##// END OF EJS Templates
branchmap-v3: introduce a "stop_rev" argument to `headsrevs`...
branchmap-v3: introduce a "stop_rev" argument to `headsrevs` The `headsrevs` method of the revlog already have a `revs` argument to compute the headrevs of a limited set of heads. However, it disable the use of the native compiled code to compute the heads, which slows down the branchmap v3 code a lot. The branchmap v3 usage is actually quite constrained as we will always only ignores a part at the top of the graph. So we could be significantly faster. We start by making small change to the python side to improve the situation and introduce the new API. More collaboration with the native code are coming later. This massively speedup operation and close most of the remaining gaps between branchmap-v3 and branchmap-v2. especially on repository with many revs like mozilla-try. A small overhead remains mostly because the `headrevs` logic currently has some inefficiently. We will look into them from there. ### benchmark.name = hg.command.unbundle # bin-env-vars.hg.py-re2-module = default # benchmark.variants.issue6528 = disabled # benchmark.variants.resource-usage = default # benchmark.variants.reuse-external-delta-parent = yes # benchmark.variants.revs = any-1-extra-rev # benchmark.variants.source = unbundle # benchmark.variants.validate = default # benchmark.variants.verbosity = quiet ## data-env-vars.name = netbeans-2018-08-01-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.233711 ~~~~~ branch-v3 before: 0.368769 (+57.79%, +0.14) branch-v3 after: 0.239857 (+2.63%, +0.01) # bin-env-vars.hg.flavor = rust branch-v2: 0.235230 ~~~~~ branch-v3 before: 0.372460 (+58.34%, +0.14) branch-v3 after: 0.240972 (+2.44%, +0.01) ## data-env-vars.name = netbeans-2018-08-01-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.255586 ~~~~~ branch-v3 before: 0.318907 (+24.78%, +0.06) branch-v3 after: 0.268560 (+5.08%, +0.01) ## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.339010 ~~~~~ branch-v3 before: 0.349752 (+3.17%, +0.01) branch-v3 after: 0.349389 (+3.06%, +0.01) # bin-env-vars.hg.flavor = rust branch-v2: 0.346525 ~~~~~ branch-v3 before: 0.354300 (+2.24%, +0.01) branch-v3 after: 0.355661 (+2.64%, +0.01) ## data-env-vars.name = mozilla-central-2024-03-22-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.380202 ~~~~~ branch-v3 before: 0.396293 (+4.23%, +0.02) branch-v3 after: 0.408851 (+7.54%, +0.03) ## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.412165 ~~~~~ branch-v3 before: 0.424769 (+3.06%, +0.01) branch-v3 after: 0.427782 (+3.79%, +0.02) # bin-env-vars.hg.flavor = rust branch-v2: 0.412397 ~~~~~ branch-v3 before: 0.421796 (+2.28%, +0.01) branch-v3 after: 0.422354 (+2.41%, +0.01) ## data-env-vars.name = mozilla-unified-2024-03-22-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.429501 ~~~~~ branch-v3 before: 0.443849 (+3.34%, +0.01) branch-v3 after: 0.443197 (+3.19%, +0.01) ## data-env-vars.name = mozilla-try-2024-03-26-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 3.403171 ~~~~~ branch-v3 before: 6.234055 (+83.18%, +2.83) branch-v3 after: 3.819477 (+12.23%, +0.42) # bin-env-vars.hg.flavor = rust branch-v2: 3.454876 ~~~~~ branch-v3 before: 6.307813 (+82.58%, +2.85) branch-v3 after: 3.590284 (+3.92%, +0.14) ## data-env-vars.name = mozilla-try-2024-03-26-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 3.465435 ~~~~~ branch-v3 before: 5.176076 (+49.36%, +1.71) branch-v3 after: 3.633278 (+4.84%, +0.17)

File last commit:

r49676:b0dd39b9 default
r52870:42a116f1 default
Show More
mpatch.c
203 lines | 4.4 KiB | text/x-c | CLexer
/*
mpatch.c - efficient binary patching for Mercurial
This implements a patch algorithm that's O(m + nlog n) where m is the
size of the output and n is the number of patches.
Given a list of binary patches, it unpacks each into a hunk list,
then combines the hunk lists with a treewise recursion to form a
single hunk list. This hunk list is then applied to the original
text.
The text (or binary) fragments are copied directly from their source
Python objects into a preallocated output string to avoid the
allocation of intermediate Python objects. Working memory is about 2x
the total number of hunks.
Copyright 2005, 2006 Olivia Mackall <olivia@selenic.com>
This software may be used and distributed according to the terms
of the GNU General Public License, incorporated herein by reference.
*/
#define PY_SSIZE_T_CLEAN
#include <Python.h>
#include <stdlib.h>
#include <string.h>
#include "bitmanipulation.h"
#include "compat.h"
#include "mpatch.h"
#include "util.h"
static char mpatch_doc[] = "Efficient binary patching.";
static PyObject *mpatch_Error;
static void setpyerr(int r)
{
switch (r) {
case MPATCH_ERR_NO_MEM:
PyErr_NoMemory();
break;
case MPATCH_ERR_CANNOT_BE_DECODED:
PyErr_SetString(mpatch_Error, "patch cannot be decoded");
break;
case MPATCH_ERR_INVALID_PATCH:
PyErr_SetString(mpatch_Error, "invalid patch");
break;
}
}
struct mpatch_flist *cpygetitem(void *bins, ssize_t pos)
{
Py_buffer buffer;
struct mpatch_flist *res = NULL;
int r;
PyObject *tmp = PyList_GetItem((PyObject *)bins, pos);
if (!tmp) {
return NULL;
}
if (PyObject_GetBuffer(tmp, &buffer, PyBUF_CONTIG_RO)) {
return NULL;
}
if ((r = mpatch_decode(buffer.buf, buffer.len, &res)) < 0) {
if (!PyErr_Occurred()) {
setpyerr(r);
}
res = NULL;
}
PyBuffer_Release(&buffer);
return res;
}
static PyObject *patches(PyObject *self, PyObject *args)
{
PyObject *text, *bins, *result;
struct mpatch_flist *patch;
Py_buffer buffer;
int r = 0;
char *out;
Py_ssize_t len, outlen;
if (!PyArg_ParseTuple(args, "OO:mpatch", &text, &bins)) {
return NULL;
}
len = PyList_Size(bins);
if (!len) {
/* nothing to do */
Py_INCREF(text);
return text;
}
if (PyObject_GetBuffer(text, &buffer, PyBUF_CONTIG_RO)) {
return NULL;
}
patch = mpatch_fold(bins, cpygetitem, 0, len);
if (!patch) { /* error already set or memory error */
if (!PyErr_Occurred()) {
PyErr_NoMemory();
}
result = NULL;
goto cleanup;
}
outlen = mpatch_calcsize(buffer.len, patch);
if (outlen < 0) {
r = (int)outlen;
result = NULL;
goto cleanup;
}
result = PyBytes_FromStringAndSize(NULL, outlen);
if (!result) {
result = NULL;
goto cleanup;
}
out = PyBytes_AsString(result);
/* clang-format off */
{
Py_BEGIN_ALLOW_THREADS
r = mpatch_apply(out, buffer.buf, buffer.len, patch);
Py_END_ALLOW_THREADS
}
/* clang-format on */
if (r < 0) {
Py_DECREF(result);
result = NULL;
}
cleanup:
mpatch_lfree(patch);
PyBuffer_Release(&buffer);
if (!result && !PyErr_Occurred()) {
setpyerr(r);
}
return result;
}
/* calculate size of a patched file directly */
static PyObject *patchedsize(PyObject *self, PyObject *args)
{
long orig, start, end, len, outlen = 0, last = 0, pos = 0;
Py_ssize_t patchlen;
char *bin;
if (!PyArg_ParseTuple(args, "ly#", &orig, &bin, &patchlen)) {
return NULL;
}
while (pos >= 0 && pos < patchlen) {
start = getbe32(bin + pos);
end = getbe32(bin + pos + 4);
len = getbe32(bin + pos + 8);
if (start > end) {
break; /* sanity check */
}
pos += 12 + len;
outlen += start - last;
last = end;
outlen += len;
}
if (pos != patchlen) {
if (!PyErr_Occurred()) {
PyErr_SetString(mpatch_Error,
"patch cannot be decoded");
}
return NULL;
}
outlen += orig - last;
return Py_BuildValue("l", outlen);
}
static PyMethodDef methods[] = {
{"patches", patches, METH_VARARGS, "apply a series of patches\n"},
{"patchedsize", patchedsize, METH_VARARGS, "calculed patched size\n"},
{NULL, NULL},
};
static const int version = 1;
static struct PyModuleDef mpatch_module = {
PyModuleDef_HEAD_INIT, "mpatch", mpatch_doc, -1, methods,
};
PyMODINIT_FUNC PyInit_mpatch(void)
{
PyObject *m;
m = PyModule_Create(&mpatch_module);
if (m == NULL)
return NULL;
mpatch_Error =
PyErr_NewException("mercurial.cext.mpatch.mpatchError", NULL, NULL);
Py_INCREF(mpatch_Error);
PyModule_AddObject(m, "mpatchError", mpatch_Error);
PyModule_AddIntConstant(m, "version", version);
return m;
}