/** Block synchronization */
void syncBlock(RecoveringBlock rBlock,
List<BlockRecord> syncList) throws IOException {
ExtendedBlock block = rBlock.getBlock();
DatanodeProtocol nn = getBPNamenode(block.getBlockPoolId());
long recoveryId = rBlock.getNewGenerationStamp();
if (LOG.isDebugEnabled()) {
LOG.debug("block=" + block + ", (length=" + block.getNumBytes()
+ "), syncList=" + syncList);
}
// syncList.isEmpty() means that all data-nodes do not have the block
// or their replicas have 0 length.
// The block can be deleted.
if (syncList.isEmpty()) {
nn.commitBlockSynchronization(block, recoveryId, 0,
true, true, DatanodeID.EMPTY_ARRAY);
return;
}
// Calculate the best available replica state.
ReplicaState bestState = ReplicaState.RWR;
long finalizedLength = -1;
for(BlockRecord r : syncList) {
assert r.rInfo.getNumBytes() > 0 : "zero length replica";
ReplicaState rState = r.rInfo.getOriginalReplicaState();
if(rState.getValue() < bestState.getValue())
bestState = rState;
if(rState == ReplicaState.FINALIZED) {
if(finalizedLength > 0 && finalizedLength != r.rInfo.getNumBytes())
throw new IOException("Inconsistent size of finalized replicas. " +
"Replica " + r.rInfo + " expected size: " + finalizedLength);
finalizedLength = r.rInfo.getNumBytes();
}
}
// Calculate list of nodes that will participate in the recovery
// and the new block size
List<BlockRecord> participatingList = new ArrayList<BlockRecord>();
final ExtendedBlock newBlock = new ExtendedBlock(block.getBlockPoolId(), block
.getBlockId(), -1, recoveryId);
switch(bestState) {
case FINALIZED:
assert finalizedLength > 0 : "finalizedLength is not positive";
for(BlockRecord r : syncList) {
ReplicaState rState = r.rInfo.getOriginalReplicaState();
if(rState == ReplicaState.FINALIZED ||
rState == ReplicaState.RBW &&
r.rInfo.getNumBytes() == finalizedLength)
participatingList.add(r);
}
newBlock.setNumBytes(finalizedLength);
break;
case RBW:
case RWR:
long minLength = Long.MAX_VALUE;
for(BlockRecord r : syncList) {
ReplicaState rState = r.rInfo.getOriginalReplicaState();
if(rState == bestState) {
minLength = Math.min(minLength, r.rInfo.getNumBytes());
participatingList.add(r);
}
}
newBlock.setNumBytes(minLength);
break;
case RUR:
case TEMPORARY:
assert false : "bad replica state: " + bestState;
}
List<DatanodeID> failedList = new ArrayList<DatanodeID>();
List<DatanodeID> successList = new ArrayList<DatanodeID>();
for(BlockRecord r : participatingList) {
try {
ExtendedBlock reply = r.datanode.updateReplicaUnderRecovery(
new ExtendedBlock(newBlock.getBlockPoolId(), r.rInfo), recoveryId,
newBlock.getNumBytes());
assert reply.equals(newBlock) &&
reply.getNumBytes() == newBlock.getNumBytes() :
"Updated replica must be the same as the new block.";
successList.add(r.id);
} catch (IOException e) {
InterDatanodeProtocol.LOG.warn("Failed to updateBlock (newblock="
+ newBlock + ", datanode=" + r.id + ")", e);
failedList.add(r.id);
}
}
// If any of the data-nodes failed, the recovery fails, because
// we never know the actual state of the replica on failed data-nodes.
// The recovery should be started over.
if(!failedList.isEmpty()) {
StringBuilder b = new StringBuilder();
for(DatanodeID id : failedList) {
b.append("\n " + id);
}
throw new IOException("Cannot recover " + block + ", the following "
+ failedList.size() + " data-nodes failed {" + b + "\n}");
}
// Notify the name-node about successfully recovered replicas.
DatanodeID[] nlist = successList.toArray(new DatanodeID[successList.size()]);
nn.commitBlockSynchronization(block,
newBlock.getGenerationStamp(), newBlock.getNumBytes(), true, false,
nlist);
}