logstash-integration-kafka 10.12.0-java → 11.1.0-java

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ad714dd5a1201d57e98cc740560fb96fdeb999b500065ba5c5dcb0d950cab3fa
-  data.tar.gz: 148938661749ae182a0ea2e2482d846bf7225390c2e418605cd83ad1242ba9b0
+  metadata.gz: c8f85bfdadbbd496495603c82ed577db4c23a168db59e6d0034549de6ebb66d1
+  data.tar.gz: 0b3b0bc33d6e64eebcb9e757fede56f747625c864160844ed2a3c76d0b22a155
 SHA512:
-  metadata.gz: afac318b49b8a489b3c0e7919067417eee1cc3f6097c1e71e86647a66c1383c9054f81742fe70cc8673f2c6ba377c2734a17426d2541abecb0f941465a037f0f
-  data.tar.gz: c8f7c382bbb00680fdb4a2c9d72a31ddcd231644d683503ba3eb0996da7236ac5fdd55a7aaa40f01a8737b9d3b5419052f1fd2b054ee3f6da1c23b2e1631ce99
+  metadata.gz: '09e8814f1697c1d38d478881b35102a1e9885c23cdb0b9b2d8860c7577d4b2a40eb580b535afff46273e7139fbbaf603b0ea0de1fbeb68644bcea95b79d9e470'
+  data.tar.gz: 1b0c7ee3ffbcb589268174753db91d0ba7272fc44c04e7ceb2e17d43f9fe2ec31ed4eee7450390adc0bada77c36fedaf14d46bf9b09372a6b55a6e76047a56e4

data/CHANGELOG.md

@@ -1,5 +1,13 @@
+## 11.1.0
+ - Added config `group_instance_id` to use the Kafka's consumer static membership feature [#135](https://github.com/logstash-plugins/logstash-integration-kafka/pull/135)
+
+## 11.0.0
+  - Changed Kafka client to 3.3.1, requires Logstash >= 8.3.0. 
+  - Deprecated `default` value for setting `client_dns_lookup` forcing to `use_all_dns_ips` when explicitly used [#130](https://github.com/logstash-plugins/logstash-integration-kafka/pull/130)
+  - Changed the consumer's poll from using the one that blocks on metadata retrieval to the one that doesn't [#136](https://github.com/logstash-plugins/logstash-integration-kafka/pull/133)
+
 ## 10.12.0
-  - bump kafka client to 2.8.1 [#115](https://api.github.com/repos/logstash-plugins/logstash-integration-kafka/pulls/115)
+  - bump kafka client to 2.8.1 [#115](https://github.com/logstash-plugins/logstash-integration-kafka/pull/115)
 
 ## 10.11.0
   - Feat: added connections_max_idle_ms setting for output [#118](https://github.com/logstash-plugins/logstash-integration-kafka/pull/118)

data/docs/index.asciidoc

@@ -1,7 +1,7 @@
 :plugin: kafka
 :type: integration
 :no_codec:
-:kafka_client: 2.8.1
+:kafka_client: 3.3.1
 
 ///////////////////////////////////////////
 START - GENERATED VARIABLES, DO NOT EDIT!

data/docs/input-kafka.asciidoc

@@ -2,8 +2,8 @@
 :plugin: kafka
 :type: input
 :default_codec: plain
-:kafka_client: 2.8
-:kafka_client_doc: 25
+:kafka_client: 3.3
+:kafka_client_doc: 33
 
 ///////////////////////////////////////////
 START - GENERATED VARIABLES, DO NOT EDIT!
@@ -113,6 +113,7 @@ See the https://kafka.apache.org/{kafka_client_doc}/documentation for more detai
 | <<plugins-{type}s-{plugin}-fetch_max_wait_ms>> |<<number,number>>|No
 | <<plugins-{type}s-{plugin}-fetch_min_bytes>> |<<number,number>>|No
 | <<plugins-{type}s-{plugin}-group_id>> |<<string,string>>|No
+| <<plugins-{type}s-{plugin}-group_instance_id>> |<<string,string>>|No
 | <<plugins-{type}s-{plugin}-heartbeat_interval_ms>> |<<number,number>>|No
 | <<plugins-{type}s-{plugin}-isolation_level>> |<<string,string>>|No
 | <<plugins-{type}s-{plugin}-jaas_path>> |a valid filesystem path|No
@@ -143,10 +144,10 @@ See the https://kafka.apache.org/{kafka_client_doc}/documentation for more detai
 | <<plugins-{type}s-{plugin}-ssl_key_password>> |<<password,password>>|No
 | <<plugins-{type}s-{plugin}-ssl_keystore_location>> |a valid filesystem path|No
 | <<plugins-{type}s-{plugin}-ssl_keystore_password>> |<<password,password>>|No
-| <<plugins-{type}s-{plugin}-ssl_keystore_type>> |<<string,string>>|No
+| <<plugins-{type}s-{plugin}-ssl_keystore_type>> |<<string,string>>, one of `["jks", "PKCS12"]`|No
 | <<plugins-{type}s-{plugin}-ssl_truststore_location>> |a valid filesystem path|No
 | <<plugins-{type}s-{plugin}-ssl_truststore_password>> |<<password,password>>|No
-| <<plugins-{type}s-{plugin}-ssl_truststore_type>> |<<string,string>>|No
+| <<plugins-{type}s-{plugin}-ssl_truststore_type>> |<<string,string>>, one of `["jks", "PKCS12"]`|No
 | <<plugins-{type}s-{plugin}-topics>> |<<array,array>>|No
 | <<plugins-{type}s-{plugin}-topics_pattern>> |<<string,string>>|No
 | <<plugins-{type}s-{plugin}-value_deserializer_class>> |<<string,string>>|No
@@ -211,6 +212,12 @@ IP addresses for a hostname, they will all be attempted to connect to before fai
 connection. If the value is `resolve_canonical_bootstrap_servers_only` each entry will be 
 resolved and expanded into a list of canonical names.
 
+[NOTE]
+====
+Starting from Kafka 3 `default` value for `client.dns.lookup` value has been removed.
+If explicitly configured it fallbacks to `use_all_dns_ips`.
+====
+
 [id="plugins-{type}s-{plugin}-client_id"]
 ===== `client_id` 
 
@@ -338,6 +345,28 @@ NOTE: In cases when multiple inputs are being used in a single pipeline, reading
 it's essential to set a different `group_id => ...` for each input. Setting a unique `client_id => ...`
 is also recommended.
 
+[id="plugins-{type}s-{plugin}-group_instance_id"]
+===== `group_instance_id`
+
+* Value type is <<string,string>>
+* There is no default value for this setting.
+
+The static membership identifier for this Logstash Kafka consumer. Static membership feature was introduced in
+https://cwiki.apache.org/confluence/display/KAFKA/KIP-345%3A+Introduce+static+membership+protocol+to+reduce+consumer+rebalances[KIP-345],
+available under Kafka property `group.instance.id`.
+Its purpose is to avoid rebalances in situations in which a lot of data
+has to be forwarded after a consumer goes offline.
+This feature mitigates cases where the service state is heavy and the rebalance of one topic partition from instance
+A to B would cause a huge amount of data to be transferred.
+A client that goes offline/online frequently can avoid frequent and heavy rebalances by using this option.
+
+NOTE: The `group_instance_id` setting must be unique across all the clients belonging to the same <<plugins-{type}s-{plugin}-group_id>>.
+Otherwise, another client connecting with same `group.instance.id` value would cause the oldest instance to be disconnected.
+You can set this value to use information such as a hostname, an IP, or anything that uniquely identifies the client application.
+
+NOTE: In cases when multiple threads are configured and `consumer_threads` is greater than one, a suffix is appended to
+the `group_instance_id` to avoid collisions.
+
 [id="plugins-{type}s-{plugin}-heartbeat_interval_ms"]
 ===== `heartbeat_interval_ms` 
 
@@ -659,7 +688,7 @@ If client authentication is required, this setting stores the keystore password
   * Value type is <<string,string>>
   * There is no default value for this setting.
 
-The keystore type.
+The format of the keystore file. It must be either `jks` or `PKCS12`.
 
 [id="plugins-{type}s-{plugin}-ssl_truststore_location"]
 ===== `ssl_truststore_location` 
@@ -683,7 +712,7 @@ The truststore password.
   * Value type is <<string,string>>
   * There is no default value for this setting.
 
-The truststore type.
+The format of the truststore file. It must be either `jks` or `PKCS12`.
 
 [id="plugins-{type}s-{plugin}-topics"]
 ===== `topics` 
@@ -699,8 +728,13 @@ A list of topics to subscribe to, defaults to ["logstash"].
   * Value type is <<string,string>>
   * There is no default value for this setting.
 
-A topic regex pattern to subscribe to. 
-The topics configuration will be ignored when using this configuration.
+A topic regular expression pattern to subscribe to.
+
+Filtering by a regular expression is done by retrieving the full list of topic names from the broker and applying the pattern locally. When used with brokers with a lot of topics this operation could be very slow, especially if there are a lot of consumers.
+
+NOTE:  When the broker has some topics configured with ACL rules and they miss the DESCRIBE permission, then the subscription
+happens but on the broker side it is logged that the subscription of some topics was denied to the configured user.
+
 
 [id="plugins-{type}s-{plugin}-value_deserializer_class"]
 ===== `value_deserializer_class` 

data/docs/output-kafka.asciidoc

@@ -2,8 +2,8 @@
 :plugin: kafka
 :type: output
 :default_codec: plain
-:kafka_client: 2.8
-:kafka_client_doc: 25
+:kafka_client: 3.3
+:kafka_client_doc: 33
 
 ///////////////////////////////////////////
 START - GENERATED VARIABLES, DO NOT EDIT!
@@ -181,6 +181,12 @@ all IP addresses returned for a hostname before failing the connection.
 If set to `resolve_canonical_bootstrap_servers_only`, each entry will be 
 resolved and expanded into a list of canonical names.
 
+[NOTE]
+====
+Starting from Kafka 3 `default` value for `client.dns.lookup` value has been removed.
+If explicitly configured it fallbacks to `use_all_dns_ips`.
+====
+
 [id="plugins-{type}s-{plugin}-client_id"]
 ===== `client_id` 
 

data/lib/logstash/inputs/kafka.rb

@@ -92,7 +92,8 @@ class LogStash::Inputs::Kafka < LogStash::Inputs::Base
   # IP addresses for a hostname, they will all be attempted to connect to before failing the 
   # connection. If the value is `resolve_canonical_bootstrap_servers_only` each entry will be 
   # resolved and expanded into a list of canonical names.
-  config :client_dns_lookup, :validate => ["default", "use_all_dns_ips", "resolve_canonical_bootstrap_servers_only"], :default => "default"
+  # Starting from Kafka 3 `default` value for `client.dns.lookup` value has been removed. If explicitly configured it fallbacks to `use_all_dns_ips`.
+  config :client_dns_lookup, :validate => ["default", "use_all_dns_ips", "resolve_canonical_bootstrap_servers_only"], :default => "use_all_dns_ips"
   # The id string to pass to the server when making requests. The purpose of this
   # is to be able to track the source of requests beyond just ip/port by allowing
   # a logical application name to be included.
@@ -123,6 +124,11 @@ class LogStash::Inputs::Kafka < LogStash::Inputs::Base
   # that happens to be made up of multiple processors. Messages in a topic will be distributed to all
   # Logstash instances with the same `group_id`
   config :group_id, :validate => :string, :default => "logstash"
+  # Set a static group instance id used in static membership feature to avoid rebalancing when a
+  # consumer goes offline. If set and `consumer_threads` is greater than 1 then for each
+  # consumer crated by each thread an artificial suffix is appended to the user provided `group_instance_id`
+  # to avoid clashing.
+  config :group_instance_id, :validate => :string
   # The expected time between heartbeats to the consumer coordinator. Heartbeats are used to ensure 
   # that the consumer's session stays active and to facilitate rebalancing when new
   # consumers join or leave the group. The value must be set lower than
@@ -135,7 +141,7 @@ class LogStash::Inputs::Kafka < LogStash::Inputs::Base
   # been aborted. Non-transactional messages will be returned unconditionally in either mode.
   config :isolation_level, :validate => ["read_uncommitted", "read_committed"], :default => "read_uncommitted" # Kafka default
   # Java Class used to deserialize the record's key
-  config :key_deserializer_class, :validate => :string, :default => "org.apache.kafka.common.serialization.StringDeserializer"
+  config :key_deserializer_class, :validate => :string, :default => DEFAULT_DESERIALIZER_CLASS
   # The maximum delay between invocations of poll() when using consumer group management. This places 
   # an upper bound on the amount of time that the consumer can be idle before fetching more records. 
   # If poll() is not called before expiration of this timeout, then the consumer is considered failed and 
@@ -257,6 +263,7 @@ class LogStash::Inputs::Kafka < LogStash::Inputs::Base
   def register
     @runner_threads = []
     @metadata_mode = extract_metadata_level(@decorate_events)
+    reassign_dns_lookup
     @pattern ||= java.util.regex.Pattern.compile(@topics_pattern) unless @topics_pattern.nil?
     check_schema_registry_parameters
   end
@@ -285,7 +292,10 @@ class LogStash::Inputs::Kafka < LogStash::Inputs::Base
 
   public
   def run(logstash_queue)
-    @runner_consumers = consumer_threads.times.map { |i| subscribe(create_consumer("#{client_id}-#{i}")) }
+    @runner_consumers = consumer_threads.times.map do |i|
+      thread_group_instance_id = consumer_threads > 1 && group_instance_id ? "#{group_instance_id}-#{i}" : group_instance_id
+      subscribe(create_consumer("#{client_id}-#{i}", thread_group_instance_id))
+    end
     @runner_threads = @runner_consumers.map.with_index { |consumer, i| thread_runner(logstash_queue, consumer,
                                                                                      "kafka-input-worker-#{client_id}-#{i}") }
     @runner_threads.each(&:start)
@@ -329,10 +339,13 @@ class LogStash::Inputs::Kafka < LogStash::Inputs::Base
   def do_poll(consumer)
     records = []
     begin
-      records = consumer.poll(poll_timeout_ms)
+      records = consumer.poll(java.time.Duration.ofMillis(poll_timeout_ms))
     rescue org.apache.kafka.common.errors.WakeupException => e
       logger.debug("Wake up from poll", :kafka_error_message => e)
       raise e unless stop?
+    rescue org.apache.kafka.common.errors.FencedInstanceIdException => e
+      logger.error("Another consumer with same group.instance.id has connected", :original_error_message => e.message)
+      raise e unless stop?
     rescue => e
       logger.error("Unable to poll Kafka consumer",
                    :kafka_error_message => e,
@@ -387,7 +400,7 @@ class LogStash::Inputs::Kafka < LogStash::Inputs::Base
   end
 
   private
-  def create_consumer(client_id)
+  def create_consumer(client_id, group_instance_id)
     begin
       props = java.util.Properties.new
       kafka = org.apache.kafka.clients.consumer.ConsumerConfig
@@ -405,6 +418,7 @@ class LogStash::Inputs::Kafka < LogStash::Inputs::Base
       props.put(kafka::FETCH_MAX_WAIT_MS_CONFIG, fetch_max_wait_ms.to_s) unless fetch_max_wait_ms.nil?
       props.put(kafka::FETCH_MIN_BYTES_CONFIG, fetch_min_bytes.to_s) unless fetch_min_bytes.nil?
       props.put(kafka::GROUP_ID_CONFIG, group_id)
+      props.put(kafka::GROUP_INSTANCE_ID_CONFIG, group_instance_id) unless group_instance_id.nil?
       props.put(kafka::HEARTBEAT_INTERVAL_MS_CONFIG, heartbeat_interval_ms.to_s) unless heartbeat_interval_ms.nil?
       props.put(kafka::ISOLATION_LEVEL_CONFIG, isolation_level)
       props.put(kafka::KEY_DESERIALIZER_CLASS_CONFIG, key_deserializer_class)

data/lib/logstash/outputs/kafka.rb

@@ -86,7 +86,8 @@ class LogStash::Outputs::Kafka < LogStash::Outputs::Base
   # IP addresses for a hostname, they will all be attempted to connect to before failing the 
   # connection. If the value is `resolve_canonical_bootstrap_servers_only` each entry will be 
   # resolved and expanded into a list of canonical names.
-  config :client_dns_lookup, :validate => ["default", "use_all_dns_ips", "resolve_canonical_bootstrap_servers_only"], :default => "default"
+  # Starting from Kafka 3 `default` value for `client.dns.lookup` value has been removed. If explicitly configured it fallbacks to `use_all_dns_ips`.
+  config :client_dns_lookup, :validate => ["default", "use_all_dns_ips", "resolve_canonical_bootstrap_servers_only"], :default => "use_all_dns_ips"
   # The id string to pass to the server when making requests.
   # The purpose of this is to be able to track the source of requests beyond just
   # ip/port by allowing a logical application name to be included with the request
@@ -190,6 +191,7 @@ class LogStash::Outputs::Kafka < LogStash::Outputs::Base
       logger.warn("Kafka output is configured with finite retry. This instructs Logstash to LOSE DATA after a set number of send attempts fails. If you do not want to lose data if Kafka is down, then you must remove the retry setting.", :retries => @retries)
     end
 
+    reassign_dns_lookup
 
     @producer = create_producer
     if value_serializer == 'org.apache.kafka.common.serialization.StringSerializer'

data/lib/logstash/plugin_mixins/kafka/common.rb

@@ -43,5 +43,13 @@ module LogStash module PluginMixins module Kafka
       props.put("sasl.jaas.config", sasl_jaas_config) unless sasl_jaas_config.nil?
     end
 
+    def reassign_dns_lookup
+      if @client_dns_lookup == "default"
+        @client_dns_lookup = "use_all_dns_ips"
+        logger.warn("client_dns_lookup setting 'default' value is deprecated, forced to 'use_all_dns_ips', please update your configuration")
+        deprecation_logger.deprecated("Deprecated value `default` for `client_dns_lookup` option; use `use_all_dns_ips` instead.")
+      end
+    end
+
   end
 end end end

data/lib/logstash-integration-kafka_jars.rb

@@ -1,17 +1,17 @@
 # AUTOGENERATED BY THE GRADLE SCRIPT. DO NOT EDIT.
 
 require 'jar_dependencies'
-require_jar('io.confluent', 'kafka-avro-serializer', '6.2.2')
-require_jar('io.confluent', 'kafka-schema-serializer', '6.2.2')
-require_jar('io.confluent', 'common-config', '6.2.2')
+require_jar('io.confluent', 'kafka-avro-serializer', '7.3.0')
+require_jar('io.confluent', 'kafka-schema-serializer', '7.3.0')
+require_jar('io.confluent', 'common-config', '7.3.0')
 require_jar('org.apache.avro', 'avro', '1.11.0')
-require_jar('io.confluent', 'kafka-schema-registry-client', '6.2.2')
-require_jar('org.apache.kafka', 'kafka_2.12', '2.8.1')
-require_jar('io.confluent', 'common-utils', '6.2.2')
+require_jar('io.confluent', 'kafka-schema-registry-client', '7.3.0')
+require_jar('org.apache.kafka', 'kafka_2.12', '3.3.1')
+require_jar('io.confluent', 'common-utils', '7.3.0')
 require_jar('javax.ws.rs', 'javax.ws.rs-api', '2.1.1')
 require_jar('org.glassfish.jersey.core', 'jersey-common', '2.33')
-require_jar('org.apache.kafka', 'kafka-clients', '2.8.1')
+require_jar('org.apache.kafka', 'kafka-clients', '3.3.1')
 require_jar('com.github.luben', 'zstd-jni', '1.5.2-2')
 require_jar('org.slf4j', 'slf4j-api', '1.7.36')
-require_jar('org.lz4', 'lz4-java', '1.7.1')
+require_jar('org.lz4', 'lz4-java', '1.8.0')
 require_jar('org.xerial.snappy', 'snappy-java', '1.1.8.4')

data/logstash-integration-kafka.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name            = 'logstash-integration-kafka'
-  s.version         = '10.12.0'
+  s.version         = '11.1.0'
   s.licenses        = ['Apache-2.0']
   s.summary         = "Integration with Kafka - input and output plugins"
   s.description     = "This gem is a Logstash plugin required to be installed on top of the Logstash core pipeline "+
@@ -41,7 +41,7 @@ Gem::Specification.new do |s|
 
   # Gem dependencies
   s.add_runtime_dependency "logstash-core-plugin-api", ">= 1.60", "<= 2.99"
-  s.add_runtime_dependency "logstash-core", ">= 6.5.0"
+  s.add_runtime_dependency "logstash-core", ">= 8.3.0"
 
   s.add_runtime_dependency 'logstash-codec-json'
   s.add_runtime_dependency 'logstash-codec-plain'

data/spec/integration/inputs/kafka_spec.rb

@@ -79,6 +79,7 @@ describe "inputs/kafka", :integration => true do
     producer = org.apache.kafka.clients.producer.KafkaProducer.new(props)
 
     producer.send(record)
+    producer.flush
     producer.close
   end
 
@@ -185,10 +186,105 @@ describe "inputs/kafka", :integration => true do
       end
     end
   end
+
+  context "static membership 'group.instance.id' setting" do
+    let(:base_config) do
+      {
+        "topics" => ["logstash_integration_static_membership_topic"],
+        "group_id" => "logstash",
+        "consumer_threads" => 1,
+        # this is needed because the worker thread could be executed little after the producer sent the "up" message
+        "auto_offset_reset" => "earliest",
+        "group_instance_id" => "test_static_group_id"
+      }
+    end
+    let(:consumer_config) { base_config }
+    let(:logger) { double("logger") }
+    let(:queue) { java.util.concurrent.ArrayBlockingQueue.new(10) }
+    let(:kafka_input) { LogStash::Inputs::Kafka.new(consumer_config) }
+    before :each do
+      allow(LogStash::Inputs::Kafka).to receive(:logger).and_return(logger)
+      [:error, :warn, :info, :debug].each do |level|
+        allow(logger).to receive(level)
+      end
+
+      kafka_input.register
+    end
+
+    it "input plugin disconnects from the broker when another client with same static membership connects" do
+      expect(logger).to receive(:error).with("Another consumer with same group.instance.id has connected", anything)
+
+      input_worker = java.lang.Thread.new { kafka_input.run(queue) }
+      begin
+        input_worker.start
+        wait_kafka_input_is_ready("logstash_integration_static_membership_topic", queue)
+        saboteur_kafka_consumer = create_consumer_and_start_consuming("test_static_group_id")
+        saboteur_kafka_consumer.run # ask to be scheduled
+        saboteur_kafka_consumer.join
+
+        expect(saboteur_kafka_consumer.value).to eq("saboteur exited")
+      ensure
+        input_worker.join(30_000)
+      end
+    end
+
+    context "when the plugin is configured with multiple consumer threads" do
+      let(:consumer_config) { base_config.merge({"consumer_threads" => 2}) }
+
+      it "should avoid to connect with same 'group.instance.id'" do
+        expect(logger).to_not receive(:error).with("Another consumer with same group.instance.id has connected", anything)
+
+        input_worker = java.lang.Thread.new { kafka_input.run(queue) }
+        begin
+          input_worker.start
+          wait_kafka_input_is_ready("logstash_integration_static_membership_topic", queue)
+        ensure
+          kafka_input.stop
+          input_worker.join(1_000)
+        end
+      end
+    end
+  end
+end
+
+# return consumer Ruby Thread
+def create_consumer_and_start_consuming(static_group_id)
+  props = java.util.Properties.new
+  kafka = org.apache.kafka.clients.consumer.ConsumerConfig
+  props.put(kafka::BOOTSTRAP_SERVERS_CONFIG, "localhost:9092")
+  props.put(kafka::KEY_DESERIALIZER_CLASS_CONFIG, LogStash::Inputs::Kafka::DEFAULT_DESERIALIZER_CLASS)
+  props.put(kafka::VALUE_DESERIALIZER_CLASS_CONFIG, LogStash::Inputs::Kafka::DEFAULT_DESERIALIZER_CLASS)
+  props.put(kafka::GROUP_ID_CONFIG, "logstash")
+  props.put(kafka::GROUP_INSTANCE_ID_CONFIG, static_group_id)
+  consumer = org.apache.kafka.clients.consumer.KafkaConsumer.new(props)
+
+  Thread.new do
+    LogStash::Util::set_thread_name("integration_test_simple_consumer")
+    begin
+      consumer.subscribe(["logstash_integration_static_membership_topic"])
+      records = consumer.poll(java.time.Duration.ofSeconds(3))
+      "saboteur exited"
+    rescue => e
+      e # return the exception reached in thread.value
+    ensure
+      consumer.close
+    end
+  end
 end
 
 private
 
+def wait_kafka_input_is_ready(topic, queue)
+  # this is needed to give time to the kafka input to be up and running
+  header = org.apache.kafka.common.header.internals.RecordHeader.new("name", "Ping Up".to_java_bytes)
+  record = org.apache.kafka.clients.producer.ProducerRecord.new(topic, 0, "key", "value", [header])
+  send_message(record)
+
+  # Wait the message is processed
+  message = queue.poll(1, java.util.concurrent.TimeUnit::MINUTES)
+  expect(message).to_not eq(nil)
+end
+
 def consume_messages(config, queue: Queue.new, timeout:, event_count:)
   kafka_input = LogStash::Inputs::Kafka.new(config)
   kafka_input.register

data/spec/unit/inputs/kafka_spec.rb

@@ -83,6 +83,16 @@ describe LogStash::Inputs::Kafka do
     it "should register" do
       expect { subject.register }.to_not raise_error
     end
+
+    context "when the deprecated `default` is specified" do
+      let(:config) { common_config.merge('client_dns_lookup' => 'default') }
+
+      it 'should fallback `client_dns_lookup` to `use_all_dns_ips`' do
+        subject.register
+
+        expect(subject.client_dns_lookup).to eq('use_all_dns_ips')
+      end
+    end
   end
 
   describe '#running' do
@@ -287,7 +297,7 @@ describe LogStash::Inputs::Kafka do
           to receive(:new).with(hash_including('client.rack' => 'EU-R1')).
               and_return kafka_client = double('kafka-consumer')
 
-      expect( subject.send(:create_consumer, 'sample_client-0') ).to be kafka_client
+      expect( subject.send(:create_consumer, 'sample_client-0', 'group_instance_id') ).to be kafka_client
     end
   end
 
@@ -299,7 +309,7 @@ describe LogStash::Inputs::Kafka do
           to receive(:new).with(hash_including('session.timeout.ms' => '25000', 'max.poll.interval.ms' => '345000')).
               and_return kafka_client = double('kafka-consumer')
 
-      expect( subject.send(:create_consumer, 'sample_client-1') ).to be kafka_client
+      expect( subject.send(:create_consumer, 'sample_client-1', 'group_instance_id') ).to be kafka_client
     end
   end
 
@@ -311,7 +321,7 @@ describe LogStash::Inputs::Kafka do
           to receive(:new).with(hash_including('session.timeout.ms' => '25200', 'max.poll.interval.ms' => '123000')).
               and_return kafka_client = double('kafka-consumer')
 
-      expect( subject.send(:create_consumer, 'sample_client-2') ).to be kafka_client
+      expect( subject.send(:create_consumer, 'sample_client-2', 'group_instance_id') ).to be kafka_client
     end
   end
 
@@ -323,7 +333,7 @@ describe LogStash::Inputs::Kafka do
           to receive(:new).with(hash_including('enable.auto.commit' => 'false', 'check.crcs' => 'true')).
               and_return kafka_client = double('kafka-consumer')
 
-      expect( subject.send(:create_consumer, 'sample_client-3') ).to be kafka_client
+      expect( subject.send(:create_consumer, 'sample_client-3', 'group_instance_id') ).to be kafka_client
       expect( subject.enable_auto_commit ).to be false
     end
   end
@@ -336,7 +346,7 @@ describe LogStash::Inputs::Kafka do
           to receive(:new).with(hash_including('enable.auto.commit' => 'true', 'check.crcs' => 'false')).
               and_return kafka_client = double('kafka-consumer')
 
-      expect( subject.send(:create_consumer, 'sample_client-4') ).to be kafka_client
+      expect( subject.send(:create_consumer, 'sample_client-4', 'group_instance_id') ).to be kafka_client
       expect( subject.enable_auto_commit ).to be true
     end
   end

data/spec/unit/outputs/kafka_spec.rb

@@ -22,6 +22,14 @@ describe "outputs/kafka" do
       expect(kafka.topic_id).to eql 'test'
       expect(kafka.key_serializer).to eql 'org.apache.kafka.common.serialization.StringSerializer'
     end
+
+    it 'should fallback `client_dns_lookup` to `use_all_dns_ips` when the deprecated `default` is specified' do
+      simple_kafka_config["client_dns_lookup"] = 'default'
+      kafka = LogStash::Outputs::Kafka.new(simple_kafka_config)
+      kafka.register
+
+      expect(kafka.client_dns_lookup).to eq('use_all_dns_ips')
+    end
   end
 
   context 'when outputting messages' do

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: logstash-integration-kafka
 version: !ruby/object:Gem::Version
-  version: 10.12.0
+  version: 11.1.0
 platform: java
 authors:
 - Elastic
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-05-09 00:00:00.000000000 Z
+date: 2023-01-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement
@@ -49,7 +49,7 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 6.5.0
+        version: 8.3.0
   name: logstash-core
   prerelease: false
   type: :runtime
@@ -57,7 +57,7 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 6.5.0
+        version: 8.3.0
 - !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement
     requirements:
@@ -258,17 +258,17 @@ files:
 - spec/unit/inputs/kafka_spec.rb
 - spec/unit/outputs/kafka_spec.rb
 - vendor/jar-dependencies/com/github/luben/zstd-jni/1.5.2-2/zstd-jni-1.5.2-2.jar
-- vendor/jar-dependencies/io/confluent/common-config/6.2.2/common-config-6.2.2.jar
-- vendor/jar-dependencies/io/confluent/common-utils/6.2.2/common-utils-6.2.2.jar
-- vendor/jar-dependencies/io/confluent/kafka-avro-serializer/6.2.2/kafka-avro-serializer-6.2.2.jar
-- vendor/jar-dependencies/io/confluent/kafka-schema-registry-client/6.2.2/kafka-schema-registry-client-6.2.2.jar
-- vendor/jar-dependencies/io/confluent/kafka-schema-serializer/6.2.2/kafka-schema-serializer-6.2.2.jar
+- vendor/jar-dependencies/io/confluent/common-config/7.3.0/common-config-7.3.0.jar
+- vendor/jar-dependencies/io/confluent/common-utils/7.3.0/common-utils-7.3.0.jar
+- vendor/jar-dependencies/io/confluent/kafka-avro-serializer/7.3.0/kafka-avro-serializer-7.3.0.jar
+- vendor/jar-dependencies/io/confluent/kafka-schema-registry-client/7.3.0/kafka-schema-registry-client-7.3.0.jar
+- vendor/jar-dependencies/io/confluent/kafka-schema-serializer/7.3.0/kafka-schema-serializer-7.3.0.jar
 - vendor/jar-dependencies/javax/ws/rs/javax.ws.rs-api/2.1.1/javax.ws.rs-api-2.1.1.jar
 - vendor/jar-dependencies/org/apache/avro/avro/1.11.0/avro-1.11.0.jar
-- vendor/jar-dependencies/org/apache/kafka/kafka-clients/2.8.1/kafka-clients-2.8.1.jar
-- vendor/jar-dependencies/org/apache/kafka/kafka_2.12/2.8.1/kafka_2.12-2.8.1.jar
+- vendor/jar-dependencies/org/apache/kafka/kafka-clients/3.3.1/kafka-clients-3.3.1.jar
+- vendor/jar-dependencies/org/apache/kafka/kafka_2.12/3.3.1/kafka_2.12-3.3.1.jar
 - vendor/jar-dependencies/org/glassfish/jersey/core/jersey-common/2.33/jersey-common-2.33.jar
-- vendor/jar-dependencies/org/lz4/lz4-java/1.7.1/lz4-java-1.7.1.jar
+- vendor/jar-dependencies/org/lz4/lz4-java/1.8.0/lz4-java-1.8.0.jar
 - vendor/jar-dependencies/org/slf4j/slf4j-api/1.7.36/slf4j-api-1.7.36.jar
 - vendor/jar-dependencies/org/xerial/snappy/snappy-java/1.1.8.4/snappy-java-1.1.8.4.jar
 homepage: http://www.elastic.co/guide/en/logstash/current/index.html