List of usage examples for org.apache.hadoop.io MD5Hash write
@Override
public void write(DataOutput out) throws IOException
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. * // w ww . j a v a2 s.c om * @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.tripadvisor.hadoop.ExternalHDFSChecksumGenerator.java
License:Apache License
/** * * This is the function that calculates the hdfs-style checksum for a local file in the same way that * hdfs does it in a parallel fashion on all of the blocks in hdsf. * * @param strPath//from w w w . ja v a2s .c om * @param bytesPerCRC * @param lBlockSize * @return * @throws IOException */ public MD5MD5CRC32FileChecksum getLocalFilesystemHDFSStyleChecksum(String strPath, int bytesPerCRC, long lBlockSize) throws IOException { long lFileSize = 0; int iBlockCount = 0; DataOutputBuffer md5outDataBuffer = new DataOutputBuffer(); DataChecksum chksm = DataChecksum.newDataChecksum(DataChecksum.CHECKSUM_CRC32, 512); InputStream in = null; MD5MD5CRC32FileChecksum returnChecksum = null; long crc_per_block = lBlockSize / bytesPerCRC; java.io.File file = new java.io.File(strPath); // FileStatus f_stats = srcFs.getFileStatus( srcPath ); lFileSize = file.length(); iBlockCount = (int) Math.ceil((double) lFileSize / (double) lBlockSize); // System.out.println( "Debug > getLen == " + f_stats.getLen() + // " bytes" ); // System.out.println( "Debug > iBlockCount == " + iBlockCount ); if (file.isDirectory()) { throw new IOException("Cannot compute local hdfs hash, " + strPath + " is a directory! "); } try { in = new FileInputStream(file); long lTotalBytesRead = 0; for (int x = 0; x < iBlockCount; x++) { ByteArrayOutputStream ar_CRC_Bytes = new ByteArrayOutputStream(); byte crc[] = new byte[4]; byte buf[] = new byte[512]; try { int bytesRead = 0; while ((bytesRead = in.read(buf)) > 0) { lTotalBytesRead += bytesRead; chksm.reset(); chksm.update(buf, 0, bytesRead); chksm.writeValue(crc, 0, true); ar_CRC_Bytes.write(crc); if (lTotalBytesRead >= (x + 1) * lBlockSize) { break; } } // while DataInputStream inputStream = new DataInputStream( new ByteArrayInputStream(ar_CRC_Bytes.toByteArray())); // this actually computes one ---- run on the server // (DataXceiver) side final MD5Hash md5_dataxceiver = MD5Hash.digest(inputStream); md5_dataxceiver.write(md5outDataBuffer); } catch (IOException e) { e.printStackTrace(); } catch (Exception e) { e.printStackTrace(); } } // for // this is in 0.19.0 style with the extra padding bug final MD5Hash md5_of_md5 = MD5Hash.digest(md5outDataBuffer.getData()); returnChecksum = new MD5MD5CRC32FileChecksum(bytesPerCRC, crc_per_block, md5_of_md5); } catch (IOException e) { e.printStackTrace(); } catch (Exception e) { e.printStackTrace(); } finally { in.close(); } // try return returnChecksum; }