Sets up Prometheus for comprehensive metrics collection, storage, and monitoring of infrastructure and applications. Use this when implementing metrics collection, deploying monitoring infrastructure, or configuring alerting systems.
English | 日本語
Prometheusのセットアップ、メトリクス収集、スクレイプ設定、レコーディングルールの完全ガイド。
インフラストラクチャとアプリケーションの包括的なメトリクス収集、アラート、モニタリングのためのPrometheusを設定します。
┌──────────────┐
│ Applications │ ← クライアントライブラリで計装
└──────┬───────┘
│ /metricsエンドポイント
↓
┌──────────────┐
│ Prometheus │ ← 定期的にメトリクスをスクレイプ
│ Server │
└──────┬───────┘
│
├─→ AlertManager（アラート）
├─→ Grafana（可視化）
└─→ 長期ストレージ（Thanos/Cortex）
helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
helm repo update
helm install prometheus prometheus-community/kube-prometheus-stack \
--namespace monitoring \
--create-namespace \
--set prometheus.prometheusSpec.retention=30d \
--set prometheus.prometheusSpec.storageVolumeSize=50Gi
version: '3.8'
services:
prometheus:
image: prom/prometheus:latest
ports:
- "9090:9090"
volumes:
- ./prometheus.yml:/etc/prometheus/prometheus.yml
- prometheus-data:/prometheus
command:
- '--config.file=/etc/prometheus/prometheus.yml'
- '--storage.tsdb.path=/prometheus'
- '--storage.tsdb.retention.time=30d'
volumes:
prometheus-data:
prometheus.yml:
global:
scrape_interval: 15s
evaluation_interval: 15s
external_labels:
cluster: 'production'
region: 'us-west-2'
# Alertmanager設定
alerting:
alertmanagers:
- static_configs:
- targets:
- alertmanager:9093
# ルールファイルの読み込み
rule_files:
- /etc/prometheus/rules/*.yml
# スクレイプ設定
scrape_configs:
# Prometheus自身
- job_name: 'prometheus'
static_configs:
- targets: ['localhost:9090']
# Nodeエクスポーター
- job_name: 'node-exporter'
static_configs:
- targets:
- 'node1:9100'
- 'node2:9100'
- 'node3:9100'
relabel_configs:
- source_labels: [__address__]
target_label: instance
regex: '([^:]+)(:[0-9]+)?'
replacement: '${1}'
# アノテーション付きKubernetes Pod
- 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__
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: namespace
- source_labels: [__meta_kubernetes_pod_name]
action: replace
target_label: pod
# アプリケーションメトリクス
- job_name: 'my-app'
static_configs:
- targets:
- 'app1.example.com:9090'
- 'app2.example.com:9090'
metrics_path: '/metrics'
scheme: 'https'
tls_config:
ca_file: /etc/prometheus/ca.crt
cert_file: /etc/prometheus/client.crt
key_file: /etc/prometheus/client.key
参照: assets/prometheus.yml.templateを参照
scrape_configs:
- job_name: 'static-targets'
static_configs:
- targets: ['host1:9100', 'host2:9100']
labels:
env: 'production'
region: 'us-west-2'
scrape_configs:
- job_name: 'file-sd'
file_sd_configs:
- files:
- /etc/prometheus/targets/*.json
- /etc/prometheus/targets/*.yml
refresh_interval: 5m
targets/production.json:
[
{
"targets": ["app1:9090", "app2:9090"],
"labels": {
"env": "production",
"service": "api"
}
}
]
scrape_configs:
- job_name: 'kubernetes-services'
kubernetes_sd_configs:
- role: service
relabel_configs:
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
action: keep
regex: true
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
action: replace
target_label: __scheme__
regex: (https?)
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
action: replace
target_label: __metrics_path__
regex: (.+)
参照: references/scrape-configs.mdを参照
頻繁にクエリされる式のために事前計算されたメトリクスを作成します：
# /etc/prometheus/rules/recording_rules.yml
groups:
- name: api_metrics
interval: 15s
rules:
# サービスごとのHTTPリクエスト率
- record: job:http_requests:rate5m
expr: sum by (job) (rate(http_requests_total[5m]))
# エラー率パーセンテージ
- record: job:http_requests_errors:rate5m
expr: sum by (job) (rate(http_requests_total{status=~"5.."}[5m]))
- record: job:http_requests_error_rate:percentage
expr: |
(job:http_requests_errors:rate5m / job:http_requests:rate5m) * 100
# P95レイテンシ
- record: job:http_request_duration:p95
expr: |
histogram_quantile(0.95,
sum by (job, le) (rate(http_request_duration_seconds_bucket[5m]))
)
- name: resource_metrics
interval: 30s
rules:
# CPU使用率パーセンテージ
- record: instance:node_cpu:utilization
expr: |
100 - (avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100)
# メモリ使用率パーセンテージ
- record: instance:node_memory:utilization
expr: |
100 - ((node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100)
# ディスク使用率パーセンテージ
- record: instance:node_disk:utilization
expr: |
100 - ((node_filesystem_avail_bytes / node_filesystem_size_bytes) * 100)
参照: references/recording-rules.mdを参照
# /etc/prometheus/rules/alert_rules.yml
groups:
- name: availability
interval: 30s
rules:
- alert: ServiceDown
expr: up{job="my-app"} == 0
for: 1m
labels:
severity: critical
annotations:
summary: "Service {{ $labels.instance }} is down"
description: "{{ $labels.job }} has been down for more than 1 minute"
- alert: HighErrorRate
expr: job:http_requests_error_rate:percentage > 5
for: 5m
labels:
severity: warning
annotations:
summary: "High error rate for {{ $labels.job }}"
description: "Error rate is {{ $value }}% (threshold: 5%)"
- alert: HighLatency
expr: job:http_request_duration:p95 > 1
for: 5m
labels:
severity: warning
annotations:
summary: "High latency for {{ $labels.job }}"
description: "P95 latency is {{ $value }}s (threshold: 1s)"
- name: resources
interval: 1m
rules:
- alert: HighCPUUsage
expr: instance:node_cpu:utilization > 80
for: 5m
labels:
severity: warning
annotations:
summary: "High CPU usage on {{ $labels.instance }}"
description: "CPU usage is {{ $value }}%"
- alert: HighMemoryUsage
expr: instance:node_memory:utilization > 85
for: 5m
labels:
severity: warning
annotations:
summary: "High memory usage on {{ $labels.instance }}"
description: "Memory usage is {{ $value }}%"
- alert: DiskSpaceLow
expr: instance:node_disk:utilization > 90
for: 5m
labels:
severity: critical
annotations:
summary: "Low disk space on {{ $labels.instance }}"
description: "Disk usage is {{ $value }}%"
# 設定の検証
promtool check config prometheus.yml
# ルールの検証
promtool check rules /etc/prometheus/rules/*.yml
# クエリのテスト
promtool query instant http://localhost:9090 'up'
参照: scripts/validate-prometheus.shを参照
スクレイプターゲットを確認:
curl http://localhost:9090/api/v1/targets
設定を確認:
curl http://localhost:9090/api/v1/status/config
クエリをテスト:
curl 'http://localhost:9090/api/v1/query?query=up'
assets/prometheus.yml.template - 完全な設定テンプレートreferences/scrape-configs.md - スクレイプ設定パターンreferences/recording-rules.md - レコーディングルールの例scripts/validate-prometheus.sh - 検証スクリプトgrafana-dashboards - 可視化のためslo-implementation - SLOモニタリングのためdistributed-tracing - リクエストトレーシングのためnpx skills add amurata/prometheus-configuration下载完整 Skill 目录，包含 SKILL.md 及所有相关文件
Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Start voice calls via the OpenClaw voice-call plugin.
Notion API for creating and managing pages, databases, and blocks.
Gemini CLI for one-shot Q&A, summaries, and generation.
Category:developer