Java Code Examples for org.apache.hadoop.mapred.JobConf#getFloat()

The following examples show how to use org.apache.hadoop.mapred.JobConf#getFloat() . 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: LinkRank.java    From anthelion with Apache License 2.0 6 votes vote down vote up
/**
 * Configures the job, sets the damping factor, rank one score, and other
 * needed values for analysis.
 */
public void configure(JobConf conf) {

  try {
    this.conf = conf;
    this.dampingFactor = conf.getFloat("link.analyze.damping.factor", 0.85f);
    this.rankOne = conf.getFloat("link.analyze.rank.one", 0.0f);
    this.itNum = conf.getInt("link.analyze.iteration", 0);
    limitPages = conf.getBoolean("link.ignore.limit.page", true);
    limitDomains = conf.getBoolean("link.ignore.limit.domain", true);
  }
  catch (Exception e) {
    LOG.error(StringUtils.stringifyException(e));
    throw new IllegalArgumentException(e);
  }
}
 
Example 2
Source File: LinkRank.java    From nutch-htmlunit with Apache License 2.0 6 votes vote down vote up
/**
 * Configures the job, sets the damping factor, rank one score, and other
 * needed values for analysis.
 */
public void configure(JobConf conf) {

  try {
    this.conf = conf;
    this.dampingFactor = conf.getFloat("link.analyze.damping.factor", 0.85f);
    this.rankOne = conf.getFloat("link.analyze.rank.one", 0.0f);
    this.itNum = conf.getInt("link.analyze.iteration", 0);
    limitPages = conf.getBoolean("link.ignore.limit.page", true);
    limitDomains = conf.getBoolean("link.ignore.limit.domain", true);
  }
  catch (Exception e) {
    LOG.error(StringUtils.stringifyException(e));
    throw new IllegalArgumentException(e);
  }
}
 
Example 3
Source File: MergeManagerImpl.java    From hadoop with Apache License 2.0 4 votes vote down vote up
public MergeManagerImpl(TaskAttemptID reduceId, JobConf jobConf, 
                    FileSystem localFS,
                    LocalDirAllocator localDirAllocator,  
                    Reporter reporter,
                    CompressionCodec codec,
                    Class<? extends Reducer> combinerClass,
                    CombineOutputCollector<K,V> combineCollector,
                    Counters.Counter spilledRecordsCounter,
                    Counters.Counter reduceCombineInputCounter,
                    Counters.Counter mergedMapOutputsCounter,
                    ExceptionReporter exceptionReporter,
                    Progress mergePhase, MapOutputFile mapOutputFile) {
  this.reduceId = reduceId;
  this.jobConf = jobConf;
  this.localDirAllocator = localDirAllocator;
  this.exceptionReporter = exceptionReporter;
  
  this.reporter = reporter;
  this.codec = codec;
  this.combinerClass = combinerClass;
  this.combineCollector = combineCollector;
  this.reduceCombineInputCounter = reduceCombineInputCounter;
  this.spilledRecordsCounter = spilledRecordsCounter;
  this.mergedMapOutputsCounter = mergedMapOutputsCounter;
  this.mapOutputFile = mapOutputFile;
  this.mapOutputFile.setConf(jobConf);
  
  this.localFS = localFS;
  this.rfs = ((LocalFileSystem)localFS).getRaw();
  
  final float maxInMemCopyUse =
    jobConf.getFloat(MRJobConfig.SHUFFLE_INPUT_BUFFER_PERCENT,
        MRJobConfig.DEFAULT_SHUFFLE_INPUT_BUFFER_PERCENT);
  if (maxInMemCopyUse > 1.0 || maxInMemCopyUse < 0.0) {
    throw new IllegalArgumentException("Invalid value for " +
        MRJobConfig.SHUFFLE_INPUT_BUFFER_PERCENT + ": " +
        maxInMemCopyUse);
  }

  // Allow unit tests to fix Runtime memory
  this.memoryLimit = 
    (long)(jobConf.getLong(MRJobConfig.REDUCE_MEMORY_TOTAL_BYTES,
        Math.min(Runtime.getRuntime().maxMemory(), Integer.MAX_VALUE))
      * maxInMemCopyUse);
 
  this.ioSortFactor = jobConf.getInt(MRJobConfig.IO_SORT_FACTOR, 100);

  final float singleShuffleMemoryLimitPercent =
      jobConf.getFloat(MRJobConfig.SHUFFLE_MEMORY_LIMIT_PERCENT,
          DEFAULT_SHUFFLE_MEMORY_LIMIT_PERCENT);
  if (singleShuffleMemoryLimitPercent <= 0.0f
      || singleShuffleMemoryLimitPercent > 1.0f) {
    throw new IllegalArgumentException("Invalid value for "
        + MRJobConfig.SHUFFLE_MEMORY_LIMIT_PERCENT + ": "
        + singleShuffleMemoryLimitPercent);
  }

  usedMemory = 0L;
  commitMemory = 0L;
  this.maxSingleShuffleLimit = 
    (long)(memoryLimit * singleShuffleMemoryLimitPercent);
  this.memToMemMergeOutputsThreshold = 
          jobConf.getInt(MRJobConfig.REDUCE_MEMTOMEM_THRESHOLD, ioSortFactor);
  this.mergeThreshold = (long)(this.memoryLimit * 
                        jobConf.getFloat(MRJobConfig.SHUFFLE_MERGE_PERCENT, 
                                         0.90f));
  LOG.info("MergerManager: memoryLimit=" + memoryLimit + ", " +
           "maxSingleShuffleLimit=" + maxSingleShuffleLimit + ", " +
           "mergeThreshold=" + mergeThreshold + ", " + 
           "ioSortFactor=" + ioSortFactor + ", " +
           "memToMemMergeOutputsThreshold=" + memToMemMergeOutputsThreshold);

  if (this.maxSingleShuffleLimit >= this.mergeThreshold) {
    throw new RuntimeException("Invalid configuration: "
        + "maxSingleShuffleLimit should be less than mergeThreshold"
        + "maxSingleShuffleLimit: " + this.maxSingleShuffleLimit
        + "mergeThreshold: " + this.mergeThreshold);
  }

  boolean allowMemToMemMerge = 
    jobConf.getBoolean(MRJobConfig.REDUCE_MEMTOMEM_ENABLED, false);
  if (allowMemToMemMerge) {
    this.memToMemMerger = 
      new IntermediateMemoryToMemoryMerger(this,
                                           memToMemMergeOutputsThreshold);
    this.memToMemMerger.start();
  } else {
    this.memToMemMerger = null;
  }
  
  this.inMemoryMerger = createInMemoryMerger();
  this.inMemoryMerger.start();
  
  this.onDiskMerger = new OnDiskMerger(this);
  this.onDiskMerger.start();
  
  this.mergePhase = mergePhase;
}
 
Example 4
Source File: MergeManagerImpl.java    From big-c with Apache License 2.0 4 votes vote down vote up
public MergeManagerImpl(TaskAttemptID reduceId, JobConf jobConf, 
                    FileSystem localFS,
                    LocalDirAllocator localDirAllocator,  
                    Reporter reporter,
                    CompressionCodec codec,
                    Class<? extends Reducer> combinerClass,
                    CombineOutputCollector<K,V> combineCollector,
                    Counters.Counter spilledRecordsCounter,
                    Counters.Counter reduceCombineInputCounter,
                    Counters.Counter mergedMapOutputsCounter,
                    ExceptionReporter exceptionReporter,
                    Progress mergePhase, MapOutputFile mapOutputFile) {
  this.reduceId = reduceId;
  this.jobConf = jobConf;
  this.localDirAllocator = localDirAllocator;
  this.exceptionReporter = exceptionReporter;
  
  this.reporter = reporter;
  this.codec = codec;
  this.combinerClass = combinerClass;
  this.combineCollector = combineCollector;
  this.reduceCombineInputCounter = reduceCombineInputCounter;
  this.spilledRecordsCounter = spilledRecordsCounter;
  this.mergedMapOutputsCounter = mergedMapOutputsCounter;
  this.mapOutputFile = mapOutputFile;
  this.mapOutputFile.setConf(jobConf);
  
  this.localFS = localFS;
  this.rfs = ((LocalFileSystem)localFS).getRaw();
  
  final float maxInMemCopyUse =
    jobConf.getFloat(MRJobConfig.SHUFFLE_INPUT_BUFFER_PERCENT,
        MRJobConfig.DEFAULT_SHUFFLE_INPUT_BUFFER_PERCENT);
  if (maxInMemCopyUse > 1.0 || maxInMemCopyUse < 0.0) {
    throw new IllegalArgumentException("Invalid value for " +
        MRJobConfig.SHUFFLE_INPUT_BUFFER_PERCENT + ": " +
        maxInMemCopyUse);
  }

  // Allow unit tests to fix Runtime memory
  this.memoryLimit = 
    (long)(jobConf.getLong(MRJobConfig.REDUCE_MEMORY_TOTAL_BYTES,
        Math.min(Runtime.getRuntime().maxMemory(), Integer.MAX_VALUE))
      * maxInMemCopyUse);
 
  this.ioSortFactor = jobConf.getInt(MRJobConfig.IO_SORT_FACTOR, 100);

  final float singleShuffleMemoryLimitPercent =
      jobConf.getFloat(MRJobConfig.SHUFFLE_MEMORY_LIMIT_PERCENT,
          DEFAULT_SHUFFLE_MEMORY_LIMIT_PERCENT);
  if (singleShuffleMemoryLimitPercent <= 0.0f
      || singleShuffleMemoryLimitPercent > 1.0f) {
    throw new IllegalArgumentException("Invalid value for "
        + MRJobConfig.SHUFFLE_MEMORY_LIMIT_PERCENT + ": "
        + singleShuffleMemoryLimitPercent);
  }

  usedMemory = 0L;
  commitMemory = 0L;
  this.maxSingleShuffleLimit = 
    (long)(memoryLimit * singleShuffleMemoryLimitPercent);
  this.memToMemMergeOutputsThreshold = 
          jobConf.getInt(MRJobConfig.REDUCE_MEMTOMEM_THRESHOLD, ioSortFactor);
  this.mergeThreshold = (long)(this.memoryLimit * 
                        jobConf.getFloat(MRJobConfig.SHUFFLE_MERGE_PERCENT, 
                                         0.90f));
  LOG.info("MergerManager: memoryLimit=" + memoryLimit + ", " +
           "maxSingleShuffleLimit=" + maxSingleShuffleLimit + ", " +
           "mergeThreshold=" + mergeThreshold + ", " + 
           "ioSortFactor=" + ioSortFactor + ", " +
           "memToMemMergeOutputsThreshold=" + memToMemMergeOutputsThreshold);

  if (this.maxSingleShuffleLimit >= this.mergeThreshold) {
    throw new RuntimeException("Invalid configuration: "
        + "maxSingleShuffleLimit should be less than mergeThreshold"
        + "maxSingleShuffleLimit: " + this.maxSingleShuffleLimit
        + "mergeThreshold: " + this.mergeThreshold);
  }

  boolean allowMemToMemMerge = 
    jobConf.getBoolean(MRJobConfig.REDUCE_MEMTOMEM_ENABLED, false);
  if (allowMemToMemMerge) {
    this.memToMemMerger = 
      new IntermediateMemoryToMemoryMerger(this,
                                           memToMemMergeOutputsThreshold);
    this.memToMemMerger.start();
  } else {
    this.memToMemMerger = null;
  }
  
  this.inMemoryMerger = createInMemoryMerger();
  this.inMemoryMerger.start();
  
  this.onDiskMerger = new OnDiskMerger(this);
  this.onDiskMerger.start();
  
  this.mergePhase = mergePhase;
}
 
Example 5
Source File: ScoreUpdater.java    From anthelion with Apache License 2.0 4 votes vote down vote up
public void configure(JobConf conf) {
  this.conf = conf;
  clearScore = conf.getFloat("link.score.updater.clear.score", 0.0f);
}
 
Example 6
Source File: LinkRank.java    From anthelion with Apache License 2.0 4 votes vote down vote up
public void configure(JobConf conf) {
  this.conf = conf;
  initialScore = conf.getFloat("link.analyze.initial.score", 1.0f);
}
 
Example 7
Source File: ScoreUpdater.java    From nutch-htmlunit with Apache License 2.0 4 votes vote down vote up
public void configure(JobConf conf) {
  this.conf = conf;
  clearScore = conf.getFloat("link.score.updater.clear.score", 0.0f);
}
 
Example 8
Source File: LinkRank.java    From nutch-htmlunit with Apache License 2.0 4 votes vote down vote up
public void configure(JobConf conf) {
  this.conf = conf;
  initialScore = conf.getFloat("link.analyze.initial.score", 1.0f);
}