karafka 2.0.0.beta5 → 2.0.0.rc3

data/lib/karafka/connection/listener.rb

@@ -18,15 +18,18 @@ module Karafka
       # @param jobs_queue [Karafka::Processing::JobsQueue] queue where we should push work
       # @return [Karafka::Connection::Listener] listener instance
       def initialize(subscription_group, jobs_queue)
+        proc_config = ::Karafka::App.config.internal.processing
+
         @id = SecureRandom.uuid
         @subscription_group = subscription_group
         @jobs_queue = jobs_queue
-        @jobs_builder = ::Karafka::App.config.internal.processing.jobs_builder
         @coordinators = Processing::CoordinatorsBuffer.new
         @client = Client.new(@subscription_group)
         @executors = Processing::ExecutorsBuffer.new(@client, subscription_group)
+        @jobs_builder = proc_config.jobs_builder
+        @partitioner = proc_config.partitioner_class.new(subscription_group)
         # We reference scheduler here as it is much faster than fetching this each time
-        @scheduler = ::Karafka::App.config.internal.processing.scheduler
+        @scheduler = proc_config.scheduler
         # We keep one buffer for messages to preserve memory and not allocate extra objects
         # We can do this that way because we always first schedule jobs using messages before we
         # fetch another batch.
@@ -79,10 +82,6 @@ module Karafka
             poll_and_remap_messages
           end
 
-          # This will ensure, that in the next poll, we continue processing (if we get them back)
-          # partitions that we have paused
-          resume_assigned_partitions
-
           # If there were revoked partitions, we need to wait on their jobs to finish before
           # distributing consuming jobs as upon revoking, we might get assigned to the same
           # partitions, thus getting their jobs. The revoking jobs need to finish before
@@ -159,8 +158,6 @@ module Karafka
 
         revoked_partitions.each do |topic, partitions|
           partitions.each do |partition|
-            # We revoke the coordinator here, so we do not have to revoke it in the revoke job
-            # itself (this happens prior to scheduling those jobs)
             @coordinators.revoke(topic, partition)
 
             # There may be a case where we have lost partition of which data we have never
@@ -204,17 +201,6 @@ module Karafka
         )
       end
 
-      # Revoked partition needs to be resumed if we were processing them earlier. This will do
-      # nothing to things that we are planning to process. Without this, things we get
-      # re-assigned would not be polled.
-      def resume_assigned_partitions
-        @client.rebalance_manager.assigned_partitions.each do |topic, partitions|
-          partitions.each do |partition|
-            @client.resume(topic, partition)
-          end
-        end
-      end
-
       # Takes the messages per topic partition and enqueues processing jobs in threads using
       # given scheduler.
       def build_and_schedule_consumption_jobs
@@ -226,14 +212,16 @@ module Karafka
           coordinator = @coordinators.find_or_create(topic, partition)
 
           # Start work coordination for this topic partition
-          coordinator.start
+          coordinator.start(messages)
 
-          # Count the job we're going to create here
-          coordinator.increment
+          @partitioner.call(topic, messages) do |group_id, partition_messages|
+            # Count the job we're going to create here
+            coordinator.increment
 
-          executor = @executors.find_or_create(topic, partition, 0)
+            executor = @executors.find_or_create(topic, partition, group_id)
 
-          jobs << @jobs_builder.consume(executor, messages, coordinator)
+            jobs << @jobs_builder.consume(executor, partition_messages, coordinator)
+          end
         end
 
         @scheduler.schedule_consumption(@jobs_queue, jobs)

data/lib/karafka/connection/pauses_manager.rb

@@ -25,14 +25,6 @@ module Karafka
         )
       end
 
-      # Revokes pause tracker for a given topic partition
-      #
-      # @param topic [String] topic name
-      # @param partition [Integer] partition number
-      def revoke(topic, partition)
-        @pauses[topic].delete(partition)
-      end
-
       # Resumes processing of partitions for which pause time has ended.
       #
       # @yieldparam [String] topic name

data/lib/karafka/contracts/base.rb

@@ -3,20 +3,14 @@
 module Karafka
   module Contracts
     # Base contract for all Karafka contracts
-    class Base < Dry::Validation::Contract
-      config.messages.load_paths << File.join(Karafka.gem_root, 'config', 'errors.yml')
-
+    class Base < ::WaterDrop::Contractable::Contract
       # @param data [Hash] data for validation
       # @return [Boolean] true if all good
       # @raise [Errors::InvalidConfigurationError] invalid configuration error
       # @note We use contracts only in the config validation context, so no need to add support
       #   for multiple error classes. It will be added when it will be needed.
       def validate!(data)
-        result = call(data)
-
-        return true if result.success?
-
-        raise Errors::InvalidConfigurationError, result.errors.to_h
+        super(data, Errors::InvalidConfigurationError)
       end
     end
   end

data/lib/karafka/contracts/config.rb

@@ -9,70 +9,90 @@ module Karafka
     #   validated per each route (topic + consumer_group) because they can be overwritten,
     #   so we validate all of that once all the routes are defined and ready.
     class Config < Base
-      params do
-        # License validity happens in the licenser. Here we do only the simple consistency checks
-        required(:license).schema do
-          required(:token) { bool? | str? }
-          required(:entity) { str? }
-          required(:expires_on) { date? }
+      configure do |config|
+        config.error_messages = YAML.safe_load(
+          File.read(
+            File.join(Karafka.gem_root, 'config', 'errors.yml')
+          )
+        ).fetch('en').fetch('validations').fetch('config')
+      end
+
+      # License validity happens in the licenser. Here we do only the simple consistency checks
+      nested(:license) do
+        required(:token) { |val| [true, false].include?(val) || val.is_a?(String) }
+        required(:entity) { |val| val.is_a?(String) }
+        required(:expires_on) { |val| val.is_a?(Date) }
+      end
+
+      required(:client_id) { |val| val.is_a?(String) && Contracts::TOPIC_REGEXP.match?(val) }
+      required(:concurrency) { |val| val.is_a?(Integer) && val.positive? }
+      required(:consumer_mapper) { |val| !val.nil? }
+      required(:consumer_persistence) { |val| [true, false].include?(val) }
+      required(:pause_timeout) { |val| val.is_a?(Integer) && val.positive? }
+      required(:pause_max_timeout) { |val| val.is_a?(Integer) && val.positive? }
+      required(:pause_with_exponential_backoff) { |val| [true, false].include?(val) }
+      required(:shutdown_timeout) { |val| val.is_a?(Integer) && val.positive? }
+      required(:max_wait_time) { |val| val.is_a?(Integer) && val.positive? }
+      required(:kafka) { |val| val.is_a?(Hash) && !val.empty? }
+
+      # We validate internals just to be sure, that they are present and working
+      nested(:internal) do
+        required(:status) { |val| !val.nil? }
+        required(:process) { |val| !val.nil? }
+
+        nested(:routing) do
+          required(:builder) { |val| !val.nil? }
+          required(:subscription_groups_builder) { |val| !val.nil? }
+        end
+
+        nested(:processing) do
+          required(:jobs_builder) { |val| !val.nil? }
+          required(:scheduler) { |val| !val.nil? }
+          required(:coordinator_class) { |val| !val.nil? }
+          required(:partitioner_class) { |val| !val.nil? }
         end
 
-        required(:client_id).filled(:str?, format?: Karafka::Contracts::TOPIC_REGEXP)
-        required(:concurrency) { int? & gt?(0) }
-        required(:consumer_mapper).filled
-        required(:consumer_persistence).filled(:bool?)
-        required(:pause_timeout) { int? & gt?(0) }
-        required(:pause_max_timeout) { int? & gt?(0) }
-        required(:pause_with_exponential_backoff).filled(:bool?)
-        required(:shutdown_timeout) { int? & gt?(0) }
-        required(:max_wait_time) { int? & gt?(0) }
-        required(:kafka).filled(:hash)
-
-        # We validate internals just to be sure, that they are present and working
-        required(:internal).schema do
-          required(:status)
-          required(:process)
-
-          required(:routing).schema do
-            required(:builder)
-            required(:subscription_groups_builder)
-          end
-
-          required(:processing).schema do
-            required(:jobs_builder)
-            required(:scheduler)
-            required(:coordinator_class)
-          end
-
-          required(:active_job).schema do
-            required(:dispatcher)
-            required(:job_options_contract)
-            required(:consumer_class)
-          end
+        nested(:active_job) do
+          required(:dispatcher) { |val| !val.nil? }
+          required(:job_options_contract) { |val| !val.nil? }
+          required(:consumer_class) { |val| !val.nil? }
         end
       end
 
-      # rdkafka requires all the keys to be strings, so we ensure that
-      rule(:kafka) do
-        next unless value.is_a?(Hash)
+      virtual do |data, errors|
+        next unless errors.empty?
+
+        detected_errors = []
 
-        value.each_key do |key|
+        data.fetch(:kafka).each_key do |key|
           next if key.is_a?(Symbol)
 
-          key(:"kafka.#{key}").failure(:kafka_key_must_be_a_symbol)
+          detected_errors << [[:kafka, key], :key_must_be_a_symbol]
         end
+
+        detected_errors
       end
 
-      rule(:pause_timeout, :pause_max_timeout) do
-        if values[:pause_timeout].to_i > values[:pause_max_timeout].to_i
-          key(:pause_timeout).failure(:max_timeout_vs_pause_max_timeout)
-        end
+      virtual do |data, errors|
+        next unless errors.empty?
+
+        pause_timeout = data.fetch(:pause_timeout)
+        pause_max_timeout = data.fetch(:pause_max_timeout)
+
+        next if pause_timeout <= pause_max_timeout
+
+        [[%i[pause_timeout], :max_timeout_vs_pause_max_timeout]]
       end
 
-      rule(:shutdown_timeout, :max_wait_time) do
-        if values[:max_wait_time].to_i >= values[:shutdown_timeout].to_i
-          key(:shutdown_timeout).failure(:shutdown_timeout_vs_max_wait_time)
-        end
+      virtual do |data, errors|
+        next unless errors.empty?
+
+        shutdown_timeout = data.fetch(:shutdown_timeout)
+        max_wait_time = data.fetch(:max_wait_time)
+
+        next if max_wait_time < shutdown_timeout
+
+        [[%i[shutdown_timeout], :shutdown_timeout_vs_max_wait_time]]
       end
     end
   end

data/lib/karafka/contracts/consumer_group.rb

@@ -4,32 +4,39 @@ module Karafka
   module Contracts
     # Contract for single full route (consumer group + topics) validation.
     class ConsumerGroup < Base
-      # Internal contract for sub-validating topics schema
-      TOPIC_CONTRACT = ConsumerGroupTopic.new.freeze
+      configure do |config|
+        config.error_messages = YAML.safe_load(
+          File.read(
+            File.join(Karafka.gem_root, 'config', 'errors.yml')
+          )
+        ).fetch('en').fetch('validations').fetch('consumer_group')
+      end
 
-      private_constant :TOPIC_CONTRACT
+      required(:id) { |id| id.is_a?(String) && Contracts::TOPIC_REGEXP.match?(id) }
+      required(:topics) { |topics| topics.is_a?(Array) && !topics.empty? }
 
-      params do
-        required(:id).filled(:str?, format?: Karafka::Contracts::TOPIC_REGEXP)
-        required(:topics).value(:array, :filled?)
-      end
+      virtual do |data, errors|
+        next unless errors.empty?
 
-      rule(:topics) do
-        if value.is_a?(Array)
-          names = value.map { |topic| topic[:name] }
+        names = data.fetch(:topics).map { |topic| topic[:name] }
 
-          key.failure(:topics_names_not_unique) if names.size != names.uniq.size
-        end
+        next if names.size == names.uniq.size
+
+        [[%i[topics], :names_not_unique]]
       end
 
-      rule(:topics) do
-        if value.is_a?(Array)
-          value.each_with_index do |topic, index|
-            TOPIC_CONTRACT.call(topic).errors.each do |error|
-              key([:topics, index, error.path[0]]).failure(error.text)
-            end
+      virtual do |data, errors|
+        next unless errors.empty?
+
+        fetched_errors = []
+
+        data.fetch(:topics).each do |topic|
+          ConsumerGroupTopic.new.call(topic).errors.each do |key, value|
+            fetched_errors << [[topic, key].flatten, value]
           end
         end
+
+        fetched_errors
       end
     end
   end

data/lib/karafka/contracts/consumer_group_topic.rb

@@ -4,24 +4,38 @@ module Karafka
   module Contracts
     # Consumer group topic validation rules.
     class ConsumerGroupTopic < Base
-      params do
-        required(:consumer).filled
-        required(:deserializer).filled
-        required(:id).filled(:str?, format?: Karafka::Contracts::TOPIC_REGEXP)
-        required(:kafka).filled
-        required(:max_messages) { int? & gteq?(1) }
-        required(:initial_offset).filled(included_in?: %w[earliest latest])
-        required(:max_wait_time).filled { int? & gteq?(10) }
-        required(:manual_offset_management).filled(:bool?)
-        required(:name).filled(:str?, format?: Karafka::Contracts::TOPIC_REGEXP)
+      configure do |config|
+        config.error_messages = YAML.safe_load(
+          File.read(
+            File.join(Karafka.gem_root, 'config', 'errors.yml')
+          )
+        ).fetch('en').fetch('validations').fetch('consumer_group_topic')
       end
 
-      rule(:kafka) do
-        # This will trigger rdkafka validations that we catch and re-map the info and use dry
-        # compatible format
-        Rdkafka::Config.new(value).send(:native_config)
-      rescue Rdkafka::Config::ConfigError => e
-        key(:kafka).failure(e.message)
+      required(:consumer) { |consumer_group| !consumer_group.nil? }
+      required(:deserializer) { |deserializer| !deserializer.nil? }
+      required(:id) { |id| id.is_a?(String) && Contracts::TOPIC_REGEXP.match?(id) }
+      required(:kafka) { |kafka| kafka.is_a?(Hash) && !kafka.empty? }
+      required(:max_messages) { |mm| mm.is_a?(Integer) && mm >= 1 }
+      required(:initial_offset) { |io| %w[earliest latest].include?(io) }
+      required(:max_wait_time) { |mwt| mwt.is_a?(Integer) && mwt >= 10 }
+      required(:manual_offset_management) { |mmm| [true, false].include?(mmm) }
+      required(:name) { |name| name.is_a?(String) && Contracts::TOPIC_REGEXP.match?(name) }
+
+      virtual do |data, errors|
+        next unless errors.empty?
+
+        value = data.fetch(:kafka)
+
+        begin
+          # This will trigger rdkafka validations that we catch and re-map the info and use dry
+          # compatible format
+          Rdkafka::Config.new(value).send(:native_config)
+
+          nil
+        rescue Rdkafka::Config::ConfigError => e
+          [[%w[kafka], e.message]]
+        end
       end
     end
   end

data/lib/karafka/contracts/server_cli_options.rb

@@ -4,17 +4,28 @@ module Karafka
   module Contracts
     # Contract for validating correctness of the server cli command options.
     class ServerCliOptions < Base
-      params do
-        optional(:consumer_groups).value(:array, :filled?)
+      configure do |config|
+        config.error_messages = YAML.safe_load(
+          File.read(
+            File.join(Karafka.gem_root, 'config', 'errors.yml')
+          )
+        ).fetch('en').fetch('validations').fetch('server_cli_options')
       end
 
-      rule(:consumer_groups) do
+      optional(:consumer_groups) { |cg| cg.is_a?(Array) && !cg.empty? }
+
+      virtual do |data, errors|
+        next unless errors.empty?
+        next unless data.key?(:consumer_groups)
+
+        value = data.fetch(:consumer_groups)
+
         # If there were no consumer_groups declared in the server cli, it means that we will
         # run all of them and no need to validate them here at all
-        if !value.nil? &&
-           !(value - Karafka::App.config.internal.routing.builder.map(&:name)).empty?
-          key(:consumer_groups).failure(:consumer_groups_inclusion)
-        end
+        next if value.nil?
+        next if (value - Karafka::App.config.internal.routing.builder.map(&:name)).empty?
+
+        [[%i[consumer_groups], :consumer_groups_inclusion]]
       end
     end
   end

data/lib/karafka/helpers/colorize.rb

@@ -0,0 +1,20 @@
+# frozen_string_literal: true
+
+module Karafka
+  module Helpers
+    # Simple wrapper for adding colors to strings
+    module Colorize
+      # @param string [String] string we want to have in green
+      # @return [String] green string
+      def green(string)
+        "\033[0;32m#{string}\033[0m"
+      end
+
+      # @param string [String] string we want to have in red
+      # @return [String] red string
+      def red(string)
+        "\033[0;31m#{string}\033[0m"
+      end
+    end
+  end
+end

data/lib/karafka/instrumentation/logger_listener.rb

@@ -18,7 +18,7 @@ module Karafka
       # @param event [Dry::Events::Event] event details including payload
       def on_connection_listener_fetch_loop(event)
         listener = event[:caller]
-        info "[#{listener.id}] Polling messages..."
+        debug "[#{listener.id}] Polling messages..."
       end
 
       # Logs about messages that we've received from Kafka
@@ -28,7 +28,13 @@ module Karafka
         listener = event[:caller]
         time = event[:time]
         messages_count = event[:messages_buffer].size
-        info "[#{listener.id}] Polled #{messages_count} messages in #{time}ms"
+
+        message = "[#{listener.id}] Polled #{messages_count} messages in #{time}ms"
+
+        # We don't want the "polled 0" in dev as it would spam the log
+        # Instead we publish only info when there was anything we could poll and fail over to the
+        # zero notifications when in debug mode
+        messages_count.zero? ? debug(message) : info(message)
       end
 
       # Prints info about the fact that a given job has started

data/lib/karafka/instrumentation/vendors/datadog/dashboard.json

@@ -0,0 +1 @@
+{"title":"Karafka monitoring dashboard","description":"","widgets":[{"id":7444969424381053,"definition":{"title":"Stability & errors","type":"group","show_title":true,"layout_type":"ordered","widgets":[{"id":8304008422587936,"definition":{"title":"Client connects and disconnects","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Connects","formula":"query1"},{"alias":"Disconnects","formula":"query2"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.connection.connects{*} by {host}.as_count()","data_source":"metrics","name":"query1"},{"query":"sum:karafka.connection.disconnects{*} by {host}.as_count()","data_source":"metrics","name":"query2"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"bars"}]},"layout":{"x":0,"y":0,"width":4,"height":2}},{"id":3722865443336921,"definition":{"title":"Errors encountered (any)","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"in-karafka errors","formula":"query1"},{"alias":"librdkafka consume errors","formula":"query2"},{"alias":"librdkafka receive errors","formula":"query3"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.error_occurred{*} by {type}.as_count()","data_source":"metrics","name":"query1"},{"query":"sum:karafka.consume.errors{*}.as_count()","data_source":"metrics","name":"query2"},{"query":"sum:karafka.receive.errors{*}.as_count()","data_source":"metrics","name":"query3"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":4,"y":0,"width":4,"height":2}},{"id":5477381252952760,"definition":{"title":"Processing errors","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.error_occurred{type:consumer.consume.error} by {partition,topic}.as_count()","data_source":"metrics","name":"query1"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":8,"y":0,"width":4,"height":2}},{"id":2357301680769076,"definition":{"title":"Processing errors rate per topic","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"% error rate per topic","formula":"(query1 / (query1 + query2)) * 100"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.error_occurred{type:consumer.consume.error} by {topic,partition}.as_count()","data_source":"metrics","name":"query1"},{"query":"sum:karafka.consumer.batches{*} by {topic,partition}.as_count()","data_source":"metrics","name":"query2"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"bars"}]},"layout":{"x":0,"y":2,"width":4,"height":2}},{"id":3902930069982135,"definition":{"title":"Batches successful vs failures","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Successfully processed batch","formula":"query1"},{"alias":"Batch processing with error","formula":"query2"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.consumer.batches{*} by {partition,topic}.as_count()","data_source":"metrics","name":"query1"},{"query":"avg:karafka.error_occurred{type:consumer.consume.error} by {partition,topic}.as_count()","data_source":"metrics","name":"query2"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":4,"y":2,"width":4,"height":2}},{"id":718749162159145,"definition":{"title":"Consumer instances revocations and shutdowns","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Consumer instances revokations","formula":"query1"},{"alias":"Consumer instances shutdowns","formula":"query2"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.consumer.revoked{*}.as_count()","data_source":"metrics","name":"query1"},{"query":"sum:karafka.consumer.shutdown{*}.as_count()","data_source":"metrics","name":"query2"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":8,"y":2,"width":4,"height":2}}]},"layout":{"x":0,"y":0,"width":12,"height":5}},{"id":5988438511387100,"definition":{"title":"Workers poll","type":"group","show_title":true,"layout_type":"ordered","widgets":[{"id":8769294644934352,"definition":{"title":"Enqueued jobs","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Enqueued jobs","formula":"query1"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.worker.enqueued_jobs.avg{*}","data_source":"metrics","name":"query1"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":0,"y":0,"width":4,"height":2}},{"id":2714502141463873,"definition":{"title":"Workers usage","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Busy workers (p95)","formula":"query1"},{"alias":"Total workers","formula":"query2"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.worker.processing.95percentile{*}","data_source":"metrics","name":"query1"},{"query":"sum:karafka.worker.total_threads{*}","data_source":"metrics","name":"query2"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":4,"y":0,"width":4,"height":2}},{"id":5370086629441984,"definition":{"title":"Workers % utilization","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"% workers utilization","formula":"(query1 / query2) * 100"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.worker.processing.95percentile{*}","data_source":"metrics","name":"query1"},{"query":"sum:karafka.worker.total_threads{*}","data_source":"metrics","name":"query2"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":8,"y":0,"width":4,"height":2}}]},"layout":{"x":0,"y":5,"width":12,"height":3}},{"id":8544040083223278,"definition":{"title":"Throughput ","type":"group","show_title":true,"layout_type":"ordered","widgets":[{"id":3740207481939733,"definition":{"title":"Offset lag changes","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"derivative(query1)"}],"response_format":"timeseries","queries":[{"query":"max:karafka.consumer.offset{*} by {topic,partition}","data_source":"metrics","name":"query1"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":0,"y":0,"width":4,"height":2}},{"id":6319110548544878,"definition":{"title":"Batches processed per topic","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.consumer.batches{*} by {partition,topic}.as_count()","data_source":"metrics","name":"query1"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":4,"y":0,"width":4,"height":2}},{"id":6232784865331443,"definition":{"title":"Messages consumed per topic","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Messages consumed","formula":"query1"},{"alias":"Average batch size","formula":"query1 / query2"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.consumer.messages{*} by {partition,topic}.as_count()","data_source":"metrics","name":"query1"},{"query":"sum:karafka.consumer.batches{*} by {partition,topic}.as_count()","data_source":"metrics","name":"query2"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":8,"y":0,"width":4,"height":2}},{"id":2321394598982770,"definition":{"title":"Consumption lag (in seconds)","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Consumption lag in s (max)","formula":"query2 / 1000"},{"alias":"Consumption lag in s (avg)","formula":"query3 / 1000"},{"alias":"Consumption lag in s (p95)","formula":"query1 / 1000"}],"response_format":"timeseries","queries":[{"query":"max:karafka.consumer.consumption_lag.max{*}","data_source":"metrics","name":"query2"},{"query":"max:karafka.consumer.consumption_lag.avg{*}","data_source":"metrics","name":"query3"},{"query":"max:karafka.consumer.consumption_lag.95percentile{*}","data_source":"metrics","name":"query1"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":0,"y":2,"width":4,"height":2}},{"id":1062074781483741,"definition":{"title":"Processing lag (in ms)","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Processing lag in ms (p95)","formula":"query1"},{"alias":"Processing lag in ms (max)","formula":"query2"},{"alias":"Processing lag in ms (avg)","formula":"query3"}],"response_format":"timeseries","queries":[{"query":"max:karafka.consumer.processing_lag.95percentile{*}","data_source":"metrics","name":"query1"},{"query":"max:karafka.consumer.processing_lag.max{*}","data_source":"metrics","name":"query2"},{"query":"max:karafka.consumer.processing_lag.avg{*}","data_source":"metrics","name":"query3"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":4,"y":2,"width":4,"height":2}},{"id":7497794728674267,"definition":{"title":"Batch processing time","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1"},{"formula":"query2"},{"formula":"query3"}],"response_format":"timeseries","queries":[{"query":"max:karafka.consumer.consumed.time_taken.95percentile{*} by {topic,partition}","data_source":"metrics","name":"query1"},{"query":"max:karafka.consumer.consumed.time_taken.max{*} by {topic,partition}","data_source":"metrics","name":"query2"},{"query":"max:karafka.consumer.consumed.time_taken.avg{*} by {topic,partition}","data_source":"metrics","name":"query3"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":8,"y":2,"width":4,"height":2}},{"id":4192833027984161,"definition":{"title":"Batch size per topic","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Batch size p95","formula":"query1"},{"alias":"Batch size avg","formula":"query2"},{"alias":"Batch size max","formula":"query3"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.consumer.batch_size.95percentile{*} by {partition,topic}","data_source":"metrics","name":"query1"},{"query":"sum:karafka.consumer.batch_size.avg{*} by {partition,topic}","data_source":"metrics","name":"query2"},{"query":"sum:karafka.consumer.batch_size.max{*} by {partition,topic}","data_source":"metrics","name":"query3"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":0,"y":4,"width":4,"height":2}},{"id":4741598444771147,"definition":{"title":"Messages consumed overall","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"alias":"Messages consumed","formula":"query1"},{"alias":"Average batch size","formula":"query1 / query2"}],"response_format":"timeseries","queries":[{"query":"sum:karafka.consumer.messages{*}.as_count()","data_source":"metrics","name":"query1"},{"query":"sum:karafka.consumer.batches{*}.as_count()","data_source":"metrics","name":"query2"}],"style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":4,"y":4,"width":4,"height":2}},{"id":4502534794102513,"definition":{"title":"Polling times (ms)","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"time":{},"type":"timeseries","requests":[{"formulas":[{"alias":"p95 ms polling time","formula":"query1"},{"alias":"max ms polling time","formula":"query2"},{"alias":"average ms polling time","formula":"query3"}],"queries":[{"name":"query1","data_source":"metrics","query":"avg:karafka.listener.polling.time_taken.95percentile{*}"},{"name":"query2","data_source":"metrics","query":"avg:karafka.listener.polling.time_taken.max{*}"},{"name":"query3","data_source":"metrics","query":"avg:karafka.listener.polling.time_taken.avg{*}"}],"response_format":"timeseries","style":{"palette":"dog_classic","line_type":"solid","line_width":"normal"},"display_type":"line"}]},"layout":{"x":8,"y":4,"width":4,"height":2}}]},"layout":{"x":0,"y":0,"width":12,"height":7,"is_column_break":true}}],"template_variables":[],"layout_type":"ordered","is_read_only":false,"notify_list":[],"reflow_type":"fixed","id":"s3u-z47-i6u"}