##// END OF EJS Templates
branchmap-v3: filter topo heads using node for performance reason...
branchmap-v3: filter topo heads using node for performance reason The branchmap currently contains heads as nodeid. If we build a set of revnum with the topological heads, we need to turn the nodeid in the branchmap to revnum to be able to check if they are topo-heads. That nodeid → revnum lookup is "expensive" and adds up to something noticeable if you do it hundreds of thousand of time. Instead we turn all the topo-heads revnums into nodes and build a set. So we can directly test membership of the nodeids stored in the branchmap. That is much faster. Ideally we would have revnum in the branchmap and could directly test revnum against a revnum set and that would be even faster. However that's an adventure for another time. Without this change, the branchmap format "v3" was significantly slower than the "v2" format. With this changes, some of that gap is recovered With rust + persistent nodemap, this overhead was smaller because the extra lookup did not had to to build the nodemap from scratch. In addition the mozilla-unified repository is able to use the "pure_top" mode of branchmap v3, so it was not really affected by this. Future changeset will work of the remaining of the performance gap. ### 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: 0.380994 (+63.02%, +0.15) branch-v3 after: 0.368769 (+57.79%, +0.14) # bin-env-vars.hg.flavor = rust branch-v2: 0.235230 ~~~~~ branch-v3 before: 0.385060 (+63.70%, +0.15) branch-v3 after: 0.372460 (+58.34%, +0.14) ## data-env-vars.name = netbeans-2018-08-01-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.255586 ~~~~~ branch-v3 before: 0.317524 (+24.23%, +0.06) branch-v3 after: 0.318907 (+24.78%, +0.06) ## 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: 0.410007 (+20.94%, +0.07) branch-v3 after: 0.349752 (+3.17%, +0.01) # bin-env-vars.hg.flavor = rust branch-v2: 0.346525 ~~~~~ branch-v3 before: 0.410428 (+18.44%, +0.06) branch-v3 after: 0.354300 (+2.24%, +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: 0.393871 (+3.60%, +0.01) branch-v3 after: 0.396293 (+4.23%, +0.02) ## 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: 0.438105 (+6.29%, +0.03) branch-v3 after: 0.424769 (+3.06%, +0.01) # bin-env-vars.hg.flavor = rust branch-v2: 0.412397 ~~~~~ branch-v3 before: 0.438405 (+6.31%, +0.03) branch-v3 after: 0.421796 (+2.28%, +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: 0.452692 (+5.40%, +0.02) branch-v3 after: 0.443849 (+3.34%, +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: 6.562345 (+92.83%, +3.16) branch-v3 after: 6.234055 (+83.18%, +2.83) # bin-env-vars.hg.flavor = rust branch-v2: 3.454876 ~~~~~ branch-v3 before: 6.160248 (+78.31%, +2.71) branch-v3 after: 6.307813 (+82.58%, +2.85) ## data-env-vars.name = mozilla-try-2024-03-26-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 3.465435 ~~~~~ branch-v3 before: 5.381648 (+55.30%, +1.92) branch-v3 after: 5.176076 (+49.36%, +1.71)

File last commit:

r49676:b0dd39b9 default
r52869:41b8892a default
Show More
bdiff.c
348 lines | 7.3 KiB | text/x-c | CLexer
/*
bdiff.c - efficient binary diff extension for Mercurial
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.
Based roughly on Python difflib
*/
#define PY_SSIZE_T_CLEAN
#include <Python.h>
#include <limits.h>
#include <stdlib.h>
#include <string.h>
#include "bdiff.h"
#include "bitmanipulation.h"
#include "thirdparty/xdiff/xdiff.h"
#include "util.h"
static PyObject *blocks(PyObject *self, PyObject *args)
{
PyObject *sa, *sb, *rl = NULL, *m;
struct bdiff_line *a, *b;
struct bdiff_hunk l, *h;
int an, bn, count, pos = 0;
l.next = NULL;
if (!PyArg_ParseTuple(args, "SS:bdiff", &sa, &sb)) {
return NULL;
}
an = bdiff_splitlines(PyBytes_AsString(sa), PyBytes_Size(sa), &a);
bn = bdiff_splitlines(PyBytes_AsString(sb), PyBytes_Size(sb), &b);
if (!a || !b) {
goto nomem;
}
count = bdiff_diff(a, an, b, bn, &l);
if (count < 0) {
goto nomem;
}
rl = PyList_New(count);
if (!rl) {
goto nomem;
}
for (h = l.next; h; h = h->next) {
m = Py_BuildValue("iiii", h->a1, h->a2, h->b1, h->b2);
PyList_SetItem(rl, pos, m);
pos++;
}
nomem:
free(a);
free(b);
bdiff_freehunks(l.next);
return rl ? rl : PyErr_NoMemory();
}
static PyObject *bdiff(PyObject *self, PyObject *args)
{
Py_buffer ba, bb;
char *rb, *ia, *ib;
PyObject *result = NULL;
struct bdiff_line *al = NULL, *bl = NULL;
struct bdiff_hunk l, *h;
int an, bn, count;
Py_ssize_t len = 0, la, lb, li = 0, lcommon = 0, lmax;
PyThreadState *_save = NULL;
l.next = NULL;
if (!PyArg_ParseTuple(args, "y*y*:bdiff", &ba, &bb)) {
return NULL;
}
if (!PyBuffer_IsContiguous(&ba, 'C') || ba.ndim > 1) {
PyErr_SetString(PyExc_ValueError, "bdiff input not contiguous");
goto cleanup;
}
if (!PyBuffer_IsContiguous(&bb, 'C') || bb.ndim > 1) {
PyErr_SetString(PyExc_ValueError, "bdiff input not contiguous");
goto cleanup;
}
la = ba.len;
lb = bb.len;
if (la > UINT_MAX || lb > UINT_MAX) {
PyErr_SetString(PyExc_ValueError, "bdiff inputs too large");
goto cleanup;
}
_save = PyEval_SaveThread();
lmax = la > lb ? lb : la;
for (ia = ba.buf, ib = bb.buf; li < lmax && *ia == *ib;
++li, ++ia, ++ib) {
if (*ia == '\n') {
lcommon = li + 1;
}
}
/* we can almost add: if (li == lmax) lcommon = li; */
an = bdiff_splitlines((char *)ba.buf + lcommon, la - lcommon, &al);
bn = bdiff_splitlines((char *)bb.buf + lcommon, lb - lcommon, &bl);
if (!al || !bl) {
PyErr_NoMemory();
goto cleanup;
}
count = bdiff_diff(al, an, bl, bn, &l);
if (count < 0) {
PyErr_NoMemory();
goto cleanup;
}
/* calculate length of output */
la = lb = 0;
for (h = l.next; h; h = h->next) {
if (h->a1 != la || h->b1 != lb) {
len += 12 + bl[h->b1].l - bl[lb].l;
}
la = h->a2;
lb = h->b2;
}
PyEval_RestoreThread(_save);
_save = NULL;
result = PyBytes_FromStringAndSize(NULL, len);
if (!result) {
goto cleanup;
}
/* build binary patch */
rb = PyBytes_AsString(result);
la = lb = 0;
for (h = l.next; h; h = h->next) {
if (h->a1 != la || h->b1 != lb) {
len = bl[h->b1].l - bl[lb].l;
putbe32((uint32_t)(al[la].l + lcommon - al->l), rb);
putbe32((uint32_t)(al[h->a1].l + lcommon - al->l),
rb + 4);
putbe32((uint32_t)len, rb + 8);
memcpy(rb + 12, bl[lb].l, len);
rb += 12 + len;
}
la = h->a2;
lb = h->b2;
}
cleanup:
if (_save) {
PyEval_RestoreThread(_save);
}
PyBuffer_Release(&ba);
PyBuffer_Release(&bb);
free(al);
free(bl);
bdiff_freehunks(l.next);
return result;
}
/*
* If allws != 0, remove all whitespace (' ', \t and \r). Otherwise,
* reduce whitespace sequences to a single space and trim remaining whitespace
* from end of lines.
*/
static PyObject *fixws(PyObject *self, PyObject *args)
{
PyObject *s, *result = NULL;
char allws, c;
const char *r;
Py_ssize_t i, rlen, wlen = 0;
char *w;
if (!PyArg_ParseTuple(args, "Sb:fixws", &s, &allws)) {
return NULL;
}
r = PyBytes_AsString(s);
rlen = PyBytes_Size(s);
w = (char *)PyMem_Malloc(rlen ? rlen : 1);
if (!w) {
goto nomem;
}
for (i = 0; i != rlen; i++) {
c = r[i];
if (c == ' ' || c == '\t' || c == '\r') {
if (!allws && (wlen == 0 || w[wlen - 1] != ' ')) {
w[wlen++] = ' ';
}
} else if (c == '\n' && !allws && wlen > 0 &&
w[wlen - 1] == ' ') {
w[wlen - 1] = '\n';
} else {
w[wlen++] = c;
}
}
result = PyBytes_FromStringAndSize(w, wlen);
nomem:
PyMem_Free(w);
return result ? result : PyErr_NoMemory();
}
static bool sliceintolist(PyObject *list, Py_ssize_t destidx,
const char *source, Py_ssize_t len)
{
PyObject *sliced = PyBytes_FromStringAndSize(source, len);
if (sliced == NULL) {
return false;
}
PyList_SET_ITEM(list, destidx, sliced);
return true;
}
static PyObject *splitnewlines(PyObject *self, PyObject *args)
{
const char *text;
Py_ssize_t nelts = 0, size, i, start = 0;
PyObject *result = NULL;
if (!PyArg_ParseTuple(args, "y#", &text, &size)) {
goto abort;
}
if (!size) {
return PyList_New(0);
}
/* This loops to size-1 because if the last byte is a newline,
* we don't want to perform a split there. */
for (i = 0; i < size - 1; ++i) {
if (text[i] == '\n') {
++nelts;
}
}
if ((result = PyList_New(nelts + 1)) == NULL) {
goto abort;
}
nelts = 0;
for (i = 0; i < size - 1; ++i) {
if (text[i] == '\n') {
if (!sliceintolist(result, nelts++, text + start,
i - start + 1)) {
goto abort;
}
start = i + 1;
}
}
if (!sliceintolist(result, nelts++, text + start, size - start)) {
goto abort;
}
return result;
abort:
Py_XDECREF(result);
return NULL;
}
static int hunk_consumer(int64_t a1, int64_t a2, int64_t b1, int64_t b2,
void *priv)
{
PyObject *rl = (PyObject *)priv;
PyObject *m = Py_BuildValue("LLLL", a1, a2, b1, b2);
int r;
if (!m) {
return -1;
}
r = PyList_Append(rl, m);
Py_DECREF(m);
return r;
}
static PyObject *xdiffblocks(PyObject *self, PyObject *args)
{
Py_ssize_t la, lb;
mmfile_t a, b;
PyObject *rl;
xpparam_t xpp = {
XDF_INDENT_HEURISTIC, /* flags */
};
xdemitconf_t xecfg = {
XDL_EMIT_BDIFFHUNK, /* flags */
hunk_consumer, /* hunk_consume_func */
};
xdemitcb_t ecb = {
NULL, /* priv */
};
if (!PyArg_ParseTuple(args, "y#y#", &a.ptr, &la, &b.ptr, &lb)) {
return NULL;
}
a.size = la;
b.size = lb;
rl = PyList_New(0);
if (!rl) {
return PyErr_NoMemory();
}
ecb.priv = rl;
if (xdl_diff(&a, &b, &xpp, &xecfg, &ecb) != 0) {
Py_DECREF(rl);
return PyErr_NoMemory();
}
return rl;
}
static char mdiff_doc[] = "Efficient binary diff.";
static PyMethodDef methods[] = {
{"bdiff", bdiff, METH_VARARGS, "calculate a binary diff\n"},
{"blocks", blocks, METH_VARARGS, "find a list of matching lines\n"},
{"fixws", fixws, METH_VARARGS, "normalize diff whitespaces\n"},
{"splitnewlines", splitnewlines, METH_VARARGS,
"like str.splitlines, but only split on newlines\n"},
{"xdiffblocks", xdiffblocks, METH_VARARGS,
"find a list of matching lines using xdiff algorithm\n"},
{NULL, NULL},
};
static const int version = 3;
static struct PyModuleDef bdiff_module = {
PyModuleDef_HEAD_INIT, "bdiff", mdiff_doc, -1, methods,
};
PyMODINIT_FUNC PyInit_bdiff(void)
{
PyObject *m;
m = PyModule_Create(&bdiff_module);
PyModule_AddIntConstant(m, "version", version);
return m;
}