fix: use modern kafka server.properties in vagrant

Rather than copying and templating an old copy of a Kafka
server.properties, modify the install_cluster.sh to append a small
number of custom values to the end of the Java properties file as
shipped with each Kafka version. This ensures we are otherwise testing
the defaults for each version apart from where we have made
customisations.

Signed-off-by: Dominic Evans <dominic.evans@uk.ibm.com>

vagrant/boot_cluster.sh

@@ -17,6 +17,25 @@ while ! nc -q 1 localhost 21805 </dev/null; do echo "Waiting"; sleep 1; done
 # Launch and wait for Kafka
 for i in 1 2 3 4 5; do
     KAFKA_PORT=`expr $i + 9090`
-    cd ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT} && bin/kafka-server-start.sh -daemon config/server.properties
+    cd ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT} && bash bin/kafka-server-start.sh -daemon config/server.properties
 done
-while ! nc -q 1 localhost 29095 </dev/null; do echo "Waiting"; sleep 1; done
+ps auxww | grep -i kafka
+
+N=10
+RC=1
+set +x
+printf "Waiting for Kafka to become available."
+for _ in $(seq 1 "$N"); do
+  if nc -z 127.0.0.1 29095 </dev/null; then
+      RC=0
+      break
+  fi
+  printf "."
+  sleep 1
+done
+printf "\n"
+if [ "$RC" -gt 0 ]; then
+  echo 'Error: Kafka failed to startup' >&2
+  find "${KAFKA_INSTALL_ROOT}" -name "server.log" -print0 | xargs tail -256
+  exit ${RC}
+fi

vagrant/install_cluster.sh

@@ -16,25 +16,62 @@ rm -f ${KAFKA_INSTALL_ROOT}/toxiproxy
 ln -s ${KAFKA_INSTALL_ROOT}/toxiproxy-${TOXIPROXY_VERSION} ${KAFKA_INSTALL_ROOT}/toxiproxy
 
 for i in 1 2 3 4 5; do
-    ZK_PORT=`expr $i + 2180`
-    ZK_PORT_REAL=`expr $i + 21800`
-    KAFKA_PORT=`expr $i + 9090`
-    KAFKA_PORT_REAL=`expr $i + 29090`
+    ZK_PORT=$((i + 2180))
+    ZK_PORT_REAL=$((i + 21800))
+    KAFKA_PORT=$((i + 9090))
+    KAFKA_PORT_REAL=$((i + 29090))
 
     # 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/KAFKAPORT/${KAFKA_PORT_REAL}/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
-    sed -i s/ZK_PORT/${ZK_PORT}/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
+    mkdir -p "${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT}/data"
+
+    # Append to default server.properties with a small number of customisations
+    printf "\n\n" >> "${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT}/config/server.properties"
+    cat << EOF >> "${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT}/config/server.properties"
+############################# Sarama Test Cluster #############################
+
+broker.id=${KAFKA_PORT}
+broker.rack=${i}
+
+# Listen on "real" port
+listeners=PLAINTEXT://:${KAFKA_PORT_REAL}
+# Advertise Toxiproxy port
+advertised.listeners=PLAINTEXT://${KAFKA_HOSTNAME}:${KAFKA_PORT}
+
+# Connect to Zookeeper via Toxiproxy port
+zookeeper.connect=127.0.0.1:${ZK_PORT}
+
+# Data directory
+log.dirs="${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT}/data"
+
+# Create new topics with a replication factor of 2 so failover can be tested
+# more easily.
+default.replication.factor=2
+
+# Turn on log.retention.bytes to avoid filling up the VM's disk
+log.retention.bytes=268435456
+log.segment.bytes=268435456
+
+# Enable topic deletion and disable auto-creation
+delete.topic.enable=true
+auto.create.topics.enable=false
+
+# Lower the zookeeper timeouts so we don't have to wait forever for a node
+# to die when we use toxiproxy to kill its zookeeper connection
+zookeeper.session.timeout.ms=3000
+zookeeper.connection.timeout.ms=3000
+
+# Disable broker ID length constraint
+reserved.broker.max.id=10000
+
+# Permit follower fetching (KIP-392)
+replica.selector.class=org.apache.kafka.common.replica.RackAwareReplicaSelector
+
+###############################################################################
+EOF
 
     # zookeeper configuration
     cp ${REPOSITORY_ROOT}/vagrant/zookeeper.properties ${KAFKA_INSTALL_ROOT}/kafka-${KAFKA_PORT}/config/

vagrant/server.properties

@@ -1,127 +0,0 @@
-# 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
-reserved.broker.max.id=10000
-
-############################# Socket Server Settings #############################
-
-# The port the socket server listens on
-port=KAFKAPORT
-
-# 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
-advertised.port=KAFKAID
-
-# 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
-
-# Create new topics with a replication factor of 2 so failover can be tested
-# more easily.
-default.replication.factor=2
-
-auto.create.topics.enable=false
-delete.topic.enable=true
-
-############################# 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=268435456
-
-# The maximum size of a log segment file. When this size is reached a new log segment will be created.
-log.segment.bytes=268435456
-
-# 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.session.timeout.ms=3000
-zookeeper.connection.timeout.ms=3000