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);
}