##// END OF EJS Templates
sidedatacopies: only fetch information once for merge...
sidedatacopies: only fetch information once for merge Before this change, merge would result in reading the data from revlog twice. With this change, we keep the information in memory until we encounter the other parent. When looking at pypy, I see about 1/3 of the changesets with copy information being merge. Not doing duplicated fetch for them provide a significant speedup. revision: large amount; added files: large amount; rename small amount; c3b14617fbd7 9ba6ab77fd29 before: ! wall 0.767042 comb 0.760000 user 0.750000 sys 0.010000 (median of 11) after: ! wall 0.671162 comb 0.670000 user 0.650000 sys 0.020000 (median of 13) revision: large amount; added files: small amount; rename small amount; c3b14617fbd7 f650a9b140d2 before: ! wall 1.170169 comb 1.170000 user 1.130000 sys 0.040000 (median of 10) after: ! wall 1.030596 comb 1.040000 user 1.010000 sys 0.030000 (median of 10) revision: large amount; added files: large amount; rename large amount; 08ea3258278e d9fa043f30c0 before: ! wall 0.209846 comb 0.200000 user 0.200000 sys 0.000000 (median of 46) after: ! wall 0.170981 comb 0.170000 user 0.170000 sys 0.000000 (median of 56) revision: small amount; added files: large amount; rename large amount; df6f7a526b60 a83dc6a2d56f before: ! wall 0.013248 comb 0.010000 user 0.010000 sys 0.000000 (median of 223) after: ! wall 0.013295 comb 0.020000 user 0.020000 sys 0.000000 (median of 222) revision: small amount; added files: large amount; rename small amount; 4aa4e1f8e19a 169138063d63 before: ! wall 0.001672 comb 0.000000 user 0.000000 sys 0.000000 (median of 1000) after: ! wall 0.001666 comb 0.000000 user 0.000000 sys 0.000000 (median of 1000) revision: small amount; added files: small amount; rename small amount; 4bc173b045a6 964879152e2e before: ! wall 0.000119 comb 0.000000 user 0.000000 sys 0.000000 (median of 8010) after: ! wall 0.000119 comb 0.000000 user 0.000000 sys 0.000000 (median of 8007) revision: medium amount; added files: large amount; rename medium amount; c95f1ced15f2 2c68e87c3efe before: ! wall 0.168599 comb 0.160000 user 0.160000 sys 0.000000 (median of 58) after: ! wall 0.133316 comb 0.140000 user 0.140000 sys 0.000000 (median of 73) revision: medium amount; added files: medium amount; rename small amount; d343da0c55a8 d7746d32bf9d before: ! wall 0.036052 comb 0.030000 user 0.030000 sys 0.000000 (median of 100) after: ! wall 0.032558 comb 0.030000 user 0.030000 sys 0.000000 (median of 100) Differential Revision: https://phab.mercurial-scm.org/D7127

File last commit:

r42237:675775c3 default
r43595:90213d02 default
Show More
decompressoriterator.c
249 lines | 7.2 KiB | text/x-c | CLexer
/**
* Copyright (c) 2016-present, Gregory Szorc
* All rights reserved.
*
* This software may be modified and distributed under the terms
* of the BSD license. See the LICENSE file for details.
*/
#include "python-zstandard.h"
#define min(a, b) (((a) < (b)) ? (a) : (b))
extern PyObject* ZstdError;
PyDoc_STRVAR(ZstdDecompressorIterator__doc__,
"Represents an iterator of decompressed data.\n"
);
static void ZstdDecompressorIterator_dealloc(ZstdDecompressorIterator* self) {
Py_XDECREF(self->decompressor);
Py_XDECREF(self->reader);
if (self->buffer.buf) {
PyBuffer_Release(&self->buffer);
memset(&self->buffer, 0, sizeof(self->buffer));
}
if (self->input.src) {
PyMem_Free((void*)self->input.src);
self->input.src = NULL;
}
PyObject_Del(self);
}
static PyObject* ZstdDecompressorIterator_iter(PyObject* self) {
Py_INCREF(self);
return self;
}
static DecompressorIteratorResult read_decompressor_iterator(ZstdDecompressorIterator* self) {
size_t zresult;
PyObject* chunk;
DecompressorIteratorResult result;
size_t oldInputPos = self->input.pos;
result.chunk = NULL;
chunk = PyBytes_FromStringAndSize(NULL, self->outSize);
if (!chunk) {
result.errored = 1;
return result;
}
self->output.dst = PyBytes_AsString(chunk);
self->output.size = self->outSize;
self->output.pos = 0;
Py_BEGIN_ALLOW_THREADS
zresult = ZSTD_decompressStream(self->decompressor->dctx, &self->output, &self->input);
Py_END_ALLOW_THREADS
/* We're done with the pointer. Nullify to prevent anyone from getting a
handle on a Python object. */
self->output.dst = NULL;
if (ZSTD_isError(zresult)) {
Py_DECREF(chunk);
PyErr_Format(ZstdError, "zstd decompress error: %s",
ZSTD_getErrorName(zresult));
result.errored = 1;
return result;
}
self->readCount += self->input.pos - oldInputPos;
/* Frame is fully decoded. Input exhausted and output sitting in buffer. */
if (0 == zresult) {
self->finishedInput = 1;
self->finishedOutput = 1;
}
/* If it produced output data, return it. */
if (self->output.pos) {
if (self->output.pos < self->outSize) {
if (safe_pybytes_resize(&chunk, self->output.pos)) {
Py_XDECREF(chunk);
result.errored = 1;
return result;
}
}
}
else {
Py_DECREF(chunk);
chunk = NULL;
}
result.errored = 0;
result.chunk = chunk;
return result;
}
static PyObject* ZstdDecompressorIterator_iternext(ZstdDecompressorIterator* self) {
PyObject* readResult = NULL;
char* readBuffer;
Py_ssize_t readSize;
Py_ssize_t bufferRemaining;
DecompressorIteratorResult result;
if (self->finishedOutput) {
PyErr_SetString(PyExc_StopIteration, "output flushed");
return NULL;
}
/* If we have data left in the input, consume it. */
if (self->input.pos < self->input.size) {
result = read_decompressor_iterator(self);
if (result.chunk || result.errored) {
return result.chunk;
}
/* Else fall through to get more data from input. */
}
read_from_source:
if (!self->finishedInput) {
if (self->reader) {
readResult = PyObject_CallMethod(self->reader, "read", "I", self->inSize);
if (!readResult) {
return NULL;
}
PyBytes_AsStringAndSize(readResult, &readBuffer, &readSize);
}
else {
assert(self->buffer.buf);
/* Only support contiguous C arrays for now */
assert(self->buffer.strides == NULL && self->buffer.suboffsets == NULL);
assert(self->buffer.itemsize == 1);
/* TODO avoid memcpy() below */
readBuffer = (char *)self->buffer.buf + self->bufferOffset;
bufferRemaining = self->buffer.len - self->bufferOffset;
readSize = min(bufferRemaining, (Py_ssize_t)self->inSize);
self->bufferOffset += readSize;
}
if (readSize) {
if (!self->readCount && self->skipBytes) {
assert(self->skipBytes < self->inSize);
if ((Py_ssize_t)self->skipBytes >= readSize) {
PyErr_SetString(PyExc_ValueError,
"skip_bytes larger than first input chunk; "
"this scenario is currently unsupported");
Py_XDECREF(readResult);
return NULL;
}
readBuffer = readBuffer + self->skipBytes;
readSize -= self->skipBytes;
}
/* Copy input into previously allocated buffer because it can live longer
than a single function call and we don't want to keep a ref to a Python
object around. This could be changed... */
memcpy((void*)self->input.src, readBuffer, readSize);
self->input.size = readSize;
self->input.pos = 0;
}
/* No bytes on first read must mean an empty input stream. */
else if (!self->readCount) {
self->finishedInput = 1;
self->finishedOutput = 1;
Py_XDECREF(readResult);
PyErr_SetString(PyExc_StopIteration, "empty input");
return NULL;
}
else {
self->finishedInput = 1;
}
/* We've copied the data managed by memory. Discard the Python object. */
Py_XDECREF(readResult);
}
result = read_decompressor_iterator(self);
if (result.errored || result.chunk) {
return result.chunk;
}
/* No new output data. Try again unless we know there is no more data. */
if (!self->finishedInput) {
goto read_from_source;
}
PyErr_SetString(PyExc_StopIteration, "input exhausted");
return NULL;
}
PyTypeObject ZstdDecompressorIteratorType = {
PyVarObject_HEAD_INIT(NULL, 0)
"zstd.ZstdDecompressorIterator", /* tp_name */
sizeof(ZstdDecompressorIterator), /* tp_basicsize */
0, /* tp_itemsize */
(destructor)ZstdDecompressorIterator_dealloc, /* tp_dealloc */
0, /* tp_print */
0, /* tp_getattr */
0, /* tp_setattr */
0, /* tp_compare */
0, /* tp_repr */
0, /* tp_as_number */
0, /* tp_as_sequence */
0, /* tp_as_mapping */
0, /* tp_hash */
0, /* tp_call */
0, /* tp_str */
0, /* tp_getattro */
0, /* tp_setattro */
0, /* tp_as_buffer */
Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE, /* tp_flags */
ZstdDecompressorIterator__doc__, /* tp_doc */
0, /* tp_traverse */
0, /* tp_clear */
0, /* tp_richcompare */
0, /* tp_weaklistoffset */
ZstdDecompressorIterator_iter, /* tp_iter */
(iternextfunc)ZstdDecompressorIterator_iternext, /* tp_iternext */
0, /* tp_methods */
0, /* tp_members */
0, /* tp_getset */
0, /* tp_base */
0, /* tp_dict */
0, /* tp_descr_get */
0, /* tp_descr_set */
0, /* tp_dictoffset */
0, /* tp_init */
0, /* tp_alloc */
PyType_GenericNew, /* tp_new */
};
void decompressoriterator_module_init(PyObject* mod) {
Py_TYPE(&ZstdDecompressorIteratorType) = &PyType_Type;
if (PyType_Ready(&ZstdDecompressorIteratorType) < 0) {
return;
}
}