Java Code Examples for org.apache.hadoop.hbase.mapreduce.PutSortReducer

The following examples show how to use org.apache.hadoop.hbase.mapreduce.PutSortReducer. These examples are extracted from open source projects. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source Project: kylin-on-parquet-v2   Source File: HFileOutputFormat3.java    License: Apache License 2.0 5 votes vote down vote up
static void configureIncrementalLoad(Job job, HTableDescriptor tableDescriptor, RegionLocator regionLocator,
        Class<? extends OutputFormat<?, ?>> cls) throws IOException, UnsupportedEncodingException {
    Configuration conf = job.getConfiguration();
    job.setOutputKeyClass(ImmutableBytesWritable.class);
    job.setOutputValueClass(KeyValue.class);
    job.setOutputFormatClass(cls);

    // Based on the configured map output class, set the correct reducer to properly
    // sort the incoming values.
    // TODO it would be nice to pick one or the other of these formats.
    if (KeyValue.class.equals(job.getMapOutputValueClass())) {
        job.setReducerClass(KeyValueSortReducer.class);
    } else if (Put.class.equals(job.getMapOutputValueClass())) {
        job.setReducerClass(PutSortReducer.class);
    } else if (Text.class.equals(job.getMapOutputValueClass())) {
        job.setReducerClass(TextSortReducer.class);
    } else {
        LOG.warn("Unknown map output value type:" + job.getMapOutputValueClass());
    }

    conf.setStrings("io.serializations", conf.get("io.serializations"), MutationSerialization.class.getName(),
            ResultSerialization.class.getName(), KeyValueSerialization.class.getName());

    // Use table's region boundaries for TOP split points.
    LOG.info("Looking up current regions for table " + tableDescriptor.getTableName());
    List<ImmutableBytesWritable> startKeys = getRegionStartKeys(regionLocator);
    LOG.info("Configuring " + startKeys.size() + " reduce partitions " + "to match current region count");
    job.setNumReduceTasks(startKeys.size());

    configurePartitioner(job, startKeys);
    // Set compression algorithms based on column families
    configureCompression(conf, tableDescriptor);
    configureBloomType(tableDescriptor, conf);
    configureBlockSize(tableDescriptor, conf);
    configureDataBlockEncoding(tableDescriptor, conf);

    TableMapReduceUtil.addDependencyJars(job);
    TableMapReduceUtil.initCredentials(job);
    LOG.info("Incremental table " + regionLocator.getName() + " output configured.");
}
 
Example 2
Source Project: kylin   Source File: HFileOutputFormat3.java    License: Apache License 2.0 4 votes vote down vote up
static void configureIncrementalLoad(Job job, HTableDescriptor tableDescriptor, RegionLocator regionLocator,
        Class<? extends OutputFormat<?, ?>> cls) throws IOException, UnsupportedEncodingException {
    Configuration conf = job.getConfiguration();
    job.setOutputKeyClass(ImmutableBytesWritable.class);
    job.setOutputValueClass(KeyValue.class);
    job.setOutputFormatClass(cls);

    // Based on the configured map output class, set the correct reducer to properly
    // sort the incoming values.
    // TODO it would be nice to pick one or the other of these formats.
    if (KeyValue.class.equals(job.getMapOutputValueClass())) {
        job.setReducerClass(KeyValueSortReducer.class);
    } else if (Put.class.equals(job.getMapOutputValueClass())) {
        job.setReducerClass(PutSortReducer.class);
    } else if (Text.class.equals(job.getMapOutputValueClass())) {
        job.setReducerClass(TextSortReducer.class);
    } else {
        LOG.warn("Unknown map output value type:" + job.getMapOutputValueClass());
    }

    conf.setStrings("io.serializations", conf.get("io.serializations"), MutationSerialization.class.getName(),
            ResultSerialization.class.getName(), KeyValueSerialization.class.getName());

    if (conf.getBoolean(LOCALITY_SENSITIVE_CONF_KEY, DEFAULT_LOCALITY_SENSITIVE)) {
        // record this table name for creating writer by favored nodes
        LOG.info("bulkload locality sensitive enabled");
        conf.set(OUTPUT_TABLE_NAME_CONF_KEY, regionLocator.getName().getNameAsString());
    }
    
    // Use table's region boundaries for TOP split points.
    LOG.info("Looking up current regions for table " + tableDescriptor.getTableName());
    List<ImmutableBytesWritable> startKeys = getRegionStartKeys(regionLocator);
    LOG.info("Configuring " + startKeys.size() + " reduce partitions " + "to match current region count");
    job.setNumReduceTasks(startKeys.size());

    configurePartitioner(job, startKeys);
    // Set compression algorithms based on column families
    configureCompression(conf, tableDescriptor);
    configureBloomType(tableDescriptor, conf);
    configureBlockSize(tableDescriptor, conf);
    configureDataBlockEncoding(tableDescriptor, conf);

    TableMapReduceUtil.addDependencyJars(job);
    TableMapReduceUtil.initCredentials(job);
    LOG.info("Incremental table " + regionLocator.getName() + " output configured.");
}
 
Example 3
Source Project: learning-hadoop   Source File: ImportTsv.java    License: Apache License 2.0 4 votes vote down vote up
/**
 * Sets up the actual job.
 * 
 * @param conf
 *            The current configuration.
 * @param args
 *            The command line parameters.
 * @return The newly created job.
 * @throws IOException
 *             When setting up the job fails.
 */
public static Job createSubmittableJob(Configuration conf, String[] args)
		throws IOException, ClassNotFoundException {

	// Support non-XML supported characters
	// by re-encoding the passed separator as a Base64 string.
	String actualSeparator = conf.get(SEPARATOR_CONF_KEY);
	if (actualSeparator != null) {
		conf.set(SEPARATOR_CONF_KEY,
				new String(Base64.encodeBytes(actualSeparator.getBytes())));
	}

	// See if a non-default Mapper was set
	String mapperClassName = conf.get(MAPPER_CONF_KEY);
	Class mapperClass = mapperClassName != null ? Class
			.forName(mapperClassName) : DEFAULT_MAPPER;

	String tableName = args[0];
	Path inputDir = new Path(args[1]);
	Job job = new Job(conf, NAME + "_" + tableName);
	job.setJarByClass(mapperClass);
	FileInputFormat.setInputPaths(job, inputDir);

	String inputCodec = conf.get(INPUT_LZO_KEY);
	if (inputCodec == null) {
		FileInputFormat.setMaxInputSplitSize(job, 67108864l); // max split
																// size =
																// 64m
		job.setInputFormatClass(TextInputFormat.class);
	} else {
		if (inputCodec.equalsIgnoreCase("lzo"))
			job.setInputFormatClass(LzoTextInputFormat.class);
		else {
			usage("not supported compression codec!");
			System.exit(-1);
		}
	}

	job.setMapperClass(mapperClass);

	String hfileOutPath = conf.get(BULK_OUTPUT_CONF_KEY);
	if (hfileOutPath != null) {
		HTable table = new HTable(conf, tableName);
		job.setReducerClass(PutSortReducer.class);
		Path outputDir = new Path(hfileOutPath);
		FileOutputFormat.setOutputPath(job, outputDir);
		job.setMapOutputKeyClass(ImmutableBytesWritable.class);
		job.setMapOutputValueClass(Put.class);
		HFileOutputFormat.configureIncrementalLoad(job, table);
	} else {
		// No reducers. Just write straight to table. Call
		// initTableReducerJob
		// to set up the TableOutputFormat.
		TableMapReduceUtil.initTableReducerJob(tableName, null, job);
		job.setNumReduceTasks(0);
	}

	TableMapReduceUtil.addDependencyJars(job);
	TableMapReduceUtil.addDependencyJars(job.getConfiguration(),
			com.google.common.base.Function.class /*
												 * Guava used by TsvParser
												 */);
	return job;
}