comparison contrib/python-zstandard/c-ext/compressionwriter.c @ 30895: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
author Gregory Szorc <gregory.szorc@gmail.com>
date Tue, 07 Feb 2017 23:24:47 -0800
parents b54a2984cdd4
children e0dc40530c5a
comparison
equal deleted inserted replaced
30894:5b60464efbde 30895:c32454d69b85
50 size_t zresult; 50 size_t zresult;
51 51
52 ZSTD_outBuffer output; 52 ZSTD_outBuffer output;
53 PyObject* res; 53 PyObject* res;
54 54
55 if (!PyArg_ParseTuple(args, "OOO", &exc_type, &exc_value, &exc_tb)) { 55 if (!PyArg_ParseTuple(args, "OOO:__exit__", &exc_type, &exc_value, &exc_tb)) {
56 return NULL; 56 return NULL;
57 } 57 }
58 58
59 self->entered = 0; 59 self->entered = 0;
60 60
117 Py_ssize_t sourceSize; 117 Py_ssize_t sourceSize;
118 size_t zresult; 118 size_t zresult;
119 ZSTD_inBuffer input; 119 ZSTD_inBuffer input;
120 ZSTD_outBuffer output; 120 ZSTD_outBuffer output;
121 PyObject* res; 121 PyObject* res;
122 122 Py_ssize_t totalWrite = 0;
123 #if PY_MAJOR_VERSION >= 3 123
124 if (!PyArg_ParseTuple(args, "y#", &source, &sourceSize)) { 124 #if PY_MAJOR_VERSION >= 3
125 #else 125 if (!PyArg_ParseTuple(args, "y#:write", &source, &sourceSize)) {
126 if (!PyArg_ParseTuple(args, "s#", &source, &sourceSize)) { 126 #else
127 if (!PyArg_ParseTuple(args, "s#:write", &source, &sourceSize)) {
127 #endif 128 #endif
128 return NULL; 129 return NULL;
129 } 130 }
130 131
131 if (!self->entered) { 132 if (!self->entered) {
162 #else 163 #else
163 res = PyObject_CallMethod(self->writer, "write", "s#", 164 res = PyObject_CallMethod(self->writer, "write", "s#",
164 #endif 165 #endif
165 output.dst, output.pos); 166 output.dst, output.pos);
166 Py_XDECREF(res); 167 Py_XDECREF(res);
168 totalWrite += output.pos;
167 } 169 }
168 output.pos = 0; 170 output.pos = 0;
169 } 171 }
170 172
171 PyMem_Free(output.dst); 173 PyMem_Free(output.dst);
172 174
173 /* TODO return bytes written */ 175 return PyLong_FromSsize_t(totalWrite);
174 Py_RETURN_NONE;
175 } 176 }
176 177
177 static PyObject* ZstdCompressionWriter_flush(ZstdCompressionWriter* self, PyObject* args) { 178 static PyObject* ZstdCompressionWriter_flush(ZstdCompressionWriter* self, PyObject* args) {
178 size_t zresult; 179 size_t zresult;
179 ZSTD_outBuffer output; 180 ZSTD_outBuffer output;
180 PyObject* res; 181 PyObject* res;
182 Py_ssize_t totalWrite = 0;
181 183
182 if (!self->entered) { 184 if (!self->entered) {
183 PyErr_SetString(ZstdError, "flush must be called from an active context manager"); 185 PyErr_SetString(ZstdError, "flush must be called from an active context manager");
184 return NULL; 186 return NULL;
185 } 187 }
213 #else 215 #else
214 res = PyObject_CallMethod(self->writer, "write", "s#", 216 res = PyObject_CallMethod(self->writer, "write", "s#",
215 #endif 217 #endif
216 output.dst, output.pos); 218 output.dst, output.pos);
217 Py_XDECREF(res); 219 Py_XDECREF(res);
220 totalWrite += output.pos;
218 } 221 }
219 output.pos = 0; 222 output.pos = 0;
220 } 223 }
221 224
222 PyMem_Free(output.dst); 225 PyMem_Free(output.dst);
223 226
224 /* TODO return bytes written */ 227 return PyLong_FromSsize_t(totalWrite);
225 Py_RETURN_NONE;
226 } 228 }
227 229
228 static PyMethodDef ZstdCompressionWriter_methods[] = { 230 static PyMethodDef ZstdCompressionWriter_methods[] = {
229 { "__enter__", (PyCFunction)ZstdCompressionWriter_enter, METH_NOARGS, 231 { "__enter__", (PyCFunction)ZstdCompressionWriter_enter, METH_NOARGS,
230 PyDoc_STR("Enter a compression context.") }, 232 PyDoc_STR("Enter a compression context.") },