/**
* Calculate how many maps to run. Number of maps is bounded by a minimum of the cumulative size
* of the copy / (distcp.bytes.per.map, default BYTES_PER_MAP or -m on the command line) and at
* most (distcp.max.map.tasks, default MAX_MAPS_PER_NODE * nodes in the cluster).
*
* @param totalBytes Count of total bytes for job
* @param job The job to configure
* @return Count of maps to run.
*/
private static void setMapCount(long totalBytes, JobConf job) throws IOException {
int numMaps = (int) (totalBytes / job.getLong(BYTES_PER_MAP_LABEL, BYTES_PER_MAP));
numMaps =
Math.min(
numMaps,
job.getInt(
MAX_MAPS_LABEL,
MAX_MAPS_PER_NODE * new JobClient(job).getClusterStatus().getTaskTrackers()));
job.setNumMapTasks(Math.max(numMaps, 1));
}
@Override
public void reduce(
Text key, /*[*/
Iterator /*]*/<IntWritable> values,
/*[*/ OutputCollector<Text, IntWritable> output,
Reporter reporter /*]*/)
throws IOException {
int maxValue = Integer.MIN_VALUE;
while (
/*[*/ values.hasNext() /*]*/) {
maxValue = Math.max(maxValue, /*[*/ values.next().get() /*]*/);
}
/*[*/ output.collect /*]*/(key, new IntWritable(maxValue));
}
