@Override
public void compute2() {
_in.read_lock(_jobKey);
// simply create a bogus new vector (don't even put it into KV) with appropriate number of lines
// per chunk and then use it as a source to do multiple makeZero calls
// to create empty vecs and than call RebalanceTask on each one of them.
// RebalanceTask will fetch the appropriate src chunks and fetch the data from them.
int rpc = (int) (_in.numRows() / _nchunks);
int rem = (int) (_in.numRows() % _nchunks);
long[] espc = new long[_nchunks + 1];
Arrays.fill(espc, rpc);
for (int i = 0; i < rem; ++i) ++espc[i];
long sum = 0;
for (int i = 0; i < espc.length; ++i) {
long s = espc[i];
espc[i] = sum;
sum += s;
}
assert espc[espc.length - 1] == _in.numRows()
: "unexpected number of rows, expected " + _in.numRows() + ", got " + espc[espc.length - 1];
final Vec[] srcVecs = _in.vecs();
_out =
new Frame(
_okey,
_in.names(),
new Vec(Vec.newKey(), espc).makeZeros(srcVecs.length, _in.domains()));
_out.delete_and_lock(_jobKey);
new RebalanceTask(this, srcVecs).asyncExec(_out);
}
@Override
public void compute2() {
// Lock all possible data
dataset.read_lock(jobKey);
// Create a template vector for each segment
final Vec[][] templates = makeTemplates(dataset, ratios);
final int nsplits = templates.length;
assert nsplits == ratios.length + 1 : "Unexpected number of split templates!";
// Launch number of distributed FJ for each split part
final Vec[] datasetVecs = dataset.vecs();
splits = new Frame[nsplits];
for (int s = 0; s < nsplits; s++) {
Frame split = new Frame(destKeys[s], dataset.names(), templates[s]);
split.delete_and_lock(jobKey);
splits[s] = split;
}
setPendingCount(1);
H2O.submitTask(
new H2OCountedCompleter(FrameSplitter.this) {
@Override
public void compute2() {
setPendingCount(nsplits);
for (int s = 0; s < nsplits; s++) {
new FrameSplitTask(
new H2OCountedCompleter(this) { // Completer for this task
@Override
public void compute2() {}
@Override
public boolean onExceptionalCompletion(
Throwable ex, CountedCompleter caller) {
synchronized (
FrameSplitter
.this) { // synchronized on this since can be accessed from
// different workers
workersExceptions =
workersExceptions != null
? Arrays.copyOf(workersExceptions, workersExceptions.length + 1)
: new Throwable[1];
workersExceptions[workersExceptions.length - 1] = ex;
}
tryComplete(); // we handle the exception so wait perform normal
// completion
return false;
}
},
datasetVecs,
ratios,
s)
.asyncExec(splits[s]);
}
tryComplete(); // complete the computation of nsplits-tasks
}
});
tryComplete(); // complete the computation of thrown tasks
}
