Merge pull request #295 from dpkp/kafka_0_8_2

Kafka 0.8.2.0 updates

kafka/client.py

@@ -11,7 +11,7 @@ from kafka.common import (TopicAndPartition, BrokerMetadata,
                           ConnectionError, FailedPayloadsError,
                           KafkaTimeoutError, KafkaUnavailableError,
                           LeaderNotAvailableError, UnknownTopicOrPartitionError,
-                          NotLeaderForPartitionError)
+                          NotLeaderForPartitionError, ReplicaNotAvailableError)
 
 from kafka.conn import collect_hosts, KafkaConnection, DEFAULT_SOCKET_TIMEOUT_SECONDS
 from kafka.protocol import KafkaProtocol
@@ -350,6 +350,11 @@ class KafkaClient(object):
                     log.error('No leader for topic %s partition %d', topic, partition)
                     self.topics_to_brokers[topic_part] = None
                     continue
+                # If one of the replicas is unavailable -- ignore
+                # this error code is provided for admin purposes only
+                # we never talk to replicas, only the leader
+                except ReplicaNotAvailableError:
+                    log.warning('Some (non-leader) replicas not available for topic %s partition %d', topic, partition)
 
                 # If Known Broker, topic_partition -> BrokerMetadata
                 if leader in self.brokers:

servers/0.8.2.0/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/0.8.2.0/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/0.8.2.0/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

test/fixtures.py

@@ -123,7 +123,7 @@ class ZookeeperFixture(Fixture):
         # Party!
         self.out("Starting...")
         self.child.start()
-        self.child.wait_for(r"Snapshotting")
+        self.child.wait_for(r"binding to port")
         self.out("Done!")
 
     def close(self):
@@ -212,8 +212,8 @@ class KafkaFixture(Fixture):
 
         if proc.wait() != 0:
             self.out("Failed to create Zookeeper chroot node")
-            self.out(proc.stdout)
-            self.out(proc.stderr)
+            self.out(proc.stdout.read())
+            self.out(proc.stderr.read())
             raise RuntimeError("Failed to create Zookeeper chroot node")
         self.out("Done!")
 

test/test_client_integration.py

@@ -54,7 +54,7 @@ class TestKafkaClientIntegration(KafkaIntegrationTestCase):
     #   Offset Tests   #
     ####################
 
-    @kafka_versions("0.8.1", "0.8.1.1")
+    @kafka_versions("0.8.1", "0.8.1.1", "0.8.2.0")
     def test_commit_fetch_offsets(self):
         req = OffsetCommitRequest(self.topic, 0, 42, b"metadata")
         (resp,) = self.client.send_offset_commit_request(b"group", [req])

test/test_consumer_integration.py

@@ -257,7 +257,7 @@ class TestConsumerIntegration(KafkaIntegrationTestCase):
 
         big_consumer.stop()
 
-    @kafka_versions("0.8.1", "0.8.1.1")
+    @kafka_versions("0.8.1", "0.8.1.1", "0.8.2.0")
     def test_offset_behavior__resuming_behavior(self):
         self.send_messages(0, range(0, 100))
         self.send_messages(1, range(100, 200))
@@ -357,7 +357,7 @@ class TestConsumerIntegration(KafkaIntegrationTestCase):
         self.assertEqual(len(messages), 5)
         self.assertGreaterEqual(t.interval, TIMEOUT_MS / 1000.0 )
 
-    @kafka_versions("0.8.1", "0.8.1.1")
+    @kafka_versions("0.8.1", "0.8.1.1", "0.8.2.0")
     def test_kafka_consumer__offset_commit_resume(self):
         GROUP_ID = random_string(10)