This commit is contained in:
Toby
2026-01-27 17:35:45 -05:00
commit 2639af6531
176 changed files with 27104 additions and 0 deletions
@@ -0,0 +1,198 @@
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"editable": true,
"gnetId": null,
"graphTooltip": 0,
"id": null,
"links": [],
"panels": [
{
"datasource": "Prometheus",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{"color": "green", "value": null},
{"color": "yellow", "value": 70},
{"color": "red", "value": 90}
]
},
"unit": "percent"
}
},
"gridPos": {"h": 8, "w": 6, "x": 0, "y": 0},
"id": 1,
"options": {
"reduceOptions": {
"calcs": ["lastNotNull"],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true
},
"pluginVersion": "8.0.0",
"targets": [
{
"expr": "100 - (avg(irate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100)",
"refId": "A"
}
],
"title": "CPU Usage",
"type": "gauge"
},
{
"datasource": "Prometheus",
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{"color": "green", "value": null},
{"color": "yellow", "value": 70},
{"color": "red", "value": 90}
]
},
"unit": "percent"
}
},
"gridPos": {"h": 8, "w": 6, "x": 6, "y": 0},
"id": 2,
"options": {
"reduceOptions": {
"calcs": ["lastNotNull"],
"fields": "",
"values": false
}
},
"targets": [
{
"expr": "(1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100",
"refId": "A"
}
],
"title": "Memory Usage",
"type": "gauge"
},
{
"datasource": "Prometheus",
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"custom": {
"axisLabel": "",
"axisPlacement": "auto",
"drawStyle": "line",
"fillOpacity": 10,
"lineInterpolation": "linear",
"lineWidth": 1,
"showPoints": "never"
},
"unit": "reqps"
}
},
"gridPos": {"h": 8, "w": 12, "x": 12, "y": 0},
"id": 3,
"options": {
"legend": {"displayMode": "list", "placement": "bottom"},
"tooltip": {"mode": "single"}
},
"targets": [
{
"expr": "sum(rate(http_requests_total[5m])) by (status)",
"legendFormat": "{{status}}",
"refId": "A"
}
],
"title": "Request Rate by Status",
"type": "timeseries"
},
{
"datasource": "Prometheus",
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"custom": {
"drawStyle": "line",
"fillOpacity": 10,
"lineWidth": 1
},
"unit": "s"
}
},
"gridPos": {"h": 8, "w": 12, "x": 0, "y": 8},
"id": 4,
"targets": [
{
"expr": "histogram_quantile(0.95, sum(rate(http_request_duration_seconds_bucket[5m])) by (le))",
"legendFormat": "P95",
"refId": "A"
},
{
"expr": "histogram_quantile(0.50, sum(rate(http_request_duration_seconds_bucket[5m])) by (le))",
"legendFormat": "P50",
"refId": "B"
}
],
"title": "Request Latency",
"type": "timeseries"
},
{
"datasource": "Prometheus",
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"custom": {
"drawStyle": "line",
"fillOpacity": 10
},
"unit": "percent"
}
},
"gridPos": {"h": 8, "w": 12, "x": 12, "y": 8},
"id": 5,
"targets": [
{
"expr": "sum(rate(http_requests_total{status=~\"5..\"}[5m])) / sum(rate(http_requests_total[5m])) * 100",
"legendFormat": "Error Rate",
"refId": "A"
}
],
"title": "Error Rate",
"type": "timeseries"
}
],
"schemaVersion": 30,
"style": "dark",
"tags": ["template", "prometheus"],
"templating": {
"list": []
},
"time": {
"from": "now-1h",
"to": "now"
},
"timepicker": {},
"timezone": "",
"title": "Application Dashboard Template",
"version": 1
}
@@ -0,0 +1,115 @@
# Prometheus Configuration Template
# Customize for your environment
global:
scrape_interval: 15s
evaluation_interval: 15s
external_labels:
cluster: production
environment: prod
# Alertmanager configuration
alerting:
alertmanagers:
- static_configs:
- targets:
- alertmanager:9093
# Rule files
rule_files:
- /etc/prometheus/rules/*.yaml
# Scrape configurations
scrape_configs:
# Prometheus self-monitoring
- job_name: 'prometheus'
static_configs:
- targets: ['localhost:9090']
# Node Exporter
- job_name: 'node'
static_configs:
- targets:
- 'node1:9100'
- 'node2:9100'
- 'node3:9100'
# Kubernetes API Server
- job_name: 'kubernetes-apiservers'
kubernetes_sd_configs:
- role: endpoints
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
relabel_configs:
- source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
action: keep
regex: default;kubernetes;https
# Kubernetes Nodes
- job_name: 'kubernetes-nodes'
kubernetes_sd_configs:
- role: node
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
# Kubernetes Pods with prometheus.io annotations
- job_name: 'kubernetes-pods'
kubernetes_sd_configs:
- role: pod
relabel_configs:
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
action: keep
regex: true
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
action: replace
target_label: __metrics_path__
regex: (.+)
- source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
action: replace
regex: ([^:]+)(?::\d+)?;(\d+)
replacement: $1:$2
target_label: __address__
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: kubernetes_namespace
- source_labels: [__meta_kubernetes_pod_name]
action: replace
target_label: kubernetes_pod_name
# Kubernetes Services with prometheus.io annotations
- job_name: 'kubernetes-services'
kubernetes_sd_configs:
- role: service
metrics_path: /probe
params:
module: [http_2xx]
relabel_configs:
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_probe]
action: keep
regex: true
- source_labels: [__address__]
target_label: __param_target
- target_label: __address__
replacement: blackbox-exporter:9115
- source_labels: [__param_target]
target_label: instance
- action: labelmap
regex: __meta_kubernetes_service_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
target_label: kubernetes_namespace
- source_labels: [__meta_kubernetes_service_name]
target_label: kubernetes_name
# Remote write (optional - for long-term storage)
# remote_write:
# - url: "http://thanos-receive:19291/api/v1/receive"