Improve docker config

2025-07-20 02:16:51 +02:00
parent 9a67f3d175
commit 1c730c3c81
27 changed files with 2598 additions and 1161 deletions
--- a/infrastructure/monitoring/grafana/dashboards/dashboard.yml
+++ b/infrastructure/monitoring/grafana/dashboards/dashboard.yml
@@ -1,11 +1,15 @@
+# infrastructure/monitoring/grafana/dashboards/dashboard.yml
+# Grafana dashboard provisioning
+
 apiVersion: 1

 providers:
-  - name: 'Bakery Forecasting'
+  - name: 'bakery-dashboards'
    orgId: 1
-    folder: ''
+    folder: 'Bakery Forecasting'
    type: file
    disableDeletion: false
    updateIntervalSeconds: 10
+    allowUiUpdates: true
    options:
      path: /etc/grafana/provisioning/dashboards
--- a/infrastructure/monitoring/grafana/datasources/prometheus.yml
+++ b/infrastructure/monitoring/grafana/datasources/prometheus.yml
@@ -1,3 +1,6 @@
+# infrastructure/monitoring/grafana/datasources/prometheus.yml
+# Grafana Prometheus datasource configuration
+
 apiVersion: 1

 datasources:
@@ -6,4 +9,20 @@ datasources:
    access: proxy
    url: http://prometheus:9090
    isDefault: true
+    version: 1
+    editable: true
+    jsonData:
+      timeInterval: "15s"
+      queryTimeout: "60s"
+      httpMethod: "POST"
+      exemplarTraceIdDestinations:
+        - name: trace_id
+          datasourceUid: jaeger
+
+  - name: Jaeger
+    type: jaeger
+    access: proxy
+    url: http://jaeger:16686
+    uid: jaeger
+    version: 1
    editable: true
--- a/infrastructure/monitoring/prometheus/prometheus.yml
+++ b/infrastructure/monitoring/prometheus/prometheus.yml
@@ -1,17 +1,30 @@
---
+# infrastructure/monitoring/prometheus/prometheus.yml
+# Prometheus configuration
+
 global:
  scrape_interval: 15s
  evaluation_interval: 15s
+  external_labels:
+    cluster: 'bakery-forecasting'
+    replica: 'prometheus-01'

 rule_files:
-  - "alerts.yml"
+  - "/etc/prometheus/rules/*.yml"
+
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets:
+          # - alertmanager:9093

 scrape_configs:
+  # Service discovery for microservices
  - job_name: 'gateway'
    static_configs:
      - targets: ['gateway:8000']
    metrics_path: '/metrics'
    scrape_interval: 30s
+    scrape_timeout: 10s

  - job_name: 'auth-service'
    static_configs:
@@ -49,11 +62,21 @@ scrape_configs:
    metrics_path: '/metrics'
    scrape_interval: 30s

+  # Infrastructure monitoring
  - job_name: 'redis'
    static_configs:
      - targets: ['redis:6379']
+    metrics_path: '/metrics'
+    scrape_interval: 30s

  - job_name: 'rabbitmq'
    static_configs:
      - targets: ['rabbitmq:15692']
+    metrics_path: '/metrics'
+    scrape_interval: 30s

+  # Database monitoring (requires postgres_exporter)
+  - job_name: 'postgres'
+    static_configs:
+      - targets: ['postgres-exporter:9187']
+    scrape_interval: 30s
--- a/infrastructure/monitoring/prometheus/rules/alerts.yml
+++ b/infrastructure/monitoring/prometheus/rules/alerts.yml
@@ -0,0 +1,86 @@
+# infrastructure/monitoring/prometheus/rules/alerts.yml
+# Prometheus alerting rules
+
+groups:
+  - name: bakery_services
+    rules:
+      # Service availability alerts
+      - alert: ServiceDown
+        expr: up == 0
+        for: 2m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Service {{ $labels.job }} is down"
+          description: "Service {{ $labels.job }} has been down for more than 2 minutes."
+
+      # High error rate alerts
+      - alert: HighErrorRate
+        expr: rate(http_requests_total{status=~"5.."}[5m]) > 0.1
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High error rate on {{ $labels.job }}"
+          description: "Error rate is {{ $value }} errors per second on {{ $labels.job }}."
+
+      # High response time alerts
+      - alert: HighResponseTime
+        expr: histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m])) > 1
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High response time on {{ $labels.job }}"
+          description: "95th percentile response time is {{ $value }}s on {{ $labels.job }}."
+
+      # Memory usage alerts
+      - alert: HighMemoryUsage
+        expr: process_resident_memory_bytes / 1024 / 1024 > 500
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High memory usage on {{ $labels.job }}"
+          description: "Memory usage is {{ $value }}MB on {{ $labels.job }}."
+
+      # Database connection alerts
+      - alert: DatabaseConnectionHigh
+        expr: pg_stat_activity_count > 80
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High database connections"
+          description: "Database has {{ $value }} active connections."
+
+  - name: bakery_business
+    rules:
+      # Training job alerts
+      - alert: TrainingJobFailed
+        expr: increase(training_jobs_failed_total[1h]) > 0
+        labels:
+          severity: warning
+        annotations:
+          summary: "Training job failed"
+          description: "{{ $value }} training jobs have failed in the last hour."
+
+      # Prediction accuracy alerts
+      - alert: LowPredictionAccuracy
+        expr: prediction_accuracy < 0.7
+        for: 15m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Low prediction accuracy"
+          description: "Prediction accuracy is {{ $value }} for tenant {{ $labels.tenant_id }}."
+
+      # API rate limit alerts
+      - alert: APIRateLimitHit
+        expr: increase(rate_limit_hits_total[5m]) > 10
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "API rate limit hit frequently"
+          description: "Rate limit has been hit {{ $value }} times in 5 minutes."
--- a/infrastructure/pgadmin/pgpass
+++ b/infrastructure/pgadmin/pgpass
@@ -0,0 +1,6 @@
+auth-db:5432:auth_db:auth_user:auth_pass123
+training-db:5432:training_db:training_user:training_pass123
+forecasting-db:5432:forecasting_db:forecasting_user:forecasting_pass123
+data-db:5432:data_db:data_user:data_pass123
+tenant-db:5432:tenant_db:tenant_user:tenant_pass123
+notification-db:5432:notification_db:notification_user:notification_pass123
--- a/infrastructure/pgadmin/servers.json
+++ b/infrastructure/pgadmin/servers.json
@@ -0,0 +1,64 @@
+{
+  "Servers": {
+    "1": {
+      "Name": "Auth Database",
+      "Group": "Bakery Services",
+      "Host": "auth-db",
+      "Port": 5432,
+      "MaintenanceDB": "auth_db",
+      "Username": "auth_user",
+      "PassFile": "/pgadmin4/pgpass",
+      "SSLMode": "prefer"
+    },
+    "2": {
+      "Name": "Training Database",
+      "Group": "Bakery Services",
+      "Host": "training-db",
+      "Port": 5432,
+      "MaintenanceDB": "training_db",
+      "Username": "training_user",
+      "PassFile": "/pgadmin4/pgpass",
+      "SSLMode": "prefer"
+    },
+    "3": {
+      "Name": "Forecasting Database",
+      "Group": "Bakery Services",
+      "Host": "forecasting-db",
+      "Port": 5432,
+      "MaintenanceDB": "forecasting_db",
+      "Username": "forecasting_user",
+      "PassFile": "/pgadmin4/pgpass",
+      "SSLMode": "prefer"
+    },
+    "4": {
+      "Name": "Data Database",
+      "Group": "Bakery Services",
+      "Host": "data-db",
+      "Port": 5432,
+      "MaintenanceDB": "data_db",
+      "Username": "data_user",
+      "PassFile": "/pgadmin4/pgpass",
+      "SSLMode": "prefer"
+    },
+    "5": {
+      "Name": "Tenant Database",
+      "Group": "Bakery Services",
+      "Host": "tenant-db",
+      "Port": 5432,
+      "MaintenanceDB": "tenant_db",
+      "Username": "tenant_user",
+      "PassFile": "/pgadmin4/pgpass",
+      "SSLMode": "prefer"
+    },
+    "6": {
+      "Name": "Notification Database",
+      "Group": "Bakery Services",
+      "Host": "notification-db",
+      "Port": 5432,
+      "MaintenanceDB": "notification_db",
+      "Username": "notification_user",
+      "PassFile": "/pgadmin4/pgpass",
+      "SSLMode": "prefer"
+    }
+  }
+}
--- a/infrastructure/postgres/init-scripts/init.sql
+++ b/infrastructure/postgres/init-scripts/init.sql
@@ -0,0 +1,26 @@
+-- Create extensions for all databases
+CREATE EXTENSION IF NOT EXISTS "uuid-ossp";
+CREATE EXTENSION IF NOT EXISTS "pg_stat_statements";
+CREATE EXTENSION IF NOT EXISTS "pg_trgm";
+
+-- Create Spanish collation for proper text sorting
+-- This will be used for bakery names, product names, etc.
+-- CREATE COLLATION IF NOT EXISTS spanish (provider = icu, locale = 'es-ES');
+
+-- Set timezone to Madrid
+SET timezone = 'Europe/Madrid';
+
+-- Performance tuning for small to medium databases
+ALTER SYSTEM SET shared_preload_libraries = 'pg_stat_statements';
+ALTER SYSTEM SET max_connections = 100;
+ALTER SYSTEM SET shared_buffers = '256MB';
+ALTER SYSTEM SET effective_cache_size = '1GB';
+ALTER SYSTEM SET maintenance_work_mem = '64MB';
+ALTER SYSTEM SET checkpoint_completion_target = 0.9;
+ALTER SYSTEM SET wal_buffers = '16MB';
+ALTER SYSTEM SET default_statistics_target = 100;
+ALTER SYSTEM SET random_page_cost = 1.1;
+ALTER SYSTEM SET effective_io_concurrency = 200;
+
+-- Reload configuration
+SELECT pg_reload_conf();
--- a/infrastructure/rabbitmq/definitions.json
+++ b/infrastructure/rabbitmq/definitions.json
@@ -0,0 +1,94 @@
+{
+  "rabbit_version": "3.12.0",
+  "rabbitmq_version": "3.12.0",
+  "product_name": "RabbitMQ",
+  "product_version": "3.12.0",
+  "users": [
+    {
+      "name": "bakery",
+      "password_hash": "hash_of_forecast123",
+      "hashing_algorithm": "rabbit_password_hashing_sha256",
+      "tags": ["administrator"]
+    }
+  ],
+  "vhosts": [
+    {
+      "name": "/"
+    }
+  ],
+  "permissions": [
+    {
+      "user": "bakery",
+      "vhost": "/",
+      "configure": ".*",
+      "write": ".*",
+      "read": ".*"
+    }
+  ],
+  "exchanges": [
+    {
+      "name": "bakery_events",
+      "vhost": "/",
+      "type": "topic",
+      "durable": true,
+      "auto_delete": false,
+      "internal": false,
+      "arguments": {}
+    }
+  ],
+  "queues": [
+    {
+      "name": "training_events",
+      "vhost": "/",
+      "durable": true,
+      "auto_delete": false,
+      "arguments": {
+        "x-message-ttl": 86400000
+      }
+    },
+    {
+      "name": "forecasting_events",
+      "vhost": "/",
+      "durable": true,
+      "auto_delete": false,
+      "arguments": {
+        "x-message-ttl": 86400000
+      }
+    },
+    {
+      "name": "notification_events",
+      "vhost": "/",
+      "durable": true,
+      "auto_delete": false,
+      "arguments": {
+        "x-message-ttl": 86400000
+      }
+    }
+  ],
+  "bindings": [
+    {
+      "source": "bakery_events",
+      "vhost": "/",
+      "destination": "training_events",
+      "destination_type": "queue",
+      "routing_key": "training.*",
+      "arguments": {}
+    },
+    {
+      "source": "bakery_events",
+      "vhost": "/",
+      "destination": "forecasting_events",
+      "destination_type": "queue",
+      "routing_key": "forecasting.*",
+      "arguments": {}
+    },
+    {
+      "source": "bakery_events",
+      "vhost": "/",
+      "destination": "notification_events",
+      "destination_type": "queue",
+      "routing_key": "notification.*",
+      "arguments": {}
+    }
+  ]
+}
--- a/infrastructure/rabbitmq/rabbitmq.conf
+++ b/infrastructure/rabbitmq/rabbitmq.conf
@@ -0,0 +1,26 @@
+# infrastructure/rabbitmq/rabbitmq.conf
+# RabbitMQ configuration file
+
+# Network settings
+listeners.tcp.default = 5672
+management.tcp.port = 15672
+
+# Memory and disk thresholds
+vm_memory_high_watermark.relative = 0.6
+disk_free_limit.relative = 2.0
+
+# Default user (will be overridden by environment variables)
+default_user = bakery
+default_pass = forecast123
+default_vhost = /
+
+# Management plugin
+management.load_definitions = /etc/rabbitmq/definitions.json
+
+# Logging
+log.console = true
+log.console.level = info
+log.file = false
+
+# Queue settings
+queue_master_locator = min-masters
--- a/infrastructure/redis/redis.conf
+++ b/infrastructure/redis/redis.conf
@@ -0,0 +1,51 @@
+# infrastructure/redis/redis.conf
+# Redis configuration file
+
+# Network settings
+bind 0.0.0.0
+port 6379
+timeout 300
+tcp-keepalive 300
+
+# General settings
+daemonize no
+supervised no
+pidfile /var/run/redis_6379.pid
+loglevel notice
+logfile ""
+
+# Persistence settings
+save 900 1
+save 300 10
+save 60 10000
+stop-writes-on-bgsave-error yes
+rdbcompression yes
+rdbchecksum yes
+dbfilename dump.rdb
+dir ./
+
+# Append only file settings
+appendonly yes
+appendfilename "appendonly.aof"
+appendfsync everysec
+no-appendfsync-on-rewrite no
+auto-aof-rewrite-percentage 100
+auto-aof-rewrite-min-size 64mb
+aof-load-truncated yes
+
+# Memory management
+maxmemory 512mb
+maxmemory-policy allkeys-lru
+maxmemory-samples 5
+
+# Security
+requirepass redis_pass123
+
+# Slow log
+slowlog-log-slower-than 10000
+slowlog-max-len 128
+
+# Client output buffer limits
+client-output-buffer-limit normal 0 0 0
+client-output-buffer-limit replica 256mb 64mb 60
+client-output-buffer-limit pubsub 32mb 8mb 60