big-data/hadoop
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

HADOOP-11283. SequenceFile.Writer can leak file descriptors in DistCpV1#setup(). (Contributed by Varun Saxena via ozawa)

Browse Source
This commit is contained in:
Tsuyoshi Ozawa 2014-12-25 23:29:54 +09:00
parent b256dd7600
commit a164ce2ac9
2 changed files with 30 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
hadoop-common-project/hadoop-common/CHANGES.txt
View File

@ -650,6 +650,9 @@ Release 2.7.0 - UNRELEASED
HADOOP-11414. FileBasedIPList#readLines() can leak file descriptors.
(ozawa)
HADOOP-11283. SequenceFile.Writer can leak file descriptors in
DistCpV1#setup(). (Varun Saxena via ozawa)
Release 2.6.0 - 2014-11-18
INCOMPATIBLE CHANGES

34
hadoop-tools/hadoop-extras/src/main/java/org/apache/hadoop/tools/DistCpV1.java
View File

@ -1258,30 +1258,29 @@ static boolean setup(Configuration conf, JobConf jobConf,
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(SRC_LIST_LABEL, srcfilelist.toString());
jobConf.set(DST_DIR_LIST_LABEL, dstdirlist.toString());
SequenceFile.Writer dir_writer = SequenceFile.createWriter(jobfs, jobConf,
dstdirlist, Text.class, FilePair.class,
int srcCount = 0, cnsyncf = 0, dirsyn = 0;
long fileCount = 0L, dirCount = 0L, byteCount = 0L, cbsyncs = 0L,
skipFileCount = 0L, skipByteCount = 0L;
try (
SequenceFile.Writer src_writer = SequenceFile.createWriter(jobfs,
jobConf, srcfilelist, LongWritable.class, FilePair.class,
SequenceFile.CompressionType.NONE);
SequenceFile.Writer dst_writer = SequenceFile.createWriter(jobfs,
jobConf, dstfilelist, Text.class, Text.class,
SequenceFile.CompressionType.NONE);
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, dirCount = 0L, byteCount = 0L, cbsyncs = 0L,
skipFileCount = 0L, skipByteCount = 0L;
Path basedir = null;
HashSet<Path> parentDirsToCopy = new HashSet<Path>();
@ -1293,7 +1292,6 @@ static boolean setup(Configuration conf, JobConf jobConf,
}
}
try {
for(Iterator<Path> srcItr = args.srcs.iterator(); srcItr.hasNext(); ) {
final Path src = srcItr.next();
FileSystem srcfs = src.getFileSystem(conf);
@ -1426,10 +1424,6 @@ static boolean setup(Configuration conf, JobConf jobConf,
}
}
}
} finally {
checkAndClose(src_writer);
checkAndClose(dst_writer);
checkAndClose(dir_writer);
}
LOG.info("sourcePathsCount(files+directories)=" + srcCount);
LOG.info("filesToCopyCount=" + fileCount);