2025-11-17 14:22:46 -03:00
|
|
|
# services/monitoring/grafana-dashboard-nodes.yaml
|
2025-11-14 00:02:59 -03:00
|
|
|
apiVersion: v1
|
|
|
|
|
kind: ConfigMap
|
|
|
|
|
metadata:
|
2025-11-17 14:22:46 -03:00
|
|
|
name: grafana-dashboard-nodes
|
2025-11-14 00:02:59 -03:00
|
|
|
labels:
|
|
|
|
|
grafana_dashboard: "1"
|
|
|
|
|
data:
|
2025-11-17 14:22:46 -03:00
|
|
|
atlas-nodes.json: |
|
2025-11-14 00:02:59 -03:00
|
|
|
{
|
2025-11-17 14:22:46 -03:00
|
|
|
"uid": "atlas-nodes",
|
|
|
|
|
"title": "Atlas Nodes",
|
|
|
|
|
"folderUid": "atlas-nodes",
|
2025-11-14 00:02:59 -03:00
|
|
|
"editable": true,
|
|
|
|
|
"panels": [
|
|
|
|
|
{
|
2025-11-15 21:03:11 -03:00
|
|
|
"id": 1,
|
|
|
|
|
"type": "stat",
|
2025-11-17 14:22:46 -03:00
|
|
|
"title": "Node count",
|
2025-11-14 00:02:59 -03:00
|
|
|
"datasource": {
|
|
|
|
|
"type": "prometheus",
|
|
|
|
|
"uid": "atlas-vm"
|
|
|
|
|
},
|
2025-11-15 21:03:11 -03:00
|
|
|
"gridPos": {
|
|
|
|
|
"h": 5,
|
|
|
|
|
"w": 6,
|
|
|
|
|
"x": 0,
|
|
|
|
|
"y": 0
|
|
|
|
|
},
|
|
|
|
|
"targets": [
|
|
|
|
|
{
|
2025-11-17 14:22:46 -03:00
|
|
|
"expr": "count(kube_node_info)",
|
2025-11-15 21:03:11 -03:00
|
|
|
"refId": "A"
|
|
|
|
|
}
|
|
|
|
|
],
|
2025-11-14 00:02:59 -03:00
|
|
|
"fieldConfig": {
|
|
|
|
|
"defaults": {
|
|
|
|
|
"color": {
|
2025-11-15 21:03:11 -03:00
|
|
|
"mode": "palette-classic"
|
2025-11-14 00:02:59 -03:00
|
|
|
},
|
|
|
|
|
"mappings": [],
|
|
|
|
|
"thresholds": {
|
2025-11-17 14:22:46 -03:00
|
|
|
"mode": "absolute",
|
2025-11-14 00:02:59 -03:00
|
|
|
"steps": [
|
|
|
|
|
{
|
2025-11-17 14:22:46 -03:00
|
|
|
"color": "rgba(115, 115, 115, 1)",
|
2025-11-14 00:02:59 -03:00
|
|
|
"value": null
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"color": "green",
|
2025-11-17 14:22:46 -03:00
|
|
|
"value": 1
|
2025-11-14 00:02:59 -03:00
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
2025-11-17 14:22:46 -03:00
|
|
|
"unit": "none"
|
2025-11-14 00:02:59 -03:00
|
|
|
},
|
|
|
|
|
"overrides": []
|
|
|
|
|
},
|
2025-11-15 21:03:11 -03:00
|
|
|
"options": {
|
|
|
|
|
"colorMode": "value",
|
|
|
|
|
"graphMode": "area",
|
|
|
|
|
"justifyMode": "center",
|
|
|
|
|
"reduceOptions": {
|
|
|
|
|
"calcs": [
|
|
|
|
|
"lastNotNull"
|
|
|
|
|
],
|
|
|
|
|
"fields": "",
|
|
|
|
|
"values": false
|
2025-11-16 00:55:28 -03:00
|
|
|
},
|
|
|
|
|
"textMode": "value"
|
2025-11-15 21:03:11 -03:00
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"id": 2,
|
|
|
|
|
"type": "stat",
|
2025-11-17 14:22:46 -03:00
|
|
|
"title": "Ready nodes",
|
2025-11-15 21:03:11 -03:00
|
|
|
"datasource": {
|
|
|
|
|
"type": "prometheus",
|
|
|
|
|
"uid": "atlas-vm"
|
|
|
|
|
},
|
2025-11-14 00:02:59 -03:00
|
|
|
"gridPos": {
|
2025-11-15 21:03:11 -03:00
|
|
|
"h": 5,
|
2025-11-14 00:02:59 -03:00
|
|
|
"w": 6,
|
2025-11-15 21:03:11 -03:00
|
|
|
"x": 6,
|
2025-11-14 00:02:59 -03:00
|
|
|
"y": 0
|
|
|
|
|
},
|
2025-11-15 21:03:11 -03:00
|
|
|
"targets": [
|
|
|
|
|
{
|
2025-11-17 14:22:46 -03:00
|
|
|
"expr": "sum(kube_node_status_condition{condition=\"Ready\",status=\"true\"})",
|
2025-11-15 21:03:11 -03:00
|
|
|
"refId": "A"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"fieldConfig": {
|
|
|
|
|
"defaults": {
|
|
|
|
|
"color": {
|
|
|
|
|
"mode": "palette-classic"
|
|
|
|
|
},
|
|
|
|
|
"mappings": [],
|
|
|
|
|
"thresholds": {
|
|
|
|
|
"mode": "absolute",
|
|
|
|
|
"steps": [
|
|
|
|
|
{
|
2025-11-17 14:22:46 -03:00
|
|
|
"color": "rgba(115, 115, 115, 1)",
|
2025-11-15 21:03:11 -03:00
|
|
|
"value": null
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-11-17 14:22:46 -03:00
|
|
|
"color": "green",
|
|
|
|
|
"value": 1
|
2025-11-15 21:03:11 -03:00
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"unit": "none"
|
|
|
|
|
},
|
|
|
|
|
"overrides": []
|
|
|
|
|
},
|
2025-11-14 00:02:59 -03:00
|
|
|
"options": {
|
|
|
|
|
"colorMode": "value",
|
2025-11-15 21:03:11 -03:00
|
|
|
"graphMode": "area",
|
2025-11-14 00:02:59 -03:00
|
|
|
"justifyMode": "center",
|
|
|
|
|
"reduceOptions": {
|
|
|
|
|
"calcs": [
|
|
|
|
|
"lastNotNull"
|
|
|
|
|
],
|
|
|
|
|
"fields": "",
|
|
|
|
|
"values": false
|
2025-11-16 00:55:28 -03:00
|
|
|
},
|
|
|
|
|
"textMode": "value"
|
2025-11-15 21:03:11 -03:00
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"id": 3,
|
|
|
|
|
"type": "stat",
|
2025-11-17 14:22:46 -03:00
|
|
|
"title": "Control plane CPU avg",
|
2025-11-15 21:03:11 -03:00
|
|
|
"datasource": {
|
|
|
|
|
"type": "prometheus",
|
|
|
|
|
"uid": "atlas-vm"
|
|
|
|
|
},
|
|
|
|
|
"gridPos": {
|
|
|
|
|
"h": 5,
|
|
|
|
|
"w": 6,
|
|
|
|
|
"x": 12,
|
|
|
|
|
"y": 0
|
2025-11-14 00:02:59 -03:00
|
|
|
},
|
|
|
|
|
"targets": [
|
|
|
|
|
{
|
2025-11-17 14:22:46 -03:00
|
|
|
"expr": "avg by (node) ((((1 - label_replace(rate(node_cpu_seconds_total{mode=\"idle\"}[5m]), \"internal_ip\", \"$1\", \"instance\", \"([^:]+):.*\")) * 100) * on (internal_ip) group_left(node) kube_node_info)) * on(node) group_left() kube_node_info{node=~\"titan-0a|titan-0b|titan-0c\"}",
|
|
|
|
|
"refId": "A",
|
|
|
|
|
"legendFormat": "{{node}}"
|
2025-11-14 00:02:59 -03:00
|
|
|
}
|
|
|
|
|
],
|
2025-11-15 21:03:11 -03:00
|
|
|
"fieldConfig": {
|
|
|
|
|
"defaults": {
|
|
|
|
|
"color": {
|
|
|
|
|
"mode": "palette-classic"
|
|
|
|
|
},
|
|
|
|
|
"mappings": [],
|
|
|
|
|
"thresholds": {
|
|
|
|
|
"mode": "absolute",
|
|
|
|
|
"steps": [
|
|
|
|
|
{
|
2025-11-17 14:22:46 -03:00
|
|
|
"color": "rgba(115, 115, 115, 1)",
|
2025-11-15 21:03:11 -03:00
|
|
|
"value": null
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-11-17 14:22:46 -03:00
|
|
|
"color": "green",
|
2025-11-15 21:03:11 -03:00
|
|
|
"value": 1
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
2025-11-17 14:22:46 -03:00
|
|
|
"unit": "percent"
|
2025-11-15 21:03:11 -03:00
|
|
|
},
|
|
|
|
|
"overrides": []
|
|
|
|
|
},
|
|
|
|
|
"options": {
|
|
|
|
|
"colorMode": "value",
|
|
|
|
|
"graphMode": "area",
|
|
|
|
|
"justifyMode": "center",
|
|
|
|
|
"reduceOptions": {
|
|
|
|
|
"calcs": [
|
|
|
|
|
"lastNotNull"
|
|
|
|
|
],
|
|
|
|
|
"fields": "",
|
|
|
|
|
"values": false
|
2025-11-16 00:55:28 -03:00
|
|
|
},
|
2025-11-17 14:22:46 -03:00
|
|
|
"textMode": "value_and_name"
|
2025-11-15 21:03:11 -03:00
|
|
|
}
|
2025-11-14 00:02:59 -03:00
|
|
|
},
|
|
|
|
|
{
|
2025-11-15 21:03:11 -03:00
|
|
|
"id": 4,
|
|
|
|
|
"type": "stat",
|
2025-11-17 14:22:46 -03:00
|
|
|
"title": "Control plane RAM avg",
|
2025-11-14 00:02:59 -03:00
|
|
|
"datasource": {
|
|
|
|
|
"type": "prometheus",
|
|
|
|
|
"uid": "atlas-vm"
|
|
|
|
|
},
|
|
|
|
|
"gridPos": {
|
2025-11-15 21:03:11 -03:00
|
|
|
"h": 5,
|
2025-11-14 00:02:59 -03:00
|
|
|
"w": 6,
|
2025-11-15 21:03:11 -03:00
|
|
|
"x": 18,
|
2025-11-14 00:02:59 -03:00
|
|
|
"y": 0
|
|
|
|
|
},
|
2025-11-15 21:03:11 -03:00
|
|
|
"targets": [
|
|
|
|
|
{
|
2025-11-17 14:22:46 -03:00
|
|
|
"expr": "avg by (node) (((label_replace((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes, \"internal_ip\", \"$1\", \"instance\", \"([^:]+):.*\") * 100) * on (internal_ip) group_left(node) kube_node_info)) * on(node) group_left() kube_node_info{node=~\"titan-0a|titan-0b|titan-0c\"}",
|
|
|
|
|
"refId": "A",
|
|
|
|
|
"legendFormat": "{{node}}"
|
2025-11-15 21:03:11 -03:00
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"fieldConfig": {
|
|
|
|
|
"defaults": {
|
|
|
|
|
"color": {
|
|
|
|
|
"mode": "palette-classic"
|
|
|
|
|
},
|
|
|
|
|
"mappings": [],
|
|
|
|
|
"thresholds": {
|
|
|
|
|
"mode": "absolute",
|
|
|
|
|
"steps": [
|
|
|
|
|
{
|
2025-11-17 14:22:46 -03:00
|
|
|
"color": "rgba(115, 115, 115, 1)",
|
2025-11-15 21:03:11 -03:00
|
|
|
"value": null
|
|
|
|
|
},
|
|
|
|
|
{
|
2025-11-17 14:22:46 -03:00
|
|
|
"color": "green",
|
2025-11-15 21:03:11 -03:00
|
|
|
"value": 1
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
},
|
2025-11-17 14:22:46 -03:00
|
|
|
"unit": "percent"
|
2025-11-15 21:03:11 -03:00
|
|
|
},
|
|
|
|
|
"overrides": []
|
|
|
|
|
},
|
|
|
|
|
"options": {
|
|
|
|
|
"colorMode": "value",
|
|
|
|
|
"graphMode": "area",
|
|
|
|
|
"justifyMode": "center",
|
|
|
|
|
"reduceOptions": {
|
|
|
|
|
"calcs": [
|
|
|
|
|
"lastNotNull"
|
|
|
|
|
],
|
|
|
|
|
"fields": "",
|
|
|
|
|
"values": false
|
2025-11-16 00:55:28 -03:00
|
|
|
},
|
2025-11-17 14:22:46 -03:00
|
|
|
"textMode": "value_and_name"
|
2025-11-15 21:03:11 -03:00
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"id": 5,
|
|
|
|
|
"type": "timeseries",
|
2025-11-17 14:22:46 -03:00
|
|
|
"title": "Node CPU",
|
2025-11-15 21:03:11 -03:00
|
|
|
"datasource": {
|
|
|
|
|
"type": "prometheus",
|
|
|
|
|
"uid": "atlas-vm"
|
|
|
|
|
},
|
|
|
|
|
"gridPos": {
|
|
|
|
|
"h": 9,
|
2025-11-17 14:22:46 -03:00
|
|
|
"w": 24,
|
2025-11-15 21:03:11 -03:00
|
|
|
"x": 0,
|
|
|
|
|
"y": 5
|
|
|
|
|
},
|
|
|
|
|
"targets": [
|
|
|
|
|
{
|
2025-11-16 00:55:28 -03:00
|
|
|
"expr": "avg by (node) ((((1 - label_replace(rate(node_cpu_seconds_total{mode=\"idle\"}[5m]), \"internal_ip\", \"$1\", \"instance\", \"([^:]+):.*\")) * 100) * on (internal_ip) group_left(node) kube_node_info))",
|
2025-11-15 21:03:11 -03:00
|
|
|
"refId": "A",
|
2025-11-16 00:55:28 -03:00
|
|
|
"legendFormat": "{{node}}"
|
2025-11-15 21:03:11 -03:00
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"fieldConfig": {
|
|
|
|
|
"defaults": {
|
|
|
|
|
"unit": "percent"
|
|
|
|
|
},
|
|
|
|
|
"overrides": []
|
|
|
|
|
},
|
2025-11-14 00:02:59 -03:00
|
|
|
"options": {
|
|
|
|
|
"legend": {
|
|
|
|
|
"displayMode": "table",
|
2025-11-17 14:22:46 -03:00
|
|
|
"placement": "right",
|
|
|
|
|
"calcs": [
|
|
|
|
|
"last"
|
|
|
|
|
]
|
2025-11-14 00:02:59 -03:00
|
|
|
},
|
|
|
|
|
"tooltip": {
|
|
|
|
|
"mode": "multi"
|
|
|
|
|
}
|
2025-11-15 21:03:11 -03:00
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"id": 6,
|
|
|
|
|
"type": "timeseries",
|
2025-11-17 14:22:46 -03:00
|
|
|
"title": "Node RAM",
|
2025-11-15 21:03:11 -03:00
|
|
|
"datasource": {
|
|
|
|
|
"type": "prometheus",
|
|
|
|
|
"uid": "atlas-vm"
|
|
|
|
|
},
|
|
|
|
|
"gridPos": {
|
|
|
|
|
"h": 9,
|
2025-11-17 14:22:46 -03:00
|
|
|
"w": 24,
|
|
|
|
|
"x": 0,
|
|
|
|
|
"y": 14
|
2025-11-14 00:02:59 -03:00
|
|
|
},
|
|
|
|
|
"targets": [
|
|
|
|
|
{
|
2025-11-16 00:55:28 -03:00
|
|
|
"expr": "avg by (node) (((label_replace((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes, \"internal_ip\", \"$1\", \"instance\", \"([^:]+):.*\") * 100) * on (internal_ip) group_left(node) kube_node_info))",
|
2025-11-15 21:03:11 -03:00
|
|
|
"refId": "A",
|
2025-11-16 00:55:28 -03:00
|
|
|
"legendFormat": "{{node}}"
|
2025-11-14 00:02:59 -03:00
|
|
|
}
|
|
|
|
|
],
|
2025-11-15 21:03:11 -03:00
|
|
|
"fieldConfig": {
|
|
|
|
|
"defaults": {
|
|
|
|
|
"unit": "percent"
|
|
|
|
|
},
|
|
|
|
|
"overrides": []
|
|
|
|
|
},
|
|
|
|
|
"options": {
|
|
|
|
|
"legend": {
|
|
|
|
|
"displayMode": "table",
|
2025-11-17 14:22:46 -03:00
|
|
|
"placement": "right",
|
|
|
|
|
"calcs": [
|
|
|
|
|
"last"
|
|
|
|
|
]
|
2025-11-15 21:03:11 -03:00
|
|
|
},
|
|
|
|
|
"tooltip": {
|
|
|
|
|
"mode": "multi"
|
|
|
|
|
}
|
|
|
|
|
}
|
2025-11-14 00:02:59 -03:00
|
|
|
},
|
|
|
|
|
{
|
2025-11-15 21:03:11 -03:00
|
|
|
"id": 7,
|
|
|
|
|
"type": "timeseries",
|
2025-11-17 14:22:46 -03:00
|
|
|
"title": "Root filesystem",
|
2025-11-14 00:02:59 -03:00
|
|
|
"datasource": {
|
|
|
|
|
"type": "prometheus",
|
|
|
|
|
"uid": "atlas-vm"
|
|
|
|
|
},
|
|
|
|
|
"gridPos": {
|
2025-11-15 21:03:11 -03:00
|
|
|
"h": 9,
|
2025-11-17 14:22:46 -03:00
|
|
|
"w": 24,
|
2025-11-14 00:02:59 -03:00
|
|
|
"x": 0,
|
2025-11-15 21:03:11 -03:00
|
|
|
"y": 23
|
|
|
|
|
},
|
|
|
|
|
"targets": [
|
|
|
|
|
{
|
2025-11-17 14:22:46 -03:00
|
|
|
"expr": "avg by (node) (((1 - (label_replace(node_filesystem_avail_bytes{mountpoint=\"/\",fstype!~\"tmpfs|overlay\"} / node_filesystem_size_bytes{mountpoint=\"/\",fstype!~\"tmpfs|overlay\"}, \"internal_ip\", \"$1\", \"instance\", \"([^:]+):.*\"))) * 100) * on (internal_ip) group_left(node) kube_node_info)",
|
2025-11-15 21:03:11 -03:00
|
|
|
"refId": "A",
|
2025-11-17 14:22:46 -03:00
|
|
|
"legendFormat": "{{node}}"
|
2025-11-15 21:03:11 -03:00
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"fieldConfig": {
|
|
|
|
|
"defaults": {
|
|
|
|
|
"unit": "percent"
|
|
|
|
|
},
|
|
|
|
|
"overrides": []
|
|
|
|
|
},
|
|
|
|
|
"options": {
|
|
|
|
|
"legend": {
|
|
|
|
|
"displayMode": "table",
|
2025-11-17 14:22:46 -03:00
|
|
|
"placement": "right"
|
2025-11-15 21:03:11 -03:00
|
|
|
},
|
|
|
|
|
"tooltip": {
|
|
|
|
|
"mode": "multi"
|
|
|
|
|
}
|
2025-11-17 14:22:46 -03:00
|
|
|
},
|
|
|
|
|
"timeFrom": "7d"
|
2025-11-14 00:02:59 -03:00
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"time": {
|
|
|
|
|
"from": "now-12h",
|
|
|
|
|
"to": "now"
|
|
|
|
|
},
|
2025-11-17 14:22:46 -03:00
|
|
|
"annotations": {
|
|
|
|
|
"list": []
|
|
|
|
|
},
|
|
|
|
|
"schemaVersion": 39,
|
|
|
|
|
"style": "dark",
|
|
|
|
|
"tags": [
|
|
|
|
|
"atlas",
|
|
|
|
|
"nodes"
|
|
|
|
|
]
|
2025-11-14 00:02:59 -03:00
|
|
|
}
|