List of usage examples for org.apache.hadoop.fs Path Path
public Path(URI aUri)
From source file:ai.grakn.graph.internal.computer.GraknSparkComputer.java
License:Open Source License
public GraknSparkComputer(final HadoopGraph hadoopGraph) { super(hadoopGraph); this.sparkConfiguration = new HadoopConfiguration(); ConfigurationUtils.copy(this.hadoopGraph.configuration(), this.sparkConfiguration); this.apacheConfiguration = new HadoopConfiguration(this.sparkConfiguration); apacheConfiguration.setProperty(Constants.GREMLIN_HADOOP_GRAPH_OUTPUT_FORMAT_HAS_EDGES, false); hadoopConfiguration = ConfUtil.makeHadoopConfiguration(apacheConfiguration); if (hadoopConfiguration.get(Constants.GREMLIN_SPARK_GRAPH_INPUT_RDD, null) == null && hadoopConfiguration.get(Constants.GREMLIN_HADOOP_GRAPH_INPUT_FORMAT, null) != null && FileInputFormat.class.isAssignableFrom(hadoopConfiguration .getClass(Constants.GREMLIN_HADOOP_GRAPH_INPUT_FORMAT, InputFormat.class))) { try {/* ww w.ja va 2s.c o m*/ final String inputLocation = FileSystem.get(hadoopConfiguration) .getFileStatus(new Path(hadoopConfiguration.get(Constants.GREMLIN_HADOOP_INPUT_LOCATION))) .getPath().toString(); apacheConfiguration.setProperty(Constants.MAPREDUCE_INPUT_FILEINPUTFORMAT_INPUTDIR, inputLocation); hadoopConfiguration.set(Constants.MAPREDUCE_INPUT_FILEINPUTFORMAT_INPUTDIR, inputLocation); } catch (final IOException e) { throw new IllegalStateException(e.getMessage(), e); } } }
From source file:ai.grakn.kb.internal.computer.GraknSparkComputer.java
License:Open Source License
@SuppressWarnings("PMD.UnusedFormalParameter") private Future<ComputerResult> submitWithExecutor() { jobGroupId = Integer.toString(ThreadLocalRandom.current().nextInt(Integer.MAX_VALUE)); String jobDescription = this.vertexProgram == null ? this.mapReducers.toString() : this.vertexProgram + "+" + this.mapReducers; // Use different output locations this.sparkConfiguration.setProperty(Constants.GREMLIN_HADOOP_OUTPUT_LOCATION, this.sparkConfiguration.getString(Constants.GREMLIN_HADOOP_OUTPUT_LOCATION) + "/" + jobGroupId); updateConfigKeys(sparkConfiguration); final Future<ComputerResult> result = computerService.submit(() -> { final long startTime = System.currentTimeMillis(); // apache and hadoop configurations that are used throughout the graph computer computation final org.apache.commons.configuration.Configuration graphComputerConfiguration = new HadoopConfiguration( this.sparkConfiguration); if (!graphComputerConfiguration.containsKey(Constants.SPARK_SERIALIZER)) { graphComputerConfiguration.setProperty(Constants.SPARK_SERIALIZER, GryoSerializer.class.getCanonicalName()); }//ww w . j a v a 2 s . co m graphComputerConfiguration.setProperty(Constants.GREMLIN_HADOOP_GRAPH_WRITER_HAS_EDGES, this.persist.equals(GraphComputer.Persist.EDGES)); final Configuration hadoopConfiguration = ConfUtil.makeHadoopConfiguration(graphComputerConfiguration); final Storage fileSystemStorage = FileSystemStorage.open(hadoopConfiguration); final boolean inputFromHDFS = FileInputFormat.class.isAssignableFrom( hadoopConfiguration.getClass(Constants.GREMLIN_HADOOP_GRAPH_READER, Object.class)); final boolean inputFromSpark = PersistedInputRDD.class.isAssignableFrom( hadoopConfiguration.getClass(Constants.GREMLIN_HADOOP_GRAPH_READER, Object.class)); final boolean outputToHDFS = FileOutputFormat.class.isAssignableFrom( hadoopConfiguration.getClass(Constants.GREMLIN_HADOOP_GRAPH_WRITER, Object.class)); final boolean outputToSpark = PersistedOutputRDD.class.isAssignableFrom( hadoopConfiguration.getClass(Constants.GREMLIN_HADOOP_GRAPH_WRITER, Object.class)); final boolean skipPartitioner = graphComputerConfiguration .getBoolean(Constants.GREMLIN_SPARK_SKIP_PARTITIONER, false); final boolean skipPersist = graphComputerConfiguration .getBoolean(Constants.GREMLIN_SPARK_SKIP_GRAPH_CACHE, false); if (inputFromHDFS) { String inputLocation = Constants .getSearchGraphLocation(hadoopConfiguration.get(Constants.GREMLIN_HADOOP_INPUT_LOCATION), fileSystemStorage) .orElse(null); if (null != inputLocation) { try { graphComputerConfiguration.setProperty(Constants.MAPREDUCE_INPUT_FILEINPUTFORMAT_INPUTDIR, FileSystem.get(hadoopConfiguration).getFileStatus(new Path(inputLocation)).getPath() .toString()); hadoopConfiguration.set(Constants.MAPREDUCE_INPUT_FILEINPUTFORMAT_INPUTDIR, FileSystem.get(hadoopConfiguration).getFileStatus(new Path(inputLocation)).getPath() .toString()); } catch (final IOException e) { throw new IllegalStateException(e.getMessage(), e); } } } final InputRDD inputRDD; final OutputRDD outputRDD; final boolean filtered; try { inputRDD = InputRDD.class.isAssignableFrom( hadoopConfiguration.getClass(Constants.GREMLIN_HADOOP_GRAPH_READER, Object.class)) ? hadoopConfiguration.getClass(Constants.GREMLIN_HADOOP_GRAPH_READER, InputRDD.class, InputRDD.class).newInstance() : InputFormatRDD.class.newInstance(); outputRDD = OutputRDD.class.isAssignableFrom( hadoopConfiguration.getClass(Constants.GREMLIN_HADOOP_GRAPH_WRITER, Object.class)) ? hadoopConfiguration.getClass(Constants.GREMLIN_HADOOP_GRAPH_WRITER, OutputRDD.class, OutputRDD.class).newInstance() : OutputFormatRDD.class.newInstance(); // if the input class can filter on load, then set the filters if (inputRDD instanceof InputFormatRDD && GraphFilterAware.class.isAssignableFrom(hadoopConfiguration.getClass( Constants.GREMLIN_HADOOP_GRAPH_READER, InputFormat.class, InputFormat.class))) { GraphFilterAware.storeGraphFilter(graphComputerConfiguration, hadoopConfiguration, this.graphFilter); filtered = false; } else if (inputRDD instanceof GraphFilterAware) { ((GraphFilterAware) inputRDD).setGraphFilter(this.graphFilter); filtered = false; } else filtered = this.graphFilter.hasFilter(); } catch (final InstantiationException | IllegalAccessException e) { throw new IllegalStateException(e.getMessage(), e); } // create the spark context from the graph computer configuration final JavaSparkContext sparkContext = new JavaSparkContext(Spark.create(hadoopConfiguration)); final Storage sparkContextStorage = SparkContextStorage.open(); sparkContext.setJobGroup(jobGroupId, jobDescription); GraknSparkMemory memory = null; // delete output location final String outputLocation = hadoopConfiguration.get(Constants.GREMLIN_HADOOP_OUTPUT_LOCATION, null); if (null != outputLocation) { if (outputToHDFS && fileSystemStorage.exists(outputLocation)) { fileSystemStorage.rm(outputLocation); } if (outputToSpark && sparkContextStorage.exists(outputLocation)) { sparkContextStorage.rm(outputLocation); } } // the Spark application name will always be set by SparkContextStorage, // thus, INFO the name to make it easier to debug logger.debug(Constants.GREMLIN_HADOOP_SPARK_JOB_PREFIX + (null == this.vertexProgram ? "No VertexProgram" : this.vertexProgram) + "[" + this.mapReducers + "]"); // add the project jars to the cluster this.loadJars(hadoopConfiguration, sparkContext); updateLocalConfiguration(sparkContext, hadoopConfiguration); // create a message-passing friendly rdd from the input rdd boolean partitioned = false; JavaPairRDD<Object, VertexWritable> loadedGraphRDD = inputRDD.readGraphRDD(graphComputerConfiguration, sparkContext); // if there are vertex or edge filters, filter the loaded graph rdd prior to partitioning and persisting if (filtered) { this.logger.debug("Filtering the loaded graphRDD: " + this.graphFilter); loadedGraphRDD = GraknSparkExecutor.applyGraphFilter(loadedGraphRDD, this.graphFilter); } // if the loaded graph RDD is already partitioned use that partitioner, // else partition it with HashPartitioner if (loadedGraphRDD.partitioner().isPresent()) { this.logger.debug("Using the existing partitioner associated with the loaded graphRDD: " + loadedGraphRDD.partitioner().get()); } else { if (!skipPartitioner) { final Partitioner partitioner = new HashPartitioner( this.workersSet ? this.workers : loadedGraphRDD.partitions().size()); this.logger.debug("Partitioning the loaded graphRDD: " + partitioner); loadedGraphRDD = loadedGraphRDD.partitionBy(partitioner); partitioned = true; assert loadedGraphRDD.partitioner().isPresent(); } else { // no easy way to test this with a test case assert skipPartitioner == !loadedGraphRDD.partitioner().isPresent(); this.logger.debug("Partitioning has been skipped for the loaded graphRDD via " + Constants.GREMLIN_SPARK_SKIP_PARTITIONER); } } // if the loaded graphRDD was already partitioned previous, // then this coalesce/repartition will not take place if (this.workersSet) { // ensures that the loaded graphRDD does not have more partitions than workers if (loadedGraphRDD.partitions().size() > this.workers) { loadedGraphRDD = loadedGraphRDD.coalesce(this.workers); } else { // ensures that the loaded graphRDD does not have less partitions than workers if (loadedGraphRDD.partitions().size() < this.workers) { loadedGraphRDD = loadedGraphRDD.repartition(this.workers); } } } // persist the vertex program loaded graph as specified by configuration // or else use default cache() which is MEMORY_ONLY if (!skipPersist && (!inputFromSpark || partitioned || filtered)) { loadedGraphRDD = loadedGraphRDD.persist(StorageLevel.fromString( hadoopConfiguration.get(Constants.GREMLIN_SPARK_GRAPH_STORAGE_LEVEL, "MEMORY_ONLY"))); } // final graph with view // (for persisting and/or mapReducing -- may be null and thus, possible to save space/time) JavaPairRDD<Object, VertexWritable> computedGraphRDD = null; try { //////////////////////////////// // process the vertex program // //////////////////////////////// if (null != this.vertexProgram) { memory = new GraknSparkMemory(this.vertexProgram, this.mapReducers, sparkContext); ///////////////// // if there is a registered VertexProgramInterceptor, use it to bypass the GraphComputer semantics if (graphComputerConfiguration .containsKey(Constants.GREMLIN_HADOOP_VERTEX_PROGRAM_INTERCEPTOR)) { try { final GraknSparkVertexProgramInterceptor<VertexProgram> interceptor = (GraknSparkVertexProgramInterceptor) Class .forName(graphComputerConfiguration .getString(Constants.GREMLIN_HADOOP_VERTEX_PROGRAM_INTERCEPTOR)) .newInstance(); computedGraphRDD = interceptor.apply(this.vertexProgram, loadedGraphRDD, memory); } catch (final ClassNotFoundException | IllegalAccessException | InstantiationException e) { throw new IllegalStateException(e.getMessage()); } } else { // standard GraphComputer semantics // get a configuration that will be propagated to all workers final HadoopConfiguration vertexProgramConfiguration = new HadoopConfiguration(); this.vertexProgram.storeState(vertexProgramConfiguration); // set up the vertex program and wire up configurations this.vertexProgram.setup(memory); JavaPairRDD<Object, ViewIncomingPayload<Object>> viewIncomingRDD = null; memory.broadcastMemory(sparkContext); // execute the vertex program while (true) { if (Thread.interrupted()) { sparkContext.cancelAllJobs(); throw new TraversalInterruptedException(); } memory.setInExecute(true); viewIncomingRDD = GraknSparkExecutor.executeVertexProgramIteration(loadedGraphRDD, viewIncomingRDD, memory, graphComputerConfiguration, vertexProgramConfiguration); memory.setInExecute(false); if (this.vertexProgram.terminate(memory)) { break; } else { memory.incrIteration(); memory.broadcastMemory(sparkContext); } } // if the graph will be continued to be used (persisted or mapreduced), // then generate a view+graph if ((null != outputRDD && !this.persist.equals(Persist.NOTHING)) || !this.mapReducers.isEmpty()) { computedGraphRDD = GraknSparkExecutor.prepareFinalGraphRDD(loadedGraphRDD, viewIncomingRDD, this.vertexProgram.getVertexComputeKeys()); assert null != computedGraphRDD && computedGraphRDD != loadedGraphRDD; } else { // ensure that the computedGraphRDD was not created assert null == computedGraphRDD; } } ///////////////// memory.complete(); // drop all transient memory keys // write the computed graph to the respective output (rdd or output format) if (null != outputRDD && !this.persist.equals(Persist.NOTHING)) { // the logic holds that a computeGraphRDD must be created at this point assert null != computedGraphRDD; outputRDD.writeGraphRDD(graphComputerConfiguration, computedGraphRDD); } } final boolean computedGraphCreated = computedGraphRDD != null && computedGraphRDD != loadedGraphRDD; if (!computedGraphCreated) { computedGraphRDD = loadedGraphRDD; } final Memory.Admin finalMemory = null == memory ? new MapMemory() : new MapMemory(memory); ////////////////////////////// // process the map reducers // ////////////////////////////// if (!this.mapReducers.isEmpty()) { // create a mapReduceRDD for executing the map reduce jobs on JavaPairRDD<Object, VertexWritable> mapReduceRDD = computedGraphRDD; if (computedGraphCreated && !outputToSpark) { // drop all the edges of the graph as they are not used in mapReduce processing mapReduceRDD = computedGraphRDD.mapValues(vertexWritable -> { vertexWritable.get().dropEdges(Direction.BOTH); return vertexWritable; }); // if there is only one MapReduce to execute, don't bother wasting the clock cycles. if (this.mapReducers.size() > 1) { mapReduceRDD = mapReduceRDD.persist(StorageLevel.fromString(hadoopConfiguration .get(Constants.GREMLIN_SPARK_GRAPH_STORAGE_LEVEL, "MEMORY_ONLY"))); } } for (final MapReduce mapReduce : this.mapReducers) { // execute the map reduce job final HadoopConfiguration newApacheConfiguration = new HadoopConfiguration( graphComputerConfiguration); mapReduce.storeState(newApacheConfiguration); // map final JavaPairRDD mapRDD = GraknSparkExecutor.executeMap(mapReduceRDD, mapReduce, newApacheConfiguration); // combine final JavaPairRDD combineRDD = mapReduce.doStage(MapReduce.Stage.COMBINE) ? GraknSparkExecutor.executeCombine(mapRDD, newApacheConfiguration) : mapRDD; // reduce final JavaPairRDD reduceRDD = mapReduce.doStage(MapReduce.Stage.REDUCE) ? GraknSparkExecutor.executeReduce(combineRDD, mapReduce, newApacheConfiguration) : combineRDD; // write the map reduce output back to disk and computer result memory if (null != outputRDD) { mapReduce.addResultToMemory(finalMemory, outputRDD.writeMemoryRDD( graphComputerConfiguration, mapReduce.getMemoryKey(), reduceRDD)); } } // if the mapReduceRDD is not simply the computed graph, unpersist the mapReduceRDD if (computedGraphCreated && !outputToSpark) { assert loadedGraphRDD != computedGraphRDD; assert mapReduceRDD != computedGraphRDD; mapReduceRDD.unpersist(); } else { assert mapReduceRDD == computedGraphRDD; } } // unpersist the loaded graph if it will not be used again (no PersistedInputRDD) // if the graphRDD was loaded from Spark, but then partitioned or filtered, its a different RDD if (!inputFromSpark || partitioned || filtered) { loadedGraphRDD.unpersist(); } // unpersist the computed graph if it will not be used again (no PersistedOutputRDD) // if the computed graph is the loadedGraphRDD because it was not mutated and not-unpersisted, // then don't unpersist the computedGraphRDD/loadedGraphRDD if ((!outputToSpark || this.persist.equals(GraphComputer.Persist.NOTHING)) && computedGraphCreated) { computedGraphRDD.unpersist(); } // delete any file system or rdd data if persist nothing if (null != outputLocation && this.persist.equals(GraphComputer.Persist.NOTHING)) { if (outputToHDFS) { fileSystemStorage.rm(outputLocation); } if (outputToSpark) { sparkContextStorage.rm(outputLocation); } } // update runtime and return the newly computed graph finalMemory.setRuntime(System.currentTimeMillis() - startTime); // clear properties that should not be propagated in an OLAP chain graphComputerConfiguration.clearProperty(Constants.GREMLIN_HADOOP_GRAPH_FILTER); graphComputerConfiguration.clearProperty(Constants.GREMLIN_HADOOP_VERTEX_PROGRAM_INTERCEPTOR); graphComputerConfiguration.clearProperty(Constants.GREMLIN_SPARK_SKIP_GRAPH_CACHE); graphComputerConfiguration.clearProperty(Constants.GREMLIN_SPARK_SKIP_PARTITIONER); return new DefaultComputerResult(InputOutputHelper.getOutputGraph(graphComputerConfiguration, this.resultGraph, this.persist), finalMemory.asImmutable()); } catch (Exception e) { // So it throws the same exception as tinker does throw new RuntimeException(e); } }); computerService.shutdown(); return result; }
From source file:AllLab_Skeleton.Lab1.Lab1_Wordcount.java
/** * @param args the command line arguments *///from w w w. java 2s . c om public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "word count"); job.setJarByClass(Lab1_Wordcount.class); job.setMapperClass(WordCount_Mapper.class); job.setCombinerClass(WordCount_Reducer.class); job.setReducerClass(WordCount_Reducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:AllLab_Skeleton.Lab2.Lab2SecondarySort.java
/** * @param args the command line arguments *///from w w w . jav a 2s .c om public static void main(String[] args) { try { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "SecondarySort"); job.setJarByClass(Lab2SecondarySort.class); job.setMapperClass(Lab2Mapper.class); job.setMapOutputKeyClass(CompositeKeyWritable.class); job.setMapOutputValueClass(NullWritable.class); job.setPartitionerClass(Lab2Partitioner.class); job.setGroupingComparatorClass(Lab2GroupComparator.class); job.setReducerClass(Lab2Reducer.class); job.setOutputKeyClass(CompositeKeyWritable.class); job.setOutputValueClass(NullWritable.class); job.setNumReduceTasks(8); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } catch (IOException | InterruptedException | ClassNotFoundException ex) { System.out.println("Erorr Message" + ex.getMessage()); } }
From source file:AllLab_Skeleton.Lab4.Lab4_Std_dev.java
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "medianstd"); job.setJarByClass(Lab4_Std_dev.class); job.setMapperClass(Map.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(DoubleWritable.class); job.setReducerClass(Reduce.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(MedianSDCustomWritable.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:AllLab_Skeleton.Lab6.BloomFilterBhavesh.java
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "Bloom Filter"); job.setJarByClass(BloomFilterBhavesh.class); job.setMapperClass(BloomFilterMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(NullWritable.class); job.setNumReduceTasks(0);/* ww w.j av a2 s . c o m*/ FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); boolean success = job.waitForCompletion(true); System.out.println(success); }
From source file:AllLab_Skeleton.Lab6.BloomFilterUsingDistributedCache.java
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "Bloom Filter"); job.setJarByClass(BloomFilterUsingDistributedCache.class); job.setMapperClass(BloomFilterMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(NullWritable.class); //adding the file in the cache having the Person class records //job.addCacheFile(new Path("localhost:9000/bhavesh/LabAssignment/CacheInput/cache.txt").toUri()); DistributedCache.addCacheFile(new URI(args[2]), job.getConfiguration()); job.setNumReduceTasks(0);//from w ww. j av a2 s .c o m FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.waitForCompletion(true); }
From source file:AllLab_Skeleton.Lab6.ReduceSideJoin.java
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "ReduceSideJoin"); job.setJarByClass(ReduceSideJoin.class); // Use MultipleInputs to set which input uses what mapper // This will keep parsing of each data set separate from a logical // standpoint // The first two elements of the args array are the two inputs MultipleInputs.addInputPath(job, new Path(args[0]), TextInputFormat.class, UserJoinMapper.class); MultipleInputs.addInputPath(job, new Path(args[1]), TextInputFormat.class, CommentJoinMapper.class); job.getConfiguration().set("join.type", "leftouter"); //job.setNumReduceTasks(0); job.setReducerClass(UserJoinReducer.class); job.setOutputFormatClass(TextOutputFormat.class); TextOutputFormat.setOutputPath(job, new Path(args[2])); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.waitForCompletion(true);/*from ww w .j a va 2 s .c o m*/ }
From source file:alluxio.checker.MapReduceIntegrationChecker.java
License:Apache License
/** * Creates the HDFS filesystem to store output files. * * @param conf Hadoop configuration/* w w w .ja va 2 s . c o m*/ */ private void createHdfsFilesystem(Configuration conf) throws Exception { // Inits HDFS file system object mFileSystem = FileSystem.get(URI.create(conf.get("fs.defaultFS")), conf); mOutputFilePath = new Path("./MapReduceOutputFile"); if (mFileSystem.exists(mOutputFilePath)) { mFileSystem.delete(mOutputFilePath, true); } }
From source file:alluxio.client.hadoop.contract.FileSystemContract.java
License:Apache License
@Override public Path getTestPath() { Path path = mFS.makeQualified(new Path(getTestDataDir())); return path; }