incus-contrib/bin/data/observability-dashboards/core/network-deep-dive.json

860 lines
21 KiB
JSON

{
"uid": "incus-network-deep-dive",
"title": "Network Deep Dive",
"description": "Per-node and per-device network traffic, instance-level network metrics, receive/transmit errors, and packet drops.",
"tags": [
"incus",
"incusos",
"network",
"node-exporter"
],
"timezone": "browser",
"schemaVersion": 39,
"refresh": "30s",
"time": {
"from": "now-1h",
"to": "now"
},
"fiscalYearStartMonth": 0,
"liveNow": false,
"editable": true,
"graphTooltip": 1,
"links": [
{
"asDropdown": true,
"icon": "external link",
"includeVars": true,
"keepTime": true,
"tags": [
"incus"
],
"targetBlank": false,
"title": "Incus Dashboards",
"tooltip": "Navigate to other Incus dashboards",
"type": "dashboards"
}
],
"templating": {
"list": [
{
"current": {},
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"definition": "label_values(node_network_receive_bytes_total{job=\"node-exporter\"}, instance)",
"includeAll": false,
"multi": true,
"name": "node",
"query": "label_values(node_network_receive_bytes_total{job=\"node-exporter\"}, instance)",
"refresh": 2,
"sort": 1,
"type": "query",
"label": "Node"
},
{
"current": {},
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"definition": "label_values(node_network_receive_bytes_total{job=\"node-exporter\", instance=~\"$node\"}, device)",
"includeAll": true,
"multi": true,
"name": "device",
"query": "label_values(node_network_receive_bytes_total{job=\"node-exporter\", instance=~\"$node\"}, device)",
"refresh": 2,
"regex": "/^(?!lo$).*/",
"sort": 1,
"type": "query",
"label": "Device",
"allValue": ".*"
}
]
},
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "grafana",
"uid": "-- Grafana --"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"panels": [
{
"type": "row",
"title": "Cluster Summary",
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
"id": 1,
"panels": []
},
{
"type": "stat",
"title": "Total Ingress",
"description": "Aggregate inbound network throughput across all selected nodes and devices.",
"gridPos": {
"h": 4,
"w": 6,
"x": 0,
"y": 1
},
"id": 2,
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"targets": [
{
"expr": "sum(rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=~\"$node\", device=~\"$device\"}[$__rate_interval]))",
"legendFormat": "Ingress",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "Bps",
"color": {
"mode": "thresholds"
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"orientation": "auto",
"textMode": "auto",
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto"
}
},
{
"type": "stat",
"title": "Total Egress",
"description": "Aggregate outbound network throughput across all selected nodes and devices.",
"gridPos": {
"h": 4,
"w": 6,
"x": 6,
"y": 1
},
"id": 3,
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"targets": [
{
"expr": "sum(rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=~\"$node\", device=~\"$device\"}[$__rate_interval]))",
"legendFormat": "Egress",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "Bps",
"color": {
"mode": "thresholds"
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"orientation": "auto",
"textMode": "auto",
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto"
}
},
{
"type": "stat",
"title": "Total Errors",
"description": "Combined receive and transmit error rate across all selected nodes. Any non-zero value warrants investigation.",
"gridPos": {
"h": 4,
"w": 6,
"x": 12,
"y": 1
},
"id": 4,
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"targets": [
{
"expr": "sum(rate(node_network_receive_errs_total{job=\"node-exporter\", instance=~\"$node\"}[$__rate_interval])) + sum(rate(node_network_transmit_errs_total{job=\"node-exporter\", instance=~\"$node\"}[$__rate_interval]))",
"legendFormat": "Errors",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 0.1
},
{
"color": "red",
"value": 1
}
]
},
"unit": "pps",
"color": {
"mode": "thresholds"
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"orientation": "auto",
"textMode": "auto",
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto"
}
},
{
"type": "stat",
"title": "Total Drops",
"description": "Combined receive and transmit packet drop rate across all selected nodes. Drops indicate buffer or queue exhaustion.",
"gridPos": {
"h": 4,
"w": 6,
"x": 18,
"y": 1
},
"id": 5,
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"targets": [
{
"expr": "sum(rate(node_network_receive_drop_total{job=\"node-exporter\", instance=~\"$node\"}[$__rate_interval])) + sum(rate(node_network_transmit_drop_total{job=\"node-exporter\", instance=~\"$node\"}[$__rate_interval]))",
"legendFormat": "Drops",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 0.1
},
{
"color": "red",
"value": 1
}
]
},
"unit": "pps",
"color": {
"mode": "thresholds"
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"orientation": "auto",
"textMode": "auto",
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto"
}
},
{
"type": "row",
"title": "Per-Node Traffic",
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 5
},
"id": 10,
"panels": []
},
{
"type": "timeseries",
"title": "Receive Rate by Node & Device",
"description": "Inbound network throughput broken down by node and network device. Identifies which interfaces are handling the most receive traffic.",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 6
},
"id": 11,
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"targets": [
{
"expr": "rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=~\"$node\", device=~\"$device\"}[$__rate_interval])",
"legendFormat": "{{instance}} {{device}} rx",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineInterpolation": "smooth",
"lineWidth": 1,
"fillOpacity": 15,
"gradientMode": "none",
"spanNulls": false,
"showPoints": "never",
"pointSize": 5,
"stacking": {
"mode": "none",
"group": "A"
},
"axisPlacement": "auto",
"axisLabel": "",
"scaleDistribution": {
"type": "linear"
},
"thresholdsStyle": {
"mode": "off"
}
},
"unit": "Bps",
"color": {
"mode": "palette-classic"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
},
"legend": {
"displayMode": "table",
"placement": "right",
"calcs": [
"mean",
"max",
"lastNotNull"
]
}
}
},
{
"type": "timeseries",
"title": "Transmit Rate by Node & Device",
"description": "Outbound network throughput broken down by node and network device. Identifies which interfaces are handling the most transmit traffic.",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 6
},
"id": 12,
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"targets": [
{
"expr": "rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=~\"$node\", device=~\"$device\"}[$__rate_interval])",
"legendFormat": "{{instance}} {{device}} tx",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineInterpolation": "smooth",
"lineWidth": 1,
"fillOpacity": 15,
"gradientMode": "none",
"spanNulls": false,
"showPoints": "never",
"pointSize": 5,
"stacking": {
"mode": "none",
"group": "A"
},
"axisPlacement": "auto",
"axisLabel": "",
"scaleDistribution": {
"type": "linear"
},
"thresholdsStyle": {
"mode": "off"
}
},
"unit": "Bps",
"color": {
"mode": "palette-classic"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
},
"legend": {
"displayMode": "table",
"placement": "right",
"calcs": [
"mean",
"max",
"lastNotNull"
]
}
}
},
{
"type": "row",
"title": "Instance Network (Incus metrics)",
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 14
},
"id": 20,
"panels": []
},
{
"type": "timeseries",
"title": "Instance Receive Rate",
"description": "Inbound network throughput per Incus instance, aggregated across all instance network devices. Uses Incus-native metrics for container and VM visibility.",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 15
},
"id": 21,
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"targets": [
{
"expr": "sum by (name) (rate(incus_network_receive_bytes_total[$__rate_interval]))",
"legendFormat": "{{name}}",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineInterpolation": "smooth",
"lineWidth": 1,
"fillOpacity": 15,
"gradientMode": "none",
"spanNulls": false,
"showPoints": "never",
"pointSize": 5,
"stacking": {
"mode": "none",
"group": "A"
},
"axisPlacement": "auto",
"axisLabel": "",
"scaleDistribution": {
"type": "linear"
},
"thresholdsStyle": {
"mode": "off"
}
},
"unit": "Bps",
"color": {
"mode": "palette-classic"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
},
"legend": {
"displayMode": "table",
"placement": "right",
"calcs": [
"mean",
"max",
"lastNotNull"
]
}
}
},
{
"type": "timeseries",
"title": "Instance Transmit Rate",
"description": "Outbound network throughput per Incus instance, aggregated across all instance network devices. Uses Incus-native metrics for container and VM visibility.",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 15
},
"id": 22,
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"targets": [
{
"expr": "sum by (name) (rate(incus_network_transmit_bytes_total[$__rate_interval]))",
"legendFormat": "{{name}}",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineInterpolation": "smooth",
"lineWidth": 1,
"fillOpacity": 15,
"gradientMode": "none",
"spanNulls": false,
"showPoints": "never",
"pointSize": 5,
"stacking": {
"mode": "none",
"group": "A"
},
"axisPlacement": "auto",
"axisLabel": "",
"scaleDistribution": {
"type": "linear"
},
"thresholdsStyle": {
"mode": "off"
}
},
"unit": "Bps",
"color": {
"mode": "palette-classic"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
},
"legend": {
"displayMode": "table",
"placement": "right",
"calcs": [
"mean",
"max",
"lastNotNull"
]
}
}
},
{
"type": "row",
"title": "Errors & Drops",
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 23
},
"id": 30,
"panels": []
},
{
"type": "timeseries",
"title": "Receive/Transmit Errors",
"description": "Network interface error rates broken down by node and device. Receive errors may indicate CRC failures or framing issues; transmit errors may indicate collisions or driver problems.",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 24
},
"id": 31,
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"targets": [
{
"expr": "rate(node_network_receive_errs_total{job=\"node-exporter\", instance=~\"$node\", device=~\"$device\"}[$__rate_interval])",
"legendFormat": "{{instance}} {{device}} rx errors",
"refId": "A"
},
{
"expr": "rate(node_network_transmit_errs_total{job=\"node-exporter\", instance=~\"$node\", device=~\"$device\"}[$__rate_interval])",
"legendFormat": "{{instance}} {{device}} tx errors",
"refId": "B"
}
],
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineInterpolation": "smooth",
"lineWidth": 1,
"fillOpacity": 15,
"gradientMode": "none",
"spanNulls": false,
"showPoints": "never",
"pointSize": 5,
"stacking": {
"mode": "none",
"group": "A"
},
"axisPlacement": "auto",
"axisLabel": "",
"scaleDistribution": {
"type": "linear"
},
"thresholdsStyle": {
"mode": "off"
}
},
"unit": "pps",
"color": {
"mode": "palette-classic"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
},
"legend": {
"displayMode": "table",
"placement": "right",
"calcs": [
"mean",
"max",
"lastNotNull"
]
}
}
},
{
"type": "timeseries",
"title": "Packet Drops",
"description": "Network interface packet drop rates broken down by node and device. Drops indicate kernel buffer or queue exhaustion and may cause retransmissions or connection failures.",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 24
},
"id": 32,
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"targets": [
{
"expr": "rate(node_network_receive_drop_total{job=\"node-exporter\", instance=~\"$node\", device=~\"$device\"}[$__rate_interval])",
"legendFormat": "{{instance}} {{device}} rx drops",
"refId": "A"
},
{
"expr": "rate(node_network_transmit_drop_total{job=\"node-exporter\", instance=~\"$node\", device=~\"$device\"}[$__rate_interval])",
"legendFormat": "{{instance}} {{device}} tx drops",
"refId": "B"
}
],
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineInterpolation": "smooth",
"lineWidth": 1,
"fillOpacity": 15,
"gradientMode": "none",
"spanNulls": false,
"showPoints": "never",
"pointSize": 5,
"stacking": {
"mode": "none",
"group": "A"
},
"axisPlacement": "auto",
"axisLabel": "",
"scaleDistribution": {
"type": "linear"
},
"thresholdsStyle": {
"mode": "off"
}
},
"unit": "pps",
"color": {
"mode": "palette-classic"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
},
"legend": {
"displayMode": "table",
"placement": "right",
"calcs": [
"mean",
"max",
"lastNotNull"
]
}
}
}
]
}