Use locally versioned config files

50kafka.yml

@@ -27,12 +27,12 @@ spec:
         volumeMounts:
         - name: datadir
           mountPath: /opt/kafka/data
-      #  - name: conf
-      #    mountPath: /opt/kafka/config/server.properties
-      #volumes:
-      #- name: conf
-      #  configMap:
-      #    name: conf-d
+        - name: config
+          mountPath: /opt/kafka/config
+      volumes:
+      - name: config
+        configMap:
+          name: kafka-config
   volumeClaimTemplates:
   - metadata:
       name: datadir

README.md

@@ -8,6 +8,13 @@ To get consistent service DNS names `kafka-N.broker.kafka`(`.svc.cluster.local`)
 kubectl create -f 00namespace.yml
 ```
 
+A typical Kafka install (see `docker-images` branch) comes with more config files than the server needs.
+The PetSet mounts instead a [ConfigMap](http://kubernetes.io/docs/user-guide/configmap/) with a minimal set of files.
+Load `./config/` into Kubernetes using:
+```
+./bootstrap/config.sh
+```
+
 ## Set up volume claims
 
 This step can be skipped in clusters that support automatic volume provisioning, such as GKE.
@@ -64,7 +71,7 @@ See `./test/test.sh` for some sample commands.
 
 This is WIP, but topic creation has been automated. Note that as a [Job](http://kubernetes.io/docs/user-guide/jobs/), it will restart if the command fails, including if the topic exists :(
 ```
-kubectl create -f test/10topic-create-test1.yml
+kubectl create -f test/11topic-create-test1.yml
 ```
 
 ## Teardown & cleanup

bootstrap/config.sh

@@ -0,0 +1 @@
+kubectl create configmap kafka-config --from-file=config --namespace=kafka

config/log4j.properties

@@ -0,0 +1,87 @@
+# 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.appender.kafkaAppender=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.kafkaAppender.DatePattern='.'yyyy-MM-dd-HH
+log4j.appender.kafkaAppender.File=${kafka.logs.dir}/server.log
+log4j.appender.kafkaAppender.layout=org.apache.log4j.PatternLayout
+log4j.appender.kafkaAppender.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+log4j.appender.stateChangeAppender=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.stateChangeAppender.DatePattern='.'yyyy-MM-dd-HH
+log4j.appender.stateChangeAppender.File=${kafka.logs.dir}/state-change.log
+log4j.appender.stateChangeAppender.layout=org.apache.log4j.PatternLayout
+log4j.appender.stateChangeAppender.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+log4j.appender.requestAppender=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.requestAppender.DatePattern='.'yyyy-MM-dd-HH
+log4j.appender.requestAppender.File=${kafka.logs.dir}/kafka-request.log
+log4j.appender.requestAppender.layout=org.apache.log4j.PatternLayout
+log4j.appender.requestAppender.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+log4j.appender.cleanerAppender=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.cleanerAppender.DatePattern='.'yyyy-MM-dd-HH
+log4j.appender.cleanerAppender.File=${kafka.logs.dir}/log-cleaner.log
+log4j.appender.cleanerAppender.layout=org.apache.log4j.PatternLayout
+log4j.appender.cleanerAppender.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+log4j.appender.controllerAppender=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.controllerAppender.DatePattern='.'yyyy-MM-dd-HH
+log4j.appender.controllerAppender.File=${kafka.logs.dir}/controller.log
+log4j.appender.controllerAppender.layout=org.apache.log4j.PatternLayout
+log4j.appender.controllerAppender.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+log4j.appender.authorizerAppender=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.authorizerAppender.DatePattern='.'yyyy-MM-dd-HH
+log4j.appender.authorizerAppender.File=${kafka.logs.dir}/kafka-authorizer.log
+log4j.appender.authorizerAppender.layout=org.apache.log4j.PatternLayout
+log4j.appender.authorizerAppender.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+# Turn on all our debugging info
+#log4j.logger.kafka.producer.async.DefaultEventHandler=DEBUG, kafkaAppender
+#log4j.logger.kafka.client.ClientUtils=DEBUG, kafkaAppender
+#log4j.logger.kafka.perf=DEBUG, kafkaAppender
+#log4j.logger.kafka.perf.ProducerPerformance$ProducerThread=DEBUG, kafkaAppender
+#log4j.logger.org.I0Itec.zkclient.ZkClient=DEBUG
+log4j.logger.kafka=INFO, kafkaAppender
+
+log4j.logger.kafka.network.RequestChannel$=WARN, requestAppender
+log4j.additivity.kafka.network.RequestChannel$=false
+
+#log4j.logger.kafka.network.Processor=TRACE, requestAppender
+#log4j.logger.kafka.server.KafkaApis=TRACE, requestAppender
+#log4j.additivity.kafka.server.KafkaApis=false
+log4j.logger.kafka.request.logger=WARN, requestAppender
+log4j.additivity.kafka.request.logger=false
+
+log4j.logger.kafka.controller=TRACE, controllerAppender
+log4j.additivity.kafka.controller=false
+
+log4j.logger.kafka.log.LogCleaner=INFO, cleanerAppender
+log4j.additivity.kafka.log.LogCleaner=false
+
+log4j.logger.state.change.logger=TRACE, stateChangeAppender
+log4j.additivity.state.change.logger=false
+
+#Change this to debug to get the actual audit log for authorizer.
+log4j.logger.kafka.authorizer.logger=WARN, authorizerAppender
+log4j.additivity.kafka.authorizer.logger=false
+

config/server.properties

@@ -0,0 +1,115 @@
+# 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=0
+
+############################# Socket Server Settings #############################
+
+# The address the socket server listens on. It will get the value returned from
+# java.net.InetAddress.getCanonicalHostName() if not configured.
+#   FORMAT:
+#     listeners = security_protocol://host_name:port
+#   EXAMPLE:
+#     listeners = PLAINTEXT://your.host.name:9092
+#listeners=PLAINTEXT://:9092
+
+# Hostname and port the broker will advertise to producers and consumers. If not set,
+# it uses the value for "listeners" if configured.  Otherwise, it will use the value
+# returned from java.net.InetAddress.getCanonicalHostName().
+#advertised.listeners=PLAINTEXT://your.host.name:9092
+
+# The number of threads handling network requests
+num.network.threads=3
+
+# 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=102400
+
+# The receive buffer (SO_RCVBUF) used by the socket server
+socket.receive.buffer.bytes=102400
+
+# 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/kafka-logs
+
+# 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=1
+
+# The number of threads per data directory to be used for log recovery at startup and flushing at shutdown.
+# This value is recommended to be increased for installations with data dirs located in RAID array.
+num.recovery.threads.per.data.dir=1
+
+############################# 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=1073741824
+
+# 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=300000
+
+############################# 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=zookeeper:2181
+
+# Timeout in ms for connecting to zookeeper
+zookeeper.connection.timeout.ms=6000