private static BlockReaderLocalLegacy.LocalDatanodeInfo GetLocalDatanodeInfo(int
port)
{
lock (typeof(BlockReaderLocalLegacy))
{
BlockReaderLocalLegacy.LocalDatanodeInfo ldInfo = localDatanodeInfoMap[port];
if (ldInfo == null)
{
ldInfo = new BlockReaderLocalLegacy.LocalDatanodeInfo();
localDatanodeInfoMap[port] = ldInfo;
}
return(ldInfo);
}
}
/// <exception cref="System.IO.IOException"/>
private static BlockLocalPathInfo GetBlockPathInfo(UserGroupInformation ugi, ExtendedBlock
blk, DatanodeInfo node, Configuration conf, int timeout, Org.Apache.Hadoop.Security.Token.Token
<BlockTokenIdentifier> token, bool connectToDnViaHostname, StorageType storageType
)
{
BlockReaderLocalLegacy.LocalDatanodeInfo localDatanodeInfo = GetLocalDatanodeInfo
(node.GetIpcPort());
BlockLocalPathInfo pathinfo = null;
ClientDatanodeProtocol proxy = localDatanodeInfo.GetDatanodeProxy(ugi, node, conf
, timeout, connectToDnViaHostname);
try
{
// make RPC to local datanode to find local pathnames of blocks
pathinfo = proxy.GetBlockLocalPathInfo(blk, token);
// We cannot cache the path information for a replica on transient storage.
// If the replica gets evicted, then it moves to a different path. Then,
// our next attempt to read from the cached path would fail to find the
// file. Additionally, the failure would cause us to disable legacy
// short-circuit read for all subsequent use in the ClientContext. Unlike
// the newer short-circuit read implementation, we have no communication
// channel for the DataNode to notify the client that the path has been
// invalidated. Therefore, our only option is to skip caching.
if (pathinfo != null && !storageType.IsTransient())
{
if (Log.IsDebugEnabled())
{
Log.Debug("Cached location of block " + blk + " as " + pathinfo);
}
localDatanodeInfo.SetBlockLocalPathInfo(blk, pathinfo);
}
}
catch (IOException e)
{
localDatanodeInfo.ResetDatanodeProxy();
// Reset proxy on error
throw;
}
return(pathinfo);
}
// Multiple datanodes could be running on the local machine. Store proxies in
// a map keyed by the ipc port of the datanode.
// reader for the data file
// reader for the checksum file
/// <summary>The only way this object can be instantiated.</summary>
/// <exception cref="System.IO.IOException"/>
internal static BlockReaderLocalLegacy NewBlockReader(DFSClient.Conf conf, UserGroupInformation
userGroupInformation, Configuration configuration, string file, ExtendedBlock blk
, Org.Apache.Hadoop.Security.Token.Token <BlockTokenIdentifier> token, DatanodeInfo
node, long startOffset, long length, StorageType storageType)
{
BlockReaderLocalLegacy.LocalDatanodeInfo localDatanodeInfo = GetLocalDatanodeInfo
(node.GetIpcPort());
// check the cache first
BlockLocalPathInfo pathinfo = localDatanodeInfo.GetBlockLocalPathInfo(blk);
if (pathinfo == null)
{
if (userGroupInformation == null)
{
userGroupInformation = UserGroupInformation.GetCurrentUser();
}
pathinfo = GetBlockPathInfo(userGroupInformation, blk, node, configuration, conf.
socketTimeout, token, conf.connectToDnViaHostname, storageType);
}
// check to see if the file exists. It may so happen that the
// HDFS file has been deleted and this block-lookup is occurring
// on behalf of a new HDFS file. This time, the block file could
// be residing in a different portion of the fs.data.dir directory.
// In this case, we remove this entry from the cache. The next
// call to this method will re-populate the cache.
FileInputStream dataIn = null;
FileInputStream checksumIn = null;
BlockReaderLocalLegacy localBlockReader = null;
bool skipChecksumCheck = conf.skipShortCircuitChecksums || storageType.IsTransient
();
try
{
// get a local file system
FilePath blkfile = new FilePath(pathinfo.GetBlockPath());
dataIn = new FileInputStream(blkfile);
if (Log.IsDebugEnabled())
{
Log.Debug("New BlockReaderLocalLegacy for file " + blkfile + " of size " + blkfile
.Length() + " startOffset " + startOffset + " length " + length + " short circuit checksum "
+ !skipChecksumCheck);
}
if (!skipChecksumCheck)
{
// get the metadata file
FilePath metafile = new FilePath(pathinfo.GetMetaPath());
checksumIn = new FileInputStream(metafile);
DataChecksum checksum = BlockMetadataHeader.ReadDataChecksum(new DataInputStream(
checksumIn), blk);
long firstChunkOffset = startOffset - (startOffset % checksum.GetBytesPerChecksum
());
localBlockReader = new BlockReaderLocalLegacy(conf, file, blk, token, startOffset
, length, pathinfo, checksum, true, dataIn, firstChunkOffset, checksumIn);
}
else
{
localBlockReader = new BlockReaderLocalLegacy(conf, file, blk, token, startOffset
, length, pathinfo, dataIn);
}
}
catch (IOException e)
{
// remove from cache
localDatanodeInfo.RemoveBlockLocalPathInfo(blk);
DFSClient.Log.Warn("BlockReaderLocalLegacy: Removing " + blk + " from cache because local file "
+ pathinfo.GetBlockPath() + " could not be opened.");
throw;
}
finally
{
if (localBlockReader == null)
{
if (dataIn != null)
{
dataIn.Close();
}
if (checksumIn != null)
{
checksumIn.Close();
}
}
}
return(localBlockReader);
}
