List of usage examples for org.apache.hadoop.hdfs.protocol.datatransfer Sender Sender
public Sender(final DataOutputStream out)
From source file:BlockReaderFactory.java
License:Apache License
/** * Request file descriptors from a DomainPeer. * * @param peer The peer to use for communication. * @param slot If non-null, the shared memory slot to associate with the * new ShortCircuitReplica. * /*from w ww.j ava 2 s. c o m*/ * @return A ShortCircuitReplica object if we could communicate with the * datanode; null, otherwise. * @throws IOException If we encountered an I/O exception while communicating * with the datanode. */ private ShortCircuitReplicaInfo requestFileDescriptors(DomainPeer peer, Slot slot) throws IOException { ShortCircuitCache cache = clientContext.getShortCircuitCache(); final DataOutputStream out = new DataOutputStream(new BufferedOutputStream(peer.getOutputStream())); SlotId slotId = slot == null ? null : slot.getSlotId(); new Sender(out).requestShortCircuitFds(block, token, slotId, 1); DataInputStream in = new DataInputStream(peer.getInputStream()); BlockOpResponseProto resp = BlockOpResponseProto.parseFrom(PBHelper.vintPrefixed(in)); DomainSocket sock = peer.getDomainSocket(); switch (resp.getStatus()) { case SUCCESS: byte buf[] = new byte[1]; FileInputStream fis[] = new FileInputStream[2]; sock.recvFileInputStreams(fis, buf, 0, buf.length); ShortCircuitReplica replica = null; try { ExtendedBlockId key = new ExtendedBlockId(block.getBlockId(), block.getBlockPoolId()); replica = new ShortCircuitReplica(key, fis[0], fis[1], cache, Time.monotonicNow(), slot); } catch (IOException e) { // This indicates an error reading from disk, or a format error. Since // it's not a socket communication problem, we return null rather than // throwing an exception. LOG.warn(this + ": error creating ShortCircuitReplica.", e); return null; } finally { if (replica == null) { IOUtils.cleanup(DFSClient.LOG, fis[0], fis[1]); } } return new ShortCircuitReplicaInfo(replica); case ERROR_UNSUPPORTED: if (!resp.hasShortCircuitAccessVersion()) { LOG.warn("short-circuit read access is disabled for " + "DataNode " + datanode + ". reason: " + resp.getMessage()); clientContext.getDomainSocketFactory().disableShortCircuitForPath(pathInfo.getPath()); } else { LOG.warn("short-circuit read access for the file " + fileName + " is disabled for DataNode " + datanode + ". reason: " + resp.getMessage()); } return null; case ERROR_ACCESS_TOKEN: String msg = "access control error while " + "attempting to set up short-circuit access to " + fileName + resp.getMessage(); if (LOG.isDebugEnabled()) { LOG.debug(this + ":" + msg); } return new ShortCircuitReplicaInfo(new InvalidToken(msg)); default: LOG.warn(this + ": unknown response code " + resp.getStatus() + " while attempting to set up short-circuit access. " + resp.getMessage()); clientContext.getDomainSocketFactory().disableShortCircuitForPath(pathInfo.getPath()); return null; } }
From source file:com.mellanox.r4h.DFSClient.java
License:Apache License
/** * Get the checksum of the whole file of a range of the file. Note that the * range always starts from the beginning of the file. * /*from w w w . ja v a2 s .c o m*/ * @param src * The file path * @param length * the length of the range, i.e., the range is [0, length] * @return The checksum * @see DistributedFileSystem#getFileChecksum(Path) */ public MD5MD5CRC32FileChecksum getFileChecksum(String src, long length) throws IOException { checkOpen(); Preconditions.checkArgument(length >= 0); // get block locations for the file range LocatedBlocks blockLocations = callGetBlockLocations(namenode, src, 0, length); if (null == blockLocations) { throw new FileNotFoundException("File does not exist: " + src); } List<LocatedBlock> locatedblocks = blockLocations.getLocatedBlocks(); final DataOutputBuffer md5out = new DataOutputBuffer(); int bytesPerCRC = -1; DataChecksum.Type crcType = DataChecksum.Type.DEFAULT; long crcPerBlock = 0; boolean refetchBlocks = false; int lastRetriedIndex = -1; // get block checksum for each block long remaining = length; if (src.contains(HdfsConstants.SEPARATOR_DOT_SNAPSHOT_DIR_SEPARATOR)) { remaining = Math.min(length, blockLocations.getFileLength()); } for (int i = 0; i < locatedblocks.size() && remaining > 0; i++) { if (refetchBlocks) { // refetch to get fresh tokens blockLocations = callGetBlockLocations(namenode, src, 0, length); if (null == blockLocations) { throw new FileNotFoundException("File does not exist: " + src); } locatedblocks = blockLocations.getLocatedBlocks(); refetchBlocks = false; } LocatedBlock lb = locatedblocks.get(i); final ExtendedBlock block = lb.getBlock(); if (remaining < block.getNumBytes()) { block.setNumBytes(remaining); } remaining -= block.getNumBytes(); final DatanodeInfo[] datanodes = lb.getLocations(); // try each datanode location of the block final int timeout = 3000 * datanodes.length + dfsClientConf.socketTimeout(); boolean done = false; for (int j = 0; !done && j < datanodes.length; j++) { DataOutputStream out = null; DataInputStream in = null; try { // connect to a datanode IOStreamPair pair = connectToDN(datanodes[j], timeout, lb); out = new DataOutputStream(new BufferedOutputStream(pair.out, HdfsConstants.SMALL_BUFFER_SIZE)); in = new DataInputStream(pair.in); if (LOG.isDebugEnabled()) { LOG.debug("write to " + datanodes[j] + ": " + Op.BLOCK_CHECKSUM + ", block=" + block); } // get block MD5 new Sender(out).blockChecksum(block, lb.getBlockToken()); final BlockOpResponseProto reply = BlockOpResponseProto.parseFrom(PBHelper.vintPrefixed(in)); String logInfo = "for block " + block + " from datanode " + datanodes[j]; DataTransferProtoUtil.checkBlockOpStatus(reply, logInfo); OpBlockChecksumResponseProto checksumData = reply.getChecksumResponse(); // read byte-per-checksum final int bpc = checksumData.getBytesPerCrc(); if (i == 0) { // first block bytesPerCRC = bpc; } else if (bpc != bytesPerCRC) { throw new IOException( "Byte-per-checksum not matched: bpc=" + bpc + " but bytesPerCRC=" + bytesPerCRC); } // read crc-per-block final long cpb = checksumData.getCrcPerBlock(); if (locatedblocks.size() > 1 && i == 0) { crcPerBlock = cpb; } // read md5 final MD5Hash md5 = new MD5Hash(checksumData.getMd5().toByteArray()); md5.write(md5out); // read crc-type final DataChecksum.Type ct; if (checksumData.hasCrcType()) { ct = PBHelper.convert(checksumData.getCrcType()); } else { LOG.debug("Retrieving checksum from an earlier-version DataNode: " + "inferring checksum by reading first byte"); ct = inferChecksumTypeByReading(lb, datanodes[j]); } if (i == 0) { // first block crcType = ct; } else if (crcType != DataChecksum.Type.MIXED && crcType != ct) { // if crc types are mixed in a file crcType = DataChecksum.Type.MIXED; } done = true; if (LOG.isDebugEnabled()) { if (i == 0) { LOG.debug("set bytesPerCRC=" + bytesPerCRC + ", crcPerBlock=" + crcPerBlock); } LOG.debug("got reply from " + datanodes[j] + ": md5=" + md5); } } catch (InvalidBlockTokenException ibte) { if (i > lastRetriedIndex) { if (LOG.isDebugEnabled()) { LOG.debug("Got access token error in response to OP_BLOCK_CHECKSUM " + "for file " + src + " for block " + block + " from datanode " + datanodes[j] + ". Will retry the block once."); } lastRetriedIndex = i; done = true; // actually it's not done; but we'll retry i--; // repeat at i-th block refetchBlocks = true; break; } } catch (IOException ie) { LOG.warn("src=" + src + ", datanodes[" + j + "]=" + datanodes[j], ie); } finally { IOUtils.closeStream(in); IOUtils.closeStream(out); } } if (!done) { throw new IOException("Fail to get block MD5 for " + block); } } // compute file MD5 final MD5Hash fileMD5 = MD5Hash.digest(md5out.getData()); switch (crcType) { case CRC32: return new MD5MD5CRC32GzipFileChecksum(bytesPerCRC, crcPerBlock, fileMD5); case CRC32C: return new MD5MD5CRC32CastagnoliFileChecksum(bytesPerCRC, crcPerBlock, fileMD5); default: // If there is no block allocated for the file, // return one with the magic entry that matches what previous // hdfs versions return. if (locatedblocks.size() == 0) { return new MD5MD5CRC32GzipFileChecksum(0, 0, fileMD5); } // we should never get here since the validity was checked // when getCrcType() was called above. return null; } }
From source file:com.mellanox.r4h.DFSClient.java
License:Apache License
/** * Infer the checksum type for a replica by sending an OP_READ_BLOCK * for the first byte of that replica. This is used for compatibility * with older HDFS versions which did not include the checksum type in * OpBlockChecksumResponseProto./*from w w w . j ava 2s. c o m*/ * * @param lb * the located block * @param dn * the connected datanode * @return the inferred checksum type * @throws IOException * if an error occurs */ private Type inferChecksumTypeByReading(LocatedBlock lb, DatanodeInfo dn) throws IOException { IOStreamPair pair = connectToDN(dn, dfsClientConf.socketTimeout(), lb); try { DataOutputStream out = new DataOutputStream( new BufferedOutputStream(pair.out, HdfsConstants.SMALL_BUFFER_SIZE)); DataInputStream in = new DataInputStream(pair.in); new Sender(out).readBlock(lb.getBlock(), lb.getBlockToken(), clientName, 0, 1, true, CachingStrategy.newDefaultStrategy()); final BlockOpResponseProto reply = BlockOpResponseProto.parseFrom(PBHelper.vintPrefixed(in)); String logInfo = "trying to read " + lb.getBlock() + " from datanode " + dn; DataTransferProtoUtil.checkBlockOpStatus(reply, logInfo); return PBHelper.convert(reply.getReadOpChecksumInfo().getChecksum().getType()); } finally { IOUtils.cleanup(null, pair.in, pair.out); } }