Mercurial > public > mercurial-scm > hg

comparison contrib/python-zstandard/c-ext/compressor.c @ 30895:c32454d69b85

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
zstd: vendor python-zstandard 0.7.0 Commit 3054ae3a66112970a091d3939fee32c2d0c1a23e from https://github.com/indygreg/python-zstandard is imported without modifications (other than removing unwanted files). The vendored zstd library within has been upgraded from 1.1.2 to 1.1.3. This version introduced new APIs for threads, thread pools, multi-threaded compression, and a new dictionary builder (COVER). These features are not yet used by python-zstandard (or Mercurial for that matter). However, that will likely change in the next python-zstandard release (and I think there are opportunities for Mercurial to take advantage of the multi-threaded APIs). Relevant to Mercurial, the CFFI bindings are now fully implemented. This means zstd should "just work" with PyPy (although I haven't tried). The python-zstandard test suite also runs all tests against both the C extension and CFFI bindings to ensure feature parity. There is also a "decompress_content_dict_chain()" API. This was derived from discussions with Yann Collet on list about alternate ways of encoding delta chains. The change most relevant to Mercurial is a performance enhancement in the simple decompression API to reuse a data structure across operations. This makes decompression of multiple inputs significantly faster. (This scenario occurs when reading revlog delta chains, for example.) Using python-zstandard's bench.py to measure the performance difference... On changelog chunks in the mozilla-unified repo: decompress discrete decompress() reuse zctx 1.262243 wall; 1.260000 CPU; 1.260000 user; 0.000000 sys 170.43 MB/s (best of 3) 0.949106 wall; 0.950000 CPU; 0.950000 user; 0.000000 sys 226.66 MB/s (best of 4) decompress discrete dict decompress() reuse zctx 0.692170 wall; 0.690000 CPU; 0.690000 user; 0.000000 sys 310.80 MB/s (best of 5) 0.437088 wall; 0.440000 CPU; 0.440000 user; 0.000000 sys 492.17 MB/s (best of 7) On manifest chunks in the mozilla-unified repo: decompress discrete decompress() reuse zctx 1.367284 wall; 1.370000 CPU; 1.370000 user; 0.000000 sys 274.01 MB/s (best of 3) 1.086831 wall; 1.080000 CPU; 1.080000 user; 0.000000 sys 344.72 MB/s (best of 3) decompress discrete dict decompress() reuse zctx 0.993272 wall; 0.990000 CPU; 0.990000 user; 0.000000 sys 377.19 MB/s (best of 3) 0.678651 wall; 0.680000 CPU; 0.680000 user; 0.000000 sys 552.06 MB/s (best of 5) That should make reads on zstd revlogs a bit faster ;) # no-check-commit
author Gregory Szorc <gregory.szorc@gmail.com>
date Tue, 07 Feb 2017 23:24:47 -0800
parents 08fa3a76a080
children e0dc40530c5a
comparison
equal deleted inserted replaced
30894:5b60464efbde 30895:c32454d69b85
14 ZSTD_customMem zmem; 14 ZSTD_customMem zmem;
15 assert(!compressor->cdict); 15 assert(!compressor->cdict);
16 Py_BEGIN_ALLOW_THREADS 16 Py_BEGIN_ALLOW_THREADS
17 memset(&zmem, 0, sizeof(zmem)); 17 memset(&zmem, 0, sizeof(zmem));
18 compressor->cdict = ZSTD_createCDict_advanced(compressor->dict->dictData, 18 compressor->cdict = ZSTD_createCDict_advanced(compressor->dict->dictData,
19 compressor->dict->dictSize, *zparams, zmem); 19 compressor->dict->dictSize, 1, *zparams, zmem);
20 Py_END_ALLOW_THREADS 20 Py_END_ALLOW_THREADS
21 21
22 if (!compressor->cdict) { 22 if (!compressor->cdict) {
23 PyErr_SetString(ZstdError, "could not create compression dictionary"); 23 PyErr_SetString(ZstdError, "could not create compression dictionary");
24 return 1; 24 return 1;
126 self->cctx = NULL; 126 self->cctx = NULL;
127 self->dict = NULL; 127 self->dict = NULL;
128 self->cparams = NULL; 128 self->cparams = NULL;
129 self->cdict = NULL; 129 self->cdict = NULL;
130 130
131 if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|iO!O!OOO", kwlist, 131 if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|iO!O!OOO:ZstdCompressor",
132 &level, &ZstdCompressionDictType, &dict, 132 kwlist, &level, &ZstdCompressionDictType, &dict,
133 &CompressionParametersType, &params, 133 &CompressionParametersType, &params,
134 &writeChecksum, &writeContentSize, &writeDictID)) { 134 &writeChecksum, &writeContentSize, &writeDictID)) {
135 return -1; 135 return -1;
136 } 136 }
137 137
241 size_t zresult; 241 size_t zresult;
242 PyObject* writeResult; 242 PyObject* writeResult;
243 PyObject* totalReadPy; 243 PyObject* totalReadPy;
244 PyObject* totalWritePy; 244 PyObject* totalWritePy;
245 245
246 if (!PyArg_ParseTupleAndKeywords(args, kwargs, "OO|nkk", kwlist, &source, &dest, &sourceSize, 246 if (!PyArg_ParseTupleAndKeywords(args, kwargs, "OO|nkk:copy_stream", kwlist,
247 &inSize, &outSize)) { 247 &source, &dest, &sourceSize, &inSize, &outSize)) {
248 return NULL; 248 return NULL;
249 } 249 }
250 250
251 if (!PyObject_HasAttrString(source, "read")) { 251 if (!PyObject_HasAttrString(source, "read")) {
252 PyErr_SetString(PyExc_ValueError, "first argument must have a read() method"); 252 PyErr_SetString(PyExc_ValueError, "first argument must have a read() method");
400 size_t dictSize = 0; 400 size_t dictSize = 0;
401 size_t zresult; 401 size_t zresult;
402 ZSTD_parameters zparams; 402 ZSTD_parameters zparams;
403 403
404 #if PY_MAJOR_VERSION >= 3 404 #if PY_MAJOR_VERSION >= 3
405 if (!PyArg_ParseTupleAndKeywords(args, kwargs, "y#|O", 405 if (!PyArg_ParseTupleAndKeywords(args, kwargs, "y#|O:compress",
406 #else 406 #else
407 if (!PyArg_ParseTupleAndKeywords(args, kwargs, "s#|O", 407 if (!PyArg_ParseTupleAndKeywords(args, kwargs, "s#|O:compress",
408 #endif 408 #endif
409 kwlist, &source, &sourceSize, &allowEmpty)) { 409 kwlist, &source, &sourceSize, &allowEmpty)) {
410 return NULL; 410 return NULL;
411 } 411 }
412 412
510 ZstdCompressionObj* result = PyObject_New(ZstdCompressionObj, &ZstdCompressionObjType); 510 ZstdCompressionObj* result = PyObject_New(ZstdCompressionObj, &ZstdCompressionObjType);
511 if (!result) { 511 if (!result) {
512 return NULL; 512 return NULL;
513 } 513 }
514 514
515 if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|n", kwlist, &inSize)) { 515 if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|n:compressobj", kwlist, &inSize)) {
516 return NULL; 516 return NULL;
517 } 517 }
518 518
519 result->cstream = CStream_from_ZstdCompressor(self, inSize); 519 result->cstream = CStream_from_ZstdCompressor(self, inSize);
520 if (!result->cstream) { 520 if (!result->cstream) {
572 Py_ssize_t sourceSize = 0; 572 Py_ssize_t sourceSize = 0;
573 size_t inSize = ZSTD_CStreamInSize(); 573 size_t inSize = ZSTD_CStreamInSize();
574 size_t outSize = ZSTD_CStreamOutSize(); 574 size_t outSize = ZSTD_CStreamOutSize();
575 ZstdCompressorIterator* result; 575 ZstdCompressorIterator* result;
576 576
577 if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|nkk", kwlist, &reader, &sourceSize, 577 if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|nkk:read_from", kwlist,
578 &inSize, &outSize)) { 578 &reader, &sourceSize, &inSize, &outSize)) {
579 return NULL; 579 return NULL;
580 } 580 }
581 581
582 result = PyObject_New(ZstdCompressorIterator, &ZstdCompressorIteratorType); 582 result = PyObject_New(ZstdCompressorIterator, &ZstdCompressorIteratorType);
583 if (!result) { 583 if (!result) {
691 PyObject* writer; 691 PyObject* writer;
692 ZstdCompressionWriter* result; 692 ZstdCompressionWriter* result;
693 Py_ssize_t sourceSize = 0; 693 Py_ssize_t sourceSize = 0;
694 size_t outSize = ZSTD_CStreamOutSize(); 694 size_t outSize = ZSTD_CStreamOutSize();
695 695
696 if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|nk", kwlist, &writer, &sourceSize, 696 if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|nk:write_to", kwlist,
697 &outSize)) { 697 &writer, &sourceSize, &outSize)) {
698 return NULL; 698 return NULL;
699 } 699 }
700 700
701 if (!PyObject_HasAttrString(writer, "write")) { 701 if (!PyObject_HasAttrString(writer, "write")) {
702 PyErr_SetString(PyExc_ValueError, "must pass an object with a write() method"); 702 PyErr_SetString(PyExc_ValueError, "must pass an object with a write() method");