private File addBlock(Block b, File src, boolean createOk, boolean resetIdx) throws IOException { if (numBlocks < maxBlocksPerDir) { File dest = new File(dir, b.getBlockName()); File metaData = getMetaFile(src, b); File newmeta = getMetaFile(dest, b); if (!metaData.renameTo(newmeta) || !src.renameTo(dest)) { throw new IOException( "could not move files for " + b + " from tmp to " + dest.getAbsolutePath()); } if (DataNode.LOG.isDebugEnabled()) { DataNode.LOG.debug("addBlock: Moved " + metaData + " to " + newmeta); DataNode.LOG.debug("addBlock: Moved " + src + " to " + dest); } numBlocks += 1; return dest; } if (lastChildIdx < 0 && resetIdx) { // reset so that all children will be checked lastChildIdx = random.nextInt(children.length); } if (lastChildIdx >= 0 && children != null) { // Check if any child-tree has room for a block. for (int i = 0; i < children.length; i++) { int idx = (lastChildIdx + i) % children.length; File file = children[idx].addBlock(b, src, false, resetIdx); if (file != null) { lastChildIdx = idx; return file; } } lastChildIdx = -1; } if (!createOk) { return null; } if (children == null || children.length == 0) { children = new FSDir[maxBlocksPerDir]; for (int idx = 0; idx < maxBlocksPerDir; idx++) { children[idx] = new FSDir(new File(dir, DataStorage.BLOCK_SUBDIR_PREFIX + idx)); } } // now pick a child randomly for creating a new set of subdirs. lastChildIdx = random.nextInt(children.length); return children[lastChildIdx].addBlock(b, src, true, false); }
/** Return the block file for the given ID */ public File findBlockFile(long blockId) { final Block b = new Block(blockId); File blockfile = null; ActiveFile activefile = ongoingCreates.get(b); if (activefile != null) { blockfile = activefile.file; } if (blockfile == null) { blockfile = getFile(b); } if (blockfile == null) { if (DataNode.LOG.isDebugEnabled()) { DataNode.LOG.debug("ongoingCreates=" + ongoingCreates); DataNode.LOG.debug("volumeMap=" + volumeMap); } } return blockfile; }
/** * Start writing to a block file If isRecovery is true and the block pre-exists, then we kill all * volumeMap.put(b, v); volumeMap.put(b, v); other threads that might be writing to this block, * and then reopen the file. */ public BlockWriteStreams writeToBlock(Block b, boolean isRecovery) throws IOException { // // Make sure the block isn't a valid one - we're still creating it! // if (isValidBlock(b)) { if (!isRecovery) { throw new BlockAlreadyExistsException( "Block " + b + " is valid, and cannot be written to."); } // If the block was successfully finalized because all packets // were successfully processed at the Datanode but the ack for // some of the packets were not received by the client. The client // re-opens the connection and retries sending those packets. // The other reason is that an "append" is occurring to this block. detachBlock(b, 1); } long blockSize = b.getNumBytes(); // // Serialize access to /tmp, and check if file already there. // File f = null; List<Thread> threads = null; synchronized (this) { // // Is it already in the create process? // ActiveFile activeFile = ongoingCreates.get(b); if (activeFile != null) { f = activeFile.file; threads = activeFile.threads; if (!isRecovery) { throw new BlockAlreadyExistsException( "Block " + b + " has already been started (though not completed), and thus cannot be created."); } else { for (Thread thread : threads) { thread.interrupt(); } } ongoingCreates.remove(b); } FSVolume v = null; if (!isRecovery) { v = volumes.getNextVolume(blockSize); // create temporary file to hold block in the designated volume f = createTmpFile(v, b); volumeMap.put(b, new DatanodeBlockInfo(v)); } else if (f != null) { DataNode.LOG.info("Reopen already-open Block for append " + b); // create or reuse temporary file to hold block in the // designated volume v = volumeMap.get(b).getVolume(); volumeMap.put(b, new DatanodeBlockInfo(v)); } else { // reopening block for appending to it. DataNode.LOG.info("Reopen Block for append " + b); v = volumeMap.get(b).getVolume(); f = createTmpFile(v, b); File blkfile = getBlockFile(b); File oldmeta = getMetaFile(b); File newmeta = getMetaFile(f, b); // rename meta file to tmp directory DataNode.LOG.debug("Renaming " + oldmeta + " to " + newmeta); if (!oldmeta.renameTo(newmeta)) { throw new IOException( "Block " + b + " reopen failed. " + " Unable to move meta file " + oldmeta + " to tmp dir " + newmeta); } // rename block file to tmp directory DataNode.LOG.debug("Renaming " + blkfile + " to " + f); if (!blkfile.renameTo(f)) { if (!f.delete()) { throw new IOException( "Block " + b + " reopen failed. " + " Unable to remove file " + f); } if (!blkfile.renameTo(f)) { throw new IOException( "Block " + b + " reopen failed. " + " Unable to move block file " + blkfile + " to tmp dir " + f); } } volumeMap.put(b, new DatanodeBlockInfo(v)); } if (f == null) { DataNode.LOG.warn("Block " + b + " reopen failed " + " Unable to locate tmp file."); throw new IOException("Block " + b + " reopen failed " + " Unable to locate tmp file."); } ongoingCreates.put(b, new ActiveFile(f, threads)); } try { if (threads != null) { for (Thread thread : threads) { thread.join(); } } } catch (InterruptedException e) { throw new IOException("Recovery waiting for thread interrupted."); } // // Finally, allow a writer to the block file // REMIND - mjc - make this a filter stream that enforces a max // block size, so clients can't go crazy // File metafile = getMetaFile(f, b); DataNode.LOG.debug("writeTo blockfile is " + f + " of size " + f.length()); DataNode.LOG.debug("writeTo metafile is " + metafile + " of size " + metafile.length()); return createBlockWriteStreams(f, metafile); }
BlockSender( Block block, long startOffset, long length, boolean corruptChecksumOk, boolean chunkOffsetOK, boolean verifyChecksum, DataNode datanode, String clientTraceFmt) throws IOException { try { this.block = block; synchronized (datanode.data) { this.replica = datanode.data.getReplica(block.getBlockId()); if (replica == null) { throw new ReplicaNotFoundException(block); } this.replicaVisibleLength = replica.getVisibleLength(); } long minEndOffset = startOffset + length; // if this is a write in progress ChunkChecksum chunkChecksum = null; if (replica instanceof ReplicaBeingWritten) { for (int i = 0; i < 30 && replica.getBytesOnDisk() < minEndOffset; i++) { try { Thread.sleep(100); } catch (InterruptedException ie) { throw new IOException(ie); } } long currentBytesOnDisk = replica.getBytesOnDisk(); if (currentBytesOnDisk < minEndOffset) { throw new IOException( String.format( "need %d bytes, but only %d bytes available", minEndOffset, currentBytesOnDisk)); } ReplicaInPipeline rip = (ReplicaInPipeline) replica; chunkChecksum = rip.getLastChecksumAndDataLen(); } if (replica.getGenerationStamp() < block.getGenerationStamp()) { throw new IOException( "replica.getGenerationStamp() < block.getGenerationStamp(), block=" + block + ", replica=" + replica); } if (replicaVisibleLength < 0) { throw new IOException( "The replica is not readable, block=" + block + ", replica=" + replica); } if (DataNode.LOG.isDebugEnabled()) { DataNode.LOG.debug("block=" + block + ", replica=" + replica); } this.chunkOffsetOK = chunkOffsetOK; this.corruptChecksumOk = corruptChecksumOk; this.verifyChecksum = verifyChecksum; // transferToFully() fails on 32 bit platforms for block sizes >= 2GB, // use normal transfer in those cases this.transferToAllowed = datanode.transferToAllowed && (!is32Bit || length < (long) Integer.MAX_VALUE); this.clientTraceFmt = clientTraceFmt; if (!corruptChecksumOk || datanode.data.metaFileExists(block)) { checksumIn = new DataInputStream( new BufferedInputStream(datanode.data.getMetaDataInputStream(block), BUFFER_SIZE)); // read and handle the common header here. For now just a version BlockMetadataHeader header = BlockMetadataHeader.readHeader(checksumIn); short version = header.getVersion(); if (version != FSDataset.METADATA_VERSION) { LOG.warn( "Wrong version (" + version + ") for metadata file for " + block + " ignoring ..."); } checksum = header.getChecksum(); } else { LOG.warn("Could not find metadata file for " + block); // This only decides the buffer size. Use BUFFER_SIZE? checksum = DataChecksum.newDataChecksum(DataChecksum.CHECKSUM_NULL, 16 * 1024); } /* If bytesPerChecksum is very large, then the metadata file * is mostly corrupted. For now just truncate bytesPerchecksum to * blockLength. */ bytesPerChecksum = checksum.getBytesPerChecksum(); if (bytesPerChecksum > 10 * 1024 * 1024 && bytesPerChecksum > replicaVisibleLength) { checksum = DataChecksum.newDataChecksum( checksum.getChecksumType(), Math.max((int) replicaVisibleLength, 10 * 1024 * 1024)); bytesPerChecksum = checksum.getBytesPerChecksum(); } checksumSize = checksum.getChecksumSize(); if (length < 0) { length = replicaVisibleLength; } // end is either last byte on disk or the length for which we have a // checksum if (chunkChecksum != null) { endOffset = chunkChecksum.getDataLength(); } else { endOffset = replica.getBytesOnDisk(); } if (startOffset < 0 || startOffset > endOffset || (length + startOffset) > endOffset) { String msg = " Offset " + startOffset + " and length " + length + " don't match block " + block + " ( blockLen " + endOffset + " )"; LOG.warn(datanode.dnRegistration + ":sendBlock() : " + msg); throw new IOException(msg); } offset = (startOffset - (startOffset % bytesPerChecksum)); if (length >= 0) { // Make sure endOffset points to end of a checksumed chunk. long tmpLen = startOffset + length; if (tmpLen % bytesPerChecksum != 0) { tmpLen += (bytesPerChecksum - tmpLen % bytesPerChecksum); } if (tmpLen < endOffset) { // will use on-disk checksum here since the end is a stable chunk endOffset = tmpLen; } else if (chunkChecksum != null) { // in last chunk which is changing. flag that we need to use in-memory // checksum this.lastChunkChecksum = chunkChecksum; } } // seek to the right offsets if (offset > 0) { long checksumSkip = (offset / bytesPerChecksum) * 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 } catch (IOException ioe) { IOUtils.closeStream(this); IOUtils.closeStream(blockIn); throw ioe; } }