selfmonitoring.cfx

<setup>
    domain = NMS-PROD
    audit = 1
    callback_retry_count = 3
    nim_login = administrator
    nim_password = nim76prox
    output_directory = output
    output_cache_time = 432000
</setup>
<configuration> overwrite
    <alarms> overwrite
        intermediate = 1
        spooler = 0
    </alarms>
    check_nisbridge = no
    priority_on_ha = yes
    check_hubuptime = yes
    uptime_seconds = 600
    maxrobots_per_hub = 1250
</configuration>
<probes_monitoring>
    <discovery_server>
        callback = get_device_statistics
        alarm_on_probe_deactivated = 0
        ha_superiority = yes
    </discovery_server>
    <hub>
        callback = get_info
        alarm_on_probe_deactivated = 1
        ha_superiority = yes
    </hub>
    <spooler>
        callback = get_info
        alarm_on_probe_deactivated = 1
        ha_superiority = yes
    </spooler>
    <nas>
        callback = get_info
        alarm_on_probe_deactivated = 1
        ha_superiority = yes
    </nas>
    <automated_deployment_engine>
        callback = get_info
        alarm_on_probe_deactivated = 0
        ha_superiority = yes
    </automated_deployment_engine>
    <mpse>
        callback = get_info 
        alarm_on_probe_deactivated = 0
        ha_superiority = yes
    </mpse>
    <alarm_enrichment>
        callback = getStatistics
        alarm_on_probe_deactivated = 1
        ha_superiority = yes
    </alarm_enrichment>
    <HA>
        callback = get_status
        alarm_on_probe_deactivated = 1
        ha_superiority = yes
    </HA>
    <udm>
        callback = _status 
        alarm_on_probe_deactivated = 1
        ha_superiority = yes
    </udm>
    <udm_manager>
        callback = getRunningStatistics
        alarm_on_probe_deactivated = 0
        ha_superiority = yes
    </udm_manager>
    <data_engine>
        callback = get_stats 
        alarm_on_probe_deactivated = 1
        ha_superiority = yes
    </data_engine>
    <netcoolgtw>
        callback = _status
        alarm_on_probe_deactivated = 1
        ha_superiority = yes
    </netcoolgtw>
    <prop_processor>
        callback = _status
        alarm_on_probe_deactivated = 1
        ha_superiority = yes
    </prop_processor>
    <distsrv>
        callback = get_info
        alarm_on_probe_deactivated = 1
        ha_superiority = yes
    </distsrv>
</probes_monitoring>
<alarm_messages> overwrite
    <maxrobots> overwrite
        message = Selfmonitoring: Maximum threshold of $Threshold Robots reached on $hubName
        i18n_token = 
        severity = 2
        subsystem = 1.1.20
        supp_key = 
    </maxrobots>
    <callback_fail> overwrite
        message = Selfmonitoring: Callback $callback failed for $probeName on hub $hubname
        i18n_token = 
        severity = 2
        subsystem = 1.1.20
        supp_key = 
    </callback_fail>
    <probe_offline> overwrite
        message = Selfmonitoring: Probe $probeName is disabled on hub $hubname
        i18n_token = 
        severity = 2
        subsystem = 1.1.20
        supp_key = 
    </probe_offline>
    <spooler_fail> overwrite
        message = Selfmonitoring: Spooler from $robotname return RC $rc when get_info callback is executed
        i18n_token = 
        severity = 2
        subsystem = 1.1.20
        supp_key = 
    </spooler_fail>
    <intermediate_robot> overwrite
        message = Selfmonitoring: $count robots are in intermediate state on hub $hubName
        i18n_token = 
        severity = 2
        subsystem = 1.1.20
        supp_key = 
    </intermediate_robot>
    <nisbridge> overwrite
        message = Selfmonitoring: NIS_Bridge is incorrectly activated/disabled on $hubname/$robotname
        i18n_token = 
        severity = 2
        subsystem = 1.1.20
        supp_key = 
    </nisbridge>
    <ump_failcallback> overwrite
        message = Selfmonitoring: Callback get_info failed on wasp of $umpName
        i18n_token = 
        severity = 2
        subsystem = 1.1.20
        supp_key = 
    </ump_failcallback>
    <ump_probelist_fail> overwrite
        message = Selfmonitoring: Failed to execute callback controller/probe_list for ump $umpName 
        i18n_token = 
        severity = 2
        subsystem = 1.1.20
        supp_key = 
    </ump_probelist_fail>
    <hub_restart> overwrite
        message = Selfmonitoring: Hub $hubName restarted in the recent $second seconds!
        i18n_token = 
        severity = 2
        subsystem = 1.1.20
        supp_key = 
    </hub_restart>
    <distsrv_deployment> overwrite
        message = Selfmonitoring: Distsrv of $hubname with jobid => $jobid take a long time to be deployed.
        i18n_token = 
        severity = 2
        subsystem = 1.1.20
    </distsrv_deployment>
    <distsrv_maxjobs> overwrite
        message = Selfmonitoring: Distsrv of $hubname reach the threshold of $max cached jobs ( Total of $count )
        i18n_token = 
        severity = 2
        subsystem = 1.1.20
        supp_key = 
    </distsrv_maxjobs>
</alarm_messages>