Adds Prometheus metrics (#60)

Added Prometheus Metrics

Gemfile

@@ -40,6 +40,9 @@ gem 'kredis'
 # Windows does not include zoneinfo files, so bundle the tzinfo-data gem
 gem 'tzinfo-data', platforms: %i[mingw mswin x64_mingw jruby]
 
+# Exposes Metrics
+gem 'prometheus_exporter'
+
 # vault for secrets management
 gem 'vault-rails'
 

Gemfile.lock

@@ -138,6 +138,8 @@ GEM
     parallel (1.23.0)
     parser (3.2.2.1)
       ast (~> 2.4.1)
+    prometheus_exporter (2.0.8)
+      webrick
     puma (5.6.5)
       nio4r (~> 2.0)
     racc (1.6.2)
@@ -204,6 +206,7 @@ GEM
     vault-rails (0.8.0)
       activesupport (>= 5.0)
       vault (~> 0.17)
+    webrick (1.8.1)
     websocket-driver (0.7.5)
       websocket-extensions (>= 0.1.0)
     websocket-extensions (0.1.5)
@@ -221,6 +224,7 @@ DEPENDENCIES
   hiredis
   jbuilder
   kredis
+  prometheus_exporter
   puma (~> 5.0)
   rack-cors
   rails (~> 7.0.4, >= 7.0.4.3)

app/controllers/registration_controller.rb

@@ -11,6 +11,7 @@ def create
     event_ids = params[:event_ids]
 
     unless validate_request(competitor_id, competition_id) && !event_ids.empty?
+      Metrics.registration_validation_errors_counter.increment
       return render json: { status: 'User cannot register for competition' }, status: :forbidden
     end
 
@@ -42,6 +43,7 @@ def update
     status = params[:status]
 
     unless validate_request(competitor_id, competition_id, status)
+      Metrics.registration_validation_errors_counter.increment
       return render json: { status: 'User cannot register, wrong format' }, status: :forbidden
     end
 
@@ -67,7 +69,8 @@ def update
                             })
       render json: { status: 'ok' }
     rescue Aws::DynamoDB::Errors::ServiceError => e
-      puts e # TODO: Expose this as a metric
+      puts e
+      Metrics.registration_dynamodb_errors_counter.increment
       render json: { status: 'Failed to update registration data' }, status: :internal_server_error
     end
   end
@@ -77,6 +80,7 @@ def delete
     competition_id = params[:competition_id]
 
     unless validate_request(competitor_id, competition_id)
+      Metrics.registration_validation_errors_counter.increment
       return render json: { status: 'User cannot register, wrong format' }, status: :forbidden
     end
 
@@ -97,7 +101,8 @@ def delete
       render json: { status: 'ok' }
     rescue Aws::DynamoDB::Errors::ServiceError => e
       # Render an error response
-      puts e # TODO: Expose this as a metric
+      puts e
+      Metrics.registration_dynamodb_errors_counter.increment
       render json: { status: "Error deleting item from DynamoDB: #{e.message}" },
              status: :internal_server_error
     end
@@ -106,8 +111,14 @@ def delete
   def list
     competition_id = params[:competition_id]
     registrations = get_registrations(competition_id)
-
+    # Render a success response
     render json: registrations
+  rescue Aws::DynamoDB::Errors::ServiceError => e
+    # Render an error response
+    puts e
+    Metrics.registration_dynamodb_errors_counter.increment
+    render json: { status: "Error getting registrations" },
+           status: :internal_server_error
   end
 
   private
@@ -133,9 +144,7 @@ def can_user_register?(competitor_id, competition_id)
 
     def validate_request(competitor_id, competition_id, status = 'waiting')
       if competitor_id.present? && competitor_id =~ (/^\d{4}[a-zA-Z]{4}\d{2}$/)
-        puts 'correct competitor_id'
         if competition_id =~ (/^[a-zA-Z]+\d{4}$/) && REGISTRATION_STATUS.include?(status)
-          puts 'correct competition id and status'
           can_user_register?(competitor_id, competition_id)
         end
       else

app/helpers/competition_api.rb

@@ -12,7 +12,7 @@ def self.check_competition(competition_id)
       body = JSON.parse res.body
       body['registration_open'].present?
     else
-      # The Competition Service is unreachable TODO We should track this as a metric
+      Metrics.registration_competition_api_error_counter.increment
       puts 'network request failed'
       false
     end

app/helpers/competitor_api.rb

@@ -7,13 +7,20 @@
 class CompetitorApi
   def self.check_competitor(competitor_id)
     uri = URI("https://www.worldcubeassociation.org/api/v0/users/#{competitor_id}")
-    res = Net::HTTP.get_response(uri)
-    if res.is_a?(Net::HTTPSuccess)
-      body = JSON.parse res.body
-      body['user'].present?
-    else
-      # The Competitor Service is unreachable TODO We should track this as a metric
-      puts 'network request failed'
+    begin
+      res = Net::HTTP.get_response(uri)
+      if res.is_a?(Net::HTTPSuccess)
+        body = JSON.parse res.body
+        body['user'].present?
+      else
+        # The Competitor Service is unreachable
+        Metrics.registration_competitor_api_error_counter.increment
+        puts 'network request failed'
+        false
+      end
+    rescue StandardError => _e
+      puts 'The service does not have internet'
+      Metrics.registration_competitor_api_error_counter.increment
       false
     end
   end

app/helpers/metrics.rb

@@ -0,0 +1,7 @@
+# frozen_string_literal: true
+
+module Metrics
+  class << self
+    attr_accessor :registration_validation_errors_counter, :registration_dynamodb_errors_counter, :registrations_counter, :registration_competition_api_error_counter, :registration_competitor_api_error_counter
+  end
+end

app/worker/queue_poller.rb

@@ -2,6 +2,9 @@
 
 require 'json'
 require 'aws-sdk-sqs'
+require 'prometheus_exporter/client'
+require 'prometheus_exporter/instrumentation'
+require 'prometheus_exporter/metric'
 require_relative 'registration_processor'
 
 class QueuePoller
@@ -11,6 +14,18 @@ class QueuePoller
   MAX_MESSAGES = 10
 
   def self.perform
+    PrometheusExporter::Client.default = PrometheusExporter::Client.new(host: ENV.fetch("PROMETHEUS_EXPORTER"), port: 9091)
+    # Instrumentation of the worker process is currently disabled per https://github.com/discourse/prometheus_exporter/issues/282
+    if ENV.fetch("ENVIRONMENT", "dev") == "staging"
+      PrometheusExporter::Instrumentation::Process.start(type: "wca-registration-worker-staging", labels: { process: "1" })
+      @suffix = "-staging"
+    else
+      # PrometheusExporter::Instrumentation::Process.start(type: "wca-registration-worker", labels: { process: "1" })
+      @suffix = ""
+    end
+    registrations_counter = PrometheusExporter::Client.default.register("counter", "registrations_counter-#{@suffix}", "The number of Registrations processed")
+    error_counter = PrometheusExporter::Client.default.register("counter", "worker_error_counter-#{@suffix}", "The number of Errors in the worker")
+
     @sqs ||= if ENV['LOCALSTACK_ENDPOINT']
                Aws::SQS::Client.new(endpoint: ENV['LOCALSTACK_ENDPOINT'])
              else
@@ -27,10 +42,12 @@ def self.perform
         body = JSON.parse msg.body
         begin
           RegistrationProcessor.process_message(body)
+          registrations_counter.increment
         rescue StandardError => e
           # unexpected error occurred while processing messages,
           # log it, and skip delete so it can be re-processed later
           puts "Error #{e} when processing message with ID #{msg}"
+          error_counter.increment
           throw :skip_delete
         end
       end

config/application.rb

@@ -12,7 +12,7 @@ module WcaRegistration
   class Application < Rails::Application
     # Initialize configuration defaults for originally generated Rails version.
     config.load_defaults 7.0
-
+    config.autoload_paths << "#{root}/lib/**"
     # Only loads a smaller set of middleware suitable for API only apps.
     # Middleware like session, flash, cookies can be added back manually.
     # Skip views, helpers and assets when generating a new resource.

config/initializers/cors.rb

@@ -21,11 +21,18 @@
 else
   Rails.application.config.middleware.insert_before 0, Rack::Cors do
     allow do
-      origins '*.worldcubeassociation.org', 'http://test.registration.worldcubeassociation.org.s3-website-us-west-2.amazonaws.com'
+      origins 'https://www.worldcubeassociation.org', 'https://test-registration.worldcubeassociation.org/', 'http://test.registration.worldcubeassociation.org.s3-website-us-west-2.amazonaws.com'
 
       resource '*',
                headers: :any,
                methods: %i[get post put patch delete options head]
     end
+    allow do
+      origins '*'
+
+      resource '/api/v1/*',
+               headers: :any,
+               methods: %i[get post put patch delete options head]
+    end
   end
 end

config/initializers/prometheus.rb

@@ -0,0 +1,30 @@
+# frozen_string_literal: true
+
+require 'prometheus_exporter/client'
+require 'prometheus_exporter/instrumentation'
+require 'prometheus_exporter/metric'
+
+require_relative '../../app/helpers/metrics'
+
+PrometheusExporter::Client.default = PrometheusExporter::Client.new(host: ENV.fetch("PROMETHEUS_EXPORTER"), port: 9091)
+
+if ENV.fetch("ENVIRONMENT", "dev") == "staging"
+  PrometheusExporter::Instrumentation::Process.start(type: "wca-registration-handler-staging", labels: { process: "1" })
+  @suffix = "-staging"
+else
+  PrometheusExporter::Instrumentation::Process.start(type: "wca-registration-handler", labels: { process: "1" })
+  @suffix = ""
+end
+
+unless Rails.env.test?
+  require 'prometheus_exporter/middleware'
+
+  # This reports stats per request like HTTP status and timings
+  Rails.application.middleware.unshift PrometheusExporter::Middleware
+end
+
+# Create our Metric Counters
+Metrics.registration_dynamodb_errors_counter = PrometheusExporter::Client.default.register("counter", "registration_dynamodb_errors_counter#{@suffix}", "The number of times interacting with dynamodb fails")
+Metrics.registration_competition_api_error_counter = PrometheusExporter::Client.default.register("counter", "registration_competition_api_error_counter#{@suffix}", "The number of times interacting with the competition API failed")
+Metrics.registration_competitor_api_error_counter = PrometheusExporter::Client.default.register("counter", "registration_competitor_api_error_counter#{@suffix}", "The number of times interacting with the competitor API failed")
+Metrics.registration_validation_errors_counter = PrometheusExporter::Client.default.register("counter", "registration_validation_errors_counter#{@suffix}", "The number of times validation fails when an attendee tries to register")

config/routes.rb

@@ -6,5 +6,4 @@
   patch '/api/v1/register', to: 'registration#update'
   delete '/api/v1/register', to: 'registration#delete'
   get '/api/v1/registrations', to: 'registration#list'
-  get '/metrics', to: 'metrics#index'
 end

docker-compose.dev.yml

@@ -1,6 +1,7 @@
 version: "3.8"
 services:
   wca_registration_handler:
+    container_name: wca_registration_handler
     build:
       context: .
       dockerfile: dockerfile.dev
@@ -13,6 +14,7 @@ services:
       AWS_SECRET_ACCESS_KEY: "fake-access-key"
       VAULT_ADDR: "http://wca_vault:8200"
       VAULT_DEV_ROOT_TOKEN_ID: aDGdUASDGIUASGDKI
+      PROMETHEUS_EXPORTER: "prometheus_exporter"
     volumes:
       - .:/app
       - gems_volume_handler:/usr/local/bundle
@@ -27,8 +29,22 @@ services:
     depends_on:
       - localstack
       - wca_vault
+      - prometheus_exporter
+
+  prometheus_exporter:
+    container_name: prometheus_exporter
+    build:
+      context: .
+      dockerfile: dockerfile.metrics
+    tty: true
+    ports:
+      - "9091:9091"
+    networks:
+      - wca-registration
+
 
   wca_registration_worker:
+    container_name: wca_registration_worker
     build:
       context: .
       dockerfile: dockerfile.dev
@@ -37,6 +53,7 @@ services:
       AWS_REGION: "us-east-1"
       AWS_ACCESS_KEY_ID: "fake-key"
       AWS_SECRET_ACCESS_KEY: "fake-access-key"
+      PROMETHEUS_EXPORTER: "prometheus_exporter"
 
     volumes:
       - .:/app
@@ -71,6 +88,7 @@ services:
       - wca-registration
 
   dynamodb-admin:
+    container_name: dynamodb-admin
     image: aaronshaf/dynamodb-admin
     ports:
       - "8001:8001"
@@ -85,6 +103,7 @@ services:
       - wca-registration
 
   wca_vault:
+    container_name: vault
     image: hashicorp/vault
     environment:
       - VAULT_DEV_ROOT_TOKEN_ID=aDGdUASDGIUASGDKI
@@ -95,6 +114,7 @@ services:
 
   # Frontend
   frontend:
+    container_name: frontend
     build:
       context: Frontend
     tty:
@@ -106,15 +126,18 @@ services:
       - ./Frontend/src:/app/src
     depends_on:
       - nginx
+
   nginx:
+    container_name: nginx
     image: nginx:latest
     ports:
       - "3002:80"
     networks:
       - wca-registration
     volumes:
       - ./Frontend/frontend_local.conf:/etc/nginx/conf.d/default.conf
-
+    depends_on:
+      - frontend
 
 volumes:
   gems_volume_handler: