Use Kafka Binaries for Integration Tests (Issue #176)

.gitignore

@@ -5,3 +5,6 @@ build
 dist
 MANIFEST
 env
+servers/*/kafka-bin
+.coverage
+.noseids

.gitmodules

@@ -1,6 +0,0 @@
-[submodule "servers/0.8.0/kafka-src"]
-	path = servers/0.8.0/kafka-src
-	url = https://github.com/apache/kafka.git
-[submodule "servers/0.8.1/kafka-src"]
-	path = servers/0.8.1/kafka-src
-	url = https://github.com/apache/kafka.git

.travis.yml

@@ -5,8 +5,13 @@ python:
     - 2.7
     - pypy
 
+env:
+    - 
+    - KAFKA_VERSION=0.8.0
+    - KAFKA_VERSION=0.8.1
+    - KAFKA_VERSION=0.8.1.1
+
 before_install:
-    - git submodule update --init --recursive
     - sudo apt-get install libsnappy-dev
     - ./build_integration.sh
 
@@ -19,5 +24,3 @@ install:
 
 script:
     - tox -e `./travis_selector.sh $TRAVIS_PYTHON_VERSION`
-    - KAFKA_VERSION=0.8.0 tox -e `./travis_selector.sh $TRAVIS_PYTHON_VERSION`
-    - KAFKA_VERSION=0.8.1 tox -e `./travis_selector.sh $TRAVIS_PYTHON_VERSION`

README.md

@@ -190,32 +190,33 @@ pip install python-snappy
 tox
 ```
 
+## Run a single unit test
+```shell
+tox -e py27 -- -v --with-id 102
+```
+
 ## Run the integration tests
 
 The integration tests will actually start up real local Zookeeper
 instance and Kafka brokers, and send messages in using the client.
 
-Note that you may want to add this to your global gitignore:
+First, get the kafka binaries for integration testing:
 ```shell
-.gradle/
-clients/build/
-contrib/build/
-contrib/hadoop-consumer/build/
-contrib/hadoop-producer/build/
-core/build/
-core/data/
-examples/build/
-perf/build/
+./build_integration.sh
 ```
-
-First, check out and the Kafka source:
+By default, the build_integration.sh script will download binary
+distributions for all supported kafka versions.
+To test against the latest source build, set KAFKA_VERSION=trunk
+and optionally set SCALA_VERSION (defaults to 2.8.0, but 2.10.1 is recommended)
 ```shell
-git submodule update --init
-./build_integration.sh
+SCALA_VERSION=2.10.1 KAFKA_VERSION=trunk ./build_integration.sh
 ```
 
 Then run the tests against supported Kafka versions:
 ```shell
 KAFKA_VERSION=0.8.0 tox
 KAFKA_VERSION=0.8.1 tox
+KAFKA_VERSION=0.8.1.1 tox
+KAFKA_VERSION=trunk tox
 ```
+

build_integration.sh

@@ -1,5 +1,61 @@
 #!/bin/bash
 
-git submodule update --init
-(cd servers/0.8.0/kafka-src && ./sbt update package assembly-package-dependency)
-(cd servers/0.8.1/kafka-src && ./gradlew jar)
+# Versions available for testing via binary distributions
+OFFICIAL_RELEASES="0.8.0 0.8.1 0.8.1.1"
+
+# Useful configuration vars, with sensible defaults
+if [ -z "$SCALA_VERSION" ]; then
+  SCALA_VERSION=2.8.0
+fi
+
+# On travis CI, empty KAFKA_VERSION means skip integration tests
+# so we dont try to get binaries 
+# Otherwise it means test all official releases, so we get all of them!
+if [ -z "$KAFKA_VERSION" -a -z "$TRAVIS" ]; then
+  KAFKA_VERSION=$OFFICIAL_RELEASES
+fi
+
+# By default look for binary releases at archive.apache.org
+if [ -z "$DIST_BASE_URL" ]; then
+  DIST_BASE_URL="https://archive.apache.org/dist/kafka/"
+fi
+
+# When testing against source builds, use this git repo
+if [ -z "$KAFKA_SRC_GIT" ]; then
+  KAFKA_SRC_GIT="https://github.com/apache/kafka.git"
+fi
+
+pushd servers
+  mkdir -p dist
+  pushd dist
+    for kafka in $KAFKA_VERSION; do
+      if [ "$kafka" == "trunk" ]; then
+        if [ ! -d "$kafka" ]; then
+          git clone $KAFKA_SRC_GIT $kafka
+        fi
+        pushd $kafka
+          git pull
+          ./gradlew -PscalaVersion=$SCALA_VERSION -Pversion=$kafka releaseTarGz -x signArchives
+        popd
+        # Not sure how to construct the .tgz name accurately, so use a wildcard (ugh)
+        tar xzvf $kafka/core/build/distributions/kafka_*.tgz -C ../$kafka/
+        rm $kafka/core/build/distributions/kafka_*.tgz
+        mv ../$kafka/kafka_* ../$kafka/kafka-bin
+      else
+        echo "-------------------------------------"
+        echo "Checking kafka binaries for ${kafka}"
+        echo
+        wget -N https://archive.apache.org/dist/kafka/$kafka/kafka_${SCALA_VERSION}-${kafka}.tgz || wget -N https://archive.apache.org/dist/kafka/$kafka/kafka_${SCALA_VERSION}-${kafka}.tar.gz
+        echo
+        if [ ! -d "../$kafka/kafka-bin" ]; then
+          echo "Extracting kafka binaries for ${kafka}"
+          tar xzvf kafka_${SCALA_VERSION}-${kafka}.t* -C ../$kafka/
+          mv ../$kafka/kafka_${SCALA_VERSION}-${kafka} ../$kafka/kafka-bin
+        else
+          echo "$kafka/kafka-bin directory already exists -- skipping tgz extraction"
+        fi
+      fi
+      echo
+    done
+  popd
+popd

servers/0.8.1.1/resources/kafka.properties

@@ -0,0 +1,118 @@
+# 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={broker_id}
+
+############################# Socket Server Settings #############################
+
+# The port the socket server listens on
+port={port}
+
+# Hostname the broker will bind to. If not set, the server will bind to all interfaces
+host.name={host}
+
+# 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=<hostname routable by clients>
+
+# 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={tmp_dir}/data
+
+# 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}
+
+############################# 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={zk_host}:{zk_port}/{zk_chroot}
+
+# Timeout in ms for connecting to zookeeper
+zookeeper.connection.timeout.ms=1000000

servers/0.8.1.1/resources/log4j.properties

@@ -0,0 +1,24 @@
+# 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.
+
+log4j.rootLogger=INFO, stdout
+
+log4j.appender.stdout=org.apache.log4j.ConsoleAppender
+log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
+log4j.appender.stdout.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+log4j.logger.kafka=DEBUG, stdout
+log4j.logger.org.I0Itec.zkclient.ZkClient=INFO, stdout
+log4j.logger.org.apache.zookeeper=INFO, stdout

servers/0.8.1.1/resources/zookeeper.properties

@@ -0,0 +1,21 @@
+# 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={tmp_dir}
+# the port at which the clients will connect
+clientPort={port}
+clientPortAddress={host}
+# disable the per-ip limit on the number of connections since this is a non-production config
+maxClientCnxns=0