Mercurial > hg
view mercurial/cext/charencode.h @ 47343:9f798c1b0d89 stable
cext: fix memory leak in phases computation
Without this a buffer whose size in bytes is the number of
changesets in the repository is leaked each time the repository is
opened and changeset phases are computed.
Impact: the current code in hgwebdir creates a new `localrepository`
instance for each HTTP request. Since any pull or push is made of several
requests, a team of 100 people can easily produce thousands of such
requests per day.
Being a low-level malloc, this leak can't be seen with the gc module and
tools relying on that, but was spotted by valgrind immediately.
Reproduction
------------
for i in range(cl_args.iterations):
repo = hg.repository(baseui, repo_path)
rev = repo.revs(rev).first()
ctx = repo[rev]
del ctx
del repo
# avoid any pollution by other type of leak
# (that should be fixed in 5.8)
repoview._filteredrepotypes.clear()
gc.collect()
Measurements
------------
Resident Set Size (RSS), taken on a clone of
mozilla-central for performance analysis (440 000
changesets).
before:
5.8+hg19.5ac0f2a8ba72 1000 iterations: 1606MB
5.8+hg19.5ac0f2a8ba72 10000 iterations: 5723MB
after:
5.8+hg20.e2084d39e145 1000 iterations: 555MB
5.8+hg20.e2084d39e145 10000 iterations: 555MB
(double checked, not a copy/paste error)
(e2084d39e14 is the present changeset, before amendment
of the message to add the measurements)
author | Georges Racinet <georges.racinet@octobus.net> |
---|---|
date | Sun, 06 Jun 2021 01:24:30 +0200 |
parents | 81199632fa42 |
children |
line wrap: on
line source
/* charencode.h - miscellaneous character encoding This software may be used and distributed according to the terms of the GNU General Public License, incorporated herein by reference. */ #ifndef _HG_CHARENCODE_H_ #define _HG_CHARENCODE_H_ #include <Python.h> #include "compat.h" /* This should be kept in sync with normcasespecs in encoding.py. */ enum normcase_spec { NORMCASE_LOWER = -1, NORMCASE_UPPER = 1, NORMCASE_OTHER = 0 }; PyObject *unhexlify(const char *str, Py_ssize_t len); PyObject *isasciistr(PyObject *self, PyObject *args); PyObject *asciilower(PyObject *self, PyObject *args); PyObject *asciiupper(PyObject *self, PyObject *args); PyObject *make_file_foldmap(PyObject *self, PyObject *args); PyObject *jsonescapeu8fast(PyObject *self, PyObject *args); /* clang-format off */ static const int8_t hextable[256] = { -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, -1, -1, -1, -1, -1, -1, /* 0-9 */ -1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1, /* A-F */ -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1, /* a-f */ -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 }; /* clang-format on */ static inline int hexdigit(const char *p, Py_ssize_t off) { int8_t val = hextable[(unsigned char)p[off]]; if (val >= 0) { return val; } PyErr_SetString(PyExc_ValueError, "input contains non-hex character"); return 0; } #endif /* _HG_CHARENCODE_H_ */