/// <summary>Wait for rbw replica to reach the length</summary>
/// <param name="rbw">replica that is being written to</param>
/// <param name="len">minimum length to reach</param>
/// <exception cref="System.IO.IOException">on failing to reach the len in given wait time
/// </exception>
private static void WaitForMinLength(ReplicaBeingWritten rbw, long len)
{
// Wait for 3 seconds for rbw replica to reach the minimum length
for (int i = 0; i < 30 && rbw.GetBytesOnDisk() < len; i++)
{
try
{
Sharpen.Thread.Sleep(100);
}
catch (Exception ie)
{
throw new IOException(ie);
}
}
long bytesOnDisk = rbw.GetBytesOnDisk();
if (bytesOnDisk < len)
{
throw new IOException(string.Format("Need %d bytes, but only %d bytes available",
len, bytesOnDisk));
}
}
public virtual void TestTransferRbw()
{
HdfsConfiguration conf = new HdfsConfiguration();
MiniDFSCluster cluster = new MiniDFSCluster.Builder(conf).NumDataNodes(Replication
).Build();
try
{
cluster.WaitActive();
DistributedFileSystem fs = cluster.GetFileSystem();
//create a file, write some data and leave it open.
Path p = new Path("/foo");
int size = (1 << 16) + Ran.Next(1 << 16);
Log.Info("size = " + size);
FSDataOutputStream @out = fs.Create(p, Replication);
byte[] bytes = new byte[1024];
for (int remaining = size; remaining > 0;)
{
Ran.NextBytes(bytes);
int len = bytes.Length < remaining ? bytes.Length : remaining;
@out.Write(bytes, 0, len);
@out.Hflush();
remaining -= len;
}
//get the RBW
ReplicaBeingWritten oldrbw;
DataNode newnode;
DatanodeInfo newnodeinfo;
string bpid = cluster.GetNamesystem().GetBlockPoolId();
{
DataNode oldnode = cluster.GetDataNodes()[0];
oldrbw = GetRbw(oldnode, bpid);
Log.Info("oldrbw = " + oldrbw);
//add a datanode
cluster.StartDataNodes(conf, 1, true, null, null);
newnode = cluster.GetDataNodes()[Replication];
DatanodeInfo oldnodeinfo;
{
DatanodeInfo[] datatnodeinfos = cluster.GetNameNodeRpc().GetDatanodeReport(HdfsConstants.DatanodeReportType
.Live);
NUnit.Framework.Assert.AreEqual(2, datatnodeinfos.Length);
int i = 0;
for (DatanodeRegistration dnReg = newnode.GetDNRegistrationForBP(bpid); i < datatnodeinfos
.Length && !datatnodeinfos[i].Equals(dnReg); i++)
{
}
NUnit.Framework.Assert.IsTrue(i < datatnodeinfos.Length);
newnodeinfo = datatnodeinfos[i];
oldnodeinfo = datatnodeinfos[1 - i];
}
//transfer RBW
ExtendedBlock b = new ExtendedBlock(bpid, oldrbw.GetBlockId(), oldrbw.GetBytesAcked
(), oldrbw.GetGenerationStamp());
DataTransferProtos.BlockOpResponseProto s = DFSTestUtil.TransferRbw(b, DFSClientAdapter
.GetDFSClient(fs), oldnodeinfo, newnodeinfo);
NUnit.Framework.Assert.AreEqual(DataTransferProtos.Status.Success, s.GetStatus());
}
//check new rbw
ReplicaBeingWritten newrbw = GetRbw(newnode, bpid);
Log.Info("newrbw = " + newrbw);
NUnit.Framework.Assert.AreEqual(oldrbw.GetBlockId(), newrbw.GetBlockId());
NUnit.Framework.Assert.AreEqual(oldrbw.GetGenerationStamp(), newrbw.GetGenerationStamp
());
NUnit.Framework.Assert.AreEqual(oldrbw.GetVisibleLength(), newrbw.GetVisibleLength
());
Log.Info("DONE");
}
finally
{
cluster.Shutdown();
}
}
/// <summary>Constructor</summary>
/// <param name="block">Block that is being read</param>
/// <param name="startOffset">starting offset to read from</param>
/// <param name="length">length of data to read</param>
/// <param name="corruptChecksumOk">if true, corrupt checksum is okay</param>
/// <param name="verifyChecksum">verify checksum while reading the data</param>
/// <param name="sendChecksum">send checksum to client.</param>
/// <param name="datanode">datanode from which the block is being read</param>
/// <param name="clientTraceFmt">format string used to print client trace logs</param>
/// <exception cref="System.IO.IOException"/>
internal BlockSender(ExtendedBlock block, long startOffset, long length, bool corruptChecksumOk
, bool verifyChecksum, bool sendChecksum, DataNode datanode, string clientTraceFmt
, CachingStrategy cachingStrategy)
{
// Cache-management related fields
// 1MB
try
{
this.block = block;
this.corruptChecksumOk = corruptChecksumOk;
this.verifyChecksum = verifyChecksum;
this.clientTraceFmt = clientTraceFmt;
/*
* If the client asked for the cache to be dropped behind all reads,
* we honor that. Otherwise, we use the DataNode defaults.
* When using DataNode defaults, we use a heuristic where we only
* drop the cache for large reads.
*/
if (cachingStrategy.GetDropBehind() == null)
{
this.dropCacheBehindAllReads = false;
this.dropCacheBehindLargeReads = datanode.GetDnConf().dropCacheBehindReads;
}
else
{
this.dropCacheBehindAllReads = this.dropCacheBehindLargeReads = cachingStrategy.GetDropBehind
();
}
/*
* Similarly, if readahead was explicitly requested, we always do it.
* Otherwise, we read ahead based on the DataNode settings, and only
* when the reads are large.
*/
if (cachingStrategy.GetReadahead() == null)
{
this.alwaysReadahead = false;
this.readaheadLength = datanode.GetDnConf().readaheadLength;
}
else
{
this.alwaysReadahead = true;
this.readaheadLength = cachingStrategy.GetReadahead();
}
this.datanode = datanode;
if (verifyChecksum)
{
// To simplify implementation, callers may not specify verification
// without sending.
Preconditions.CheckArgument(sendChecksum, "If verifying checksum, currently must also send it."
);
}
Replica replica;
long replicaVisibleLength;
lock (datanode.data)
{
replica = GetReplica(block, datanode);
replicaVisibleLength = replica.GetVisibleLength();
}
// if there is a write in progress
ChunkChecksum chunkChecksum = null;
if (replica is ReplicaBeingWritten)
{
ReplicaBeingWritten rbw = (ReplicaBeingWritten)replica;
WaitForMinLength(rbw, startOffset + length);
chunkChecksum = rbw.GetLastChecksumAndDataLen();
}
if (replica.GetGenerationStamp() < block.GetGenerationStamp())
{
throw new IOException("Replica gen stamp < block genstamp, block=" + block + ", replica="
+ replica);
}
else
{
if (replica.GetGenerationStamp() > block.GetGenerationStamp())
{
if (DataNode.Log.IsDebugEnabled())
{
DataNode.Log.Debug("Bumping up the client provided" + " block's genstamp to latest "
+ replica.GetGenerationStamp() + " for block " + block);
}
block.SetGenerationStamp(replica.GetGenerationStamp());
}
}
if (replicaVisibleLength < 0)
{
throw new IOException("Replica is not readable, block=" + block + ", replica=" +
replica);
}
if (DataNode.Log.IsDebugEnabled())
{
DataNode.Log.Debug("block=" + block + ", replica=" + replica);
}
// transferToFully() fails on 32 bit platforms for block sizes >= 2GB,
// use normal transfer in those cases
this.transferToAllowed = datanode.GetDnConf().transferToAllowed&& (!is32Bit || length
<= int.MaxValue);
// Obtain a reference before reading data
this.volumeRef = datanode.data.GetVolume(block).ObtainReference();
/*
* (corruptChecksumOK, meta_file_exist): operation
* True, True: will verify checksum
* True, False: No verify, e.g., need to read data from a corrupted file
* False, True: will verify checksum
* False, False: throws IOException file not found
*/
DataChecksum csum = null;
if (verifyChecksum || sendChecksum)
{
LengthInputStream metaIn = null;
bool keepMetaInOpen = false;
try
{
metaIn = datanode.data.GetMetaDataInputStream(block);
if (!corruptChecksumOk || metaIn != null)
{
if (metaIn == null)
{
//need checksum but meta-data not found
throw new FileNotFoundException("Meta-data not found for " + block);
}
// The meta file will contain only the header if the NULL checksum
// type was used, or if the replica was written to transient storage.
// Checksum verification is not performed for replicas on transient
// storage. The header is important for determining the checksum
// type later when lazy persistence copies the block to non-transient
// storage and computes the checksum.
if (metaIn.GetLength() > BlockMetadataHeader.GetHeaderSize())
{
checksumIn = new DataInputStream(new BufferedInputStream(metaIn, HdfsConstants.IoFileBufferSize
));
csum = BlockMetadataHeader.ReadDataChecksum(checksumIn, block);
keepMetaInOpen = true;
}
}
else
{
Log.Warn("Could not find metadata file for " + block);
}
}
finally
{
if (!keepMetaInOpen)
{
IOUtils.CloseStream(metaIn);
}
}
}
if (csum == null)
{
// The number of bytes per checksum here determines the alignment
// of reads: we always start reading at a checksum chunk boundary,
// even if the checksum type is NULL. So, choosing too big of a value
// would risk sending too much unnecessary data. 512 (1 disk sector)
// is likely to result in minimal extra IO.
csum = DataChecksum.NewDataChecksum(DataChecksum.Type.Null, 512);
}
/*
* If chunkSize is very large, then the metadata file is mostly
* corrupted. For now just truncate bytesPerchecksum to blockLength.
*/
int size = csum.GetBytesPerChecksum();
if (size > 10 * 1024 * 1024 && size > replicaVisibleLength)
{
csum = DataChecksum.NewDataChecksum(csum.GetChecksumType(), Math.Max((int)replicaVisibleLength
, 10 * 1024 * 1024));
size = csum.GetBytesPerChecksum();
}
chunkSize = size;
checksum = csum;
checksumSize = checksum.GetChecksumSize();
length = length < 0 ? replicaVisibleLength : length;
// end is either last byte on disk or the length for which we have a
// checksum
long end = chunkChecksum != null?chunkChecksum.GetDataLength() : replica.GetBytesOnDisk
();
if (startOffset < 0 || startOffset > end || (length + startOffset) > end)
{
string msg = " Offset " + startOffset + " and length " + length + " don't match block "
+ block + " ( blockLen " + end + " )";
Log.Warn(datanode.GetDNRegistrationForBP(block.GetBlockPoolId()) + ":sendBlock() : "
+ msg);
throw new IOException(msg);
}
// Ensure read offset is position at the beginning of chunk
offset = startOffset - (startOffset % chunkSize);
if (length >= 0)
{
// Ensure endOffset points to end of chunk.
long tmpLen = startOffset + length;
if (tmpLen % chunkSize != 0)
{
tmpLen += (chunkSize - tmpLen % chunkSize);
}
if (tmpLen < end)
{
// will use on-disk checksum here since the end is a stable chunk
end = tmpLen;
}
else
{
if (chunkChecksum != null)
{
// last chunk is changing. flag that we need to use in-memory checksum
this.lastChunkChecksum = chunkChecksum;
}
}
}
endOffset = end;
// seek to the right offsets
if (offset > 0 && checksumIn != null)
{
long checksumSkip = (offset / chunkSize) * checksumSize;
// note blockInStream is seeked when created below
if (checksumSkip > 0)
{
// Should we use seek() for checksum file as well?
IOUtils.SkipFully(checksumIn, checksumSkip);
}
}
seqno = 0;
if (DataNode.Log.IsDebugEnabled())
{
DataNode.Log.Debug("replica=" + replica);
}
blockIn = datanode.data.GetBlockInputStream(block, offset);
// seek to offset
if (blockIn is FileInputStream)
{
blockInFd = ((FileInputStream)blockIn).GetFD();
}
else
{
blockInFd = null;
}
}
catch (IOException ioe)
{
IOUtils.CloseStream(this);
IOUtils.CloseStream(blockIn);
throw;
}
}