Skip to content

bpo-30040: optimize inserting into empty dict #12307

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
methane merged 3 commits into from
Mar 18, 2019
Merged

bpo-30040: optimize inserting into empty dict #12307

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
06fdf74
optimize for inserting into empty dict
methane Mar 13, 2019
93906f1
_PyDict_NewPresized() preallocate only when size > PyDict_MINSIZE
methane Mar 15, 2019
a0ae9d8
add comment
methane Mar 18, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
51 changes: 49 additions & 2 deletions Objects/dictobject.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1102,6 +1102,41 @@ insertdict(PyDictObject *mp, PyObject *key, Py_hash_t hash, PyObject *value)
return -1;
}

// Same to insertdict but specialized for ma_keys = Py_EMPTY_KEYS.
static int
insert_to_emptydict(PyDictObject *mp, PyObject *key, Py_hash_t hash,
PyObject *value)
{
assert(mp->ma_keys == Py_EMPTY_KEYS);

PyDictKeysObject *newkeys = new_keys_object(PyDict_MINSIZE);
if (newkeys == NULL) {
return -1;
}
if (!PyUnicode_CheckExact(key)) {
newkeys->dk_lookup = lookdict;
}
dictkeys_decref(Py_EMPTY_KEYS);
mp->ma_keys = newkeys;
mp->ma_values = NULL;

Py_INCREF(key);
Py_INCREF(value);
MAINTAIN_TRACKING(mp, key, value);

size_t hashpos = (size_t)hash & (PyDict_MINSIZE-1);
PyDictKeyEntry *ep = &DK_ENTRIES(mp->ma_keys)[0];
dictkeys_set_index(mp->ma_keys, hashpos, 0);
ep->me_key = key;
ep->me_hash = hash;
ep->me_value = value;
mp->ma_used++;
mp->ma_version_tag = DICT_NEXT_VERSION();
mp->ma_keys->dk_usable--;
mp->ma_keys->dk_nentries++;
return 0;
}

/*
Internal routine used by dictresize() to build a hashtable of entries.
*/
Expand Down Expand Up @@ -1274,7 +1309,7 @@ _PyDict_NewPresized(Py_ssize_t minused)
Py_ssize_t newsize;
PyDictKeysObject *new_keys;

if (minused == 0) {
if (minused <= USABLE_FRACTION(PyDict_MINSIZE)) {
return PyDict_New();
}
/* There are no strict guarantee that returned dict can contain minused
Expand All @@ -1286,7 +1321,7 @@ _PyDict_NewPresized(Py_ssize_t minused)
}
else {
Py_ssize_t minsize = ESTIMATE_SIZE(minused);
newsize = PyDict_MINSIZE;
newsize = PyDict_MINSIZE*2;
while (newsize < minsize) {
newsize <<= 1;
}
Expand Down Expand Up @@ -1495,6 +1530,9 @@ PyDict_SetItem(PyObject *op, PyObject *key, PyObject *value)
return -1;
}

if (mp->ma_keys == Py_EMPTY_KEYS) {
return insert_to_emptydict(mp, key, hash, value);
}
/* insertdict() handles any resizing that might be necessary */
return insertdict(mp, key, hash, value);
}
Expand All @@ -1514,6 +1552,9 @@ _PyDict_SetItem_KnownHash(PyObject *op, PyObject *key, PyObject *value,
assert(hash != -1);
mp = (PyDictObject *)op;

if (mp->ma_keys == Py_EMPTY_KEYS) {
return insert_to_emptydict(mp, key, hash, value);
}
/* insertdict() handles any resizing that might be necessary */
return insertdict(mp, key, hash, value);
}
Expand Down Expand Up @@ -2844,6 +2885,12 @@ PyDict_SetDefault(PyObject *d, PyObject *key, PyObject *defaultobj)
if (hash == -1)
return NULL;
}
if (mp->ma_keys == Py_EMPTY_KEYS) {
if (insert_to_emptydict(mp, key, hash, defaultobj) < 0) {
return NULL;
}
return defaultobj;
}

if (mp->ma_values != NULL && !PyUnicode_CheckExact(key)) {
if (insertion_resize(mp) < 0)
Expand Down