Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Adding a Grafana monitoring chart with GKE nodes types (reserved, spot, on-demand) #799

Merged
merged 1 commit into from
Sep 6, 2024
Merged

Adding a Grafana monitoring chart with GKE nodes types (reserved, spot, on-demand) #799

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
148 changes: 147 additions & 1 deletion best-practices/gke-batch-refarch/02_platform/monitoring/deploy-dashboard.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1223,6 +1223,152 @@ data:
],
"title": "Nodes",
"type": "timeseries"
},
{
"datasource": {
"default": true,
"type": "prometheus",
"uid": "P1809F7CD0C75ACF3"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"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": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 18,
"x": 0,
"y": 30
},
"id": 20,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "P1809F7CD0C75ACF3"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sum by(key) (kube_node_spec_taint{key=\"reserved\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "reserved nodes",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "P1809F7CD0C75ACF3"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sum by(key) (kube_node_spec_taint{key=\"spot\"})",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "spot nodes",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "P1809F7CD0C75ACF3"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sum(kube_node_status_condition{condition=\"Ready\",status=\"true\"})",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "sum of all nodes",
"range": true,
"refId": "Total number of nodes",
"useBackend": false
},
{
"datasource": {
"name": "Expression",
"type": "__expr__",
"uid": "__expr__"
},
"expression": "${Total number of nodes} - ${reserved nodes} - ${spot nodes}",
"hide": false,
"refId": "On-demand nodes",
"type": "math"
}
],
"title": "Node per type",
"type": "timeseries"
}
],
"refresh": "5s",
Expand Down Expand Up @@ -1255,4 +1401,4 @@ data:
}
],
"folderUid": ""
}
}
146 changes: 146 additions & 0 deletions best-practices/gke-batch-refarch/02_platform/monitoring/kueue-dashboard.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1191,6 +1191,152 @@
],
"title": "Nodes",
"type": "timeseries"
},
{
"datasource": {
"default": true,
"type": "prometheus",
"uid": "P1809F7CD0C75ACF3"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"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": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 18,
"x": 0,
"y": 30
},
"id": 20,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "P1809F7CD0C75ACF3"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sum by(key) (kube_node_spec_taint{key=\"reserved\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "reserved nodes",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "P1809F7CD0C75ACF3"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sum by(key) (kube_node_spec_taint{key=\"spot\"})",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "spot nodes",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "P1809F7CD0C75ACF3"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sum(kube_node_status_condition{condition=\"Ready\",status=\"true\"})",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "sum of all nodes",
"range": true,
"refId": "Total number of nodes",
"useBackend": false
},
{
"datasource": {
"name": "Expression",
"type": "__expr__",
"uid": "__expr__"
},
"expression": "${Total number of nodes} - ${reserved nodes} - ${spot nodes}",
"hide": false,
"refId": "On-demand nodes",
"type": "math"
}
],
"title": "Node per type",
"type": "timeseries"
}
],
"refresh": "5s",
Expand Down