PEC-REP/Current/PulsePEGuide/dcuMetrics - Revision history

WikiSysop at 19:46, April 11, 2022

2022-04-11T19:46:06Z

Tony.gilchrist@genesys.com: Published

2021-12-21T20:00:46Z

Published

New page

{{ArticlePEServiceMetrics
|IncludedServiceId=0c4f792b-b3be-45de-9e86-435cbd35f573
|CRD=PodMonitor
|Port=9091
|Endpoint=<source lang="text">selector:
matchLabels:
app.kubernetes.io/name: {{include "common.util.chart.name" . }}
app.kubernetes.io/instance: {{include "common.util.chart.fullname" . }}
service: {{.Release.Namespace }}
servicename: {{include "common.util.chart.name" . }}
tenant: {{.Values.tenant.sid }}</source>
Endpoints to query: '''/metrics/'''
|MetricsUpdateInterval=30 seconds
|MetricsDefined=Yes
|PEMetric={{PEMetric
|Metric=pulse_monitor_check_duration_seconds
|Type=Gauge
|Unit=seconds
|Label=tenant
|MetricDescription=The duration in seconds of the last health check performed by Monitor Agent.
|UsedFor=Error
}}{{PEMetric
|Metric=pulse_collector_uptime_seconds
|Type=Gauge
|Unit=seconds
|Label=tenant
|MetricDescription=The Collector container uptime in seconds.
|UsedFor=Error
}}{{PEMetric
|Metric=pulse_collector_snapshot_writing_status
|Type=Gauge
|Label=tenant
|MetricDescription=The status of writing Collector snapshots to the Redis.
|SampleValue=1
|UsedFor=Error
}}{{PEMetric
|Metric=pulse_collector_active_layouts_count
|Type=Gauge
|Label=tenant
|MetricDescription=The number of active layouts.
|SampleValue=100
|UsedFor=Saturation
}}{{PEMetric
|Metric=pulse_collector_connection_status
|Type=Gauge
|Label=tenant, connection
|MetricDescription=The status of the Collector connection to the upstream server.
|SampleValue=1
|UsedFor=Error
}}{{PEMetric
|Metric=pulse_collector_connection_connected_seconds
|Type=Gauge
|Unit=seconds
|Label=tenant, connection
|MetricDescription=Duration in seconds of connection to the upstream server.
|UsedFor=Error
}}{{PEMetric
|Metric=pulse_collector_connection_disconnected_seconds
|Type=Gauge
|Unit=seconds
|Label=tenant, connection
|MetricDescription=Duration in seconds of disconnection from the upstream server.
|UsedFor=Error
}}{{PEMetric
|Metric=pulse_collector_statistics_total_count
|Type=Gauge
|Label=tenant. connection
|MetricDescription=The total number of Collector statistics.
|SampleValue=1000
|UsedFor=Saturation
}}{{PEMetric
|Metric=pulse_collector_statistics_opened_count
|Type=Gauge
|Label=tenant, connection
|MetricDescription=The number of successfully open Collector statistics.
|SampleValue=1000
|UsedFor=Saturation
}}{{PEMetric
|Metric=pulse_collector_statistics_failed_count
|Type=Gauge
|Label=tenant, connection
|MetricDescription=The number of Collector statistics that failed to open.
|SampleValue=0
|UsedFor=Error
}}{{PEMetric
|Metric=pulse_statserver_uptime_seconds
|Type=Gauge
|Unit=seconds
|Label=tenant
|MetricDescription=The StatServer container uptime in seconds.
|UsedFor=Error
}}{{PEMetric
|Metric=pulse_statserver_clients_number
|Type=Gauge
|Label=tenant
|MetricDescription=The number of clients connected to the StatServer.
|SampleValue=1
|UsedFor=Error
}}{{PEMetric
|Metric=pulse_statserver_messages_received_total_count
|Type=Gauge
|Label=tenant
|MetricDescription=The total number of messages received by the StatServer.
|SampleValue=10000
|UsedFor=Traffic
}}{{PEMetric
|Metric=pulse_statserver_messages_sent_total_count
|Type=Gauge
|Label=tenant
|MetricDescription=The total number of messages sent by the StatServer.
|SampleValue=10000
|UsedFor=Traffic
}}{{PEMetric
|Metric=pulse_statserver_server_connected_number
|Type=Gauge
|Label=tenant, type
|MetricDescription=The number of StatServer connections to upstream servers.
|SampleValue=1
|UsedFor=Error
}}{{PEMetric
|Metric=pulse_statserver_server_messages_received_total_count
|Type=Gauge
|Label=tenant, server, type
|MetricDescription=The total number of messages received by the StatServer from the upstream server.
|SampleValue=1
|UsedFor=Traffic
}}{{PEMetric
|Metric=pulse_statserver_server_connected_seconds
|Type=Gauge
|Unit=seconds
|Label=tenant, server, type
|MetricDescription=Duration in seconds of the StatServer connection to the upstream server.
|UsedFor=Error
}}{{PEMetric
|Metric=pulse_statserver_server_disconnects_count
|Type=Gauge
|Unit=seconds
|Label=tenant, server, type
|MetricDescription=Duration in seconds of the StatServer disconnection from the upstream server.
|UsedFor=Error
}}{{PEMetric
|Metric=pulse_statserver_dn_registered
|Type=Gauge
|Label=tenant, server, type
|MetricDescription=The number of successful registration attempts during current session with the upstream T-Server.
|SampleValue=1000
|UsedFor=Saturation
}}{{PEMetric
|Metric=pulse_statserver_dn_failed
|Type=Gauge
|Label=tenant, server, type
|MetricDescription=The number of DNs for which registration failed after predefined number of attempts.
|SampleValue=0
|UsedFor=Error
}}{{PEMetric
|Metric=pulse_statserver_server_latency_avg
|Type=Gauge
|Label=tenant, server, type
|MetricDescription=The average StatServer server latency in seconds.
|SampleValue=0.25
|UsedFor=Latency
}}{{PEMetric
|Metric=pulse_statserver_server_latency_min
|Type=Gauge
|Label=tenant, server, type
|MetricDescription=The minimum StatServer server latency in seconds.
|SampleValue=0.25
|UsedFor=Latency
}}{{PEMetric
|Metric=pulse_statserver_server_latency_max
|Type=Gauge
|Label=tenant, server, type
|MetricDescription=The maximum StatServer server latency in seconds.
|SampleValue=0.25
|UsedFor=Latency
}}{{PEMetric
|Metric=pulse_statserver_server_tevents_received_total_count
|Type=Gauge
|Label=tenant, server, type
|MetricDescription=The total number of T-Events received by the StatServer from the upstream T-Server.
|SampleValue=10000
|UsedFor=Traffic
}}
|AlertsDefined=Yes
|AlertsIntro=Alerts are based on Collector, StatServer, and Kubernetes cluster metrics.
|PEAlert={{PEAlert
|Alert=pulse_dcu_monitor_data_unavailable
|Severity=Critical
|AlertDescription=Pulse DCU Monitor Agents do not provide data.
|BasedOn=pulse_monitor_check_duration_seconds, kube_statefulset_replicas
|Threshold=for 15 minutes
}}{{PEAlert
|Alert=pulse_dcu_critical_nonrunning_instances
|Severity=Critical
|AlertDescription=Triggered when Pulse DCU instances are down.
|BasedOn=kube_statefulset_status_replicas_ready, kube_statefulset_status_replicas
|Threshold=for 15 minutes
}}{{PEAlert
|Alert=pulse_dcu_too_frequent_restarts
|Severity=Critical
|AlertDescription=Detected too frequent restarts of DCU Pod container.
|BasedOn=kube_pod_container_status_restarts_total
|Threshold=2 for 1 hour
}}{{PEAlert
|Alert=pulse_dcu_critical_cpu
|Severity=Critical
|AlertDescription=Detected critical CPU usage by Pulse DCU Pod.
|BasedOn=container_cpu_usage_seconds_total, kube_pod_container_resource_limits
|Threshold=90%
}}{{PEAlert
|Alert=pulse_dcu_critical_memory
|Severity=Critical
|AlertDescription=Detected critical memory usage by Pulse DCU Pod.
|BasedOn=container_memory_working_set_bytes, kube_pod_container_resource_limits
|Threshold=90%
}}{{PEAlert
|Alert=pulse_dcu_critical_disk
|Severity=Critical
|AlertDescription=Detected critical disk usage by Pulse DCU Pod.
|BasedOn=kubelet_volume_stats_available_bytes, kubelet_volume_stats_capacity_bytes
|Threshold=90%
}}{{PEAlert
|Alert=pulse_dcu_critical_col_snapshot_writing
|Severity=Critical
|AlertDescription=Pulse DCU Collector does not write snapshots.
|BasedOn=pulse_collector_snapshot_writing_status
|Threshold=for 15 minutes
}}{{PEAlert
|Alert=pulse_dcu_critical_col_connected_configservers
|Severity=Critical
|AlertDescription=Pulse DCU Collector is not connected to ConfigServer.
|BasedOn=pulse_collector_connection_status
|Threshold=for 15 minutes
}}{{PEAlert
|Alert=pulse_dcu_critical_col_connected_dbservers
|Severity=Critical
|AlertDescription=Pulse DCU Collector is not connected to DbServer.
|BasedOn=pulse_collector_connection_status
|Threshold=for 15 minutes
}}{{PEAlert
|Alert=pulse_dcu_critical_col_connected_statservers
|Severity=Critical
|AlertDescription=Pulse DCU Collector is not connected to StatServer.
|BasedOn=pulse_collector_connection_status
|Threshold=for 15 minutes
}}{{PEAlert
|Alert=pulse_dcu_critical_ss_failed_dn_registrations
|Severity=Critical
|AlertDescription=Detected critical DN registration failures on Pulse DCU StatServer.
|BasedOn=pulse_statserver_dn_failed, pulse_statserver_dn_registered
|Threshold=0.5%
}}{{PEAlert
|Alert=pulse_dcu_critical_ss_connected_configservers
|Severity=Critical
|AlertDescription=Pulse DCU StatServer is not connected to ConfigServer.
|BasedOn=pulse_statserver_server_connected_seconds
|Threshold=for 15 minutes
}}{{PEAlert
|Alert=pulse_dcu_critical_ss_connected_tservers
|Severity=Critical
|AlertDescription=Pulse DCU StatServer is not connected to T-Servers.
|BasedOn=pulse_statserver_server_connected_number
|Threshold=2
}}{{PEAlert
|Alert=pulse_dcu_critical_ss_connected_ixnservers
|Severity=Critical
|AlertDescription=Pulse DCU StatServer is not connected to IxnServers.
|BasedOn=pulse_statserver_server_connected_seconds
|Threshold=2
}}
}}

@@ Line 88: / Line 88: @@
 |Unit=seconds
 |Label=tenant
-|MetricDescription=The StatServer container uptime in seconds.
+|MetricDescription=The Stat Server container uptime in seconds.
 |UsedFor=Error
 }}{{PEMetric
@@ Line 94: / Line 94: @@
 |Type=Gauge
 |Label=tenant
-|MetricDescription=The number of clients connected to the StatServer.
+|MetricDescription=The number of clients connected to the Stat Server.
 |SampleValue=1
 |UsedFor=Error
@@ Line 101: / Line 101: @@
 |Type=Gauge
 |Label=tenant
-|MetricDescription=The total number of messages received by the StatServer.
+|MetricDescription=The total number of messages received by the Stat Server.
 |SampleValue=10000
 |UsedFor=Traffic
@@ Line 108: / Line 108: @@
 |Type=Gauge
 |Label=tenant
-|MetricDescription=The total number of messages sent by the StatServer.
+|MetricDescription=The total number of messages sent by the Stat Server.
 |SampleValue=10000
 |UsedFor=Traffic
@@ Line 115: / Line 115: @@
 |Type=Gauge
 |Label=tenant, type
-|MetricDescription=The number of StatServer connections to upstream servers.
+|MetricDescription=The number of Stat Server connections to upstream servers.
 |SampleValue=1
 |UsedFor=Error
@@ Line 122: / Line 122: @@
 |Type=Gauge
 |Label=tenant, server, type
-|MetricDescription=The total number of messages received by the StatServer from the upstream server.
+|MetricDescription=The total number of messages received by the Stat Server from the upstream server.
 |SampleValue=1
 |UsedFor=Traffic
@@ Line 130: / Line 130: @@
 |Unit=seconds
 |Label=tenant, server, type
-|MetricDescription=Duration in seconds of the StatServer connection to the upstream server.
+|MetricDescription=Duration in seconds of the Stat Server connection to the upstream server.
 |UsedFor=Error
 }}{{PEMetric
@@ Line 137: / Line 137: @@
 |Unit=seconds
 |Label=tenant, server, type
-|MetricDescription=Duration in seconds of the StatServer disconnection from the upstream server.
+|MetricDescription=Duration in seconds of the Stat Server disconnection from the upstream server.
 |UsedFor=Error
 }}{{PEMetric
@@ Line 157: / Line 157: @@
 |Type=Gauge
 |Label=tenant, server, type
-|MetricDescription=The average StatServer server latency in seconds.
+|MetricDescription=The average Stat Server server latency in seconds.
 |SampleValue=0.25
 |UsedFor=Latency
@@ Line 164: / Line 164: @@
 |Type=Gauge
 |Label=tenant, server, type
-|MetricDescription=The minimum StatServer server latency in seconds.
+|MetricDescription=The minimum Stat Server server latency in seconds.
 |SampleValue=0.25
 |UsedFor=Latency
@@ Line 171: / Line 171: @@
 |Type=Gauge
 |Label=tenant, server, type
-|MetricDescription=The maximum StatServer server latency in seconds.
+|MetricDescription=The maximum Stat Server server latency in seconds.
 |SampleValue=0.25
 |UsedFor=Latency
@@ Line 178: / Line 178: @@
 |Type=Gauge
 |Label=tenant, server, type
-|MetricDescription=The total number of T-Events received by the StatServer from the upstream T-Server.
+|MetricDescription=The total number of T-Events received by the Stat Server from the upstream T-Server.
 |SampleValue=10000
 |UsedFor=Traffic
 }}
 |AlertsDefined=Yes
-|AlertsIntro=Alerts are based on Collector, StatServer, and Kubernetes cluster metrics.
+|AlertsIntro=Alerts are based on Collector, Stat Server, and Kubernetes cluster metrics.
 |PEAlert={{PEAlert
 |Alert=pulse_dcu_monitor_data_unavailable
@@ Line 241: / Line 241: @@
 |Alert=pulse_dcu_critical_col_connected_statservers
 |Severity=Critical
-|AlertDescription=Pulse DCU Collector is not connected to StatServer.
+|AlertDescription=Pulse DCU Collector is not connected to Stat Server.
 |BasedOn=pulse_collector_connection_status
 |Threshold=for 15 minutes
@@ Line 247: / Line 247: @@
 |Alert=pulse_dcu_critical_ss_failed_dn_registrations
 |Severity=Critical
-|AlertDescription=Detected critical DN registration failures on Pulse DCU StatServer.
+|AlertDescription=Detected critical DN registration failures on Pulse DCU Stat Server.
 |BasedOn=pulse_statserver_dn_failed, pulse_statserver_dn_registered
 |Threshold=0.5%
@@ Line 253: / Line 253: @@
 |Alert=pulse_dcu_critical_ss_connected_configservers
 |Severity=Critical
-|AlertDescription=Pulse DCU StatServer is not connected to ConfigServer.
+|AlertDescription=Pulse DCU Stat Server is not connected to ConfigServer.
 |BasedOn=pulse_statserver_server_connected_seconds
 |Threshold=for 15 minutes
@@ Line 259: / Line 259: @@
 |Alert=pulse_dcu_critical_ss_connected_tservers
 |Severity=Critical
-|AlertDescription=Pulse DCU StatServer is not connected to T-Servers.
+|AlertDescription=Pulse DCU Stat Server is not connected to T-Servers.
 |BasedOn=pulse_statserver_server_connected_number
 |Threshold=2
@@ Line 265: / Line 265: @@
 |Alert=pulse_dcu_critical_ss_connected_ixnservers
 |Severity=Critical
-|AlertDescription=Pulse DCU StatServer is not connected to IxnServers.
+|AlertDescription=Pulse DCU Stat Server is not connected to IxnServers.
 |BasedOn=pulse_statserver_server_connected_seconds
 |Threshold=2
 }}
 }}