/**
* Check whether the contents of src and dst are the same.
*
* <p>Return false if dstpath does not exist
*
* <p>If the files have different sizes, return false.
*
* <p>If the files have the same sizes, the file checksums will be compared.
*
* <p>When file checksum is not supported in any of file systems, two files are considered as the
* same if they have the same size.
*/
private static boolean sameFile(
FileSystem srcfs, FileStatus srcstatus, FileSystem dstfs, Path dstpath) throws IOException {
FileStatus dststatus;
try {
dststatus = dstfs.getFileStatus(dstpath);
} catch (FileNotFoundException fnfe) {
return false;
}
// same length?
if (srcstatus.getLen() != dststatus.getLen()) {
return false;
}
// compare checksums
try {
final FileChecksum srccs = srcfs.getFileChecksum(srcstatus.getPath());
final FileChecksum dstcs = dstfs.getFileChecksum(dststatus.getPath());
// return true if checksum is not supported
// (i.e. some of the checksums is null)
return srccs == null || dstcs == null || srccs.equals(dstcs);
} catch (FileNotFoundException fnfe) {
return false;
}
}
/**
* Produce splits such that each is no greater than the quotient of the total size and the
* number of splits requested.
*
* @param job The handle to the JobConf object
* @param numSplits Number of splits requested
*/
public InputSplit[] getSplits(JobConf job, int numSplits) throws IOException {
int cnfiles = job.getInt(SRC_COUNT_LABEL, -1);
long cbsize = job.getLong(TOTAL_SIZE_LABEL, -1);
String srcfilelist = job.get(SRC_LIST_LABEL, "");
if (cnfiles < 0 || cbsize < 0 || "".equals(srcfilelist)) {
throw new RuntimeException(
"Invalid metadata: #files("
+ cnfiles
+ ") total_size("
+ cbsize
+ ") listuri("
+ srcfilelist
+ ")");
}
Path src = new Path(srcfilelist);
FileSystem fs = src.getFileSystem(job);
FileStatus srcst = fs.getFileStatus(src);
ArrayList<FileSplit> splits = new ArrayList<FileSplit>(numSplits);
LongWritable key = new LongWritable();
FilePair value = new FilePair();
final long targetsize = cbsize / numSplits;
long pos = 0L;
long last = 0L;
long acc = 0L;
long cbrem = srcst.getLen();
SequenceFile.Reader sl = null;
try {
sl = new SequenceFile.Reader(fs, src, job);
for (; sl.next(key, value); last = sl.getPosition()) {
// if adding this split would put this split past the target size,
// cut the last split and put this next file in the next split.
if (acc + key.get() > targetsize && acc != 0) {
long splitsize = last - pos;
splits.add(new FileSplit(src, pos, splitsize, (String[]) null));
cbrem -= splitsize;
pos = last;
acc = 0L;
}
acc += key.get();
}
} finally {
checkAndClose(sl);
}
if (cbrem != 0) {
splits.add(new FileSplit(src, pos, cbrem, (String[]) null));
}
return splits.toArray(new FileSplit[splits.size()]);
}
/**
* Initialize DFSCopyFileMapper specific job-configuration.
*
* @param conf : The dfs/mapred configuration.
* @param jobConf : The handle to the jobConf object to be initialized.
* @param args Arguments
*/
private static void setup(Configuration conf, JobConf jobConf, final Arguments args)
throws IOException {
jobConf.set(DST_DIR_LABEL, args.dst.toUri().toString());
// set boolean values
final boolean update = args.flags.contains(Options.UPDATE);
final boolean overwrite = !update && args.flags.contains(Options.OVERWRITE);
jobConf.setBoolean(Options.UPDATE.propertyname, update);
jobConf.setBoolean(Options.OVERWRITE.propertyname, overwrite);
jobConf.setBoolean(
Options.IGNORE_READ_FAILURES.propertyname,
args.flags.contains(Options.IGNORE_READ_FAILURES));
jobConf.setBoolean(
Options.PRESERVE_STATUS.propertyname, args.flags.contains(Options.PRESERVE_STATUS));
final String randomId = getRandomId();
JobClient jClient = new JobClient(jobConf);
Path jobDirectory = new Path(jClient.getSystemDir(), NAME + "_" + randomId);
jobConf.set(JOB_DIR_LABEL, jobDirectory.toString());
FileSystem dstfs = args.dst.getFileSystem(conf);
boolean dstExists = dstfs.exists(args.dst);
boolean dstIsDir = false;
if (dstExists) {
dstIsDir = dstfs.getFileStatus(args.dst).isDir();
}
// default logPath
Path logPath = args.log;
if (logPath == null) {
String filename = "_distcp_logs_" + randomId;
if (!dstExists || !dstIsDir) {
Path parent = args.dst.getParent();
if (!dstfs.exists(parent)) {
dstfs.mkdirs(parent);
}
logPath = new Path(parent, filename);
} else {
logPath = new Path(args.dst, filename);
}
}
FileOutputFormat.setOutputPath(jobConf, logPath);
// create src list, dst list
FileSystem jobfs = jobDirectory.getFileSystem(jobConf);
Path srcfilelist = new Path(jobDirectory, "_distcp_src_files");
jobConf.set(SRC_LIST_LABEL, srcfilelist.toString());
SequenceFile.Writer src_writer =
SequenceFile.createWriter(
jobfs,
jobConf,
srcfilelist,
LongWritable.class,
FilePair.class,
SequenceFile.CompressionType.NONE);
Path dstfilelist = new Path(jobDirectory, "_distcp_dst_files");
SequenceFile.Writer dst_writer =
SequenceFile.createWriter(
jobfs, jobConf, dstfilelist, Text.class, Text.class, SequenceFile.CompressionType.NONE);
Path dstdirlist = new Path(jobDirectory, "_distcp_dst_dirs");
jobConf.set(DST_DIR_LIST_LABEL, dstdirlist.toString());
SequenceFile.Writer dir_writer =
SequenceFile.createWriter(
jobfs,
jobConf,
dstdirlist,
Text.class,
FilePair.class,
SequenceFile.CompressionType.NONE);
// handle the case where the destination directory doesn't exist
// and we've only a single src directory OR we're updating/overwriting
// the contents of the destination directory.
final boolean special = (args.srcs.size() == 1 && !dstExists) || update || overwrite;
int srcCount = 0, cnsyncf = 0, dirsyn = 0;
long fileCount = 0L, byteCount = 0L, cbsyncs = 0L;
try {
for (Iterator<Path> srcItr = args.srcs.iterator(); srcItr.hasNext(); ) {
final Path src = srcItr.next();
FileSystem srcfs = src.getFileSystem(conf);
FileStatus srcfilestat = srcfs.getFileStatus(src);
Path root = special && srcfilestat.isDir() ? src : src.getParent();
if (srcfilestat.isDir()) {
++srcCount;
}
Stack<FileStatus> pathstack = new Stack<FileStatus>();
for (pathstack.push(srcfilestat); !pathstack.empty(); ) {
FileStatus cur = pathstack.pop();
FileStatus[] children = srcfs.listStatus(cur.getPath());
for (int i = 0; i < children.length; i++) {
boolean skipfile = false;
final FileStatus child = children[i];
final String dst = makeRelative(root, child.getPath());
++srcCount;
if (child.isDir()) {
pathstack.push(child);
} else {
// skip file if the src and the dst files are the same.
skipfile = update && sameFile(srcfs, child, dstfs, new Path(args.dst, dst));
// skip file if it exceed file limit or size limit
skipfile |=
fileCount == args.filelimit || byteCount + child.getLen() > args.sizelimit;
if (!skipfile) {
++fileCount;
byteCount += child.getLen();
if (LOG.isTraceEnabled()) {
LOG.trace("adding file " + child.getPath());
}
++cnsyncf;
cbsyncs += child.getLen();
if (cnsyncf > SYNC_FILE_MAX || cbsyncs > BYTES_PER_MAP) {
src_writer.sync();
dst_writer.sync();
cnsyncf = 0;
cbsyncs = 0L;
}
}
}
if (!skipfile) {
src_writer.append(
new LongWritable(child.isDir() ? 0 : child.getLen()), new FilePair(child, dst));
}
dst_writer.append(new Text(dst), new Text(child.getPath().toString()));
}
if (cur.isDir()) {
String dst = makeRelative(root, cur.getPath());
dir_writer.append(new Text(dst), new FilePair(cur, dst));
if (++dirsyn > SYNC_FILE_MAX) {
dirsyn = 0;
dir_writer.sync();
}
}
}
}
} finally {
checkAndClose(src_writer);
checkAndClose(dst_writer);
checkAndClose(dir_writer);
}
FileStatus dststatus = null;
try {
dststatus = dstfs.getFileStatus(args.dst);
} catch (FileNotFoundException fnfe) {
LOG.info(args.dst + " does not exist.");
}
// create dest path dir if copying > 1 file
if (dststatus == null) {
if (srcCount > 1 && !dstfs.mkdirs(args.dst)) {
throw new IOException("Failed to create" + args.dst);
}
}
final Path sorted = new Path(jobDirectory, "_distcp_sorted");
checkDuplication(jobfs, dstfilelist, sorted, conf);
if (dststatus != null && args.flags.contains(Options.DELETE)) {
deleteNonexisting(dstfs, dststatus, sorted, jobfs, jobDirectory, jobConf, conf);
}
Path tmpDir =
new Path(
(dstExists && !dstIsDir) || (!dstExists && srcCount == 1)
? args.dst.getParent()
: args.dst,
"_distcp_tmp_" + randomId);
jobConf.set(TMP_DIR_LABEL, tmpDir.toUri().toString());
LOG.info("srcCount=" + srcCount);
jobConf.setInt(SRC_COUNT_LABEL, srcCount);
jobConf.setLong(TOTAL_SIZE_LABEL, byteCount);
setMapCount(byteCount, jobConf);
}
/**
* Copy a file to a destination.
*
* @param srcstat src path and metadata
* @param dstpath dst path
* @param reporter
*/
private void copy(
FileStatus srcstat,
Path relativedst,
OutputCollector<WritableComparable<?>, Text> outc,
Reporter reporter)
throws IOException {
Path absdst = new Path(destPath, relativedst);
int totfiles = job.getInt(SRC_COUNT_LABEL, -1);
assert totfiles >= 0 : "Invalid file count " + totfiles;
// if a directory, ensure created even if empty
if (srcstat.isDir()) {
if (destFileSys.exists(absdst)) {
if (!destFileSys.getFileStatus(absdst).isDir()) {
throw new IOException("Failed to mkdirs: " + absdst + " is a file.");
}
} else if (!destFileSys.mkdirs(absdst)) {
throw new IOException("Failed to mkdirs " + absdst);
}
// TODO: when modification times can be set, directories should be
// emitted to reducers so they might be preserved. Also, mkdirs does
// not currently return an error when the directory already exists;
// if this changes, all directory work might as well be done in reduce
return;
}
if (destFileSys.exists(absdst) && !overwrite && !needsUpdate(srcstat, destFileSys, absdst)) {
outc.collect(null, new Text("SKIP: " + srcstat.getPath()));
++skipcount;
reporter.incrCounter(Counter.SKIP, 1);
updateStatus(reporter);
return;
}
Path tmpfile = new Path(job.get(TMP_DIR_LABEL), relativedst);
long cbcopied = 0L;
FSDataInputStream in = null;
FSDataOutputStream out = null;
try {
// open src file
try {
in = srcstat.getPath().getFileSystem(job).open(srcstat.getPath());
} catch (IOException e) {
LOG.error("Failed to open src file " + srcstat.getPath() + ", ignore and return");
in = null;
return;
}
reporter.incrCounter(Counter.BYTESEXPECTED, srcstat.getLen());
// open tmp file
out = create(tmpfile, reporter, srcstat);
// copy file
for (int cbread; (cbread = in.read(buffer)) >= 0; ) {
out.write(buffer, 0, cbread);
cbcopied += cbread;
reporter.setStatus(
String.format("%.2f ", cbcopied * 100.0 / srcstat.getLen())
+ absdst
+ " [ "
+ StringUtils.humanReadableInt(cbcopied)
+ " / "
+ StringUtils.humanReadableInt(srcstat.getLen())
+ " ]");
}
} finally {
checkAndClose(in);
checkAndClose(out);
}
if (cbcopied != srcstat.getLen()) {
if (srcstat.getLen() == 0 && cbcopied > 0) {
LOG.info("most likely see a WAL file corruption: " + srcstat.getPath());
} else {
throw new IOException(
"File size not matched: copied "
+ bytesString(cbcopied)
+ " to tmpfile (="
+ tmpfile
+ ") but expected "
+ bytesString(srcstat.getLen())
+ " from "
+ srcstat.getPath());
}
} else {
if (totfiles == 1) {
// Copying a single file; use dst path provided by user as destination
// rather than destination directory, if a file
Path dstparent = absdst.getParent();
if (!(destFileSys.exists(dstparent) && destFileSys.getFileStatus(dstparent).isDir())) {
absdst = dstparent;
}
}
if (destFileSys.exists(absdst) && destFileSys.getFileStatus(absdst).isDir()) {
throw new IOException(absdst + " is a directory");
}
if (!destFileSys.mkdirs(absdst.getParent())) {
throw new IOException("Failed to craete parent dir: " + absdst.getParent());
}
rename(tmpfile, absdst);
FileStatus dststat = destFileSys.getFileStatus(absdst);
if (dststat.getLen() != srcstat.getLen()) {
destFileSys.delete(absdst, false);
throw new IOException(
"File size not matched: copied "
+ bytesString(dststat.getLen())
+ " to dst (="
+ absdst
+ ") but expected "
+ bytesString(srcstat.getLen())
+ " from "
+ srcstat.getPath());
}
updatePermissions(srcstat, dststat);
}
// report at least once for each file
++copycount;
reporter.incrCounter(Counter.BYTESCOPIED, cbcopied);
reporter.incrCounter(Counter.COPY, 1);
updateStatus(reporter);
}