dirstate: add a C implementation for nonnormalentries
Before this patch, there was only a python version of nonnormalentries.
On mozilla-central we have a 10x win by putting this function in C:
% python -m timeit -s \
'from mercurial import hg, ui, parsers; \
repo = hg.repository(ui.ui(), "mozilla-central"); \
m = repo.dirstate._map' \
'parsers.nonnormalentries(m)'
100 loops, best of 3: 3.15 msec per loop
The python implementation runs in 31ms, a similar test gives:
10 loops, best of 3: 31.7 msec per loop
On our big repos, the win is still of 10x with the python implementation running
in 350ms and the C implementation running in 30ms.
--- a/mercurial/parsers.c Mon Dec 21 16:26:44 2015 -0800
+++ b/mercurial/parsers.c Mon Dec 21 16:27:16 2015 -0800
@@ -547,6 +547,44 @@
}
/*
+ * Build a set of non-normal entries from the dirstate dmap
+*/
+static PyObject *nonnormalentries(PyObject *self, PyObject *args)
+{
+ PyObject *dmap, *nonnset = NULL, *fname, *v;
+ Py_ssize_t pos;
+
+ if (!PyArg_ParseTuple(args, "O!:nonnormalentries",
+ &PyDict_Type, &dmap))
+ goto bail;
+
+ nonnset = PySet_New(NULL);
+ if (nonnset == NULL)
+ goto bail;
+
+ pos = 0;
+ while (PyDict_Next(dmap, &pos, &fname, &v)) {
+ dirstateTupleObject *t;
+ if (!dirstate_tuple_check(v)) {
+ PyErr_SetString(PyExc_TypeError,
+ "expected a dirstate tuple");
+ goto bail;
+ }
+ t = (dirstateTupleObject *)v;
+
+ if (t->state == 'n' && t->mtime != -1)
+ continue;
+ if (PySet_Add(nonnset, fname) == -1)
+ goto bail;
+ }
+
+ return nonnset;
+bail:
+ Py_XDECREF(nonnset);
+ return NULL;
+}
+
+/*
* Efficiently pack a dirstate object into its on-disk format.
*/
static PyObject *pack_dirstate(PyObject *self, PyObject *args)
@@ -2740,6 +2778,8 @@
static PyMethodDef methods[] = {
{"pack_dirstate", pack_dirstate, METH_VARARGS, "pack a dirstate\n"},
+ {"nonnormalentries", nonnormalentries, METH_VARARGS,
+ "create a set containing non-normal entries of given dirstate\n"},
{"parse_manifest", parse_manifest, METH_VARARGS, "parse a manifest\n"},
{"parse_dirstate", parse_dirstate, METH_VARARGS, "parse a dirstate\n"},
{"parse_index2", parse_index2, METH_VARARGS, "parse a revlog index\n"},