bpo-33234 Improve list() pre-sizing for inputs with known lengths

Lib/test/test_descr.py

@@ -2028,7 +2028,7 @@ class X(Checker):
                 setattr(X, attr, obj)
             setattr(X, name, SpecialDescr(meth_impl))
             runner(X())
-            self.assertEqual(record, [1], name)
+            self.assertGreaterEqual(record.count(1), 1, name)
 
             class X(Checker):
                 pass

Lib/test/test_list.py

@@ -1,5 +1,6 @@
 import sys
 from test import list_tests
+from test.support import cpython_only
 import pickle
 import unittest
 
@@ -157,5 +158,13 @@ class L(list): pass
         with self.assertRaises(TypeError):
             (3,) + L([1,2])
 
+    @cpython_only
+    def test_preallocation(self):
+        iterable = [0] * 10
+        iter_size = sys.getsizeof(iterable)
+
+        self.assertEqual(iter_size, sys.getsizeof(list([0] * 10)))
+        self.assertEqual(iter_size, sys.getsizeof(list(range(10))))
+
 if __name__ == "__main__":
     unittest.main()

Misc/NEWS.d/next/Core and Builtins/2018-04-17-01-24-51.bpo-33234.l9IDtp.rst

@@ -0,0 +1,2 @@
+The list constructor will pre-size and not over-allocate when the input size
+is known or can be reasonably estimated.

Objects/listobject.c

@@ -76,6 +76,32 @@ list_resize(PyListObject *self, Py_ssize_t newsize)
     return 0;
 }
 
+static int
+list_preallocate_exact(PyListObject *self, Py_ssize_t size)
+{
+    PyObject **items;
+    size_t allocated, num_allocated_bytes;
+
+    allocated = (size_t)size;
+    if (allocated > (size_t)PY_SSIZE_T_MAX / sizeof(PyObject *)) {
+        PyErr_NoMemory();
+        return -1;
+    }
+
+    if (size == 0) {
+        allocated = 0;
+    }
+    num_allocated_bytes = allocated * sizeof(PyObject *);
+    items = (PyObject **)PyMem_Malloc(num_allocated_bytes);
+    if (items == NULL) {
+        PyErr_NoMemory();
+        return -1;
+    }
+    self->ob_item = items;
+    self->allocated = allocated;
+    return 0;
+}
+
 /* Debug statistic to compare allocations with reuse through the free list */
 #undef SHOW_ALLOC_COUNT
 #ifdef SHOW_ALLOC_COUNT
@@ -2649,6 +2675,13 @@ list___init___impl(PyListObject *self, PyObject *iterable)
         (void)_list_clear(self);
     }
     if (iterable != NULL) {
+        Py_ssize_t iter_len = PyObject_LengthHint(iterable, 0);
+        if (iter_len == -1){
+            PyErr_Clear();
+        }
+        if (iter_len > 0 && list_preallocate_exact(self, iter_len)) {
+            return -1;
+        }
         PyObject *rv = list_extend(self, iterable);
         if (rv == NULL)
             return -1;