{
"__inputs": [
{
"name": "datasource",
"label": "Prometheus",
"description": "",
"type": "datasource",
"pluginId": "prometheus",
"pluginName": "Prometheus"
}
],
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "datasource",
"uid": "grafana"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"target": {
"limit": 100,
"matchAny": false,
"tags": [],
"type": "dashboard"
},
"type": "dashboard"
}
]
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": 42,
"iteration": 1654694094437,
"links": [],
"liveNow": false,
"panels": [
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"uid": "${datasource}"
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 0
},
"hiddenSeries": false,
"id": 3,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "8.5.3",
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"exemplar": true,
"expr": "sum(increase(castai_autoscaler_agent_snapshots_received_total{castai_cluster=\"$cluster\"}[5m]))",
"interval": "",
"legendFormat": "Received",
"refId": "A"
}
],
"thresholds": [],
"timeRegions": [],
"title": "Agent snapshots received (5m)",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"uid": "${datasource}"
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 0
},
"hiddenSeries": false,
"id": 7,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "8.5.3",
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"exemplar": true,
"expr": "sum(increase(castai_autoscaler_agent_snapshots_processed_total{castai_cluster=\"$cluster\"}[5m]))",
"interval": "",
"legendFormat": "Processed",
"refId": "A"
}
],
"thresholds": [],
"timeRegions": [],
"title": "Agent snapshots processed (5m)",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"datasource": {
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"decimals": 2,
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "currencyUSD"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 9
},
"id": 16,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"text": {},
"textMode": "auto"
},
"pluginVersion": "8.5.3",
"targets": [
{
"exemplar": true,
"expr": "sum(castai_cluster_total_cost_hourly{castai_cluster=\"$cluster\"}) * 720",
"interval": "",
"legendFormat": "",
"refId": "A"
}
],
"title": "Cluster cost monthly",
"type": "stat"
},
{
"datasource": {
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 6,
"x": 12,
"y": 9
},
"id": 6,
"options": {
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true,
"text": {}
},
"pluginVersion": "8.5.3",
"targets": [
{
"exemplar": true,
"expr": "sum(castai_cluster_pods_count{castai_cluster=\"$cluster\"})",
"interval": "",
"legendFormat": "All pods",
"refId": "A"
},
{
"exemplar": true,
"expr": "sum(castai_cluster_unschedulable_pods_count{castai_cluster=\"$cluster\"})",
"hide": false,
"interval": "",
"legendFormat": "Unschedulable pods",
"refId": "B"
}
],
"title": "Pods",
"type": "gauge"
},
{
"datasource": {
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "decbytes"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 6,
"x": 18,
"y": 9
},
"id": 11,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"text": {},
"textMode": "auto"
},
"pluginVersion": "8.5.3",
"targets": [
{
"exemplar": true,
"expr": "sum(castai_cluster_requests_memory_bytes{castai_cluster=\"$cluster\"})",
"interval": "",
"legendFormat": "Memory requested",
"refId": "A"
},
{
"exemplar": true,
"expr": "sum(castai_cluster_provisioned_memory_bytes{castai_cluster=\"$cluster\"})",
"hide": false,
"interval": "",
"legendFormat": "Memory provisioned",
"refId": "B"
}
],
"title": "Memory",
"type": "stat"
},
{
"datasource": {
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 6,
"x": 12,
"y": 13
},
"id": 8,
"options": {
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true,
"text": {}
},
"pluginVersion": "8.5.3",
"targets": [
{
"exemplar": true,
"expr": "sum(castai_evictor_node_target_count{castai_cluster=\"$cluster\"})",
"interval": "",
"legendFormat": "Targeted nodes",
"refId": "A"
},
{
"exemplar": true,
"expr": "sum(castai_evictor_pod_target_count{castai_cluster=\"$cluster\"})",
"hide": false,
"interval": "",
"legendFormat": "Targeted pods",
"refId": "B"
}
],
"title": "Evictor",
"type": "gauge"
},
{
"datasource": {
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 6,
"x": 18,
"y": 13
},
"id": 10,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"text": {},
"textMode": "auto"
},
"pluginVersion": "8.5.3",
"targets": [
{
"exemplar": true,
"expr": "sum(castai_cluster_requests_cpu_cores{castai_cluster=\"$cluster\"}) / 1000",
"interval": "",
"legendFormat": "CPU requested",
"refId": "A"
},
{
"exemplar": true,
"expr": "sum(castai_cluster_provisioned_cpu_cores{castai_cluster=\"$cluster\"}) / 1000",
"hide": false,
"interval": "",
"legendFormat": "CPU provisioned",
"refId": "B"
}
],
"title": "CPU",
"type": "stat"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"uid": "${datasource}"
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 17
},
"hiddenSeries": false,
"id": 13,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "8.5.3",
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"exemplar": true,
"expr": "sum(castai_cluster_requests_cpu_cores{castai_cluster=\"$cluster\"}) by (castai_node_type) / 1000",
"interval": "",
"legendFormat": "Requested {{castai_node_type}}",
"refId": "A"
},
{
"exemplar": true,
"expr": "sum(castai_cluster_provisioned_cpu_cores{castai_cluster=\"$cluster\"}) by (castai_node_type) / 1000",
"hide": false,
"interval": "",
"legendFormat": "Provisioned {{castai_node_type}}",
"refId": "B"
}
],
"thresholds": [],
"timeRegions": [],
"title": "CPU utilization (cores)",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"$$hashKey": "object:101",
"format": "short",
"logBase": 1,
"show": true
},
{
"$$hashKey": "object:102",
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"datasource": {
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 6,
"x": 12,
"y": 17
},
"id": 5,
"options": {
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true,
"text": {}
},
"pluginVersion": "8.5.3",
"targets": [
{
"exemplar": true,
"expr": "sum(castai_cluster_node_count{castai_cluster=\"$cluster\"})",
"interval": "",
"legendFormat": "All nodes",
"refId": "A"
},
{
"exemplar": true,
"expr": "sum(castai_cluster_node_count{castai_cluster=\"$cluster\", castai_node_type=\"spot\"})",
"hide": false,
"interval": "",
"legendFormat": "Spot nodes",
"refId": "B"
}
],
"title": "Nodes",
"type": "gauge"
},
{
"datasource": {
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"max": 100,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 6,
"x": 18,
"y": 17
},
"id": 2,
"options": {
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true,
"text": {}
},
"pluginVersion": "8.5.3",
"targets": [
{
"exemplar": true,
"expr": "sum(castai_cluster_requests_cpu_cores{castai_cluster=\"$cluster\"}) / sum(castai_cluster_provisioned_cpu_cores{castai_cluster=\"$cluster\"}) * 100",
"interval": "",
"legendFormat": "CPU requested",
"refId": "A"
},
{
"exemplar": true,
"expr": "sum(castai_cluster_requests_memory_bytes{castai_cluster=\"$cluster\"}) / sum(castai_cluster_provisioned_memory_bytes{castai_cluster=\"$cluster\"}) * 100",
"hide": false,
"interval": "",
"legendFormat": "Memory requested",
"refId": "B"
}
],
"title": "Cluster Requests",
"type": "gauge"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"unit": "decbytes"
},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 25
},
"hiddenSeries": false,
"id": 14,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "8.1.0",
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"exemplar": true,
"expr": "sum(castai_cluster_requests_memory_bytes{castai_cluster=\"$cluster\"}) by (castai_node_type)",
"interval": "",
"legendFormat": "Requested {{castai_node_type}}",
"refId": "A"
},
{
"exemplar": true,
"expr": "sum(castai_cluster_provisioned_memory_bytes{castai_cluster=\"$cluster\"}) by (castai_node_type)",
"hide": false,
"interval": "",
"legendFormat": "Provisioned {{castai_node_type}}",
"refId": "B"
}
],
"thresholds": [],
"timeRegions": [],
"title": "Memory utilization",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "decbytes",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
}
],
"schemaVersion": 36,
"style": "dark",
"tags": [],
"templating": {
"list": [
{
"hide": 0,
"includeAll": false,
"multi": false,
"name": "datasource",
"options": [],
"query": "prometheus",
"queryValue": "",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"type": "datasource"
},
{
"datasource": {
"uid": "${datasource}"
},
"definition": "label_values(castai_cluster)",
"hide": 0,
"includeAll": false,
"multi": false,
"name": "cluster",
"options": [],
"query": {
"query": "label_values(castai_cluster)",
"refId": "StandardVariableQuery"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 0,
"tagValuesQuery": "",
"tagsQuery": "",
"type": "query",
"useTags": false
}
]
},
"time": {
"from": "now-1h",
"to": "now"
},
"timepicker": {},
"timezone": "",
"title": "Cortex cluster metrics",
"uid": "9928wJInz",
"version": 1,
"weekStart": ""
}
