##// 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
compressoriterator.c
235 lines | 6.9 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(ZstdCompressorIterator__doc__,
"Represents an iterator of compressed data.\n"
);
static void ZstdCompressorIterator_dealloc(ZstdCompressorIterator* self) {
Py_XDECREF(self->readResult);
Py_XDECREF(self->compressor);
Py_XDECREF(self->reader);
if (self->buffer.buf) {
PyBuffer_Release(&self->buffer);
memset(&self->buffer, 0, sizeof(self->buffer));
}
if (self->output.dst) {
PyMem_Free(self->output.dst);
self->output.dst = NULL;
}
PyObject_Del(self);
}
static PyObject* ZstdCompressorIterator_iter(PyObject* self) {
Py_INCREF(self);
return self;
}
static PyObject* ZstdCompressorIterator_iternext(ZstdCompressorIterator* self) {
size_t zresult;
PyObject* readResult = NULL;
PyObject* chunk;
char* readBuffer;
Py_ssize_t readSize = 0;
Py_ssize_t bufferRemaining;
if (self->finishedOutput) {
PyErr_SetString(PyExc_StopIteration, "output flushed");
return NULL;
}
feedcompressor:
/* If we have data left in the input, consume it. */
if (self->input.pos < self->input.size) {
Py_BEGIN_ALLOW_THREADS
zresult = ZSTD_compressStream2(self->compressor->cctx, &self->output,
&self->input, ZSTD_e_continue);
Py_END_ALLOW_THREADS
/* Release the Python object holding the input buffer. */
if (self->input.pos == self->input.size) {
self->input.src = NULL;
self->input.pos = 0;
self->input.size = 0;
Py_DECREF(self->readResult);
self->readResult = NULL;
}
if (ZSTD_isError(zresult)) {
PyErr_Format(ZstdError, "zstd compress error: %s", ZSTD_getErrorName(zresult));
return NULL;
}
/* If it produced output data, emit it. */
if (self->output.pos) {
chunk = PyBytes_FromStringAndSize(self->output.dst, self->output.pos);
self->output.pos = 0;
return chunk;
}
}
/* We should never have output data sitting around after a previous call. */
assert(self->output.pos == 0);
/* The code above should have either emitted a chunk and returned or consumed
the entire input buffer. So the state of the input buffer is not
relevant. */
if (!self->finishedInput) {
if (self->reader) {
readResult = PyObject_CallMethod(self->reader, "read", "I", self->inSize);
if (!readResult) {
PyErr_SetString(ZstdError, "could not read() from source");
return NULL;
}
PyBytes_AsStringAndSize(readResult, &readBuffer, &readSize);
}
else {
assert(self->buffer.buf);
/* Only support contiguous C arrays. */
assert(self->buffer.strides == NULL && self->buffer.suboffsets == NULL);
assert(self->buffer.itemsize == 1);
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 (0 == readSize) {
Py_XDECREF(readResult);
self->finishedInput = 1;
}
else {
self->readResult = readResult;
}
}
/* EOF */
if (0 == readSize) {
self->input.src = NULL;
self->input.size = 0;
self->input.pos = 0;
zresult = ZSTD_compressStream2(self->compressor->cctx, &self->output,
&self->input, ZSTD_e_end);
if (ZSTD_isError(zresult)) {
PyErr_Format(ZstdError, "error ending compression stream: %s",
ZSTD_getErrorName(zresult));
return NULL;
}
assert(self->output.pos);
if (0 == zresult) {
self->finishedOutput = 1;
}
chunk = PyBytes_FromStringAndSize(self->output.dst, self->output.pos);
self->output.pos = 0;
return chunk;
}
/* New data from reader. Feed into compressor. */
self->input.src = readBuffer;
self->input.size = readSize;
self->input.pos = 0;
Py_BEGIN_ALLOW_THREADS
zresult = ZSTD_compressStream2(self->compressor->cctx, &self->output,
&self->input, ZSTD_e_continue);
Py_END_ALLOW_THREADS
/* The input buffer currently points to memory managed by Python
(readBuffer). This object was allocated by this function. If it wasn't
fully consumed, we need to release it in a subsequent function call.
If it is fully consumed, do that now.
*/
if (self->input.pos == self->input.size) {
self->input.src = NULL;
self->input.pos = 0;
self->input.size = 0;
Py_XDECREF(self->readResult);
self->readResult = NULL;
}
if (ZSTD_isError(zresult)) {
PyErr_Format(ZstdError, "zstd compress error: %s", ZSTD_getErrorName(zresult));
return NULL;
}
assert(self->input.pos <= self->input.size);
/* If we didn't write anything, start the process over. */
if (0 == self->output.pos) {
goto feedcompressor;
}
chunk = PyBytes_FromStringAndSize(self->output.dst, self->output.pos);
self->output.pos = 0;
return chunk;
}
PyTypeObject ZstdCompressorIteratorType = {
PyVarObject_HEAD_INIT(NULL, 0)
"zstd.ZstdCompressorIterator", /* tp_name */
sizeof(ZstdCompressorIterator), /* tp_basicsize */
0, /* tp_itemsize */
(destructor)ZstdCompressorIterator_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 */
ZstdCompressorIterator__doc__, /* tp_doc */
0, /* tp_traverse */
0, /* tp_clear */
0, /* tp_richcompare */
0, /* tp_weaklistoffset */
ZstdCompressorIterator_iter, /* tp_iter */
(iternextfunc)ZstdCompressorIterator_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 compressoriterator_module_init(PyObject* mod) {
Py_TYPE(&ZstdCompressorIteratorType) = &PyType_Type;
if (PyType_Ready(&ZstdCompressorIteratorType) < 0) {
return;
}
}