/**
* 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));
}
/**
* Generate the list of files and make them into FileSplits. This needs to be copied to insert a
* filter on acceptable data
*/
@Override
public List<InputSplit> getSplits(JobContext job) throws IOException {
long minSize = Math.max(getFormatMinSplitSize(), getMinSplitSize(job));
long maxSize = getMaxSplitSize(job);
long desiredMappers =
job.getConfiguration().getLong("org.systemsbiology.jxtandem.DesiredXMLInputMappers", 0);
// generate splits
List<InputSplit> splits = new ArrayList<InputSplit>();
List<FileStatus> fileStatuses = listStatus(job);
boolean forceNumberMappers = fileStatuses.size() == 1;
for (FileStatus file : fileStatuses) {
Path path = file.getPath();
if (!isPathAcceptable(path)) // filter acceptable data
continue;
FileSystem fs = path.getFileSystem(job.getConfiguration());
long length = file.getLen();
BlockLocation[] blkLocations = fs.getFileBlockLocations(file, 0, length);
if ((length != 0) && isSplitable(job, path)) {
long blockSize = file.getBlockSize();
// use desired mappers to force more splits
if (forceNumberMappers && desiredMappers > 0)
maxSize = Math.min(maxSize, (length / desiredMappers));
long splitSize = computeSplitSize(blockSize, minSize, maxSize);
long bytesRemaining = length;
while (withinSlop(splitSize, bytesRemaining)) {
int blkIndex = getBlockIndex(blkLocations, length - bytesRemaining);
splits.add(
new FileSplit(
path, length - bytesRemaining, splitSize, blkLocations[blkIndex].getHosts()));
bytesRemaining -= splitSize;
}
if (bytesRemaining != 0) {
splits.add(
new FileSplit(
path,
length - bytesRemaining,
bytesRemaining,
blkLocations[blkLocations.length - 1].getHosts()));
}
} else if (length != 0) {
splits.add(new FileSplit(path, 0, length, blkLocations[0].getHosts()));
} else {
// Create empty hosts array for zero length files
splits.add(new FileSplit(path, 0, length, new String[0]));
}
}
System.out.println("Total # of splits: " + splits.size());
// LOG.debug("Total # of splits: " + splits.size());
return splits;
}
private static void truncateBlock(File blockFile, File metaFile, long oldlen, long newlen)
throws IOException {
if (newlen == oldlen) {
return;
}
if (newlen > oldlen) {
throw new IOException(
"Cannout truncate block to from oldlen (=" + oldlen + ") to newlen (=" + newlen + ")");
}
DataChecksum dcs = BlockMetadataHeader.readHeader(metaFile).getChecksum();
int checksumsize = dcs.getChecksumSize();
int bpc = dcs.getBytesPerChecksum();
long n = (newlen - 1) / bpc + 1;
long newmetalen = BlockMetadataHeader.getHeaderSize() + n * checksumsize;
long lastchunkoffset = (n - 1) * bpc;
int lastchunksize = (int) (newlen - lastchunkoffset);
byte[] b = new byte[Math.max(lastchunksize, checksumsize)];
RandomAccessFile blockRAF = new RandomAccessFile(blockFile, "rw");
try {
// truncate blockFile
blockRAF.setLength(newlen);
// read last chunk
blockRAF.seek(lastchunkoffset);
blockRAF.readFully(b, 0, lastchunksize);
} finally {
blockRAF.close();
}
// compute checksum
dcs.update(b, 0, lastchunksize);
dcs.writeValue(b, 0, false);
// update metaFile
RandomAccessFile metaRAF = new RandomAccessFile(metaFile, "rw");
try {
metaRAF.setLength(newmetalen);
metaRAF.seek(newmetalen - checksumsize);
metaRAF.write(b, 0, checksumsize);
} finally {
metaRAF.close();
}
}