// TCP large RECEIVE of results. Note that 'this' is NOT the RPC object
// that is hoping to get the received object, nor is the current thread the
// RPC thread blocking for the object. The current thread is the TCP
// reader thread.
static void tcp_ack(final AutoBuffer ab) throws IOException {
// Get the RPC we're waiting on
int task = ab.getTask();
RPC rpc = ab._h2o.taskGet(task);
// Race with canceling a large RPC fetch: Task is already dead. Do not
// bother reading from the TCP socket, just bail out & close socket.
if (rpc == null || rpc._done) {
ab.drainClose();
} else {
assert rpc._tasknum == task;
assert !rpc._done;
// Here we have the result, and we're on the correct Node but wrong
// Thread. If we just return, the TCP reader thread will close the
// remote, the remote will UDP ACK the RPC back, and back on the current
// Node but in the correct Thread, we'd wake up and realize we received a
// large result.
try {
rpc.response(ab);
} catch (AutoBuffer.AutoBufferException e) {
// If TCP fails, we will have done a short-read crushing the original
// _dt object, and be unable to resend. This is fatal right now.
// Really: an unimplemented feature; fix is to notice that a partial
// TCP read means that the server (1) got our remote_exec request, (2)
// has computed an answer and was trying to send it to us, (3) failed
// sending via TCP hence the server knows it failed and will send again
// without any further work from us. We need to disable all the resend
// & retry logic, and wait for the server to re-send our result.
// Meanwhile the _dt object is crushed with half-read crap, and cannot
// be trusted except in the base fields.
throw Log.throwErr(e._ioe);
}
}
// ACKACK the remote, telling him "we got the answer"
new AutoBuffer(ab._h2o, H2O.ACK_ACK_PRIORITY).putTask(UDP.udp.ackack.ordinal(), task).close();
}
// Start an RPC to fetch a Value, handling short-cutting dup-fetches
static RPC<TaskGetKey> start(H2ONode target, Key key) {
// Do we have an old TaskGetKey in-progress?
RPC<TaskGetKey> old = TGKS.get(key);
if (old != null) return old;
// Make a new TGK.
RPC<TaskGetKey> rpc = new RPC(target, new TaskGetKey(key), 1.0f);
if ((old = TGKS.putIfMatchUnlocked(key, rpc, null)) != null)
return old; // Failed because an old exists
rpc.setTaskNum().call(); // Start the op
return rpc; // Successful install of a fresh RPC
}
// TCP large RECEIVE of results. Note that 'this' is NOT the RPC object
// that is hoping to get the received object, nor is the current thread the
// RPC thread blocking for the object. The current thread is the TCP
// reader thread.
static void tcp_ack(final AutoBuffer ab) {
// Get the RPC we're waiting on
int task = ab.getTask();
RPC rpc = TASKS.get(task);
// Race with canceling a large RPC fetch: Task is already dead. Do not
// bother reading from the TCP socket, just bail out & close socket.
if (rpc == null) {
ab.drainClose();
} else {
assert rpc._tasknum == task;
assert !rpc._done;
// Here we have the result, and we're on the correct Node but wrong
// Thread. If we just return, the TCP reader thread will close the
// remote, the remote will UDP ACK the RPC back, and back on the current
// Node but in the correct Thread, we'd wake up and realize we received a
// large result.
rpc.response(ab);
}
// ACKACK the remote, telling him "we got the answer"
new AutoBuffer(ab._h2o).putTask(UDP.udp.ackack.ordinal(), task).close(true);
}
public static String store2Hdfs(Key srcKey) {
assert srcKey._kb[0] != Key.ARRAYLET_CHUNK;
assert PersistHdfs.getPathForKey(srcKey) != null; // Validate key name
Value v = DKV.get(srcKey);
if (v == null) return "Key " + srcKey + " not found";
if (v._isArray == 0) { // Simple chunk?
v.setHdfs(); // Set to HDFS and be done
return null; // Success
}
// For ValueArrays, make the .hex header
ValueArray ary = ValueArray.value(v);
String err = PersistHdfs.freeze(srcKey, ary);
if (err != null) return err;
// The task managing which chunks to write next,
// store in a known key
TaskStore2HDFS ts = new TaskStore2HDFS(srcKey);
Key selfKey = ts.selfKey();
UKV.put(selfKey, ts);
// Then start writing chunks in-order with the zero chunk
H2ONode chk0_home = ValueArray.getChunkKey(0, srcKey).home_node();
RPC.call(ts.chunkHome(), ts);
// Watch the progress key until it gets removed or an error appears
long idx = 0;
while (UKV.get(selfKey, ts) != null) {
if (ts._indexFrom != idx) {
System.out.print(" " + idx + "/" + ary.chunks());
idx = ts._indexFrom;
}
if (ts._err != null) { // Found an error?
UKV.remove(selfKey); // Cleanup & report
return ts._err;
}
try {
Thread.sleep(100);
} catch (InterruptedException e) {
}
}
System.out.println(" " + ary.chunks() + "/" + ary.chunks());
// PersistHdfs.refreshHDFSKeys();
return null;
}
@Override
public void compute() {
String path = null; // getPathFromValue(val);
ValueArray ary = ValueArray.value(_arykey);
Key self = selfKey();
while (_indexFrom < ary.chunks()) {
Key ckey = ary.getChunkKey(_indexFrom++);
if (!ckey.home()) { // Next chunk not At Home?
RPC.call(chunkHome(), this); // Hand the baton off to the next node/chunk
return;
}
Value val = DKV.get(ckey); // It IS home, so get the data
_err = PersistHdfs.appendChunk(_arykey, val);
if (_err != null) return;
UKV.put(self, this); // Update the progress/self key
}
// We did the last chunk. Removing the selfKey is the signal to the web
// thread that All Done.
UKV.remove(self);
}
static void put(H2ONode h2o, Key key, Value val, Futures fs, boolean dontCache) {
fs.add(RPC.call(h2o, new TaskPutKey(key, val, dontCache)));
}
static Value get(RPC<TaskGetKey> rpc) {
return rpc.get()._val; // Block for it
}
