Package org.apache.tez.dag.api

Examples of org.apache.tez.dag.api.DataSourceDescriptor

803
804
805
806
807
808
809
810
          .setUserPayload(MRInputHelpersInternal.createMRInputPayload(conf, null));
    } catch (IOException e) {
      throw new TezUncheckedException(e);
    }

    DataSourceDescriptor dsd = DataSourceDescriptor.create(inputDescriptor, null, null);
    return dsd;
  }
View Full Code Here
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138

  @Test
  public void testNewSplitsGen() throws Exception {

    DataSourceDescriptor dataSource = generateDataSourceDescriptorMapReduce(newSplitsDir);

    Assert.assertTrue(dataSource.getAdditionalLocalFiles()
        .containsKey(MRInputHelpers.JOB_SPLIT_RESOURCE_NAME));
    Assert.assertTrue(dataSource.getAdditionalLocalFiles()
        .containsKey(MRInputHelpers.JOB_SPLIT_METAINFO_RESOURCE_NAME));

    RemoteIterator<LocatedFileStatus> files =
        remoteFs.listFiles(newSplitsDir, false);

    boolean foundSplitsFile = false;
    boolean foundMetaFile = false;
    int totalFilesFound = 0;

    while (files.hasNext()) {
      LocatedFileStatus status = files.next();
      String fName = status.getPath().getName();
      totalFilesFound++;
      if (fName.equals(MRInputHelpers.JOB_SPLIT_RESOURCE_NAME)) {
        foundSplitsFile = true;
      } else if (fName.equals(MRInputHelpers.JOB_SPLIT_METAINFO_RESOURCE_NAME)) {
        foundMetaFile = true;
      } else {
        Assert.fail("Found invalid file in splits dir, filename=" + fName);
      }
      Assert.assertTrue(status.getLen() > 0);
    }

    Assert.assertEquals(2, totalFilesFound);
    Assert.assertTrue(foundSplitsFile);
    Assert.assertTrue(foundMetaFile);

    verifyLocationHints(newSplitsDir, dataSource.getLocationHint().getTaskLocationHints());
  }
View Full Code Here
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
    verifyLocationHints(newSplitsDir, dataSource.getLocationHint().getTaskLocationHints());
  }

  @Test
  public void testOldSplitsGen() throws Exception {
    DataSourceDescriptor dataSource = generateDataSourceDescriptorMapRed(oldSplitsDir);
    Assert.assertTrue(
        dataSource.getAdditionalLocalFiles().containsKey(MRInputHelpers.JOB_SPLIT_RESOURCE_NAME));
    Assert.assertTrue(dataSource.getAdditionalLocalFiles()
        .containsKey(MRInputHelpers.JOB_SPLIT_METAINFO_RESOURCE_NAME));

    RemoteIterator<LocatedFileStatus> files =
        remoteFs.listFiles(oldSplitsDir, false);

    boolean foundSplitsFile = false;
    boolean foundMetaFile = false;
    int totalFilesFound = 0;

    while (files.hasNext()) {
      LocatedFileStatus status = files.next();
      String fName = status.getPath().getName();
      totalFilesFound++;
      if (fName.equals(MRInputHelpers.JOB_SPLIT_RESOURCE_NAME)) {
        foundSplitsFile = true;
      } else if (fName.equals(MRInputHelpers.JOB_SPLIT_METAINFO_RESOURCE_NAME)) {
        foundMetaFile = true;
      } else {
        Assert.fail("Found invalid file in splits dir, filename=" + fName);
      }
      Assert.assertTrue(status.getLen() > 0);
    }

    Assert.assertEquals(2, totalFilesFound);
    Assert.assertTrue(foundSplitsFile);
    Assert.assertTrue(foundMetaFile);

    verifyLocationHints(oldSplitsDir, dataSource.getLocationHint().getTaskLocationHints());
  }
View Full Code Here
173
174
175
176
177
178
179
180
181
182
183
184
185
    verifyLocationHints(oldSplitsDir, dataSource.getLocationHint().getTaskLocationHints());
  }

  @Test
  public void testInputSplitLocalResourceCreation() throws Exception {
    DataSourceDescriptor dataSource = generateDataSourceDescriptorMapRed(oldSplitsDir);

    Map<String, LocalResource> localResources = dataSource.getAdditionalLocalFiles();

    Assert.assertEquals(2, localResources.size());
    Assert.assertTrue(localResources.containsKey(
        MRInputHelpers.JOB_SPLIT_RESOURCE_NAME));
    Assert.assertTrue(localResources.containsKey(
View Full Code Here
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
            (initializerClass == null ? MRInputAMSplitGenerator.class : initializerClass)
            : null;
    LOG.info("Using initializer class: " + initializerClass);


    DataSourceDescriptor dsd;
    if (!genSplitsInAM) {
      dsd = MRInputHelpers
          .configureMRInputWithLegacySplitGeneration(stage1Conf, remoteStagingDir, true);
    } else {
      if (initializerClass == null) {
        dsd = MRInputLegacy.createConfigBuilder(stage1Conf, SleepInputFormat.class).build();
      } else {
        InputInitializerDescriptor iid =
            InputInitializerDescriptor.create(inputInitializerClazz.getName());
        dsd = MRInputLegacy.createConfigBuilder(stage1Conf, SleepInputFormat.class)
            .setCustomInitializerDescriptor(iid).build();
      }
    }

    Vertex stage1Vertex = Vertex.create("map", ProcessorDescriptor.create(
            MapProcessor.class.getName()).setUserPayload(stage1Payload),
        dsd.getNumberOfShards(), Resource.newInstance(256, 1));
    stage1Vertex.addDataSource("MRInput", dsd);
    Vertex stage2Vertex = Vertex.create("ireduce", ProcessorDescriptor.create(
            ReduceProcessor.class.getName()).setUserPayload(stage2Payload),
        1, Resource.newInstance(256, 1));
    Vertex stage3Vertex = Vertex.create("reduce", ProcessorDescriptor.create(
View Full Code Here
144
145
146
147
148
149
150
151
152
153
154
  private DAG createDAG(TezConfiguration tezConf, String inputPath, String outputPath,
      int numPartitions) throws IOException {

    // Create the descriptor that describes the input data to Tez. Using MRInput to read text
    // data from the given input path. The TextInputFormat is used to read the text data.
    DataSourceDescriptor dataSource = MRInput.createConfigBuilder(new Configuration(tezConf),
        TextInputFormat.class, inputPath).build();

    // Create a descriptor that describes the output data to Tez. Using MROoutput to write text
    // data to the given output path. The TextOutputFormat is used to write the text data.
    DataSinkDescriptor dataSink = MROutput.createConfigBuilder(new Configuration(tezConf),
View Full Code Here
125
126
127
128
129
130
131
132
133
134
135
  }
 
  public static DAG createDAG(TezConfiguration tezConf, String inputPath, String outputPath,
      int numPartitions, String dagName) throws IOException {

    DataSourceDescriptor dataSource = MRInput.createConfigBuilder(new Configuration(tezConf),
        TextInputFormat.class, inputPath).build();

    DataSinkDescriptor dataSink = MROutput.createConfigBuilder(new Configuration(tezConf),
        TextOutputFormat.class, outputPath).build();
View Full Code Here
183
184
185
186
187
188
189
190
191
192
193
    List<Vertex> vertices = new ArrayList<Vertex>();

    ByteArrayOutputStream outputStream = new ByteArrayOutputStream(4096);
    mapStageConf.writeXml(outputStream);
    String mapStageHistoryText = new String(outputStream.toByteArray(), "UTF-8");
    DataSourceDescriptor dsd;
    if (generateSplitsInClient) {
      mapStageConf.set(MRJobConfig.INPUT_FORMAT_CLASS_ATTR,
          TextInputFormat.class.getName());
      mapStageConf.set(FileInputFormat.INPUT_DIR, inputPath);
      mapStageConf.setBoolean("mapred.mapper.new-api", true);
View Full Code Here
112
113
114
115
116
117
118
119
120
121
122
          .getName() : MRInput.class.getName())
          .setUserPayload(createMRInputPayload(conf, null));
      Map<String, LocalResource> additionalLocalResources = new HashMap<String, LocalResource>();
      updateLocalResourcesForInputSplits(FileSystem.get(conf), inputSplitInfo,
          additionalLocalResources);
      DataSourceDescriptor dsd =
          DataSourceDescriptor.create(inputDescriptor, null, inputSplitInfo.getNumTasks(),
              inputSplitInfo.getCredentials(),
              VertexLocationHint.create(inputSplitInfo.getTaskLocationHints()),
              additionalLocalResources);
      return dsd;
View Full Code Here
481
482
483
484
485
486
487
488
489
490
491
    }
    if (numReducer > 0) {
      MRHelpers.configureMRApiUsage(finalReduceConf);
    }

    DataSourceDescriptor dataSource = null;
    if (!generateSplitsInAM && writeSplitsToDFS) {

      LOG.info("Writing splits to DFS");
      dataSource = MRInputHelpers
          .configureMRInputWithLegacySplitGeneration(mapStageConf, remoteStagingDir, true);
View Full Code Here
TOP

Related Classes of org.apache.tez.dag.api.DataSourceDescriptor

  • cascading.flow.tez.Hadoop2TezFlowStep
  • org.apache.hadoop.hive.ql.exec.tez.DagUtils
  • org.apache.tez.examples.OrderedWordCount
  • org.apache.tez.examples.WordCount
  • org.apache.tez.mapreduce.client.YARNRunner
  • org.apache.tez.mapreduce.examples.FilterLinesByWord
  • org.apache.tez.mapreduce.examples.FilterLinesByWordOneToOne
  • org.apache.tez.mapreduce.examples.MRRSleepJob
  • org.apache.tez.mapreduce.examples.TestOrderedWordCount
  • org.apache.tez.mapreduce.examples.UnionExample
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.