mirror of
https://github.com/cozystack/cozystack.git
synced 2026-03-02 14:49:00 +00:00
docs: add Hubble network observability documentation and dashboards
Add documentation explaining how to enable Hubble for network observability in Grafana. Include four pre-built Hubble dashboards (overview, dns-namespace, l7-http-metrics, network-overview) and register them in the monitoring hub's dashboard list. Closes #749 Signed-off-by: majiayu000 <1835304752@qq.com>
This commit is contained in:
602
dashboards/hubble/dns-namespace.json
Normal file
602
dashboards/hubble/dns-namespace.json
Normal file
@@ -0,0 +1,602 @@
|
||||
{
|
||||
"__inputs": [
|
||||
{
|
||||
"name": "DS_PROMETHEUS",
|
||||
"label": "Prometheus",
|
||||
"description": "",
|
||||
"type": "datasource",
|
||||
"pluginId": "prometheus",
|
||||
"pluginName": "Prometheus"
|
||||
}
|
||||
],
|
||||
"__elements": {},
|
||||
"__requires": [
|
||||
{
|
||||
"type": "panel",
|
||||
"id": "bargauge",
|
||||
"name": "Bar gauge",
|
||||
"version": ""
|
||||
},
|
||||
{
|
||||
"type": "grafana",
|
||||
"id": "grafana",
|
||||
"name": "Grafana",
|
||||
"version": "9.4.7"
|
||||
},
|
||||
{
|
||||
"type": "datasource",
|
||||
"id": "prometheus",
|
||||
"name": "Prometheus",
|
||||
"version": "1.0.0"
|
||||
},
|
||||
{
|
||||
"type": "panel",
|
||||
"id": "timeseries",
|
||||
"name": "Time series",
|
||||
"version": ""
|
||||
}
|
||||
],
|
||||
"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"
|
||||
}
|
||||
]
|
||||
},
|
||||
"description": "",
|
||||
"editable": true,
|
||||
"fiscalYearStartMonth": 0,
|
||||
"gnetId": 16612,
|
||||
"graphTooltip": 0,
|
||||
"id": null,
|
||||
"links": [
|
||||
{
|
||||
"asDropdown": true,
|
||||
"icon": "external link",
|
||||
"includeVars": true,
|
||||
"keepTime": true,
|
||||
"tags": [
|
||||
"cilium-overview"
|
||||
],
|
||||
"targetBlank": false,
|
||||
"title": "Cilium Overviews",
|
||||
"tooltip": "",
|
||||
"type": "dashboards",
|
||||
"url": ""
|
||||
},
|
||||
{
|
||||
"asDropdown": true,
|
||||
"icon": "external link",
|
||||
"includeVars": false,
|
||||
"keepTime": true,
|
||||
"tags": [
|
||||
"hubble"
|
||||
],
|
||||
"targetBlank": false,
|
||||
"title": "Hubble",
|
||||
"tooltip": "",
|
||||
"type": "dashboards",
|
||||
"url": ""
|
||||
}
|
||||
],
|
||||
"liveNow": false,
|
||||
"panels": [
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": {
|
||||
"h": 1,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"id": 2,
|
||||
"panels": [],
|
||||
"title": "DNS",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"description": "",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "normal"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"min": 0,
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "reqps"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 9,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 1
|
||||
},
|
||||
"id": 37,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"mean",
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single",
|
||||
"sort": "none"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "sum(rate(hubble_dns_queries_total{cluster=~\"$cluster\", source_namespace=~\"$source_namespace\", destination_namespace=~\"$destination_namespace\"}[$__rate_interval])) by (source) > 0",
|
||||
"legendFormat": "{{source}}",
|
||||
"range": true,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "DNS queries",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "thresholds"
|
||||
},
|
||||
"mappings": [],
|
||||
"min": 0,
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "reqps"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 9,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 1
|
||||
},
|
||||
"id": 41,
|
||||
"options": {
|
||||
"displayMode": "gradient",
|
||||
"minVizHeight": 10,
|
||||
"minVizWidth": 0,
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
"showUnfilled": true
|
||||
},
|
||||
"pluginVersion": "9.4.7",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "topk(10, sum(rate(hubble_dns_queries_total{cluster=~\"$cluster\", source_namespace=~\"$source_namespace\", destination_namespace=~\"$destination_namespace\"}[$__rate_interval])*60) by (query))",
|
||||
"legendFormat": "{{query}}",
|
||||
"range": true,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Top 10 DNS queries",
|
||||
"type": "bargauge"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "normal"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"min": 0,
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "reqps"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 9,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 10
|
||||
},
|
||||
"id": 39,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"mean",
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single",
|
||||
"sort": "none"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "round(sum(rate(hubble_dns_queries_total{cluster=~\"$cluster\", source_namespace=~\"$source_namespace\", destination_namespace=~\"$destination_namespace\"}[$__rate_interval])) by (source) - sum(label_replace(sum(rate(hubble_dns_responses_total{cluster=~\"$cluster\", source_namespace=~\"$destination_namespace\", destination_namespace=~\"$source_namespace\"}[$__rate_interval])) by (destination), \"source\", \"$1\", \"destination\", \"(.*)\")) without (destination), 0.001) > 0",
|
||||
"legendFormat": "{{source}}",
|
||||
"range": true,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Missing DNS responses",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "normal"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"min": 0,
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "reqps"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 9,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 10
|
||||
},
|
||||
"id": 43,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"mean",
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single",
|
||||
"sort": "none"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "sum(rate(hubble_dns_responses_total{cluster=~\"$cluster\", source_namespace=~\"$destination_namespace\", destination_namespace=~\"$source_namespace\", rcode!=\"No Error\"}[$__rate_interval])) by (destination, rcode) > 0",
|
||||
"legendFormat": "{{destination}}: {{rcode}}",
|
||||
"range": true,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "DNS errors",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"refresh": "",
|
||||
"revision": 1,
|
||||
"schemaVersion": 38,
|
||||
"style": "dark",
|
||||
"tags": [
|
||||
"kubecon-demo"
|
||||
],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"current": {
|
||||
"selected": false,
|
||||
"text": "default",
|
||||
"value": "default"
|
||||
},
|
||||
"hide": 0,
|
||||
"includeAll": false,
|
||||
"label": "Data Source",
|
||||
"multi": false,
|
||||
"name": "DS_PROMETHEUS",
|
||||
"options": [],
|
||||
"query": "prometheus",
|
||||
"queryValue": "",
|
||||
"refresh": 1,
|
||||
"regex": "(?!grafanacloud-usage|grafanacloud-ml-metrics).+",
|
||||
"skipUrlSync": false,
|
||||
"type": "datasource"
|
||||
},
|
||||
{
|
||||
"current": {},
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"definition": "label_values(cilium_version, cluster)",
|
||||
"hide": 0,
|
||||
"includeAll": true,
|
||||
"multi": true,
|
||||
"name": "cluster",
|
||||
"options": [],
|
||||
"query": {
|
||||
"query": "label_values(cilium_version, cluster)",
|
||||
"refId": "StandardVariableQuery"
|
||||
},
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"skipUrlSync": false,
|
||||
"sort": 0,
|
||||
"type": "query"
|
||||
},
|
||||
{
|
||||
"allValue": ".*",
|
||||
"current": {},
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"definition": "label_values(source_namespace)",
|
||||
"hide": 0,
|
||||
"includeAll": true,
|
||||
"label": "Source Namespace",
|
||||
"multi": true,
|
||||
"name": "source_namespace",
|
||||
"options": [],
|
||||
"query": {
|
||||
"query": "label_values(source_namespace)",
|
||||
"refId": "StandardVariableQuery"
|
||||
},
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"skipUrlSync": false,
|
||||
"sort": 0,
|
||||
"type": "query"
|
||||
},
|
||||
{
|
||||
"allValue": ".*",
|
||||
"current": {},
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"definition": "label_values(destination_namespace)",
|
||||
"hide": 0,
|
||||
"includeAll": true,
|
||||
"label": "Destination Namespace",
|
||||
"multi": true,
|
||||
"name": "destination_namespace",
|
||||
"options": [],
|
||||
"query": {
|
||||
"query": "label_values(destination_namespace)",
|
||||
"refId": "StandardVariableQuery"
|
||||
},
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"skipUrlSync": false,
|
||||
"sort": 0,
|
||||
"type": "query"
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {
|
||||
"refresh_intervals": [
|
||||
"10s",
|
||||
"30s",
|
||||
"1m",
|
||||
"5m",
|
||||
"15m",
|
||||
"30m",
|
||||
"1h",
|
||||
"2h",
|
||||
"1d"
|
||||
],
|
||||
"time_options": [
|
||||
"5m",
|
||||
"15m",
|
||||
"1h",
|
||||
"6h",
|
||||
"12h",
|
||||
"24h",
|
||||
"2d",
|
||||
"7d",
|
||||
"30d"
|
||||
]
|
||||
},
|
||||
"timezone": "",
|
||||
"title": "Hubble / DNS Overview (Namespace)",
|
||||
"uid": "_f0DUpY4k",
|
||||
"version": 26,
|
||||
"weekStart": ""
|
||||
}
|
||||
|
||||
1394
dashboards/hubble/l7-http-metrics.json
Normal file
1394
dashboards/hubble/l7-http-metrics.json
Normal file
File diff suppressed because it is too large
Load Diff
1001
dashboards/hubble/network-overview.json
Normal file
1001
dashboards/hubble/network-overview.json
Normal file
File diff suppressed because it is too large
Load Diff
3357
dashboards/hubble/overview.json
Normal file
3357
dashboards/hubble/overview.json
Normal file
File diff suppressed because it is too large
Load Diff
99
docs/hubble-observability.md
Normal file
99
docs/hubble-observability.md
Normal file
@@ -0,0 +1,99 @@
|
||||
# Enabling Hubble for Network Observability
|
||||
|
||||
Hubble is a network and security observability platform built on top of Cilium. It provides deep visibility into the communication and behavior of services in your Kubernetes cluster.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- Cozystack platform running with Cilium as the CNI
|
||||
- Monitoring hub enabled for Grafana access
|
||||
|
||||
## Configuration
|
||||
|
||||
Hubble is disabled by default in Cozystack. To enable it, update the Cilium configuration.
|
||||
|
||||
### Enable Hubble
|
||||
|
||||
Edit the Cilium values in your platform configuration to enable Hubble:
|
||||
|
||||
```yaml
|
||||
cilium:
|
||||
hubble:
|
||||
enabled: true
|
||||
relay:
|
||||
enabled: true
|
||||
ui:
|
||||
enabled: true
|
||||
metrics:
|
||||
enabled:
|
||||
- dns
|
||||
- drop
|
||||
- tcp
|
||||
- flow
|
||||
- port-distribution
|
||||
- icmp
|
||||
- httpV2:exemplars=true;labelsContext=source_ip,source_namespace,source_workload,destination_ip,destination_namespace,destination_workload,traffic_direction
|
||||
```
|
||||
|
||||
### Components
|
||||
|
||||
When Hubble is enabled, the following components become available:
|
||||
|
||||
- **Hubble Relay**: Aggregates flow data from all Cilium agents
|
||||
- **Hubble UI**: Web-based interface for exploring network flows
|
||||
- **Hubble Metrics**: Prometheus metrics for network observability
|
||||
|
||||
## Grafana Dashboards
|
||||
|
||||
Once Hubble is enabled and the monitoring hub is deployed, the following dashboards become available in Grafana under the `hubble` folder:
|
||||
|
||||
| Dashboard | Description |
|
||||
|-----------|-------------|
|
||||
| **Overview** | General Hubble metrics including processing statistics |
|
||||
| **DNS Namespace** | DNS query and response metrics by namespace |
|
||||
| **L7 HTTP Metrics** | HTTP layer 7 metrics by workload |
|
||||
| **Network Overview** | Network flow overview by namespace |
|
||||
|
||||
### Accessing Dashboards
|
||||
|
||||
1. Navigate to Grafana via the monitoring hub
|
||||
2. Browse to the `hubble` folder in the dashboard browser
|
||||
3. Select a dashboard to view network observability data
|
||||
|
||||
## Metrics Available
|
||||
|
||||
Hubble exposes various metrics that can be queried in Grafana:
|
||||
|
||||
- `hubble_flows_processed_total`: Total number of flows processed
|
||||
- `hubble_dns_queries_total`: DNS queries by type
|
||||
- `hubble_dns_responses_total`: DNS responses by status
|
||||
- `hubble_drop_total`: Dropped packets by reason
|
||||
- `hubble_tcp_flags_total`: TCP connections by flag
|
||||
- `hubble_http_requests_total`: HTTP requests by method and status
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Verify Hubble Status
|
||||
|
||||
Check if Hubble is running:
|
||||
|
||||
```bash
|
||||
kubectl get pods -n cozy-cilium -l k8s-app=hubble-relay
|
||||
kubectl get pods -n cozy-cilium -l k8s-app=hubble-ui
|
||||
```
|
||||
|
||||
### Check Metrics Endpoint
|
||||
|
||||
Verify Hubble metrics are being scraped:
|
||||
|
||||
```bash
|
||||
kubectl port-forward -n cozy-cilium svc/hubble-metrics 9965:9965
|
||||
curl http://localhost:9965/metrics
|
||||
```
|
||||
|
||||
### Verify ServiceMonitor
|
||||
|
||||
Ensure the ServiceMonitor is created for Prometheus scraping:
|
||||
|
||||
```bash
|
||||
kubectl get servicemonitor -n cozy-cilium
|
||||
```
|
||||
@@ -39,3 +39,7 @@ goldpinger/goldpinger
|
||||
clickhouse/altinity-clickhouse-operator-dashboard
|
||||
storage/linstor
|
||||
seaweedfs/seaweedfs
|
||||
hubble/overview
|
||||
hubble/dns-namespace
|
||||
hubble/l7-http-metrics
|
||||
hubble/network-overview
|
||||
|
||||
Reference in New Issue
Block a user