554 lines
14 KiB
YAML
554 lines
14 KiB
YAML
apiVersion: monitoring.coreos.com/v1
|
|
kind: Probe
|
|
metadata:
|
|
name: <namespace>-<env>-<endpoint>-probe
|
|
namespace: monitoring
|
|
labels:
|
|
release: kube-prometheus-stack
|
|
spec:
|
|
jobName: <namespace>-<env>-<endpoint>-probe
|
|
interval: 30s
|
|
scrapeTimeout: 15s
|
|
module: http_2xx
|
|
prober:
|
|
url: blackbox-exporter.monitoring.svc.cluster.local:9115
|
|
scheme: http
|
|
path: /probe
|
|
targets:
|
|
staticConfig:
|
|
static:
|
|
- https://<endpoint>
|
|
---
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: <namespace>-<env>-<endpoint>-dashboard
|
|
namespace: monitoring
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
data:
|
|
<namespace>-<env>-<endpoint>-dashboard.json: |
|
|
{
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"type": "stat",
|
|
"title": "Services UP",
|
|
"id": 1,
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 6,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "sum(probe_success{job=\"<namespace>-<env>-<endpoint>-probe\",instance=~\"$instance\"})"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "red",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 1
|
|
}
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"options": {
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"orientation": "auto",
|
|
"textMode": "auto",
|
|
"colorMode": "value",
|
|
"graphMode": "none"
|
|
}
|
|
},
|
|
{
|
|
"type": "stat",
|
|
"title": "Services DOWN",
|
|
"id": 2,
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 6,
|
|
"x": 6,
|
|
"y": 0
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "count(probe_success{job=\"<namespace>-<env>-<endpoint>-probe\",instance=~\"$instance\"}) - sum(probe_success{job=\"<namespace>-<env>-<endpoint>-probe\",instance=~\"$instance\"})"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 1
|
|
}
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"options": {
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"orientation": "auto",
|
|
"textMode": "auto",
|
|
"colorMode": "value",
|
|
"graphMode": "none"
|
|
}
|
|
},
|
|
{
|
|
"type": "stat",
|
|
"title": "Availability 24h",
|
|
"id": 3,
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 6,
|
|
"x": 12,
|
|
"y": 0
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "avg(avg_over_time(probe_success{job=\"<namespace>-<env>-<endpoint>-probe\",instance=~\"$instance\"}[24h])) * 100"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"min": 0,
|
|
"max": 100,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "red",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 99
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 99.9
|
|
}
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"options": {
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"orientation": "auto",
|
|
"textMode": "auto",
|
|
"colorMode": "value",
|
|
"graphMode": "area"
|
|
}
|
|
},
|
|
{
|
|
"type": "stat",
|
|
"title": "Avg Latency",
|
|
"id": 4,
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 6,
|
|
"x": 18,
|
|
"y": 0
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "avg(probe_duration_seconds{job=\"<namespace>-<env>-<endpoint>-probe\",instance=~\"$instance\"}) * 1000"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"decimals": 0
|
|
}
|
|
},
|
|
"options": {
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"orientation": "auto",
|
|
"textMode": "auto",
|
|
"colorMode": "value",
|
|
"graphMode": "none"
|
|
}
|
|
},
|
|
{
|
|
"type": "table",
|
|
"title": "HTTP Services Status",
|
|
"id": 5,
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 5
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "probe_success{job=\"<namespace>-<env>-<endpoint>-probe\",instance=~\"$instance\"}",
|
|
"instant": true,
|
|
"format": "table"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"align": "auto",
|
|
"cellOptions": {
|
|
"type": "color-text"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"transformations": [
|
|
{
|
|
"id": "organize",
|
|
"options": {
|
|
"excludeByName": {
|
|
"Time": true
|
|
},
|
|
"renameByName": {
|
|
"Value": "Status",
|
|
"instance": "Service"
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"options": {
|
|
"showHeader": true,
|
|
"cellHeight": "sm"
|
|
}
|
|
},
|
|
{
|
|
"type": "table",
|
|
"title": "HTTP Status Code",
|
|
"id": 6,
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 5
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "probe_http_status_code{job=\"<namespace>-<env>-<endpoint>-probe\",instance=~\"$instance\"}",
|
|
"instant": true,
|
|
"format": "table"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"align": "auto",
|
|
"cellOptions": {
|
|
"type": "color-text"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"transformations": [
|
|
{
|
|
"id": "organize",
|
|
"options": {
|
|
"excludeByName": {
|
|
"Time": true
|
|
},
|
|
"renameByName": {
|
|
"Value": "HTTP Status",
|
|
"instance": "Service"
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"options": {
|
|
"showHeader": true,
|
|
"cellHeight": "sm"
|
|
}
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "HTTP Response Time",
|
|
"id": 7,
|
|
"gridPos": {
|
|
"h": 9,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 13
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "probe_duration_seconds{job=\"<namespace>-<env>-<endpoint>-probe\",instance=~\"$instance\"} * 1000",
|
|
"legendFormat": "{{instance}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"decimals": 0
|
|
}
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom"
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "table",
|
|
"title": "Currently DOWN",
|
|
"id": 8,
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 22
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "probe_success{job=\"<namespace>-<env>-<endpoint>-probe\",instance=~\"$instance\"} == 0",
|
|
"instant": true,
|
|
"format": "table"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"cellOptions": {
|
|
"type": "color-text"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"transformations": [
|
|
{
|
|
"id": "organize",
|
|
"options": {
|
|
"excludeByName": {
|
|
"Time": true
|
|
},
|
|
"renameByName": {
|
|
"Value": "Status",
|
|
"instance": "Service"
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"options": {
|
|
"showHeader": true,
|
|
"cellHeight": "sm"
|
|
}
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "Availability 24h",
|
|
"id": 9,
|
|
"gridPos": {
|
|
"h": 9,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 22
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "avg_over_time(probe_success{job=\"<namespace>-<env>-<endpoint>-probe\",instance=~\"$instance\"}[24h]) * 100",
|
|
"legendFormat": "{{instance}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"min": 0,
|
|
"max": 100,
|
|
"decimals": 2
|
|
}
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom"
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "P95 Latency - 1h",
|
|
"id": 10,
|
|
"gridPos": {
|
|
"h": 9,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 31
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "quantile_over_time(0.95, probe_duration_seconds{job=\"<namespace>-<env>-<endpoint>-probe\",instance=~\"$instance\"}[1h]) * 1000",
|
|
"legendFormat": "{{instance}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"decimals": 0
|
|
}
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom"
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"refresh": "30s",
|
|
"schemaVersion": 41,
|
|
"tags": [
|
|
"blackbox",
|
|
"http",
|
|
"monitoring"
|
|
],
|
|
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "instance",
|
|
"label": "Service",
|
|
"type": "query",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"definition": "label_values(probe_success{job=\"<namespace>-<env>-<endpoint>-probe\"}, instance)",
|
|
"query": {
|
|
"query": "label_values(probe_success{job=\"<namespace>-<env>-<endpoint>-probe\"}, instance)",
|
|
"refId": "StandardVariableQuery"
|
|
},
|
|
"includeAll": true,
|
|
"multi": true,
|
|
"allValue": ".*",
|
|
"refresh": 1,
|
|
"sort": 1
|
|
}
|
|
]
|
|
},
|
|
"time": {
|
|
"from": "now-24h",
|
|
"to": "now"
|
|
},
|
|
"timepicker": {},
|
|
"timezone": "browser",
|
|
"title": "<namespace>-<env>-<endpoint>-dashboard",
|
|
"uid": "<namespace>-<env>-<endpoint>-dashboard",
|
|
"version": 1,
|
|
"weekStart": ""
|
|
}
|