Java Code Examples for org.apache.kylin.common.util.HadoopUtil#deleteHDFSMeta()

The following examples show how to use org.apache.kylin.common.util.HadoopUtil#deleteHDFSMeta() . 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: SparkUHCDictionary.java From kylin-on-parquet-v2 with Apache License 2.0

4 votes

@Override
protected void execute(OptionsHelper optionsHelper) throws Exception {
    String cubeName = optionsHelper.getOptionValue(OPTION_CUBE_NAME);
    String metaUrl = optionsHelper.getOptionValue(OPTION_META_URL);
    String segmentId = optionsHelper.getOptionValue(OPTION_SEGMENT_ID);
    String inputPath = optionsHelper.getOptionValue(OPTION_INPUT_PATH);
    String outputPath = optionsHelper.getOptionValue(OPTION_OUTPUT_PATH);
    String counterPath = optionsHelper.getOptionValue(OPTION_COUNTER_PATH);

    Class[] kryoClassArray = new Class[]{Class.forName("scala.reflect.ClassTag$$anon$1"),
            Class.forName("org.apache.kylin.engine.mr.steps.SelfDefineSortableKey")};

    SparkConf conf = new SparkConf().setAppName("Build uhc dictionary with spark for:" + cubeName + " segment " + segmentId);
    //serialization conf
    conf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer");
    conf.set("spark.kryo.registrator", "org.apache.kylin.engine.spark.KylinKryoRegistrator");
    conf.set("spark.kryo.registrationRequired", "true").registerKryoClasses(kryoClassArray);

    KylinSparkJobListener jobListener = new KylinSparkJobListener();
    try (JavaSparkContext sc = new JavaSparkContext(conf)) {
        sc.sc().addSparkListener(jobListener);
        HadoopUtil.deletePath(sc.hadoopConfiguration(), new Path(outputPath));

        Configuration hadoopConf = sc.hadoopConfiguration();
        hadoopConf.set("mapreduce.input.pathFilter.class", "org.apache.kylin.engine.mr.steps.filter.UHCDictPathFilter");

        final SerializableConfiguration sConf = new SerializableConfiguration(hadoopConf);
        KylinConfig config = AbstractHadoopJob.loadKylinConfigFromHdfs(sConf, metaUrl);

        CubeManager cubeMgr = CubeManager.getInstance(config);
        CubeInstance cube = cubeMgr.getCube(cubeName);
        final Job job = Job.getInstance(sConf.get());

        // calculate source record bytes size
        final LongAccumulator bytesWritten = sc.sc().longAccumulator();
        String hdfsDir = sc.hadoopConfiguration().get(BatchConstants.CFG_GLOBAL_DICT_BASE_DIR);

        List<TblColRef> uhcColumns = cube.getDescriptor().getAllUHCColumns();
        int reducerCount = uhcColumns.size();
        if (reducerCount == 0) {
            return;
        }

        logger.info("RDD Output path: {}", outputPath);
        logger.info("getTotalReducerNum: {}", reducerCount);
        logger.info("counter path {}", counterPath);

        JavaPairRDD<String, String> wholeSequenceFileNames = null;
        for (TblColRef tblColRef : uhcColumns) {
            String columnPath = inputPath + "/" + tblColRef.getIdentity();
            if (!HadoopUtil.getFileSystem(columnPath).exists(new Path(columnPath))) {
                continue;
            }
            if (wholeSequenceFileNames == null) {
                wholeSequenceFileNames = sc.wholeTextFiles(columnPath);
            } else {
                wholeSequenceFileNames = wholeSequenceFileNames.union(sc.wholeTextFiles(columnPath));
            }
        }

        if (wholeSequenceFileNames == null) {
            logger.error("There're no sequence files at " + inputPath + " !");
            return;
        }

        JavaPairRDD<String, Tuple3<Writable, Writable, String>> pairRDD = wholeSequenceFileNames.map(tuple -> tuple._1)
                .mapToPair(new InputPathAndFilterAddFunction2(config, uhcColumns))
                .filter(tuple -> tuple._1 != -1)
                .reduceByKey((list1, list2) -> combineAllColumnDistinctValues(list1, list2))
                .mapToPair(new ProcessUHCColumnValues(cubeName, config, hdfsDir, uhcColumns));

        MultipleOutputs.addNamedOutput(job, BatchConstants.CFG_OUTPUT_DICT, SequenceFileOutputFormat.class,
                NullWritable.class, ArrayPrimitiveWritable.class);

        FileOutputFormat.setOutputPath(job, new Path(outputPath));
        job.getConfiguration().set(BatchConstants.CFG_OUTPUT_PATH, outputPath);
        //prevent to create zero-sized default output
        LazyOutputFormat.setOutputFormatClass(job, SequenceFileOutputFormat.class);

        MultipleOutputsRDD multipleOutputsRDD = MultipleOutputsRDD.rddToMultipleOutputsRDD(pairRDD);
        multipleOutputsRDD.saveAsNewAPIHadoopDatasetWithMultipleOutputs(job.getConfiguration());

        logger.info("Map input records={}", reducerCount);
        logger.info("HDFS Read: {} HDFS Write", bytesWritten.value());

        Map<String, String> counterMap = Maps.newHashMap();
        counterMap.put(ExecutableConstants.SOURCE_RECORDS_COUNT, String.valueOf(reducerCount));
        counterMap.put(ExecutableConstants.SOURCE_RECORDS_SIZE, String.valueOf(bytesWritten.value()));

        // save counter to hdfs
        HadoopUtil.writeToSequenceFile(sc.hadoopConfiguration(), counterPath, counterMap);
        HadoopUtil.deleteHDFSMeta(metaUrl);
    }
}

Example 2

Source File: SparkUHCDictionary.java From kylin with Apache License 2.0

4 votes

@Override
protected void execute(OptionsHelper optionsHelper) throws Exception {
    String cubeName = optionsHelper.getOptionValue(OPTION_CUBE_NAME);
    String metaUrl = optionsHelper.getOptionValue(OPTION_META_URL);
    String segmentId = optionsHelper.getOptionValue(OPTION_SEGMENT_ID);
    String inputPath = optionsHelper.getOptionValue(OPTION_INPUT_PATH);
    String outputPath = optionsHelper.getOptionValue(OPTION_OUTPUT_PATH);
    String counterPath = optionsHelper.getOptionValue(OPTION_COUNTER_PATH);

    Class[] kryoClassArray = new Class[]{Class.forName("scala.reflect.ClassTag$$anon$1"),
            Class.forName("org.apache.kylin.engine.mr.steps.SelfDefineSortableKey")};

    SparkConf conf = new SparkConf().setAppName("Build uhc dictionary with spark for:" + cubeName + " segment " + segmentId);
    //serialization conf
    conf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer");
    conf.set("spark.kryo.registrator", "org.apache.kylin.engine.spark.KylinKryoRegistrator");
    conf.set("spark.kryo.registrationRequired", "true").registerKryoClasses(kryoClassArray);

    KylinSparkJobListener jobListener = new KylinSparkJobListener();
    try (JavaSparkContext sc = new JavaSparkContext(conf)) {
        sc.sc().addSparkListener(jobListener);
        HadoopUtil.deletePath(sc.hadoopConfiguration(), new Path(outputPath));

        Configuration hadoopConf = sc.hadoopConfiguration();
        hadoopConf.set("mapreduce.input.pathFilter.class", "org.apache.kylin.engine.mr.steps.filter.UHCDictPathFilter");

        final SerializableConfiguration sConf = new SerializableConfiguration(hadoopConf);
        KylinConfig config = AbstractHadoopJob.loadKylinConfigFromHdfs(sConf, metaUrl);

        CubeManager cubeMgr = CubeManager.getInstance(config);
        CubeInstance cube = cubeMgr.getCube(cubeName);
        final Job job = Job.getInstance(sConf.get());

        // calculate source record bytes size
        final LongAccumulator bytesWritten = sc.sc().longAccumulator();
        String hdfsDir = sc.hadoopConfiguration().get(BatchConstants.CFG_GLOBAL_DICT_BASE_DIR);

        List<TblColRef> uhcColumns = cube.getDescriptor().getAllUHCColumns();
        int reducerCount = uhcColumns.size();
        if (reducerCount == 0) {
            return;
        }

        logger.info("RDD Output path: {}", outputPath);
        logger.info("getTotalReducerNum: {}", reducerCount);
        logger.info("counter path {}", counterPath);

        JavaPairRDD<String, String> wholeSequenceFileNames = null;
        for (TblColRef tblColRef : uhcColumns) {
            String columnPath = inputPath + "/" + tblColRef.getIdentity();
            if (!HadoopUtil.getFileSystem(columnPath).exists(new Path(columnPath))) {
                continue;
            }
            if (wholeSequenceFileNames == null) {
                wholeSequenceFileNames = sc.wholeTextFiles(columnPath);
            } else {
                wholeSequenceFileNames = wholeSequenceFileNames.union(sc.wholeTextFiles(columnPath));
            }
        }

        if (wholeSequenceFileNames == null) {
            logger.error("There're no sequence files at " + inputPath + " !");
            return;
        }

        JavaPairRDD<String, Tuple3<Writable, Writable, String>> pairRDD = wholeSequenceFileNames.map(tuple -> tuple._1)
                .mapToPair(new InputPathAndFilterAddFunction2(config, uhcColumns))
                .filter(tuple -> tuple._1 != -1)
                .reduceByKey((list1, list2) -> combineAllColumnDistinctValues(list1, list2))
                .mapToPair(new ProcessUHCColumnValues(cubeName, config, hdfsDir, uhcColumns));

        MultipleOutputs.addNamedOutput(job, BatchConstants.CFG_OUTPUT_DICT, SequenceFileOutputFormat.class,
                NullWritable.class, ArrayPrimitiveWritable.class);

        FileOutputFormat.setOutputPath(job, new Path(outputPath));
        job.getConfiguration().set(BatchConstants.CFG_OUTPUT_PATH, outputPath);
        //prevent to create zero-sized default output
        LazyOutputFormat.setOutputFormatClass(job, SequenceFileOutputFormat.class);

        MultipleOutputsRDD multipleOutputsRDD = MultipleOutputsRDD.rddToMultipleOutputsRDD(pairRDD);
        multipleOutputsRDD.saveAsNewAPIHadoopDatasetWithMultipleOutputs(job.getConfiguration());

        logger.info("Map input records={}", reducerCount);
        logger.info("HDFS Read: {} HDFS Write", bytesWritten.value());

        Map<String, String> counterMap = Maps.newHashMap();
        counterMap.put(ExecutableConstants.SOURCE_RECORDS_COUNT, String.valueOf(reducerCount));
        counterMap.put(ExecutableConstants.SOURCE_RECORDS_SIZE, String.valueOf(bytesWritten.value()));

        // save counter to hdfs
        HadoopUtil.writeToSequenceFile(sc.hadoopConfiguration(), counterPath, counterMap);
        HadoopUtil.deleteHDFSMeta(metaUrl);
    }
}