List of usage examples for org.apache.hadoop.mapreduce Job setOutputFormatClass
public void setOutputFormatClass(Class<? extends OutputFormat> cls) throws IllegalStateException
From source file:com.cg.mapreduce.myfpgrowth.PFPGrowth.java
License:Apache License
/** * Run the Parallel FPGrowth Map/Reduce Job to calculate the Top K features of group dependent shards *//*from w w w .j av a 2 s. c om*/ public static void startParallelFPGrowth(Parameters params, Configuration conf) throws IOException, InterruptedException, ClassNotFoundException { conf.set(PFP_PARAMETERS, params.toString()); conf.set("mapred.compress.map.output", "true"); conf.set("mapred.output.compression.type", "BLOCK"); Path input = new Path(params.get(INPUT)); Job job = new Job(conf, "PFP Growth Driver running over input" + input); job.setJarByClass(PFPGrowth.class); // Job job = initJob(conf); job.setMapOutputKeyClass(IntWritable.class); job.setMapOutputValueClass(ArrayList.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(LongWritable.class); FileInputFormat.addInputPath(job, input); Path outPath = new Path(params.get(OUTPUT), FPGROWTH); FileOutputFormat.setOutputPath(job, outPath); HadoopUtil.delete(conf, outPath); job.setInputFormatClass(TextInputFormat.class); job.setMapperClass(ParallelFPGrowthMapper.class); //job.setCombinerClass(ParallelFPGrowthCombiner.class); job.setReducerClass(ParallelFPGrowthReducer.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); boolean succeeded = job.waitForCompletion(true); if (!succeeded) { throw new IllegalStateException("Job failed!"); } }
From source file:com.ci.backports.hadoop.hbase.ZHFileOutputFormat.java
License:Apache License
/** * Configure a MapReduce Job to perform an incremental load into the given * table. This/*from ww w .j a va2 s . c om*/ * <ul> * <li>Inspects the table to configure a total order partitioner</li> * <li>Uploads the partitions file to the cluster and adds it to the DistributedCache</li> * <li>Sets the number of reduce tasks to match the current number of regions</li> * <li>Sets the output key/value class to match ZHFileOutputFormat's requirements</li> * <li>Sets the reducer up to perform the appropriate sorting (either KeyValueSortReducer or * ZPutSortReducer)</li> * </ul> * The user should be sure to set the map output value class to either KeyValue or Put before * running this function. */ public static void configureIncrementalLoad(Job job, HTable table) throws IOException { Configuration conf = job.getConfiguration(); job.setPartitionerClass(TotalOrderPartitioner.class); job.setOutputKeyClass(ImmutableBytesWritable.class); job.setOutputValueClass(KeyValue.class); job.setOutputFormatClass(ZHFileOutputFormat.class); // 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(ZPutSortReducer.class); } else { LOG.warn("Unknown map output value type:" + job.getMapOutputValueClass()); } LOG.info("Looking up current regions for table " + table); List<ImmutableBytesWritable> startKeys = getRegionStartKeys(table); LOG.info("Configuring " + startKeys.size() + " reduce partitions " + "to match current region count"); job.setNumReduceTasks(startKeys.size()); Path partitionsPath = new Path(job.getWorkingDirectory(), "partitions_" + System.currentTimeMillis()); LOG.info("Writing partition information to " + partitionsPath); FileSystem fs = partitionsPath.getFileSystem(conf); writePartitions(conf, partitionsPath, startKeys); partitionsPath.makeQualified(fs); URI cacheUri; try { cacheUri = new URI(partitionsPath.toString() + "#" + TotalOrderPartitioner.DEFAULT_PATH); } catch (URISyntaxException e) { throw new IOException(e); } DistributedCache.addCacheFile(cacheUri, conf); DistributedCache.createSymlink(conf); LOG.info("Incremental table output configured."); }
From source file:com.citic.zxyjs.zwlscx.mapreduce.lib.input.HFileOutputFormatBase.java
License:Apache License
/** * Configure a MapReduce Job to perform an incremental load into the given * table. This//from w ww . ja va 2s . c o m * <ul> * <li>Inspects the table to configure a total order partitioner</li> * <li>Uploads the partitions file to the cluster and adds it to the * DistributedCache</li> * <li>Sets the number of reduce tasks to match the current number of * regions</li> * <li>Sets the output key/value class to match HFileOutputFormat's * requirements</li> * <li>Sets the reducer up to perform the appropriate sorting (either * KeyValueSortReducer or PutSortReducer)</li> * </ul> * The user should be sure to set the map output value class to either * KeyValue or Put before running this function. */ public static void configureIncrementalLoad(Job job, HTable table, Class<? extends HFileOutputFormatBase> hfileOutputFormatBase) throws IOException { Configuration conf = job.getConfiguration(); job.setOutputKeyClass(ImmutableBytesWritable.class); job.setOutputValueClass(KeyValue.class); job.setOutputFormatClass(hfileOutputFormatBase); // 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 " + Bytes.toString(table.getTableName())); List<ImmutableBytesWritable> startKeys = getRegionStartKeys(table); 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(table, conf); configureBloomType(table, conf); configureBlockSize(table, conf); // TableMapReduceUtil.addDependencyJars(job); TableMapReduceUtil.initCredentials(job); LOG.info("Incremental table " + Bytes.toString(table.getTableName()) + " output configured."); }
From source file:com.cloudera.accumulo.upgrade.compatibility.DataCompatibilityVerify.java
License:Open Source License
@Override public int run(String[] args) throws Exception { final String jobName = this.getClass().getName(); options.parseArgs(jobName, args);//from w w w.ja v a 2s . com try { final int totalMapSlots = getConf().getInt("mapred.map.tasks", DataCompatibilityTestCli.DEFAULT_NUM_ROWS); if (-1 == options.test.numRows) { options.test.numRows = totalMapSlots; } final TableOperations ops = options.connection.getConnector().tableOperations(); final List<String> names = options.test.getTableNames(ops); int totalReduceSlots = getConf().getInt("mapred.reduce.tasks", 0); if (-1 != options.test.numReduceSlots) { totalReduceSlots = options.test.numReduceSlots; } if (0 == totalReduceSlots) { totalReduceSlots = names.size(); } final int reducesPerJob = Math.max(1, totalReduceSlots / names.size()); final List<Job> jobs = new ArrayList(); for (String name : names) { final Job job = new Job(getConf(), jobName + " " + name); job.setJarByClass(this.getClass()); options.input.useAccumuloInputFormat(job, name); job.setMapperClass(DataVerifyMapper.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(LongWritable.class); job.setReducerClass(LongSumReducer.class); job.setCombinerClass(LongSumReducer.class); job.setOutputFormatClass(TextOutputFormat.class); TextOutputFormat.setOutputPath(job, new Path(options.test.output, name)); job.setNumReduceTasks(reducesPerJob); job.submit(); jobs.add(job); } boolean success = true; final long numCellsPerRow = options.test.qualifiers * DataCompatibilityLoad.FAMILIES.length; final long numCellsPerFamily = options.test.qualifiers * options.test.numRows; for (Job job : jobs) { success &= job.waitForCompletion(true); final CounterGroup group = job.getCounters().getGroup(DataVerifyMapper.class.getName()); if (null == group) { log.error("Job '" + job.getJobName() + "' doesn't have counters for the verification mapper."); success = false; } else { final Counter badCounter = group.findCounter(BAD_COUNTER); if (null != badCounter && 0 < badCounter.getValue()) { log.error("Job '" + job.getJobName() + "' has " + badCounter.getValue() + " entries with bad checksums."); success = false; } int numRows = 0; int numFamilies = 0; for (Counter counter : group) { if (counter.getName().startsWith(ROW_COUNTER_PREFIX)) { numRows++; if (numCellsPerRow != counter.getValue()) { log.error("Job '" + job.getJobName() + "', counter '" + counter.getName() + "' should have " + numCellsPerRow + " cells, but instead has " + counter.getValue()); success = false; } } else if (counter.getName().startsWith(FAMILY_COUNTER_PREFIX)) { numFamilies++; if (numCellsPerFamily != counter.getValue()) { log.error("Job '" + job.getJobName() + "', counter '" + counter.getName() + "' should have " + numCellsPerFamily + " cells, but instead has " + counter.getValue()); success = false; } } } if (options.test.numRows != numRows) { log.error("Job '" + job.getJobName() + "' is supposed to have " + options.test.numRows + " rows, but has " + numRows); success = false; } if (DataCompatibilityLoad.FAMILIES.length != numFamilies) { log.error("Job '" + job.getJobName() + "' is supposed to have " + DataCompatibilityLoad.FAMILIES.length + " families, but has " + numFamilies); success = false; } } } if (success) { log.info("All internal checks passed."); } else { log.info("Some checks failed. see log."); } return success ? 0 : 1; } finally { options.input.close(); } }
From source file:com.cloudera.accumulo.upgrade.util.MapreduceOutputCli.java
License:Open Source License
public void useAccumuloOutputFormat(Job job, String table) throws AccumuloSecurityException { job.setOutputFormatClass(AccumuloOutputFormat.class); AccumuloOutputFormat.setZooKeeperInstance(job, connection.instance, connection.zookeepers); PasswordToken token = new PasswordToken(connection.password); AccumuloOutputFormat.setConnectorInfo(job, connection.principal, token); AccumuloOutputFormat.setCreateTables(job, false); AccumuloOutputFormat.setDefaultTableName(job, table); }
From source file:com.cloudera.avro.MapReduceColorCount.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: MapReduceColorCount <input path> <output path>"); return -1; }//w w w . j ava 2 s. co m Job job = new Job(getConf()); job.setJarByClass(MapReduceColorCount.class); job.setJobName("Color Count"); FileInputFormat.setInputPaths(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setInputFormatClass(AvroKeyInputFormat.class); job.setMapperClass(ColorCountMapper.class); AvroJob.setInputKeySchema(job, User.getClassSchema()); AvroJob.setMapOutputValueSchema(job, User.getClassSchema()); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputFormatClass(AvroKeyValueOutputFormat.class); job.setReducerClass(ColorCountReducer.class); AvroJob.setOutputKeySchema(job, Schema.create(Schema.Type.STRING)); AvroJob.setOutputValueSchema(job, Schema.create(Schema.Type.INT)); return (job.waitForCompletion(true) ? 0 : 1); }
From source file:com.cloudera.castagna.logparser.mr.StatusCodesStats.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length != 2) { System.err.printf("Usage: %s [generic options] <input> <output>\n", getClass().getName()); ToolRunner.printGenericCommandUsage(System.err); return -1; }/*from www .j a v a2 s. c om*/ Configuration configuration = getConf(); boolean useCompression = configuration.getBoolean(Constants.OPTION_USE_COMPRESSION, Constants.OPTION_USE_COMPRESSION_DEFAULT); if (useCompression) { configuration.setBoolean("mapred.compress.map.output", true); configuration.set("mapred.output.compression.type", "BLOCK"); configuration.set("mapred.map.output.compression.codec", "org.apache.hadoop.io.compress.GzipCodec"); } boolean overrideOutput = configuration.getBoolean(Constants.OPTION_OVERWRITE_OUTPUT, Constants.OPTION_OVERWRITE_OUTPUT_DEFAULT); FileSystem fs = FileSystem.get(new Path(args[1]).toUri(), configuration); if (overrideOutput) { fs.delete(new Path(args[1]), true); } Job job = Job.getInstance(configuration); job.setJobName(Constants.STATUS_CODES_STATS); job.setJarByClass(getClass()); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setInputFormatClass(TextInputFormat.class); job.setMapperClass(StatusCodesStatsMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setCombinerClass(StatusCodesStatsCombiner.class); job.setReducerClass(StatusCodesStatsReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); Utils.setReducers(job, configuration, log); job.setOutputFormatClass(TextOutputFormat.class); if (log.isDebugEnabled()) Utils.log(job, log); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.cloudera.castagna.logparser.mr.TranscodeLogs.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length != 2) { System.err.printf("Usage: %s [generic options] <input> <output>\n", getClass().getName()); ToolRunner.printGenericCommandUsage(System.err); return -1; }/*w w w .j av a 2s . c om*/ Configuration configuration = getConf(); boolean overrideOutput = configuration.getBoolean(Constants.OPTION_OVERWRITE_OUTPUT, Constants.OPTION_OVERWRITE_OUTPUT_DEFAULT); FileSystem fs = FileSystem.get(new Path(args[1]).toUri(), configuration); if (overrideOutput) { fs.delete(new Path(args[1]), true); } Job job = Job.getInstance(configuration); job.setJobName(Constants.STATUS_CODES_STATS); job.setJarByClass(getClass()); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setInputFormatClass(TextInputFormat.class); job.setMapperClass(TranscodeLogsMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setNumReduceTasks(0); job.setOutputFormatClass(TextOutputFormat.class); if (log.isDebugEnabled()) Utils.log(job, log); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.cloudera.crunch.io.hbase.HBaseTarget.java
License:Open Source License
@Override public void configureForMapReduce(Job job, PType<?> ptype, Path outputPath, String name) { Configuration conf = job.getConfiguration(); HBaseConfiguration.addHbaseResources(conf); job.setOutputFormatClass(TableOutputFormat.class); conf.set(TableOutputFormat.OUTPUT_TABLE, table); try {// www . jav a 2 s .c o m TableMapReduceUtil.addDependencyJars(job); } catch (IOException e) { throw new CrunchRuntimeException(e); } }
From source file:com.cloudera.crunch.io.impl.FileTargetImpl.java
License:Open Source License
protected void configureForMapReduce(Job job, Class keyClass, Class valueClass, Path outputPath, String name) { try {//w w w. j a v a2 s .com FileOutputFormat.setOutputPath(job, outputPath); } catch (IOException e) { throw new RuntimeException("failed to set output path to " + outputPath, e); } if (name == null) { job.setOutputFormatClass(outputFormatClass); job.setOutputKeyClass(keyClass); job.setOutputValueClass(valueClass); } else { CrunchMultipleOutputs.addNamedOutput(job, name, outputFormatClass, keyClass, valueClass); } }