136 lines
5.4 KiB
YAML
136 lines
5.4 KiB
YAML
|
|
# Grafana dashboard ConfigMaps — La Suite (Golden Signals via Linkerd)
|
||
|
|
---
|
||
|
|
apiVersion: v1
|
||
|
|
kind: ConfigMap
|
||
|
|
metadata:
|
||
|
|
name: grafana-dashboard-lasuite
|
||
|
|
namespace: monitoring
|
||
|
|
labels:
|
||
|
|
grafana_dashboard: "1"
|
||
|
|
annotations:
|
||
|
|
grafana_folder: "La Suite"
|
||
|
|
data:
|
||
|
|
lasuite.json: |
|
||
|
|
{
|
||
|
|
"annotations": { "list": [] },
|
||
|
|
"editable": true,
|
||
|
|
"panels": [
|
||
|
|
{
|
||
|
|
"title": "Request Rate",
|
||
|
|
"type": "timeseries",
|
||
|
|
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 },
|
||
|
|
"datasource": { "uid": "prometheus" },
|
||
|
|
"targets": [
|
||
|
|
{
|
||
|
|
"expr": "sum(rate(request_total{namespace=~\"$namespace\", deployment=~\"$deployment\", direction=\"inbound\"}[5m])) by (deployment)",
|
||
|
|
"legendFormat": "{{deployment}}"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"fieldConfig": { "defaults": { "unit": "reqps" } }
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"title": "Success Rate",
|
||
|
|
"type": "timeseries",
|
||
|
|
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 },
|
||
|
|
"datasource": { "uid": "prometheus" },
|
||
|
|
"targets": [
|
||
|
|
{
|
||
|
|
"expr": "sum(rate(response_total{namespace=~\"$namespace\", deployment=~\"$deployment\", direction=\"inbound\", classification=\"success\"}[5m])) by (deployment) / sum(rate(response_total{namespace=~\"$namespace\", deployment=~\"$deployment\", direction=\"inbound\"}[5m])) by (deployment)",
|
||
|
|
"legendFormat": "{{deployment}}"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"fieldConfig": { "defaults": { "unit": "percentunit", "max": 1 } }
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"title": "Error Rate",
|
||
|
|
"type": "timeseries",
|
||
|
|
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 8 },
|
||
|
|
"datasource": { "uid": "prometheus" },
|
||
|
|
"targets": [
|
||
|
|
{
|
||
|
|
"expr": "sum(rate(response_total{namespace=~\"$namespace\", deployment=~\"$deployment\", direction=\"inbound\", classification=\"failure\"}[5m])) by (deployment) / sum(rate(response_total{namespace=~\"$namespace\", deployment=~\"$deployment\", direction=\"inbound\"}[5m])) by (deployment)",
|
||
|
|
"legendFormat": "{{deployment}}"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"fieldConfig": {
|
||
|
|
"defaults": { "unit": "percentunit", "max": 1, "thresholds": { "steps": [{"color":"green","value":null},{"color":"yellow","value":0.01},{"color":"red","value":0.05}] } }
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"title": "Latency p50 / p95 / p99",
|
||
|
|
"type": "timeseries",
|
||
|
|
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 8 },
|
||
|
|
"datasource": { "uid": "prometheus" },
|
||
|
|
"targets": [
|
||
|
|
{
|
||
|
|
"expr": "histogram_quantile(0.50, sum(rate(response_latency_ms_bucket{namespace=~\"$namespace\", deployment=~\"$deployment\", direction=\"inbound\"}[5m])) by (le, deployment))",
|
||
|
|
"legendFormat": "{{deployment}} p50"
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{namespace=~\"$namespace\", deployment=~\"$deployment\", direction=\"inbound\"}[5m])) by (le, deployment))",
|
||
|
|
"legendFormat": "{{deployment}} p95"
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"expr": "histogram_quantile(0.99, sum(rate(response_latency_ms_bucket{namespace=~\"$namespace\", deployment=~\"$deployment\", direction=\"inbound\"}[5m])) by (le, deployment))",
|
||
|
|
"legendFormat": "{{deployment}} p99"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"fieldConfig": { "defaults": { "unit": "ms" } }
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"title": "Request Rate by Status Code",
|
||
|
|
"type": "timeseries",
|
||
|
|
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 16 },
|
||
|
|
"datasource": { "uid": "prometheus" },
|
||
|
|
"targets": [
|
||
|
|
{
|
||
|
|
"expr": "sum(rate(response_total{namespace=~\"$namespace\", deployment=~\"$deployment\", direction=\"inbound\"}[5m])) by (deployment, status_code)",
|
||
|
|
"legendFormat": "{{deployment}} {{status_code}}"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"fieldConfig": { "defaults": { "unit": "reqps" } }
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"title": "TCP Connections",
|
||
|
|
"type": "timeseries",
|
||
|
|
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 16 },
|
||
|
|
"datasource": { "uid": "prometheus" },
|
||
|
|
"targets": [
|
||
|
|
{
|
||
|
|
"expr": "tcp_open_connections{namespace=~\"$namespace\", deployment=~\"$deployment\", direction=\"inbound\"}",
|
||
|
|
"legendFormat": "{{deployment}}"
|
||
|
|
}
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"schemaVersion": 39,
|
||
|
|
"tags": ["lasuite", "linkerd", "golden-signals"],
|
||
|
|
"templating": {
|
||
|
|
"list": [
|
||
|
|
{
|
||
|
|
"name": "namespace",
|
||
|
|
"type": "query",
|
||
|
|
"datasource": { "uid": "prometheus" },
|
||
|
|
"query": "label_values(request_total{direction=\"inbound\"}, namespace)",
|
||
|
|
"refresh": 2,
|
||
|
|
"multi": true,
|
||
|
|
"includeAll": true,
|
||
|
|
"allValue": ".*"
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "deployment",
|
||
|
|
"type": "query",
|
||
|
|
"datasource": { "uid": "prometheus" },
|
||
|
|
"query": "label_values(request_total{direction=\"inbound\", namespace=~\"$namespace\"}, deployment)",
|
||
|
|
"refresh": 2,
|
||
|
|
"multi": true,
|
||
|
|
"includeAll": true,
|
||
|
|
"allValue": ".*"
|
||
|
|
}
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"time": { "from": "now-1h", "to": "now" },
|
||
|
|
"title": "La Suite — Golden Signals",
|
||
|
|
"uid": "lasuite-golden"
|
||
|
|
}
|