grafana e prometeus

monitoring/alertmanager/config.yml

@@ -0,0 +1,53 @@
+global:
+  resolve_timeout: 5m
+  # Configurar esses valores com informações reais
+  smtp_smarthost: 'smtp.example.com:587'
+  smtp_from: 'alertmanager@example.com'
+  smtp_auth_username: 'alertmanager@example.com'
+  smtp_auth_password: 'password'
+  # Opcional: configuração para Slack
+  slack_api_url: 'https://hooks.slack.com/services/T00000000/B00000000/XXXXXXXXXXXXXXXXXXXXXXXX'
+
+route:
+  group_by: ['alertname', 'severity']
+  group_wait: 30s
+  group_interval: 5m
+  repeat_interval: 1h
+  receiver: 'team-emails'
+  routes:
+    - match:
+        severity: critical
+      receiver: 'team-pager'
+      continue: true
+    - match:
+        severity: warning
+      receiver: 'team-emails'
+
+receivers:
+  - name: 'team-emails'
+    email_configs:
+      - to: 'team@example.com'
+        send_resolved: true
+        html: '{{ template "email.html" . }}'
+        headers:
+          Subject: '{{ template "email.subject" . }}'
+  
+  - name: 'team-pager'
+    slack_configs:
+      - channel: '#alerts'
+        send_resolved: true
+        icon_emoji: ':warning:'
+        title: '{{ template "slack.title" . }}'
+        text: '{{ template "slack.text" . }}'
+    # Adicione aqui outros sistemas de notificação para alertas críticos
+    # Por exemplo: webhook, PagerDuty, etc.
+
+templates:
+  - '/etc/alertmanager/templates/*.tmpl'
+
+inhibit_rules:
+  - source_match:
+      severity: 'critical'
+    target_match:
+      severity: 'warning'
+    equal: ['alertname'] 

monitoring/grafana/provisioning/dashboards/dashboard.yml

@@ -0,0 +1,11 @@
+apiVersion: 1
+
+providers:
+  - name: 'Prometheus'
+    orgId: 1
+    folder: ''
+    type: file
+    disableDeletion: false
+    editable: true
+    options:
+      path: /etc/grafana/provisioning/dashboards 

monitoring/grafana/provisioning/datasources/datasource.yml

@@ -0,0 +1,9 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    type: prometheus
+    access: proxy
+    url: http://prometheus:9090
+    isDefault: true
+    editable: false 

monitoring/prometheus/prometheus.yml

@@ -0,0 +1,28 @@
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+  scrape_timeout: 10s
+
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets:
+            - alertmanager:9093
+
+rule_files:
+  - "rules/*.yml"
+
+scrape_configs:
+  - job_name: 'prometheus'
+    static_configs:
+      - targets: ['localhost:9090']
+
+  - job_name: 'api-portaljuru'
+    metrics_path: '/metrics'
+    scrape_interval: 10s
+    static_configs:
+      - targets: ['host.docker.internal:8066']
+    
+  - job_name: 'node-exporter'
+    static_configs:
+      - targets: ['node-exporter:9100'] 

monitoring/prometheus/rules/portaljuru_alerts.yml

@@ -0,0 +1,52 @@
+groups:
+  - name: portaljuru_api
+    rules:
+      # Alerta se a API ficar inacessível por mais de 1 minuto
+      - alert: PortalJuruApiDown
+        expr: up{job="api-portaljuru"} == 0
+        for: 1m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Portal Jurunense API fora do ar"
+          description: "A API do Portal Jurunense está inacessível há pelo menos 1 minuto."
+
+      # Alerta se a taxa de erro HTTP for maior que 5% em 5 minutos
+      - alert: HighErrorRate
+        expr: sum(rate(http_request_total{job="api-portaljuru", statusCode=~"5.."}[5m])) / sum(rate(http_request_total{job="api-portaljuru"}[5m])) > 0.05
+        for: 2m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Taxa de erro elevada na API"
+          description: "A taxa de erros HTTP 5xx está acima de 5% nos últimos 5 minutos."
+
+      # Alerta se o tempo de resposta estiver muito alto
+      - alert: SlowResponseTime
+        expr: histogram_quantile(0.95, sum(rate(http_request_duration_seconds_bucket{job="api-portaljuru"}[5m])) by (le)) > 1
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Tempo de resposta elevado na API"
+          description: "95% das requisições estão levando mais de 1 segundo para completar."
+
+      # Alerta para uso alto de memória
+      - alert: HighMemoryUsage
+        expr: process_resident_memory_bytes{job="api-portaljuru"} > 350000000
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Uso elevado de memória"
+          description: "A API está usando mais de 350MB de memória por mais de 5 minutos."
+
+      # Alerta para pool de conexões quase esgotado
+      - alert: DatabaseConnectionPoolNearlyFull
+        expr: api_db_connection_pool_used{job="api-portaljuru"} / api_db_connection_pool_total{job="api-portaljuru"} > 0.8
+        for: 2m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Pool de conexões quase cheio"
+          description: "O pool de conexões está usando mais de 80% da capacidade máxima."