// Compute a compressed double buffer
private Chunk chunkD() {
HashMap<Long, Byte> hs = new HashMap<>(CUDChunk.MAX_UNIQUES);
Byte dummy = 0;
final byte[] bs = MemoryManager.malloc1(_len * 8, true);
int j = 0;
boolean fitsInUnique = true;
for (int i = 0; i < _len; ++i) {
double d = 0;
if (_id == null || _id.length == 0 || (j < _id.length && _id[j] == i)) {
d =
_ds != null
? _ds[j]
: (isNA2(j) || isCategorical(j)) ? Double.NaN : _ls[j] * PrettyPrint.pow10(_xs[j]);
++j;
}
if (fitsInUnique) {
if (hs.size() < CUDChunk.MAX_UNIQUES) // still got space
hs.put(
Double.doubleToLongBits(d),
dummy); // store doubles as longs to avoid NaN comparison issues during extraction
else
fitsInUnique =
(hs.size() == CUDChunk.MAX_UNIQUES)
&& // full, but might not need more space because of repeats
hs.containsKey(Double.doubleToLongBits(d));
}
UnsafeUtils.set8d(bs, 8 * i, d);
}
assert j == sparseLen() : "j = " + j + ", _len = " + sparseLen();
if (fitsInUnique && CUDChunk.computeByteSize(hs.size(), len()) < 0.8 * bs.length)
return new CUDChunk(bs, hs, len());
else return new C8DChunk(bs);
}
// Compute a sparse float buffer
private byte[] bufD(final int valsz) {
int log = 0;
while ((1 << log) < valsz) ++log;
assert (1 << log) == valsz;
final int ridsz = _len >= 65535 ? 4 : 2;
final int elmsz = ridsz + valsz;
int off = CXDChunk._OFF;
byte[] buf = MemoryManager.malloc1(off + sparseLen() * elmsz, true);
for (int i = 0; i < sparseLen(); i++, off += elmsz) {
if (ridsz == 2) UnsafeUtils.set2(buf, off, (short) _id[i]);
else UnsafeUtils.set4(buf, off, _id[i]);
final double dval =
_ds == null ? isNA2(i) ? Double.NaN : _ls[i] * PrettyPrint.pow10(_xs[i]) : _ds[i];
switch (valsz) {
case 4:
UnsafeUtils.set4f(buf, off + ridsz, (float) dval);
break;
case 8:
UnsafeUtils.set8d(buf, off + ridsz, dval);
break;
default:
throw H2O.fail();
}
}
assert off == buf.length;
return buf;
}
Col(String s, int rows, boolean isClass) {
_name = s;
_isClass = isClass;
_rawB = MemoryManager.malloc1(rows);
_isFloat = false;
_isByte = true;
_colBinLimit = 0;
}
@Override
public byte[] atomic(byte[] bits1) {
byte[] mem = DKV.get(_key).get();
int len = Math.max(_dst_off + mem.length, bits1 == null ? 0 : bits1.length);
byte[] bits2 = MemoryManager.malloc1(len);
if (bits1 != null) System.arraycopy(bits1, 0, bits2, 0, bits1.length);
System.arraycopy(mem, 0, bits2, _dst_off, mem.length);
return bits2;
}
private static void addFolder(FileSystem fs, Path p, JsonArray succeeded, JsonArray failed) {
try {
if (fs == null) return;
for (FileStatus file : fs.listStatus(p)) {
Path pfs = file.getPath();
if (file.isDir()) {
addFolder(fs, pfs, succeeded, failed);
} else {
Key k = Key.make(pfs.toString());
long size = file.getLen();
Value val = null;
if (pfs.getName().endsWith(Extensions.JSON)) {
JsonParser parser = new JsonParser();
JsonObject json = parser.parse(new InputStreamReader(fs.open(pfs))).getAsJsonObject();
JsonElement v = json.get(Constants.VERSION);
if (v == null) throw new RuntimeException("Missing version");
JsonElement type = json.get(Constants.TYPE);
if (type == null) throw new RuntimeException("Missing type");
Class c = Class.forName(type.getAsString());
OldModel model = (OldModel) c.newInstance();
model.fromJson(json);
} else if (pfs.getName().endsWith(Extensions.HEX)) { // Hex file?
FSDataInputStream s = fs.open(pfs);
int sz = (int) Math.min(1L << 20, size); // Read up to the 1st meg
byte[] mem = MemoryManager.malloc1(sz);
s.readFully(mem);
// Convert to a ValueArray (hope it fits in 1Meg!)
ValueArray ary = new ValueArray(k, 0).read(new AutoBuffer(mem));
val = new Value(k, ary, Value.HDFS);
} else if (size >= 2 * ValueArray.CHUNK_SZ) {
val =
new Value(
k,
new ValueArray(k, size),
Value.HDFS); // ValueArray byte wrapper over a large file
} else {
val = new Value(k, (int) size, Value.HDFS); // Plain Value
val.setdsk();
}
DKV.put(k, val);
Log.info("PersistHdfs: DKV.put(" + k + ")");
JsonObject o = new JsonObject();
o.addProperty(Constants.KEY, k.toString());
o.addProperty(Constants.FILE, pfs.toString());
o.addProperty(Constants.VALUE_SIZE, file.getLen());
succeeded.add(o);
}
}
} catch (Exception e) {
Log.err(e);
JsonObject o = new JsonObject();
o.addProperty(Constants.FILE, p.toString());
o.addProperty(Constants.ERROR, e.getMessage());
failed.add(o);
}
}
private void append_ss(String str) {
if (_ss == null) {
_ss = MemoryManager.malloc1((str.length() + 1) * 4);
}
while (_ss.length < (_sslen + str.length() + 1)) {
_ss = MemoryManager.arrayCopyOf(_ss, _ss.length << 1);
}
for (byte b : str.getBytes()) _ss[_sslen++] = b;
_ss[_sslen++] = (byte) 0; // for trailing 0;
}
// Compute a compressed double buffer
private Chunk chunkD() {
assert _len2 == _len;
final byte[] bs = MemoryManager.malloc1(_len * 8);
for (int i = 0; i < _len; ++i)
UDP.set8d(
bs,
8 * i,
_ds != null
? _ds[i]
: (isNA(i) || isEnum(i)) ? Double.NaN : _ls[i] * DParseTask.pow10(_xs[i]));
return new C8DChunk(bs);
}
private void append_ss(String str) {
byte[] bytes = str.getBytes(Charsets.UTF_8);
// Allocate memory if necessary
if (_ss == null) _ss = MemoryManager.malloc1((bytes.length + 1) * 4);
while (_ss.length < (_sslen + bytes.length + 1))
_ss = MemoryManager.arrayCopyOf(_ss, _ss.length << 1);
// Copy bytes to _ss
for (byte b : bytes) _ss[_sslen++] = b;
_ss[_sslen++] = (byte) 0; // for trailing 0;
}
private void append_ss(BufferedString str) {
int strlen = str.length();
int off = str.getOffset();
byte b[] = str.getBuffer();
if (_ss == null) {
_ss = MemoryManager.malloc1((strlen + 1) * 4);
}
while (_ss.length < (_sslen + strlen + 1)) {
_ss = MemoryManager.arrayCopyOf(_ss, _ss.length << 1);
}
for (int i = off; i < off + strlen; i++) _ss[_sslen++] = b[i];
_ss[_sslen++] = (byte) 0; // for trailing 0;
}
@Override
public byte[] load(final Value v) {
final byte[] b = MemoryManager.malloc1(v._max);
long skip = 0;
Key k = v._key;
final Path p;
if (_iceRoot != null) {
p = new Path(_iceRoot, getIceName(v));
} else {
// Convert an arraylet chunk into a long-offset from the base file.
if (k._kb[0] == Key.ARRAYLET_CHUNK) {
skip = ValueArray.getChunkOffset(k); // The offset
k = ValueArray.getArrayKey(k); // From the base file key
if (k.toString().endsWith(Extensions.HEX)) { // Hex file?
int value_len = DKV.get(k).memOrLoad().length; // How long is the ValueArray header?
skip += value_len;
}
}
p = new Path(k.toString());
}
final long skip_ = skip;
run(
new Callable() {
@Override
public Object call() throws Exception {
FileSystem fs = FileSystem.get(p.toUri(), CONF);
FSDataInputStream s = null;
try {
s = fs.open(p);
// NOTE:
// The following line degrades performance of HDFS load from S3 API:
// s.readFully(skip,b,0,b.length);
// Google API's simple seek has better performance
// Load of 300MB file via Google API ~ 14sec, via s.readFully ~ 5min (under the same
// condition)
ByteStreams.skipFully(s, skip_);
ByteStreams.readFully(s, b);
assert v.isPersisted();
} finally {
Utils.close(s);
}
return null;
}
},
true,
v._max);
return b;
}
// Compute a compressed UUID buffer
private Chunk chunkUUID() {
final byte[] bs = MemoryManager.malloc1(_len * 16, true);
int j = 0;
for (int i = 0; i < _len; ++i) {
long lo = 0, hi = 0;
if (_id == null || _id.length == 0 || (j < _id.length && _id[j] == i)) {
lo = _ls[j];
hi = Double.doubleToRawLongBits(_ds[j++]);
if (_xs != null && _xs[j] == Integer.MAX_VALUE) { // NA?
lo = Long.MIN_VALUE;
hi = 0; // Canonical NA value
}
}
UnsafeUtils.set8(bs, 16 * i, lo);
UnsafeUtils.set8(bs, 16 * i + 8, hi);
}
assert j == sparseLen() : "j = " + j + ", _len = " + sparseLen();
return new C16Chunk(bs);
}
// Compute a sparse integer buffer
private byte[] bufS(final int valsz) {
int log = 0;
while ((1 << log) < valsz) ++log;
assert valsz == 0 || (1 << log) == valsz;
final int ridsz = _len >= 65535 ? 4 : 2;
final int elmsz = ridsz + valsz;
int off = CXIChunk._OFF;
byte[] buf = MemoryManager.malloc1(off + sparseLen() * elmsz, true);
for (int i = 0; i < sparseLen(); i++, off += elmsz) {
if (ridsz == 2) UnsafeUtils.set2(buf, off, (short) _id[i]);
else UnsafeUtils.set4(buf, off, _id[i]);
if (valsz == 0) {
assert _xs[i] == 0 && _ls[i] == 1;
continue;
}
assert _xs[i] == Integer.MIN_VALUE || _xs[i] >= 0
: "unexpected exponent " + _xs[i]; // assert we have int or NA
final long lval =
_xs[i] == Integer.MIN_VALUE ? NAS[log] : _ls[i] * PrettyPrint.pow10i(_xs[i]);
switch (valsz) {
case 1:
buf[off + ridsz] = (byte) lval;
break;
case 2:
short sval = (short) lval;
UnsafeUtils.set2(buf, off + ridsz, sval);
break;
case 4:
int ival = (int) lval;
UnsafeUtils.set4(buf, off + ridsz, ival);
break;
case 8:
UnsafeUtils.set8(buf, off + ridsz, lval);
break;
default:
throw H2O.fail();
}
}
assert off == buf.length;
return buf;
}
@Override
public byte[] load(final Value v) {
final byte[] b = MemoryManager.malloc1(v._max);
long skip = 0;
Key k = v._key;
if (k._kb[0] == Key.ARRAYLET_CHUNK) {
skip = ValueArray.getChunkOffset(k); // The offset
k = ValueArray.getArrayKey(k); // From the base file key
} else if (k._kb[0] == Key.DVEC) {
skip = water.fvec.NFSFileVec.chunkOffset(k); // The offset
}
final Path p =
_iceRoot == null ? new Path(getPathForKey(k)) : new Path(_iceRoot, getIceName(v));
final long skip_ = skip;
run(
new Callable() {
@Override
public Object call() throws Exception {
FileSystem fs = FileSystem.get(p.toUri(), CONF);
FSDataInputStream s = null;
try {
s = fs.open(p);
// NOTE:
// The following line degrades performance of HDFS load from S3 API:
// s.readFully(skip,b,0,b.length);
// Google API's simple seek has better performance
// Load of 300MB file via Google API ~ 14sec, via s.readFully ~ 5min (under the same
// condition)
ByteStreams.skipFully(s, skip_);
ByteStreams.readFully(s, b);
assert v.isPersisted();
} finally {
Utils.close(s);
}
return null;
}
},
true,
v._max);
return b;
}
