/vars/template_os_linux.yml | 52 |
4 files changed, 491 insertions, 10 deletions
diff --git a/roles/os_zabbix/tasks/main.yml b/roles/os_zabbix/tasks/main.yml index 8347e9a61..e083296c0 100644 --- a/roles/os_zabbix/tasks/main.yml +++ b/roles/os_zabbix/tasks/main.yml @@ -12,6 +12,8 @@ - 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 - name: Include Template Heartbeat include: ../../lib_zabbix/tasks/create_template.yml @@ -52,3 +54,19 @@ 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 }}" 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..dace2aa29 --- /dev/null +++ b/roles/os_zabbix/vars/template_app_zabbix_server.yml @@ -0,0 +1,408 @@ +--- +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: '2' + + - 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: '2' + + - 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: '2' + + - 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: '2' + + - 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' + + - key: zabbix[queue] + applications: + - Zabbix server + description: '' + units: '' + value_type: int + zabbix_type: '5' + + - 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' + 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_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 84a7740b0..70c3809bd 100644 --- a/roles/os_zabbix/vars/template_os_linux.yml +++ b/roles/os_zabbix/vars/template_os_linux.yml @@ -10,17 +10,20 @@ g_template_os_linux: - key: kernel.all.cpu.wait.total applications: - Kernel - value_type: int + value_type: float + units: '%' - key: kernel.all.cpu.irq.hard applications: - Kernel - value_type: int + value_type: float + units: '%' - key: kernel.all.cpu.idle applications: - Kernel - value_type: int + value_type: float + units: '%' - key: kernel.uname.distro applications: @@ -35,7 +38,8 @@ g_template_os_linux: - key: kernel.all.cpu.irq.soft applications: - Kernel - value_type: int + value_type: float + units: '%' - key: kernel.all.load.15_minute applications: @@ -45,7 +49,8 @@ g_template_os_linux: - key: kernel.all.cpu.sys applications: - Kernel - value_type: int + value_type: float + units: '%' - key: kernel.all.load.5_minute applications: @@ -55,7 +60,8 @@ g_template_os_linux: - key: kernel.all.cpu.nice applications: - Kernel - value_type: int + value_type: float + units: '%' - key: kernel.all.load.1_minute applications: @@ -75,7 +81,8 @@ g_template_os_linux: - key: kernel.all.cpu.user applications: - Kernel - value_type: int + value_type: float + units: '%' - key: kernel.uname.machine applications: @@ -90,7 +97,8 @@ g_template_os_linux: - key: kernel.all.cpu.steal applications: - Kernel - value_type: int + value_type: float + units: '%' - key: kernel.all.pswitch applications: @@ -196,12 +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 @@ -209,6 +215,17 @@ 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 + ztriggers: - name: 'Filesystem: / has less than 10% free on {HOST.NAME}' expression: '{Template OS Linux:filesys.full.xvda2.last()}>90' @@ -240,3 +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}' |