Add Vagrantfile, and provisioning scripts that set up a working 5-node cluster.

The provisioning scripts are also used on Travis CI.

.gitignore

@@ -7,6 +7,7 @@
 # Folders
 _obj
 _test
+.vagrant
 
 # Architecture specific extensions/prefixes
 *.[568vq]

.travis.yml

@@ -1,18 +1,15 @@
 language: go
 go:
-- 1.1
-- 1.2
 - 1.3
 
+env:
+  - KAFKA_INSTALL_ROOT=/home/travis/kafka KAFKA_HOSTNAME=localhost
+
 before_install:
-- wget http://apache.mirror.nexicom.net/kafka/0.8.1.1/kafka_2.10-0.8.1.1.tgz -O kafka.tgz
-- mkdir -p kafka && tar xzf kafka.tgz -C kafka --strip-components 1
-- nohup bash -c "cd kafka && bin/zookeeper-server-start.sh config/zookeeper.properties &"
-- sleep 5
-- nohup bash -c "cd kafka && bin/kafka-server-start.sh config/server.properties &"
-- sleep 5
-- kafka/bin/kafka-topics.sh --create --partitions 1 --replication-factor 1 --topic single_partition --zookeeper localhost:2181
-- kafka/bin/kafka-topics.sh --create --partitions 2 --replication-factor 1 --topic multi_partition --zookeeper localhost:2181
+- export REPOSITORY_ROOT=${TRAVIS_BUILD_DIR}
+- vagrant/install_cluster.sh
+- vagrant/boot_cluster.sh
+- vagrant/create_topics.sh
 
 notifications:
   flowdock: 15e08f7ed3a8fd2d89ddb36435301c1a

Vagrantfile

@@ -0,0 +1,17 @@
+# -*- mode: ruby -*-
+# vi: set ft=ruby :
+
+# Vagrantfile API/syntax version. Don't touch unless you know what you're doing!
+VAGRANTFILE_API_VERSION = "2"
+
+Vagrant.configure(VAGRANTFILE_API_VERSION) do |config|
+  config.vm.box = "hashicorp/precise64"
+
+  config.vm.provision :shell, path: "vagrant/provision.sh"
+
+  config.vm.network "private_network", ip: "192.168.100.67"
+
+  config.vm.provider "vmware_fusion" do |v|
+    v.vmx["memsize"] = "2048"
+  end
+end

functional_test.go

@@ -20,7 +20,7 @@ var (
 func init() {
 	kafkaAddr = os.Getenv("KAFKA_ADDR")
 	if kafkaAddr == "" {
-		kafkaAddr = "localhost:9092"
+		kafkaAddr = "localhost:6667"
 	}
 
 	c, err := net.Dial("tcp", kafkaAddr)
@@ -60,9 +60,7 @@ func TestProducingMessages(t *testing.T) {
 	}
 	defer consumer.Close()
 
-	producerConfig := NewProducerConfig()
-	producerConfig.Partitioner = &ConstantPartitioner{Constant: 0}
-	producer, err := NewProducer(client, producerConfig)
+	producer, err := NewProducer(client, nil)
 	if err != nil {
 		t.Fatal(err)
 	}

vagrant/boot_cluster.sh

@@ -0,0 +1,13 @@
+#/bin/sh
+
+set -ex
+
+for i in 1 2 3 4 5; do
+    KAFKA_PORT=`expr $i + 6666`
+    nohup bash -c "cd ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT} && bin/zookeeper-server-start.sh config/zookeeper.properties &"
+done
+
+for i in 1 2 3 4 5; do
+    KAFKA_PORT=`expr $i + 6666`
+    nohup bash -c "cd ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT} && bin/kafka-server-start.sh config/server.properties &"
+done

vagrant/create_topics.sh

@@ -0,0 +1,9 @@
+#!/bin/sh
+
+set -ex
+
+sleep 10
+
+cd ${KAFKA_INSTALL_ROOT}/kafka-6667
+bin/kafka-topics.sh --create --partitions 1 --replication-factor 3 --topic single_partition --zookeeper localhost:2181
+bin/kafka-topics.sh --create --partitions 2 --replication-factor 3 --topic multi_partition  --zookeeper localhost:2181

vagrant/install_cluster.sh

@@ -0,0 +1,40 @@
+#/bin/sh
+
+set -ex
+
+KAFKA_VERSION=0.8.1.1
+
+mkdir -p ${KAFKA_INSTALL_ROOT}
+if [ ! -f ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_VERSION}.tgz ]; then
+    wget --quiet http://apache.mirror.nexicom.net/kafka/${KAFKA_VERSION}/kafka_2.10-${KAFKA_VERSION}.tgz -O ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_VERSION}.tgz
+fi
+
+for i in 1 2 3 4 5; do
+    ZK_PORT=`expr $i + 2180`
+    KAFKA_PORT=`expr $i + 6666`
+
+    # unpack kafka
+    mkdir -p ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT}
+    tar xzf ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_VERSION}.tgz -C ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT} --strip-components 1
+
+    # broker configuration
+    cp ${REPOSITORY_ROOT}/vagrant/server.properties ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT}/config/
+    sed -i s/KAFKAID/${KAFKA_PORT}/g ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT}/config/server.properties
+    sed -i s/ZK_PORT/${ZK_PORT}/g ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT}/config/server.properties
+    sed -i s/KAFKA_HOSTNAME/${KAFKA_HOSTNAME}/g ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT}/config/server.properties
+
+    KAFKA_DATADIR="${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT}/data"
+    mkdir -p ${KAFKA_DATADIR}
+    sed -i s#KAFKA_DATADIR#${KAFKA_DATADIR}#g ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT}/config/server.properties
+
+    # zookeeper configuration
+    cp ${REPOSITORY_ROOT}/vagrant/zookeeper.properties ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT}/config/
+    sed -i s/KAFKAID/${KAFKA_PORT}/g ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT}/config/zookeeper.properties
+    sed -i s/ZK_PORT/${ZK_PORT}/g ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT}/config/zookeeper.properties
+
+    ZK_DATADIR="${KAFKA_INSTALL_ROOT}/zookeeper-${ZK_PORT}"
+    mkdir -p ${ZK_DATADIR}
+    sed -i s#ZK_DATADIR#${ZK_DATADIR}#g ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT}/config/zookeeper.properties
+
+    echo $i > ${KAFKA_INSTALL_ROOT}/zookeeper-${ZK_PORT}/myid
+done

vagrant/kafka.conf

@@ -0,0 +1,5 @@
+start on started zookeeper-ZK_PORT
+stop on stopping zookeeper-ZK_PORT
+
+pre-start exec sleep 2
+exec /opt/kafka-KAFKAID/bin/kafka-server-start.sh /opt/kafka-KAFKAID/config/server.properties

vagrant/provision.sh

@@ -0,0 +1,14 @@
+#!/bin/sh
+
+set -ex
+
+apt-get update
+yes | apt-get install default-jre
+
+export KAFKA_INSTALL_ROOT=/opt
+export KAFKA_HOSTNAME=192.168.100.67
+export REPOSITORY_ROOT=/vagrant
+
+sh /vagrant/vagrant/install_cluster.sh
+sh /vagrant/vagrant/setup_services.sh
+sh /vagrant/vagrant/create_topics.sh

vagrant/server.properties

@@ -0,0 +1,117 @@
+# 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.
+# see kafka.server.KafkaConfig for additional details and defaults
+
+############################# Server Basics #############################
+
+# The id of the broker. This must be set to a unique integer for each broker.
+broker.id=KAFKAID
+
+############################# Socket Server Settings #############################
+
+# The port the socket server listens on
+port=KAFKAID
+
+# Hostname the broker will bind to. If not set, the server will bind to all interfaces
+#host.name=localhost
+
+# Hostname the broker will advertise to producers and consumers. If not set, it uses the
+# value for "host.name" if configured.  Otherwise, it will use the value returned from
+# java.net.InetAddress.getCanonicalHostName().
+advertised.host.name=KAFKA_HOSTNAME
+
+# The port to publish to ZooKeeper for clients to use. If this is not set,
+# it will publish the same port that the broker binds to.
+# advertised.port=<port accessible by clients>
+
+# The number of threads handling network requests
+num.network.threads=2
+
+# The number of threads doing disk I/O
+num.io.threads=8
+
+# The send buffer (SO_SNDBUF) used by the socket server
+socket.send.buffer.bytes=1048576
+
+# The receive buffer (SO_RCVBUF) used by the socket server
+socket.receive.buffer.bytes=1048576
+
+# The maximum size of a request that the socket server will accept (protection against OOM)
+socket.request.max.bytes=104857600
+
+
+############################# Log Basics #############################
+
+# A comma seperated list of directories under which to store log files
+log.dirs=KAFKA_DATADIR
+
+# 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=2
+
+############################# 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 exceessive 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
+log.retention.hours=168
+
+# A size-based retention policy for logs. Segments are pruned from the log as long as the remaining
+# segments don't drop below log.retention.bytes.
+#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=536870912
+
+# 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=60000
+
+# 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
+
+############################# Zookeeper #############################
+
+# Zookeeper connection string (see zookeeper docs for details).
+# This is a comma separated host:port pairs, each corresponding to a zk
+# server. e.g. "127.0.0.1:3000,127.0.0.1:3001,127.0.0.1:3002".
+# You can also append an optional chroot string to the urls to specify the
+# root directory for all kafka znodes.
+zookeeper.connect=localhost:ZK_PORT
+
+# Timeout in ms for connecting to zookeeper
+zookeeper.connection.timeout.ms=1000000

vagrant/setup_services.sh

@@ -0,0 +1,21 @@
+#/bin/sh
+
+set -ex
+
+for i in 1 2 3 4 5; do
+    ZK_PORT=`expr $i + 2180`
+    KAFKA_PORT=`expr $i + 6666`
+
+    stop zookeeper-${ZK_PORT} || true
+
+    # set up zk service
+    cp ${REPOSITORY_ROOT}/vagrant/zookeeper.conf /etc/init/zookeeper-${ZK_PORT}.conf
+    sed -i s/KAFKAID/${KAFKA_PORT}/g /etc/init/zookeeper-${ZK_PORT}.conf
+
+    # set up kafka service
+    cp ${REPOSITORY_ROOT}/vagrant/kafka.conf /etc/init/kafka-${KAFKA_PORT}.conf
+    sed -i s/KAFKAID/${KAFKA_PORT}/g /etc/init/kafka-${KAFKA_PORT}.conf
+    sed -i s/ZK_PORT/${ZK_PORT}/g /etc/init/kafka-${KAFKA_PORT}.conf
+
+    start zookeeper-${ZK_PORT}
+done

vagrant/zookeeper.conf

@@ -0,0 +1,4 @@
+start on filesystem or runlevel [2345]
+stop on runlevel [!2345]
+
+exec /opt/kafka-KAFKAID/bin/zookeeper-server-start.sh /opt/kafka-KAFKAID/config/zookeeper.properties

vagrant/zookeeper.properties

@@ -0,0 +1,36 @@
+# 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.
+# the directory where the snapshot is stored.
+dataDir=ZK_DATADIR
+# the port at which the clients will connect
+clientPort=ZK_PORT
+# disable the per-ip limit on the number of connections since this is a non-production config
+maxClientCnxns=0
+
+# The number of milliseconds of each tick
+tickTime=2000
+
+# The number of ticks that the initial synchronization phase can take
+initLimit=10
+
+# The number of ticks that can pass between
+# sending a request and getting an acknowledgement
+syncLimit=5
+
+server.1=localhost:2281:2381
+server.2=localhost:2282:2382
+server.3=localhost:2283:2383
+server.4=localhost:2284:2384
+server.5=localhost:2285:2385