Skip to content

Commit

Permalink
docs: Update docs to correspond with the metric updates
Browse files Browse the repository at this point in the history
  • Loading branch information
@jigisha620
jigisha620 committed Jul 19, 2024
1 parent 3f45299 commit f9df091
Show file tree
Hide file tree
Showing 2 changed files with 12 additions and 114 deletions.
104 changes: 4 additions & 100 deletions .../preview/getting-started/getting-started-with-karpenter/karpenter-capacity-dashboard.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -215,7 +215,7 @@
"uid": "${datasource}"
},
"editorMode": "builder",
"expr": "sum by(cluster,nodepool) (karpenter_nodes_terminated{nodepool=~\"$nodepool\"})",
"expr": "sum by(cluster,nodepool) (karpenter_nodes_terminated_total{nodepool=~\"$nodepool\"})",
"format": "time_series",
"legendFormat": "{{cluster}}",
"range": true,
Expand Down Expand Up @@ -408,7 +408,7 @@
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum by(action,consolidation_type,method)(karpenter_disruption_actions_performed_total)",
"expr": "sum by(action,consolidation_type,method)(karpenter_disruption_decisions_total)",
"legendFormat": "{{label_name}}",
"range": true,
"refId": "A"
Expand All @@ -417,102 +417,6 @@
"title": "Disruption Actions Performed",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "See: https://karpenter.sh/v0.35/concepts/disruption/#automated-methods",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 24,
"x": 0,
"y": 22
},
"id": 17,
"options": {
"legend": {
"calcs": [
"last"
],
"displayMode": "table",
"placement": "right",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum by(action,consolidation_type,method)(karpenter_disruption_nodes_disrupted_total{nodepool=~\"$nodepool\"})",
"legendFormat": "{{label_name}}",
"range": true,
"refId": "A"
}
],
"title": "Voluntary Node Disruptions: nodepool \"$nodepool\"",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
Expand Down Expand Up @@ -1609,15 +1513,15 @@
"type": "prometheus",
"uid": "prometheus"
},
"definition": "label_values(karpenter_disruption_actions_performed_total,method)",
"definition": "label_values(karpenter_disruption_decisions_total,method)",
"hide": 0,
"includeAll": true,
"multi": true,
"name": "method",
"options": [],
"query": {
"qryType": 1,
"query": "label_values(karpenter_disruption_actions_performed_total,method)",
"query": "label_values(karpenter_disruption_decisions_total,method)",
"refId": "PrometheusVariableQueryEditor-VariableQuery"
},
"refresh": 2,
Expand Down
22 changes: 8 additions & 14 deletions website/content/en/preview/reference/metrics.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ The nodepool limits are the limits specified on the nodepool that restrict the q
### `karpenter_nodeclaims_termination_duration_seconds`
Duration of NodeClaim termination in seconds.

### `karpenter_nodeclaims_terminated`
### `karpenter_nodeclaims_terminated_total`
Number of nodeclaims terminated in total by Karpenter. Labeled by reason the nodeclaim was terminated and the owning nodepool.

### `karpenter_nodeclaims_registered`
Expand Down Expand Up @@ -65,7 +65,7 @@ Node total daemon limits are the resources specified by DaemonSet pod limits.
### `karpenter_nodes_termination_time_seconds`
The time taken between a node's deletion request and the removal of its finalizer

### `karpenter_nodes_terminated`
### `karpenter_nodes_terminated_total`
Number of nodes terminated in total by Karpenter. Labeled by owning nodepool.

### `karpenter_nodes_system_overhead`
Expand Down Expand Up @@ -104,24 +104,21 @@ Duration of scheduling process in seconds.

## Interruption Metrics

### `karpenter_interruption_received_messages`
### `karpenter_interruption_received_messages_total`
Count of messages received from the SQS queue. Broken down by message type and whether the message was actionable.

### `karpenter_interruption_message_latency_time_seconds`
### `karpenter_interruption_message_queue_duration_seconds`
Length of time between message creation in queue and an action taken on the message by the controller.

### `karpenter_interruption_deleted_messages`
### `karpenter_interruption_deleted_messages_total`
Count of messages deleted from the SQS queue.

### `karpenter_interruption_actions_performed`
Number of notification actions performed. Labeled by action

## Disruption Metrics

### `karpenter_disruption_replacement_nodeclaim_initialized_seconds`
Amount of time required for a replacement nodeclaim to become initialized.

### `karpenter_disruption_replacement_nodeclaim_failures_total`
### `karpenter_disruption_queue_failures_total`
The number of times that Karpenter failed to launch a replacement node for disruption. Labeled by disruption method.

### `karpenter_disruption_queue_depth`
Expand All @@ -130,9 +127,6 @@ The number of commands currently being waited on in the disruption orchestration
### `karpenter_disruption_pods_disrupted_total`
Total number of reschedulable pods disrupted on nodes. Labeled by NodePool, disruption action, method, and consolidation type.

### `karpenter_disruption_nodes_disrupted_total`
Total number of nodes disrupted. Labeled by NodePool, disruption action, method, and consolidation type.

### `karpenter_disruption_evaluation_duration_seconds`
Duration of the disruption evaluation process in seconds. Labeled by method and consolidation type.

Expand All @@ -142,10 +136,10 @@ Number of nodes eligible for disruption by Karpenter. Labeled by disruption meth
### `karpenter_disruption_consolidation_timeouts_total`
Number of times the Consolidation algorithm has reached a timeout. Labeled by consolidation type.

### `karpenter_disruption_budgets_allowed_disruptions`
### `karpenter_nodepools_allowed_disruptions`
The number of nodes for a given NodePool that can be disrupted at a point in time. Labeled by NodePool. Note that allowed disruptions can change very rapidly, as new nodes may be created and others may be deleted at any point.

### `karpenter_disruption_actions_performed_total`
### `karpenter_disruption_decisions_total`
Number of disruption actions performed. Labeled by disruption action, method, and consolidation type.

## Consistency Metrics
Expand Down

0 comments on commit f9df091

Please sign in to comment.