view contrib/python-zstandard/c-ext/compressionparams.c @ 30924:c32454d69b85

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

/**
* 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"

void ztopy_compression_parameters(CompressionParametersObject* params, ZSTD_compressionParameters* zparams) {
	zparams->windowLog = params->windowLog;
	zparams->chainLog = params->chainLog;
	zparams->hashLog = params->hashLog;
	zparams->searchLog = params->searchLog;
	zparams->searchLength = params->searchLength;
	zparams->targetLength = params->targetLength;
	zparams->strategy = params->strategy;
}

CompressionParametersObject* get_compression_parameters(PyObject* self, PyObject* args) {
	int compressionLevel;
	unsigned PY_LONG_LONG sourceSize = 0;
	Py_ssize_t dictSize = 0;
	ZSTD_compressionParameters params;
	CompressionParametersObject* result;

	if (!PyArg_ParseTuple(args, "i|Kn:get_compression_parameters",
		&compressionLevel, &sourceSize, &dictSize)) {
		return NULL;
	}

	params = ZSTD_getCParams(compressionLevel, sourceSize, dictSize);

	result = PyObject_New(CompressionParametersObject, &CompressionParametersType);
	if (!result) {
		return NULL;
	}

	result->windowLog = params.windowLog;
	result->chainLog = params.chainLog;
	result->hashLog = params.hashLog;
	result->searchLog = params.searchLog;
	result->searchLength = params.searchLength;
	result->targetLength = params.targetLength;
	result->strategy = params.strategy;

	return result;
}

static int CompressionParameters_init(CompressionParametersObject* self, PyObject* args, PyObject* kwargs) {
	static char* kwlist[] = {
		"window_log",
		"chain_log",
		"hash_log",
		"search_log",
		"search_length",
		"target_length",
		"strategy",
		NULL
	};

	unsigned windowLog;
	unsigned chainLog;
	unsigned hashLog;
	unsigned searchLog;
	unsigned searchLength;
	unsigned targetLength;
	unsigned strategy;

	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "IIIIIII:CompressionParameters",
		kwlist, &windowLog, &chainLog, &hashLog, &searchLog, &searchLength,
		&targetLength, &strategy)) {
		return -1;
	}

	if (windowLog < ZSTD_WINDOWLOG_MIN || windowLog > ZSTD_WINDOWLOG_MAX) {
		PyErr_SetString(PyExc_ValueError, "invalid window log value");
		return -1;
	}

	if (chainLog < ZSTD_CHAINLOG_MIN || chainLog > ZSTD_CHAINLOG_MAX) {
		PyErr_SetString(PyExc_ValueError, "invalid chain log value");
		return -1;
	}

	if (hashLog < ZSTD_HASHLOG_MIN || hashLog > ZSTD_HASHLOG_MAX) {
		PyErr_SetString(PyExc_ValueError, "invalid hash log value");
		return -1;
	}

	if (searchLog < ZSTD_SEARCHLOG_MIN || searchLog > ZSTD_SEARCHLOG_MAX) {
		PyErr_SetString(PyExc_ValueError, "invalid search log value");
		return -1;
	}

	if (searchLength < ZSTD_SEARCHLENGTH_MIN || searchLength > ZSTD_SEARCHLENGTH_MAX) {
		PyErr_SetString(PyExc_ValueError, "invalid search length value");
		return -1;
	}

	if (targetLength < ZSTD_TARGETLENGTH_MIN || targetLength > ZSTD_TARGETLENGTH_MAX) {
		PyErr_SetString(PyExc_ValueError, "invalid target length value");
		return -1;
	}

	if (strategy < ZSTD_fast || strategy > ZSTD_btopt) {
		PyErr_SetString(PyExc_ValueError, "invalid strategy value");
		return -1;
	}

	self->windowLog = windowLog;
	self->chainLog = chainLog;
	self->hashLog = hashLog;
	self->searchLog = searchLog;
	self->searchLength = searchLength;
	self->targetLength = targetLength;
	self->strategy = strategy;

	return 0;
}

PyObject* estimate_compression_context_size(PyObject* self, PyObject* args) {
	CompressionParametersObject* params;
	ZSTD_compressionParameters zparams;
	PyObject* result;

	if (!PyArg_ParseTuple(args, "O!:estimate_compression_context_size",
		&CompressionParametersType, &params)) {
		return NULL;
	}

	ztopy_compression_parameters(params, &zparams);
	result = PyLong_FromSize_t(ZSTD_estimateCCtxSize(zparams));
	return result;
}

PyDoc_STRVAR(CompressionParameters__doc__,
"CompressionParameters: low-level control over zstd compression");

static void CompressionParameters_dealloc(PyObject* self) {
	PyObject_Del(self);
}

static PyMemberDef CompressionParameters_members[] = {
	{ "window_log", T_UINT,
	  offsetof(CompressionParametersObject, windowLog), READONLY,
	  "window log" },
	{ "chain_log", T_UINT,
	  offsetof(CompressionParametersObject, chainLog), READONLY,
	  "chain log" },
	{ "hash_log", T_UINT,
	  offsetof(CompressionParametersObject, hashLog), READONLY,
	  "hash log" },
	{ "search_log", T_UINT,
	  offsetof(CompressionParametersObject, searchLog), READONLY,
	  "search log" },
	{ "search_length", T_UINT,
	  offsetof(CompressionParametersObject, searchLength), READONLY,
	  "search length" },
	{ "target_length", T_UINT,
	  offsetof(CompressionParametersObject, targetLength), READONLY,
	  "target length" },
	{ "strategy", T_INT,
	  offsetof(CompressionParametersObject, strategy), READONLY,
	  "strategy" },
	{ NULL }
};

PyTypeObject CompressionParametersType = {
	PyVarObject_HEAD_INIT(NULL, 0)
	"CompressionParameters", /* tp_name */
	sizeof(CompressionParametersObject), /* tp_basicsize */
	0,                         /* tp_itemsize */
	(destructor)CompressionParameters_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 */
	CompressionParameters__doc__, /* tp_doc */
	0,                         /* tp_traverse */
	0,                         /* tp_clear */
	0,                         /* tp_richcompare */
	0,                         /* tp_weaklistoffset */
	0,                         /* tp_iter */
	0,                         /* tp_iternext */
	0,                         /* tp_methods */
	CompressionParameters_members, /* tp_members */
	0,                         /* tp_getset */
	0,                         /* tp_base */
	0,                         /* tp_dict */
	0,                         /* tp_descr_get */
	0,                         /* tp_descr_set */
	0,                         /* tp_dictoffset */
	(initproc)CompressionParameters_init, /* tp_init */
	0,                         /* tp_alloc */
	PyType_GenericNew,         /* tp_new */
};

void compressionparams_module_init(PyObject* mod) {
	Py_TYPE(&CompressionParametersType) = &PyType_Type;
	if (PyType_Ready(&CompressionParametersType) < 0) {
		return;
	}

	Py_IncRef((PyObject*)&CompressionParametersType);
	PyModule_AddObject(mod, "CompressionParameters",
		(PyObject*)&CompressionParametersType);
}