org.apache.hadoop.mapreduce.lib.chain.ChainMapper Maven / Gradle / Ivy
/**
* 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 org.apache.hadoop.shaded.com.liance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org.apache.hadoop.shaded.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.
*/
package org.apache.hadoop.shaded.org.apache.hadoop.mapreduce.lib.chain;
import java.org.apache.hadoop.shaded.io.IOException;
import org.apache.hadoop.shaded.org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.shaded.org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.shaded.org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.shaded.org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.shaded.org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.shaded.org.apache.hadoop.mapreduce.lib.chain.Chain.ChainBlockingQueue;
/**
* The ChainMapper class allows to use multiple Mapper classes within a single
* Map task.
*
*
* The Mapper classes are invoked in a chained (or piped) fashion, the output of
* the first becomes the input of the second, and so on until the last Mapper,
* the output of the last Mapper will be written to the task's output.
*
*
* The key functionality of this feature is that the Mappers in the chain do not
* need to be aware that they are executed in a chain. This enables having
* reusable specialized Mappers that can be org.apache.hadoop.shaded.com.ined to perform org.apache.hadoop.shaded.com.osite
* operations within a single task.
*
*
* Special care has to be taken when creating chains that the key/values output
* by a Mapper are valid for the following Mapper in the chain. It is assumed
* all Mappers and the Reduce in the chain use matching output and input key and
* value classes as no conversion is done by the chaining code.
*
*
* Using the ChainMapper and the ChainReducer classes is possible to org.apache.hadoop.shaded.com.ose
* Map/Reduce jobs that look like [MAP+ / REDUCE MAP*]. And
* immediate benefit of this pattern is a dramatic reduction in disk IO.
*
*
* IMPORTANT: There is no need to specify the output key/value classes for the
* ChainMapper, this is done by the addMapper for the last mapper in the chain.
*
* ChainMapper usage pattern:
*
*
*
* ...
* Job = new Job(conf);
*
* Configuration mapAConf = new Configuration(false);
* ...
* ChainMapper.addMapper(job, AMap.class, LongWritable.class, Text.class,
* Text.class, Text.class, true, mapAConf);
*
* Configuration mapBConf = new Configuration(false);
* ...
* ChainMapper.addMapper(job, BMap.class, Text.class, Text.class,
* LongWritable.class, Text.class, false, mapBConf);
*
* ...
*
* job.waitForComplettion(true);
* ...
*
*/
@InterfaceAudience.Public
@InterfaceStability.Stable
public class ChainMapper extends
Mapper {
/**
* Adds a {@link Mapper} class to the chain mapper.
*
*
* The key and values are passed from one element of the chain to the next, by
* value. For the added Mapper the configuration given for it,
* mapperConf, have precedence over the job's Configuration. This
* precedence is in effect when the task is running.
*
*
* IMPORTANT: There is no need to specify the output key/value classes for the
* ChainMapper, this is done by the addMapper for the last mapper in the chain
*
*
* @param job
* The job.
* @param klass
* the Mapper class to add.
* @param inputKeyClass
* mapper input key class.
* @param inputValueClass
* mapper input value class.
* @param outputKeyClass
* mapper output key class.
* @param outputValueClass
* mapper output value class.
* @param mapperConf
* a configuration for the Mapper class. It is recommended to use a
* Configuration without default values using the
* Configuration(boolean loadDefaults) constructor with
* FALSE.
*/
public static void addMapper(Job job, Class klass,
Class inputKeyClass, Class inputValueClass,
Class outputKeyClass, Class outputValueClass,
Configuration mapperConf) throws IOException {
job.setMapperClass(ChainMapper.class);
job.setMapOutputKeyClass(outputKeyClass);
job.setMapOutputValueClass(outputValueClass);
Chain.addMapper(true, job, klass, inputKeyClass, inputValueClass,
outputKeyClass, outputValueClass, mapperConf);
}
private Chain chain;
protected void setup(Context context) {
chain = new Chain(true);
chain.setup(context.getConfiguration());
}
public void run(Context context) throws IOException, InterruptedException {
setup(context);
int numMappers = chain.getAllMappers().size();
if (numMappers == 0) {
return;
}
ChainBlockingQueue> inputqueue;
ChainBlockingQueue> outputqueue;
if (numMappers == 1) {
chain.runMapper(context, 0);
} else {
// add all the mappers with proper context
// add first mapper
outputqueue = chain.createBlockingQueue();
chain.addMapper(context, outputqueue, 0);
// add other mappers
for (int i = 1; i < numMappers - 1; i++) {
inputqueue = outputqueue;
outputqueue = chain.createBlockingQueue();
chain.addMapper(inputqueue, outputqueue, context, i);
}
// add last mapper
chain.addMapper(outputqueue, context, numMappers - 1);
}
// start all threads
chain.startAllThreads();
// wait for all threads
chain.joinAllThreads();
}
}