476 lines
10 KiB
JSON
476 lines
10 KiB
JSON
{
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"liveNow": false,
|
|
"panels": [
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"id": 100,
|
|
"title": "\ud83d\udce6 Container Fleet & Pod Metrics",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"id": 1,
|
|
"title": "Monitored Containers",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 0,
|
|
"y": 1
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "count(container_last_seen{container!=''})",
|
|
"legendFormat": "{{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "none"
|
|
}
|
|
},
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "center"
|
|
}
|
|
},
|
|
{
|
|
"id": 2,
|
|
"title": "Active Kubernetes Pods",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 6,
|
|
"y": 1
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "count(count by (pod, namespace) (container_last_seen{container!=''}))",
|
|
"legendFormat": "{{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "blue",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "none"
|
|
}
|
|
},
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "center"
|
|
}
|
|
},
|
|
{
|
|
"id": 3,
|
|
"title": "Total Container CPU Load",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 12,
|
|
"y": 1
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(container_cpu_usage_seconds_total{container!=''}[2m]))",
|
|
"legendFormat": "{{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "purple",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "none"
|
|
}
|
|
},
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "center"
|
|
}
|
|
},
|
|
{
|
|
"id": 4,
|
|
"title": "Total Container RAM",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 18,
|
|
"y": 1
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "sum(container_memory_working_set_bytes{container!=''})",
|
|
"legendFormat": "{{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "orange",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "bytes"
|
|
}
|
|
},
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "center"
|
|
}
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 5
|
|
},
|
|
"id": 200,
|
|
"title": "\u26a1 Top Container CPU Utilization",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"id": 5,
|
|
"title": "Top 10 CPU Consuming Pods (Cores)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 6
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "topk(10, sum by (pod, namespace) (rate(container_cpu_usage_seconds_total{container!=''}[2m])))",
|
|
"legendFormat": "{{namespace}} / {{pod}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "none"
|
|
}
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 6,
|
|
"title": "CPU Throttling by Namespace",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 6
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (namespace) (rate(container_cpu_cfs_throttled_periods_total[2m]))",
|
|
"legendFormat": "{{namespace}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "none"
|
|
}
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 14
|
|
},
|
|
"id": 300,
|
|
"title": "\ud83e\udde0 Container Memory Working Set",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"id": 7,
|
|
"title": "Top 10 Memory Consuming Pods",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 14,
|
|
"x": 0,
|
|
"y": 15
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "topk(10, sum by (pod, namespace) (container_memory_working_set_bytes{container!=''}))",
|
|
"legendFormat": "{{namespace}} / {{pod}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "bytes"
|
|
}
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 8,
|
|
"title": "Memory by Namespace",
|
|
"type": "bargauge",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 10,
|
|
"x": 14,
|
|
"y": 15
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (namespace) (container_memory_working_set_bytes{container!=''})",
|
|
"legendFormat": "{{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 75
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 90
|
|
}
|
|
]
|
|
},
|
|
"unit": "bytes",
|
|
"min": 0,
|
|
"max": 100
|
|
}
|
|
},
|
|
"options": {
|
|
"displayMode": "gradient",
|
|
"orientation": "horizontal",
|
|
"showUnfilled": true
|
|
}
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 23
|
|
},
|
|
"id": 400,
|
|
"title": "\ud83c\udf10 Container Network Traffic",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"id": 9,
|
|
"title": "Top Pod Network RX (Receive)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 24
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "topk(10, sum by (pod, namespace) (rate(container_network_receive_bytes_total[2m])))",
|
|
"legendFormat": "RX {{namespace}}/{{pod}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "Bps"
|
|
}
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 10,
|
|
"title": "Top Pod Network TX (Transmit)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 24
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "topk(10, sum by (pod, namespace) (rate(container_network_transmit_bytes_total[2m])))",
|
|
"legendFormat": "TX {{namespace}}/{{pod}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "Bps"
|
|
}
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"refresh": "10s",
|
|
"schemaVersion": 39,
|
|
"tags": [
|
|
"kubernetes",
|
|
"containers",
|
|
"cadvisor",
|
|
"snarfnet",
|
|
"workloads"
|
|
],
|
|
"templating": {
|
|
"list": []
|
|
},
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"timepicker": {},
|
|
"timezone": "browser",
|
|
"title": "\ud83d\udce6 Kubernetes Containers & Workloads",
|
|
"uid": "snarfnet-containers"
|
|
} |