example_conf.xml

<!-- Example configuration file for a Camus2Kafka Job -->

<configuration>

	<!-- ******************* -->
	<!-- Required parameters -->
	<!-- ******************* -->


	<!-- The HDFS path of the avro schema to be use 
	     to encode the Kafka messages. -->
	<property>
		<name>c2k.avro.output.schema.path</name>
		<value>/example/avro_schema.avsc</value>
	</property>


	<!-- The Kafka topic you want to process. -->
	<property>
		<name>c2k.kafka.topic</name>
		<value>EXAMPLE_KAFKA_TOPIC</value>
	</property>
	
	
	<!-- The (high-level) Kafka consumer group whose ZK 
	offsets will be set by Camus2Kafka so that the 
	regular Kafka topic can be stitched back at the 
	correct cut off point after re-consuming all of 
	the replay topic. -->
	<property>
		<name>c2k.kafka.consumer.group</name>
		<value>EXAMPLE_CONSUMER_GROUP</value>
	</property>
	
	
	<!-- The zookeeper hosts Camus2Kafka will connect to. -->
	<property>
		<name>c2k.zk.hosts</name>
		<value>zkhost1:2181,zkhost2:2181</value>
	</property>
	
	
	<!-- The camus destination directory. -->
	<property>
		<name>c2k.camus.dest.dir</name>
		<value>/camus/destination</value>
	</property>
	
	
	<!-- The camus execution directory. -->
	<property>
		<name>c2k.camus.exec.dir</name>
		<value>/camus/execution</value>
	</property>


	<!-- *************************************** -->
	<!-- Optional parameters with default values -->
	<!-- *************************************** -->


	<!-- Default: c2k.camus.dest.dir + "/" + c2k.kafka.topic + "/hourly/*/*/*/*" -->
	<property>
		<name>c2k.hdfs.input.dir</name>
		<value></value>
	</property>
	
	
	<!-- Default: c2k.kafka.topic + "_REPLAY" -->
	<property>
		<name>c2k.kafka.replay.topic</name>
		<value></value>
	</property>
	

	<!-- Default: c2k.camus.exec.dir + "/base/history" -->
	<property>
		<name>c2k.camus.history.dir</name>
		<value></value>
	</property>
	
	
	<!-- Default: com.mate1.camus2kafka.mapper.TimeBasedC2KMapper -->
	<property>
		<name>c2k.mapper.class</name>
		<value></value>
	</property>
	
	
	<!-- Default: com.mate1.camus2kafka.reducer.JsonC2KReducer -->
	<property>
		<name>c2k.reducer.class</name>
		<value></value>
	</property>
	
	
	<!-- The mapper out Key type. Default: LongWritable -->
	<property>
		<name>c2k.mapper.outkey.class</name>
		<value></value>
	</property>
	
	
	<!-- Skip the MapReduce task. Default: false -->
	<property>
		<name>c2k.set.zk.offsets.only</name>
		<value></value>
	</property>
	
	
	<!-- Default: unset. Possible values: custom, ALL
	     custom: show only the c2k. hadoop params. ALL: show all params -->
	<property>
		<name>c2k.printconf</name>
		<value></value>
	</property>


	<!-- ***************** -->
	<!-- Hadoop parameters -->
	<!-- ***************** -->


	<property>
		<name>mapred.job.reuse.jvm.num.tasks</name>
 		<value>100</value>
	</property>

</configuration>