##// END OF EJS Templates
revlog: change generaldelta delta parent heuristic...
revlog: change generaldelta delta parent heuristic The old generaldelta heuristic was "if p1 (or p2) was closer than the last full text, use it, otherwise use prev". This was problematic when a repo contained multiple branches that were very different. If commits to branch A were pushed, and the last full text was branch B, it would generate a fulltext. Then if branch B was pushed, it would generate another fulltext. The problem is that the last fulltext (and delta'ing against `prev` in general) has no correlation with the contents of the incoming revision, and therefore will always have degenerate cases. According to the blame, that algorithm was chosen to minimize the chain length. Since there is already code that protects against that (the delta-vs-fulltext code), and since it has been improved since the original generaldelta algorithm went in (2011), I believe the chain length criteria will still be preserved. The new algorithm always diffs against p1 (or p2 if it's closer), unless the resulting delta will fail the delta-vs-fulltext check, in which case we delta against prev. Some before and after stats on manifest.d size. internal large repo old heuristic - 2.0 GB new heuristic - 1.2 GB mozilla-central old heuristic - 242 MB new heuristic - 261 MB The regression in mozilla central is due to the new heuristic choosing p2r as the delta when it's closer to the tip. Switching the algorithm to always prefer p1r brings the size back down (242 MB). This is result of the way in which mozilla does merges and pushes, and the result could easily swing the other direction in other repos (depending on if they merge X into Y or Y into X), but will never be as degenerate as before. I future patch will address the regression by introducing an optional, even more aggressive delta heuristic which will knock the mozilla manifest size down dramatically.

File last commit:

r26074:c1aefe57 default
r26117:4dc5b51f default
Show More
base85.c
185 lines | 3.4 KiB | text/x-c | CLexer
/*
base85 codec
Copyright 2006 Brendan Cully <brendan@kublai.com>
This software may be used and distributed according to the terms of
the GNU General Public License, incorporated herein by reference.
Largely based on git's implementation
*/
#define PY_SSIZE_T_CLEAN
#include <Python.h>
#include "util.h"
static const char b85chars[] = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ"
"abcdefghijklmnopqrstuvwxyz!#$%&()*+-;<=>?@^_`{|}~";
static char b85dec[256];
static void
b85prep(void)
{
unsigned i;
memset(b85dec, 0, sizeof(b85dec));
for (i = 0; i < sizeof(b85chars); i++)
b85dec[(int)(b85chars[i])] = i + 1;
}
static PyObject *
b85encode(PyObject *self, PyObject *args)
{
const unsigned char *text;
PyObject *out;
char *dst;
Py_ssize_t len, olen, i;
unsigned int acc, val, ch;
int pad = 0;
if (!PyArg_ParseTuple(args, "s#|i", &text, &len, &pad))
return NULL;
if (pad)
olen = ((len + 3) / 4 * 5) - 3;
else {
olen = len % 4;
if (olen)
olen++;
olen += len / 4 * 5;
}
if (!(out = PyBytes_FromStringAndSize(NULL, olen + 3)))
return NULL;
dst = PyBytes_AsString(out);
while (len) {
acc = 0;
for (i = 24; i >= 0; i -= 8) {
ch = *text++;
acc |= ch << i;
if (--len == 0)
break;
}
for (i = 4; i >= 0; i--) {
val = acc % 85;
acc /= 85;
dst[i] = b85chars[val];
}
dst += 5;
}
if (!pad)
_PyBytes_Resize(&out, olen);
return out;
}
static PyObject *
b85decode(PyObject *self, PyObject *args)
{
PyObject *out;
const char *text;
char *dst;
Py_ssize_t len, i, j, olen, cap;
int c;
unsigned int acc;
if (!PyArg_ParseTuple(args, "s#", &text, &len))
return NULL;
olen = len / 5 * 4;
i = len % 5;
if (i)
olen += i - 1;
if (!(out = PyBytes_FromStringAndSize(NULL, olen)))
return NULL;
dst = PyBytes_AsString(out);
i = 0;
while (i < len)
{
acc = 0;
cap = len - i - 1;
if (cap > 4)
cap = 4;
for (j = 0; j < cap; i++, j++)
{
c = b85dec[(int)*text++] - 1;
if (c < 0)
return PyErr_Format(
PyExc_ValueError,
"bad base85 character at position %d",
(int)i);
acc = acc * 85 + c;
}
if (i++ < len)
{
c = b85dec[(int)*text++] - 1;
if (c < 0)
return PyErr_Format(
PyExc_ValueError,
"bad base85 character at position %d",
(int)i);
/* overflow detection: 0xffffffff == "|NsC0",
* "|NsC" == 0x03030303 */
if (acc > 0x03030303 || (acc *= 85) > 0xffffffff - c)
return PyErr_Format(
PyExc_ValueError,
"bad base85 sequence at position %d",
(int)i);
acc += c;
}
cap = olen < 4 ? olen : 4;
olen -= cap;
for (j = 0; j < 4 - cap; j++)
acc *= 85;
if (cap && cap < 4)
acc += 0xffffff >> (cap - 1) * 8;
for (j = 0; j < cap; j++)
{
acc = (acc << 8) | (acc >> 24);
*dst++ = acc;
}
}
return out;
}
static char base85_doc[] = "Base85 Data Encoding";
static PyMethodDef methods[] = {
{"b85encode", b85encode, METH_VARARGS,
"Encode text in base85.\n\n"
"If the second parameter is true, pad the result to a multiple of "
"five characters.\n"},
{"b85decode", b85decode, METH_VARARGS, "Decode base85 text.\n"},
{NULL, NULL}
};
#ifdef IS_PY3K
static struct PyModuleDef base85_module = {
PyModuleDef_HEAD_INIT,
"base85",
base85_doc,
-1,
methods
};
PyMODINIT_FUNC PyInit_base85(void)
{
b85prep();
return PyModule_Create(&base85_module);
}
#else
PyMODINIT_FUNC initbase85(void)
{
Py_InitModule3("base85", methods, base85_doc);
b85prep();
}
#endif