Support KRaft / 4.0 brokers in tests

.github/workflows/python-package.yml

@@ -33,6 +33,7 @@ jobs:
           - "3.0.2"
           - "3.5.2"
           - "3.9.0"
+          - "4.0.0"
         python:
           - "3.13"
         include:

Makefile

@@ -68,6 +68,7 @@ kafka_scala_0_9_0_1=2.11
 kafka_scala_0_10_0_0=2.11
 kafka_scala_0_10_0_1=2.11
 kafka_scala_0_10_1_0=2.11
+kafka_scala_4_0_0=2.13
 scala_version=$(if $(SCALA_VERSION),$(SCALA_VERSION),$(if $(kafka_scala_$(subst .,_,$(1))),$(kafka_scala_$(subst .,_,$(1))),2.12))
 
 kafka_artifact_name=kafka_$(call scala_version,$(1))-$(1).$(if $(filter 0.8.0,$(1)),tar.gz,tgz)

kafka/protocol/broker_api_versions.py

@@ -63,4 +63,6 @@
 
     (3, 9): {0: (0, 11), 1: (0, 17), 2: (0, 9), 3: (0, 12), 4: (0, 7), 5: (0, 4), 6: (0, 8), 7: (0, 3), 8: (0, 9), 9: (0, 9), 10: (0, 6), 11: (0, 9), 12: (0, 4), 13: (0, 5), 14: (0, 5), 15: (0, 5), 16: (0, 5), 17: (0, 1), 18: (0, 4), 19: (0, 7), 20: (0, 6), 21: (0, 2), 22: (0, 5), 23: (0, 4), 24: (0, 5), 25: (0, 4), 26: (0, 4), 27: (0, 1), 28: (0, 4), 29: (0, 3), 30: (0, 3), 31: (0, 3), 32: (0, 4), 33: (0, 2), 34: (0, 2), 35: (0, 4), 36: (0, 2), 37: (0, 3), 38: (0, 3), 39: (0, 2), 40: (0, 2), 41: (0, 3), 42: (0, 2), 43: (0, 2), 44: (0, 1), 45: (0, 0), 46: (0, 0), 47: (0, 0), 48: (0, 1), 49: (0, 1), 50: (0, 0), 51: (0, 0), 56: (0, 3), 57: (0, 1), 58: (0, 0), 60: (0, 1), 61: (0, 0), 65: (0, 0), 66: (0, 1), 67: (0, 0), 68: (0, 0), 69: (0, 0)},
 
+    (4, 0): {0: (0, 12), 1: (4, 17), 2: (1, 10), 3: (0, 13), 8: (2, 9), 9: (1, 9), 10: (0, 6), 11: (2, 9), 12: (0, 4), 13: (0, 5), 14: (0, 5), 15: (0, 6), 16: (0, 5), 17: (0, 1), 18: (0, 4), 19: (2, 7), 20: (1, 6), 21: (0, 2), 22: (0, 5), 23: (2, 4), 24: (0, 5), 25: (0, 4), 26: (0, 5), 27: (1, 1), 28: (0, 5), 29: (1, 3), 30: (1, 3), 31: (1, 3), 32: (1, 4), 33: (0, 2), 34: (1, 2), 35: (1, 4), 36: (0, 2), 37: (0, 3), 38: (1, 3), 39: (1, 2), 40: (1, 2), 41: (1, 3), 42: (0, 2), 43: (0, 2), 44: (0, 1), 45: (0, 0), 46: (0, 0), 47: (0, 0), 48: (0, 1), 49: (0, 1), 50: (0, 0), 51: (0, 0), 55: (0, 2), 57: (0, 2), 60: (0, 2), 61: (0, 0), 64: (0, 0), 65: (0, 0), 66: (0, 1), 68: (0, 1), 69: (0, 1), 74: (0, 0), 75: (0, 0), 80: (0, 0), 81: (0, 0)},
+
 }

servers/4.0.0/resources/kafka.properties

@@ -0,0 +1,161 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+############################# Server Basics #############################
+
+# The role of this server. Setting this puts us in KRaft mode
+process.roles=broker,controller
+
+# The node id associated with this instance's roles
+node.id={broker_id}
+
+# List of controller endpoints used connect to the controller cluster
+controller.quorum.bootstrap.servers={controller_bootstrap_host}:{controller_port}
+
+############################# Socket Server Settings #############################
+
+# The address the socket server listens on.
+# Combined nodes (i.e. those with `process.roles=broker,controller`) must list the controller listener here at a minimum.
+# If the broker listener is not defined, the default listener will use a host name that is equal to the value of java.net.InetAddress.getCanonicalHostName(),
+# with PLAINTEXT listener name, and port 9092.
+#   FORMAT:
+#     listeners = listener_name://host_name:port
+#   EXAMPLE:
+#     listeners = PLAINTEXT://your.host.name:9092
+#listeners=PLAINTEXT://:9092,CONTROLLER://:9093
+listeners={transport}://{host}:{port},CONTROLLER://{host}:{controller_port}
+
+# Name of listener used for communication between brokers.
+inter.broker.listener.name={transport}
+
+{sasl_config}
+
+authorizer.class.name=org.apache.kafka.metadata.authorizer.StandardAuthorizer
+allow.everyone.if.no.acl.found=true
+
+# Listener name, hostname and port the broker or the controller will advertise to clients.
+# If not set, it uses the value for "listeners".
+advertised.listeners={transport}://{host}:{port},CONTROLLER://{host}:{controller_port}
+
+# A comma-separated list of the names of the listeners used by the controller.
+# If no explicit mapping set in `listener.security.protocol.map`, default will be using PLAINTEXT protocol
+# This is required if running in KRaft mode.
+controller.listener.names=CONTROLLER
+
+# Maps listener names to security protocols, the default is for them to be the same. See the config documentation for more details
+listener.security.protocol.map=CONTROLLER:PLAINTEXT,PLAINTEXT:PLAINTEXT,SSL:SSL,SASL_PLAINTEXT:SASL_PLAINTEXT,SASL_SSL:SASL_SSL
+
+# The number of threads that the server uses for receiving requests from the network and sending responses to the network
+num.network.threads=3
+
+# The number of threads that the server uses for processing requests, which may include disk I/O
+num.io.threads=8
+
+# The send buffer (SO_SNDBUF) used by the socket server
+socket.send.buffer.bytes=102400
+
+# The receive buffer (SO_RCVBUF) used by the socket server
+socket.receive.buffer.bytes=102400
+
+# The maximum size of a request that the socket server will accept (protection against OOM)
+socket.request.max.bytes=104857600
+
+
+############################# Log Basics #############################
+
+# A comma separated list of directories under which to store log files
+log.dirs={tmp_dir}/kraft-combined-logs
+
+# The default number of log partitions per topic. More partitions allow greater
+# parallelism for consumption, but this will also result in more files across
+# the brokers.
+num.partitions={partitions}
+default.replication.factor={replicas}
+
+## Short Replica Lag -- Drops failed brokers out of ISR
+replica.lag.time.max.ms=1000
+replica.socket.timeout.ms=1000
+
+# The number of threads per data directory to be used for log recovery at startup and flushing at shutdown.
+# This value is recommended to be increased for installations with data dirs located in RAID array.
+num.recovery.threads.per.data.dir=1
+
+############################# Internal Topic Settings  #############################
+# The replication factor for the group metadata internal topics "__consumer_offsets", "__share_group_state" and "__transaction_state"
+# For anything other than development testing, a value greater than 1 is recommended to ensure availability such as 3.
+offsets.topic.replication.factor=1
+share.coordinator.state.topic.replication.factor=1
+share.coordinator.state.topic.min.isr=1
+transaction.state.log.replication.factor=1
+transaction.state.log.min.isr=1
+
+############################# Log Flush Policy #############################
+
+# Messages are immediately written to the filesystem but by default we only fsync() to sync
+# the OS cache lazily. The following configurations control the flush of data to disk.
+# There are a few important trade-offs here:
+#    1. Durability: Unflushed data may be lost if you are not using replication.
+#    2. Latency: Very large flush intervals may lead to latency spikes when the flush does occur as there will be a lot of data to flush.
+#    3. Throughput: The flush is generally the most expensive operation, and a small flush interval may lead to excessive seeks.
+# The settings below allow one to configure the flush policy to flush data after a period of time or
+# every N messages (or both). This can be done globally and overridden on a per-topic basis.
+
+# The number of messages to accept before forcing a flush of data to disk
+#log.flush.interval.messages=10000
+
+# The maximum amount of time a message can sit in a log before we force a flush
+#log.flush.interval.ms=1000
+
+############################# Log Retention Policy #############################
+
+# The following configurations control the disposal of log segments. The policy can
+# be set to delete segments after a period of time, or after a given size has accumulated.
+# A segment will be deleted whenever *either* of these criteria are met. Deletion always happens
+# from the end of the log.
+
+# The minimum age of a log file to be eligible for deletion due to age
+log.retention.hours=168
+
+# A size-based retention policy for logs. Segments are pruned from the log unless the remaining
+# segments drop below log.retention.bytes. Functions independently of log.retention.hours.
+#log.retention.bytes=1073741824
+
+# The maximum size of a log segment file. When this size is reached a new log segment will be created.
+log.segment.bytes=1073741824
+
+# The interval at which log segments are checked to see if they can be deleted according
+# to the retention policies
+log.retention.check.interval.ms=300000
+
+# By default the log cleaner is disabled and the log retention policy will default to just delete segments after their retention expires.
+# If log.cleaner.enable=true is set the cleaner will be enabled and individual logs can then be marked for log compaction.
+log.cleaner.enable=false
+
+# tune down offset topics to reduce setup time in tests
+offsets.commit.timeout.ms=500
+offsets.topic.num.partitions=2
+offsets.topic.replication.factor=1
+
+# Allow shorter session timeouts for tests
+group.min.session.timeout.ms=1000
+
+############################# Group Coordinator Settings #############################
+
+# The following configuration specifies the time, in milliseconds, that the GroupCoordinator will delay the initial consumer rebalance.
+# The rebalance will be further delayed by the value of group.initial.rebalance.delay.ms as new members join the group, up to a maximum of max.poll.interval.ms.
+# The default value for this is 3 seconds.
+# We override this to 0 here as it makes for a better out-of-the-box experience for development and testing.
+# However, in production environments the default value of 3 seconds is more suitable as this will help to avoid unnecessary, and potentially expensive, rebalances during application startup.
+group.initial.rebalance.delay.ms=0

test/conftest.py

@@ -9,6 +9,7 @@
 from test.testutil import env_kafka_version, random_string
 from test.fixtures import KafkaFixture, ZookeeperFixture
 
+
 @pytest.fixture(scope="module")
 def zookeeper():
     """Return a Zookeeper fixture"""
@@ -23,35 +24,39 @@ def zookeeper():
 
 
 @pytest.fixture(scope="module")
-def kafka_broker(kafka_broker_factory, zookeeper):
+def kafka_broker(kafka_broker_factory):
     """Return a Kafka broker fixture"""
     if "KAFKA_URI" in os.environ:
         parse = urlparse(os.environ["KAFKA_URI"])
         (host, port) = (parse.hostname, parse.port)
-        return KafkaFixture.instance(0, zookeeper, host=host, port=port, external=True)
+        return KafkaFixture.instance(0, host=host, port=port, external=True)
     else:
-        return kafka_broker_factory()[0]
+        return kafka_broker_factory()
 
 
 @pytest.fixture(scope="module")
-def kafka_broker_factory(zookeeper):
+def kafka_broker_factory():
     """Return a Kafka broker fixture factory"""
     assert env_kafka_version(), 'KAFKA_VERSION must be specified to run integration tests'
 
     _brokers = []
     def factory(**broker_params):
         params = {} if broker_params is None else broker_params.copy()
         params.setdefault('partitions', 4)
-        num_brokers = params.pop('num_brokers', 1)
-        brokers = tuple(KafkaFixture.instance(x, zookeeper, **params)
-                        for x in range(num_brokers))
-        _brokers.extend(brokers)
-        return brokers
+        node_id = params.pop('node_id', 0)
+        broker = KafkaFixture.instance(node_id, **params)
+        _brokers.append(broker)
+        return broker
 
     yield factory
 
+    zks = set()
     for broker in _brokers:
+        zks.add(broker.zookeeper)
         broker.close()
+    for zk in zks:
+        if zk:
+            zk.close()
 
 
 @pytest.fixture
@@ -108,11 +113,13 @@ def factory(**kafka_producer_params):
     if _producer[0]:
         _producer[0].close()
 
+
 @pytest.fixture
 def kafka_admin_client(kafka_admin_client_factory):
     """Return a KafkaAdminClient fixture"""
     yield kafka_admin_client_factory()
 
+
 @pytest.fixture
 def kafka_admin_client_factory(kafka_broker):
     """Return a KafkaAdminClient factory fixture"""
@@ -128,6 +135,7 @@ def factory(**kafka_admin_client_params):
     if _admin_client[0]:
         _admin_client[0].close()
 
+
 @pytest.fixture
 def topic(kafka_broker, request):
     """Return a topic fixture"""