protected internal override bool IsSplitable(JobContext context, Path file)
{
CompressionCodec codec = new CompressionCodecFactory(context.GetConfiguration()).
GetCodec(file);
return(null == codec);
}
protected internal virtual bool IsSplitable(FileSystem fs, Path file)
{
CompressionCodec codec = new CompressionCodecFactory(fs.GetConf()).GetCodec(file);
if (null == codec)
{
return(true);
}
return(codec is SplittableCompressionCodec);
}
/// <summary>
/// Create a compression instance using the codec specified by
/// <code>codecClassName</code>
/// </summary>
/// <exception cref="System.IO.IOException"/>
internal static Org.Apache.Hadoop.Hdfs.Server.Namenode.FSImageCompression CreateCompression
(Configuration conf, string codecClassName)
{
CompressionCodecFactory factory = new CompressionCodecFactory(conf);
CompressionCodec codec = factory.GetCodecByClassName(codecClassName);
if (codec == null)
{
throw new IOException("Not a supported codec: " + codecClassName);
}
return(new Org.Apache.Hadoop.Hdfs.Server.Namenode.FSImageCompression(codec));
}
/// <exception cref="System.IO.IOException"/>
public override void Initialize(InputSplit genericSplit, TaskAttemptContext context
)
{
FileSplit split = (FileSplit)genericSplit;
Configuration job = context.GetConfiguration();
this.maxLineLength = job.GetInt(MaxLineLength, int.MaxValue);
start = split.GetStart();
end = start + split.GetLength();
Path file = split.GetPath();
// open the file and seek to the start of the split
FileSystem fs = file.GetFileSystem(job);
fileIn = fs.Open(file);
CompressionCodec codec = new CompressionCodecFactory(job).GetCodec(file);
if (null != codec)
{
isCompressedInput = true;
decompressor = CodecPool.GetDecompressor(codec);
if (codec is SplittableCompressionCodec)
{
SplitCompressionInputStream cIn = ((SplittableCompressionCodec)codec).CreateInputStream
(fileIn, decompressor, start, end, SplittableCompressionCodec.READ_MODE.Byblock);
@in = new CompressedSplitLineReader(cIn, job, this.recordDelimiterBytes);
start = cIn.GetAdjustedStart();
end = cIn.GetAdjustedEnd();
filePosition = cIn;
}
else
{
@in = new SplitLineReader(codec.CreateInputStream(fileIn, decompressor), job, this
.recordDelimiterBytes);
filePosition = fileIn;
}
}
else
{
fileIn.Seek(start);
@in = new UncompressedSplitLineReader(fileIn, job, this.recordDelimiterBytes, split
.GetLength());
filePosition = fileIn;
}
// If this is not the first split, we always throw away first record
// because we always (except the last split) read one extra line in
// next() method.
if (start != 0)
{
start += @in.ReadLine(new Text(), 0, MaxBytesToConsume(start));
}
this.pos = start;
}
/// <exception cref="System.IO.IOException"/>
public LineRecordReader(Configuration job, FileSplit split, byte[] recordDelimiter
)
{
this.maxLineLength = job.GetInt(LineRecordReader.MaxLineLength, int.MaxValue);
start = split.GetStart();
end = start + split.GetLength();
Path file = split.GetPath();
compressionCodecs = new CompressionCodecFactory(job);
codec = compressionCodecs.GetCodec(file);
// open the file and seek to the start of the split
FileSystem fs = file.GetFileSystem(job);
fileIn = fs.Open(file);
if (IsCompressedInput())
{
decompressor = CodecPool.GetDecompressor(codec);
if (codec is SplittableCompressionCodec)
{
SplitCompressionInputStream cIn = ((SplittableCompressionCodec)codec).CreateInputStream
(fileIn, decompressor, start, end, SplittableCompressionCodec.READ_MODE.Byblock);
@in = new CompressedSplitLineReader(cIn, job, recordDelimiter);
start = cIn.GetAdjustedStart();
end = cIn.GetAdjustedEnd();
filePosition = cIn;
}
else
{
// take pos from compressed stream
@in = new SplitLineReader(codec.CreateInputStream(fileIn, decompressor), job, recordDelimiter
);
filePosition = fileIn;
}
}
else
{
fileIn.Seek(start);
@in = new UncompressedSplitLineReader(fileIn, job, recordDelimiter, split.GetLength
());
filePosition = fileIn;
}
// If this is not the first split, we always throw away first record
// because we always (except the last split) read one extra line in
// next() method.
if (start != 0)
{
start += @in.ReadLine(new Text(), 0, MaxBytesToConsume(start));
}
this.pos = start;
}
// This is also called from the old FixedLengthRecordReader API implementation
/// <exception cref="System.IO.IOException"/>
public virtual void Initialize(Configuration job, long splitStart, long splitLength
, Path file)
{
start = splitStart;
end = start + splitLength;
long partialRecordLength = start % recordLength;
long numBytesToSkip = 0;
if (partialRecordLength != 0)
{
numBytesToSkip = recordLength - partialRecordLength;
}
// open the file and seek to the start of the split
FileSystem fs = file.GetFileSystem(job);
fileIn = fs.Open(file);
CompressionCodec codec = new CompressionCodecFactory(job).GetCodec(file);
if (null != codec)
{
isCompressedInput = true;
decompressor = CodecPool.GetDecompressor(codec);
CompressionInputStream cIn = codec.CreateInputStream(fileIn, decompressor);
filePosition = cIn;
inputStream = cIn;
numRecordsRemainingInSplit = long.MaxValue;
Log.Info("Compressed input; cannot compute number of records in the split");
}
else
{
fileIn.Seek(start);
filePosition = fileIn;
inputStream = fileIn;
long splitSize = end - start - numBytesToSkip;
numRecordsRemainingInSplit = (splitSize + recordLength - 1) / recordLength;
if (numRecordsRemainingInSplit < 0)
{
numRecordsRemainingInSplit = 0;
}
Log.Info("Expecting " + numRecordsRemainingInSplit + " records each with a length of "
+ recordLength + " bytes in the split with an effective size of " + splitSize +
" bytes");
}
if (numBytesToSkip != 0)
{
start += inputStream.Skip(numBytesToSkip);
}
this.pos = start;
}
protected internal virtual Configuration SetupCommonConfig()
{
tmpOivImgDir = Files.CreateTempDir();
Configuration conf = new Configuration();
conf.SetInt(DFSConfigKeys.DfsNamenodeCheckpointCheckPeriodKey, 1);
conf.SetInt(DFSConfigKeys.DfsNamenodeCheckpointTxnsKey, 5);
conf.SetInt(DFSConfigKeys.DfsHaTaileditsPeriodKey, 1);
conf.Set(DFSConfigKeys.DfsNamenodeLegacyOivImageDirKey, tmpOivImgDir.GetAbsolutePath
());
conf.SetBoolean(DFSConfigKeys.DfsImageCompressKey, true);
conf.Set(DFSConfigKeys.DfsImageCompressionCodecKey, typeof(TestStandbyCheckpoints.SlowCodec
).GetCanonicalName());
CompressionCodecFactory.SetCodecClasses(conf, ImmutableList.Of <Type>(typeof(TestStandbyCheckpoints.SlowCodec
)));
return(conf);
}
public virtual void SetUp()
{
Configuration conf = new Configuration();
conf.SetInt(DFSConfigKeys.DfsNamenodeCheckpointCheckPeriodKey, 1);
conf.SetInt(DFSConfigKeys.DfsNamenodeCheckpointTxnsKey, 5);
conf.SetInt(DFSConfigKeys.DfsHaTaileditsPeriodKey, 1);
conf.Set(DFSConfigKeys.DfsNamenodeSharedEditsDirKey, BKJMUtil.CreateJournalURI("/bootstrapStandby"
).ToString());
BKJMUtil.AddJournalManagerDefinition(conf);
conf.SetBoolean(DFSConfigKeys.DfsImageCompressKey, true);
conf.Set(DFSConfigKeys.DfsImageCompressionCodecKey, typeof(TestStandbyCheckpoints.SlowCodec
).GetCanonicalName());
CompressionCodecFactory.SetCodecClasses(conf, ImmutableList.Of <Type>(typeof(TestStandbyCheckpoints.SlowCodec
)));
MiniDFSNNTopology topology = new MiniDFSNNTopology().AddNameservice(new MiniDFSNNTopology.NSConf
("ns1").AddNN(new MiniDFSNNTopology.NNConf("nn1").SetHttpPort(10001)).AddNN(new
MiniDFSNNTopology.NNConf("nn2").SetHttpPort(10002)));
cluster = new MiniDFSCluster.Builder(conf).NnTopology(topology).NumDataNodes(1).ManageNameDfsSharedDirs
(false).Build();
cluster.WaitActive();
}
public virtual void Configure(JobConf conf)
{
compressionCodecs = new CompressionCodecFactory(conf);
}
/* (non-Javadoc)
* @see ImageLoader#processImage(java.io.DataInputStream, ImageVisitor, boolean)
*/
/// <exception cref="System.IO.IOException"/>
public override void LoadImage(DataInputStream @in, ImageVisitor v, bool skipBlocks
)
{
bool done = false;
try
{
v.Start();
v.VisitEnclosingElement(ImageVisitor.ImageElement.FsImage);
imageVersion = @in.ReadInt();
if (!CanLoadVersion(imageVersion))
{
throw new IOException("Cannot process fslayout version " + imageVersion);
}
if (NameNodeLayoutVersion.Supports(LayoutVersion.Feature.AddLayoutFlags, imageVersion
))
{
LayoutFlags.Read(@in);
}
v.Visit(ImageVisitor.ImageElement.ImageVersion, imageVersion);
v.Visit(ImageVisitor.ImageElement.NamespaceId, @in.ReadInt());
long numInodes = @in.ReadLong();
v.Visit(ImageVisitor.ImageElement.GenerationStamp, @in.ReadLong());
if (NameNodeLayoutVersion.Supports(LayoutVersion.Feature.SequentialBlockId, imageVersion
))
{
v.Visit(ImageVisitor.ImageElement.GenerationStampV2, @in.ReadLong());
v.Visit(ImageVisitor.ImageElement.GenerationStampV1Limit, @in.ReadLong());
v.Visit(ImageVisitor.ImageElement.LastAllocatedBlockId, @in.ReadLong());
}
if (NameNodeLayoutVersion.Supports(LayoutVersion.Feature.StoredTxids, imageVersion
))
{
v.Visit(ImageVisitor.ImageElement.TransactionId, @in.ReadLong());
}
if (NameNodeLayoutVersion.Supports(LayoutVersion.Feature.AddInodeId, imageVersion
))
{
v.Visit(ImageVisitor.ImageElement.LastInodeId, @in.ReadLong());
}
bool supportSnapshot = NameNodeLayoutVersion.Supports(LayoutVersion.Feature.Snapshot
, imageVersion);
if (supportSnapshot)
{
v.Visit(ImageVisitor.ImageElement.SnapshotCounter, @in.ReadInt());
int numSnapshots = @in.ReadInt();
v.Visit(ImageVisitor.ImageElement.NumSnapshotsTotal, numSnapshots);
for (int i = 0; i < numSnapshots; i++)
{
ProcessSnapshot(@in, v);
}
}
if (NameNodeLayoutVersion.Supports(LayoutVersion.Feature.FsimageCompression, imageVersion
))
{
bool isCompressed = @in.ReadBoolean();
v.Visit(ImageVisitor.ImageElement.IsCompressed, isCompressed.ToString());
if (isCompressed)
{
string codecClassName = Text.ReadString(@in);
v.Visit(ImageVisitor.ImageElement.CompressCodec, codecClassName);
CompressionCodecFactory codecFac = new CompressionCodecFactory(new Configuration(
));
CompressionCodec codec = codecFac.GetCodecByClassName(codecClassName);
if (codec == null)
{
throw new IOException("Image compression codec not supported: " + codecClassName);
}
@in = new DataInputStream(codec.CreateInputStream(@in));
}
}
ProcessINodes(@in, v, numInodes, skipBlocks, supportSnapshot);
subtreeMap.Clear();
dirNodeMap.Clear();
ProcessINodesUC(@in, v, skipBlocks);
if (NameNodeLayoutVersion.Supports(LayoutVersion.Feature.DelegationToken, imageVersion
))
{
ProcessDelegationTokens(@in, v);
}
if (NameNodeLayoutVersion.Supports(LayoutVersion.Feature.Caching, imageVersion))
{
ProcessCacheManagerState(@in, v);
}
v.LeaveEnclosingElement();
// FSImage
done = true;
}
finally
{
if (done)
{
v.Finish();
}
else
{
v.FinishAbnormally();
}
}
}
/// <exception cref="System.IO.IOException"/>
protected internal override InputStream GetInputStream(PathData item)
{
FSDataInputStream i = (FSDataInputStream)base.GetInputStream(item);
// Handle 0 and 1-byte files
short leadBytes;
try
{
leadBytes = i.ReadShort();
}
catch (EOFException)
{
i.Seek(0);
return(i);
}
switch (leadBytes)
{
case unchecked ((int)(0x1f8b)):
{
// Check type of stream first
// RFC 1952
// Must be gzip
i.Seek(0);
return(new GZIPInputStream(i));
}
case unchecked ((int)(0x5345)):
{
// 'S' 'E'
// Might be a SequenceFile
if (i.ReadByte() == 'Q')
{
i.Close();
return(new Display.TextRecordInputStream(this, item.stat));
}
goto default;
}
default:
{
// Check the type of compression instead, depending on Codec class's
// own detection methods, based on the provided path.
CompressionCodecFactory cf = new CompressionCodecFactory(GetConf());
CompressionCodec codec = cf.GetCodec(item.path);
if (codec != null)
{
i.Seek(0);
return(codec.CreateInputStream(i));
}
break;
}
case unchecked ((int)(0x4f62)):
{
// 'O' 'b'
if (i.ReadByte() == 'j')
{
i.Close();
return(new Display.AvroFileInputStream(item.stat));
}
break;
}
}
// File is non-compressed, or not a file container we know.
i.Seek(0);
return(i);
}
