org.apache.hadoop.hbase.mapreduce.KeyValueSortReducer Java Examples

The following examples show how to use org.apache.hadoop.hbase.mapreduce.KeyValueSortReducer. 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 File: HFileOutputFormat3.java    From kylin-on-parquet-v2 with 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 File: HFileOutputFormat3.java    From kylin with 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 File: CubeHFileJob.java    From Kylin with Apache License 2.0 4 votes vote down vote up
public int run(String[] args) throws Exception {
    Options options = new Options();

    try {
        options.addOption(OPTION_JOB_NAME);
        options.addOption(OPTION_CUBE_NAME);
        options.addOption(OPTION_INPUT_PATH);
        options.addOption(OPTION_OUTPUT_PATH);
        options.addOption(OPTION_HTABLE_NAME);
        parseOptions(options, args);

        Path output = new Path(getOptionValue(OPTION_OUTPUT_PATH));
        String cubeName = getOptionValue(OPTION_CUBE_NAME).toUpperCase();

        CubeManager cubeMgr = CubeManager.getInstance(KylinConfig.getInstanceFromEnv());

        CubeInstance cube = cubeMgr.getCube(cubeName);
        job = Job.getInstance(getConf(), getOptionValue(OPTION_JOB_NAME));

        setJobClasspath(job);

        addInputDirs(getOptionValue(OPTION_INPUT_PATH), job);
        FileOutputFormat.setOutputPath(job, output);

        job.setInputFormatClass(SequenceFileInputFormat.class);
        job.setMapperClass(CubeHFileMapper.class);
        job.setReducerClass(KeyValueSortReducer.class);

        // set job configuration
        job.getConfiguration().set(BatchConstants.CFG_CUBE_NAME, cubeName);
        Configuration conf = HBaseConfiguration.create(getConf());
        // add metadata to distributed cache
        attachKylinPropsAndMetadata(cube, job.getConfiguration());

        String tableName = getOptionValue(OPTION_HTABLE_NAME).toUpperCase();
        HTable htable = new HTable(conf, tableName);

        //Automatic config !
        HFileOutputFormat.configureIncrementalLoad(job, htable);

        // set block replication to 3 for hfiles
        conf.set(DFSConfigKeys.DFS_REPLICATION_KEY, "3");

        this.deletePath(job.getConfiguration(), output);

        return waitForCompletion(job);
    } catch (Exception e) {
        logger.error("error in CubeHFileJob", e);
        printUsage(options);
        throw e;
    }
}