diff --git a/.gitignore b/.gitignore index cc1d06f81..8cf9c4e72 100644 --- a/.gitignore +++ b/.gitignore @@ -5,3 +5,6 @@ build dist MANIFEST env +servers/*/kafka-bin +.coverage +.noseids diff --git a/.gitmodules b/.gitmodules index b40620c30..e69de29bb 100644 --- a/.gitmodules +++ b/.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 diff --git a/.travis.yml b/.travis.yml index bd5f63aef..22b03a3c1 100644 --- a/.travis.yml +++ b/.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 $TRAVIS_PYTHON_VERSION` diff --git a/README.md b/README.md index 8e9912426..c05631836 100644 --- a/README.md +++ b/README.md @@ -190,32 +190,33 @@ pip install python-snappy tox ``` +## Run a single unit test +```shell +tox -e py27 -- -v --with-id 102 +``` + ## Run the integration tests The integration tests will actually start up real local Zookeeper instance and Kafka brokers, and send messages in using the client. -Note that you may want to add this to your global gitignore: +First, get the kafka binaries for integration testing: ```shell -.gradle/ -clients/build/ -contrib/build/ -contrib/hadoop-consumer/build/ -contrib/hadoop-producer/build/ -core/build/ -core/data/ -examples/build/ -perf/build/ +./build_integration.sh ``` - -First, check out and the Kafka source: +By default, the build_integration.sh script will download binary +distributions for all supported kafka versions. +To test against the latest source build, set KAFKA_VERSION=trunk +and optionally set SCALA_VERSION (defaults to 2.8.0, but 2.10.1 is recommended) ```shell -git submodule update --init -./build_integration.sh +SCALA_VERSION=2.10.1 KAFKA_VERSION=trunk ./build_integration.sh ``` Then run the tests against supported Kafka versions: ```shell KAFKA_VERSION=0.8.0 tox KAFKA_VERSION=0.8.1 tox +KAFKA_VERSION=0.8.1.1 tox +KAFKA_VERSION=trunk tox ``` + diff --git a/build_integration.sh b/build_integration.sh index da87f349a..bb46e54f1 100755 --- a/build_integration.sh +++ b/build_integration.sh @@ -1,5 +1,61 @@ #!/bin/bash -git submodule update --init -(cd servers/0.8.0/kafka-src && ./sbt update package assembly-package-dependency) -(cd servers/0.8.1/kafka-src && ./gradlew jar) +# Versions available for testing via binary distributions +OFFICIAL_RELEASES="0.8.0 0.8.1 0.8.1.1" + +# Useful configuration vars, with sensible defaults +if [ -z "$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 diff --git a/servers/0.8.0/kafka-src b/servers/0.8.0/kafka-src deleted file mode 160000 index 15bb3961d..000000000 --- a/servers/0.8.0/kafka-src +++ /dev/null @@ -1 +0,0 @@ -Subproject commit 15bb3961d9171c1c54c4c840a554ce2c76168163 diff --git a/servers/0.8.1.1/resources/kafka.properties b/servers/0.8.1.1/resources/kafka.properties new file mode 100644 index 000000000..a638f394a --- /dev/null +++ b/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= + +# 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= + +# 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 diff --git a/servers/0.8.1.1/resources/log4j.properties b/servers/0.8.1.1/resources/log4j.properties new file mode 100644 index 000000000..f863b3bd7 --- /dev/null +++ b/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 diff --git a/servers/0.8.1.1/resources/zookeeper.properties b/servers/0.8.1.1/resources/zookeeper.properties new file mode 100644 index 000000000..e3fd09742 --- /dev/null +++ b/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 diff --git a/servers/0.8.1/kafka-src b/servers/0.8.1/kafka-src deleted file mode 160000 index 150d0a70c..000000000 --- a/servers/0.8.1/kafka-src +++ /dev/null @@ -1 +0,0 @@ -Subproject commit 150d0a70cbe2b1f980e9565a4fa59b0420d1c0a1 diff --git a/servers/trunk/resources/kafka.properties b/servers/trunk/resources/kafka.properties new file mode 100644 index 000000000..a638f394a --- /dev/null +++ b/servers/trunk/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= + +# 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= + +# 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 diff --git a/servers/trunk/resources/log4j.properties b/servers/trunk/resources/log4j.properties new file mode 100644 index 000000000..f863b3bd7 --- /dev/null +++ b/servers/trunk/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 diff --git a/servers/trunk/resources/zookeeper.properties b/servers/trunk/resources/zookeeper.properties new file mode 100644 index 000000000..e3fd09742 --- /dev/null +++ b/servers/trunk/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 diff --git a/test/fixtures.py b/test/fixtures.py index df8cd42b3..adb064205 100644 --- a/test/fixtures.py +++ b/test/fixtures.py @@ -1,9 +1,11 @@ import logging import glob import os +import os.path import shutil import subprocess import tempfile +import urllib2 import uuid from urlparse import urlparse @@ -14,41 +16,62 @@ class Fixture(object): kafka_version = os.environ.get('KAFKA_VERSION', '0.8.0') scala_version = os.environ.get("SCALA_VERSION", '2.8.0') project_root = os.environ.get('PROJECT_ROOT', os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))) - kafka_root = os.environ.get("KAFKA_ROOT", os.path.join(project_root, 'servers', kafka_version, "kafka-src")) + kafka_root = os.environ.get("KAFKA_ROOT", os.path.join(project_root, 'servers', kafka_version, "kafka-bin")) ivy_root = os.environ.get('IVY_ROOT', os.path.expanduser("~/.ivy2/cache")) @classmethod - def test_resource(cls, filename): - return os.path.join(cls.project_root, "servers", cls.kafka_version, "resources", filename) + def download_official_distribution(cls, + kafka_version=None, + scala_version=None, + output_dir=None): + if not kafka_version: + kafka_version = cls.kafka_version + if not scala_version: + scala_version = cls.scala_version + if not output_dir: + output_dir = os.path.join(cls.project_root, 'servers', 'dist') + + distfile = 'kafka_%s-%s' % (scala_version, kafka_version,) + url_base = 'https://archive.apache.org/dist/kafka/%s/' % (kafka_version,) + output_file = os.path.join(output_dir, distfile + '.tgz') + + if os.path.isfile(output_file): + logging.info("Found file already on disk: %s" % output_file) + return output_file + + # New tarballs are .tgz, older ones are sometimes .tar.gz + try: + url = url_base + distfile + '.tgz' + logging.info("Attempting to download %s" % (url,)) + response = urllib2.urlopen(url) + except urllib2.HTTPError: + logging.exception("HTTP Error") + url = url_base + distfile + '.tar.gz' + logging.info("Attempting to download %s" % (url,)) + response = urllib2.urlopen(url) + + logging.info("Saving distribution file to %s" % (output_file,)) + with open(os.path.join(output_dir, distfile + '.tgz'), 'w') as f: + f.write(response.read()) + + return output_file @classmethod - def test_classpath(cls): - # ./kafka-src/bin/kafka-run-class.sh is the authority. - jars = ["."] - - # 0.8.0 build path, should contain the core jar and a deps jar - jars.extend(glob.glob(cls.kafka_root + "/core/target/scala-%s/*.jar" % cls.scala_version)) - - # 0.8.1 build path, should contain the core jar and several dep jars - jars.extend(glob.glob(cls.kafka_root + "/core/build/libs/*.jar")) - jars.extend(glob.glob(cls.kafka_root + "/core/build/dependant-libs-%s/*.jar" % cls.scala_version)) - - jars = filter(os.path.exists, map(os.path.abspath, jars)) - return ":".join(jars) + def test_resource(cls, filename): + return os.path.join(cls.project_root, "servers", cls.kafka_version, "resources", filename) @classmethod def kafka_run_class_args(cls, *args): - # ./kafka-src/bin/kafka-run-class.sh is the authority. - result = ["java", "-Xmx512M", "-server"] - result.append("-Dlog4j.configuration=file:%s" % cls.test_resource("log4j.properties")) - result.append("-Dcom.sun.management.jmxremote") - result.append("-Dcom.sun.management.jmxremote.authenticate=false") - result.append("-Dcom.sun.management.jmxremote.ssl=false") - result.append("-cp") - result.append(cls.test_classpath()) + result = [os.path.join(cls.kafka_root, 'bin', 'kafka-run-class.sh')] result.extend(args) return result + @classmethod + def kafka_run_class_env(cls): + env = os.environ.copy() + env['KAFKA_LOG4J_OPTS'] = "-Dlog4j.configuration=file:%s" % cls.test_resource("log4j.properties") + return env + @classmethod def render_template(cls, source_file, target_file, binding): with open(source_file, "r") as handle: @@ -94,10 +117,11 @@ def open(self): self.render_template(template, properties, vars(self)) # Configure Zookeeper child process - self.child = SpawnedService(self.kafka_run_class_args( + self.child = SpawnedService(args=self.kafka_run_class_args( "org.apache.zookeeper.server.quorum.QuorumPeerMain", - properties - )) + properties), + env=self.kafka_run_class_env() + ) # Party! self.out("Starting...") @@ -175,9 +199,10 @@ def open(self): self.render_template(template, properties, vars(self)) # Configure Kafka child process - self.child = SpawnedService(self.kafka_run_class_args( - "kafka.Kafka", properties - )) + self.child = SpawnedService(args=self.kafka_run_class_args( + "kafka.Kafka", properties), + env=self.kafka_run_class_env() + ) # Party! self.out("Creating Zookeeper chroot node...") @@ -186,6 +211,7 @@ def open(self): "-server", "%s:%d" % (self.zk_host, self.zk_port), "create", "/%s" % self.zk_chroot, "kafka-python" ), + env=self.kafka_run_class_env(), stdout=subprocess.PIPE, stderr=subprocess.PIPE) diff --git a/test/service.py b/test/service.py index 8872c8244..df6c1ba17 100644 --- a/test/service.py +++ b/test/service.py @@ -26,10 +26,11 @@ def close(self): class SpawnedService(threading.Thread): - def __init__(self, args=[]): + def __init__(self, args=[], env=None): threading.Thread.__init__(self) self.args = args + self.env = env self.captured_stdout = [] self.captured_stderr = [] @@ -41,6 +42,7 @@ def run(self): def run_with_handles(self): self.child = subprocess.Popen( self.args, + env=self.env, bufsize=1, stdout=subprocess.PIPE, stderr=subprocess.PIPE) @@ -78,7 +80,7 @@ def dump_logs(self): for line in self.captured_stdout: logging.critical(line.rstrip()) - def wait_for(self, pattern, timeout=10): + def wait_for(self, pattern, timeout=30): t1 = time.time() while True: t2 = time.time() @@ -89,11 +91,13 @@ def wait_for(self, pattern, timeout=10): logging.exception("Received exception when killing child process") self.dump_logs() - raise RuntimeError("Waiting for %r timed out" % pattern) + raise RuntimeError("Waiting for %r timed out after %d seconds" % (pattern, timeout)) if re.search(pattern, '\n'.join(self.captured_stdout), re.IGNORECASE) is not None: + logging.info("Found pattern %r in %d seconds via stdout", pattern, (t2 - t1)) return if re.search(pattern, '\n'.join(self.captured_stderr), re.IGNORECASE) is not None: + logging.info("Found pattern %r in %d seconds via stderr", pattern, (t2 - t1)) return time.sleep(0.1) diff --git a/test/test_client_integration.py b/test/test_client_integration.py index 261d1685b..49c4b579a 100644 --- a/test/test_client_integration.py +++ b/test/test_client_integration.py @@ -53,7 +53,7 @@ def test_consume_none(self): # Offset Tests # #################### - @kafka_versions("0.8.1") + @kafka_versions("0.8.1", "0.8.1.1") def test_commit_fetch_offsets(self): req = OffsetCommitRequest(self.topic, 0, 42, "metadata") (resp,) = self.client.send_offset_commit_request("group", [req]) diff --git a/test/test_consumer_integration.py b/test/test_consumer_integration.py index a6589b360..cb3266974 100644 --- a/test/test_consumer_integration.py +++ b/test/test_consumer_integration.py @@ -213,7 +213,7 @@ def test_huge_messages(self): big_consumer.stop() - @kafka_versions("0.8.1") + @kafka_versions("0.8.1", "0.8.1.1") def test_offset_behavior__resuming_behavior(self): msgs1 = self.send_messages(0, range(0, 100)) msgs2 = self.send_messages(1, range(100, 200)) diff --git a/tox.ini b/tox.ini index 3c5fd17dd..09ec1e3a6 100644 --- a/tox.ini +++ b/tox.ini @@ -8,6 +8,6 @@ deps = mock python-snappy commands = - nosetests --with-coverage --cover-erase --cover-package kafka [] + nosetests {posargs:-v --with-id --with-coverage --cover-erase --cover-package kafka} setenv = PROJECT_ROOT = {toxinidir}