Merged revisions 70546 via svnmerge from

svn+ssh://pythondev@svn.python.org/python/trunk

........
  r70546 | antoine.pitrou | 2009-03-23 19:41:45 +0100 (lun., 23 mars 2009) | 9 lines

  Issue #4688: Add a heuristic so that tuples and dicts containing only
  untrackable objects are not tracked by the garbage collector. This can
  reduce the size of collections and therefore the garbage collection overhead
  on long-running programs, depending on their particular use of datatypes.

  (trivia: this makes the "binary_trees" benchmark from the Computer Language
  Shootout 40% faster)
........

3 files changed, 190 insertions, 0 deletions

diff --git a/Lib/test/test_dict.py b/Lib/test/test_dict.py
index 308143d..1c9bca8 100644
--- a/Lib/test/test_dict.py
+++ b/Lib/test/test_dict.py
@@ -665,6 +665,104 @@ class DictTest(unittest.TestCase):
             gc.collect()
             self.assert_(ref() is None, "Cycle was not collected")
 
+    def _not_tracked(self, t):
+        # Nested containers can take several collections to untrack
+        gc.collect()
+        gc.collect()
+        self.assertFalse(gc.is_tracked(t), t)
+
+    def _tracked(self, t):
+        self.assertTrue(gc.is_tracked(t), t)
+        gc.collect()
+        gc.collect()
+        self.assertTrue(gc.is_tracked(t), t)
+
+    def test_track_literals(self):
+        # Test GC-optimization of dict literals
+        x, y, z, w = 1.5, "a", (1, None), []
+
+        self._not_tracked({})
+        self._not_tracked({x:(), y:x, z:1})
+        self._not_tracked({1: "a", "b": 2})
+        self._not_tracked({1: 2, (None, True, False, ()): int})
+        self._not_tracked({1: object()})
+
+        # Dicts with mutable elements are always tracked, even if those
+        # elements are not tracked right now.
+        self._tracked({1: []})
+        self._tracked({1: ([],)})
+        self._tracked({1: {}})
+        self._tracked({1: set()})
+
+    def test_track_dynamic(self):
+        # Test GC-optimization of dynamically-created dicts
+        class MyObject(object):
+            pass
+        x, y, z, w, o = 1.5, "a", (1, object()), [], MyObject()
+
+        d = dict()
+        self._not_tracked(d)
+        d[1] = "a"
+        self._not_tracked(d)
+        d[y] = 2
+        self._not_tracked(d)
+        d[z] = 3
+        self._not_tracked(d)
+        self._not_tracked(d.copy())
+        d[4] = w
+        self._tracked(d)
+        self._tracked(d.copy())
+        d[4] = None
+        self._not_tracked(d)
+        self._not_tracked(d.copy())
+
+        # dd isn't tracked right now, but it may mutate and therefore d
+        # which contains it must be tracked.
+        d = dict()
+        dd = dict()
+        d[1] = dd
+        self._not_tracked(dd)
+        self._tracked(d)
+        dd[1] = d
+        self._tracked(dd)
+
+        d = dict.fromkeys([x, y, z])
+        self._not_tracked(d)
+        dd = dict()
+        dd.update(d)
+        self._not_tracked(dd)
+        d = dict.fromkeys([x, y, z, o])
+        self._tracked(d)
+        dd = dict()
+        dd.update(d)
+        self._tracked(dd)
+
+        d = dict(x=x, y=y, z=z)
+        self._not_tracked(d)
+        d = dict(x=x, y=y, z=z, w=w)
+        self._tracked(d)
+        d = dict()
+        d.update(x=x, y=y, z=z)
+        self._not_tracked(d)
+        d.update(w=w)
+        self._tracked(d)
+
+        d = dict([(x, y), (z, 1)])
+        self._not_tracked(d)
+        d = dict([(x, y), (z, w)])
+        self._tracked(d)
+        d = dict()
+        d.update([(x, y), (z, 1)])
+        self._not_tracked(d)
+        d.update([(x, y), (z, w)])
+        self._tracked(d)
+
+    def test_track_subtypes(self):
+        # Dict subtypes are always tracked
+        class MyDict(dict):
+            pass
+        self._tracked(MyDict())
+
 
 from test import mapping_tests
 
diff --git a/Lib/test/test_gc.py b/Lib/test/test_gc.py
index 414e17a..2262b36 100644
--- a/Lib/test/test_gc.py
+++ b/Lib/test/test_gc.py
@@ -415,6 +415,33 @@ class GCTests(unittest.TestCase):
 
         self.assertEqual(gc.get_referents(1, 'a', 4j), [])
 
+    def test_is_tracked(self):
+        # Atomic built-in types are not tracked, user-defined objects and
+        # mutable containers are.
+        # NOTE: types with special optimizations (e.g. tuple) have tests
+        # in their own test files instead.
+        self.assertFalse(gc.is_tracked(None))
+        self.assertFalse(gc.is_tracked(1))
+        self.assertFalse(gc.is_tracked(1.0))
+        self.assertFalse(gc.is_tracked(1.0 + 5.0j))
+        self.assertFalse(gc.is_tracked(True))
+        self.assertFalse(gc.is_tracked(False))
+        self.assertFalse(gc.is_tracked(b"a"))
+        self.assertFalse(gc.is_tracked("a"))
+        self.assertFalse(gc.is_tracked(bytearray(b"a")))
+        self.assertFalse(gc.is_tracked(type))
+        self.assertFalse(gc.is_tracked(int))
+        self.assertFalse(gc.is_tracked(object))
+        self.assertFalse(gc.is_tracked(object()))
+
+        class UserClass:
+            pass
+        self.assertTrue(gc.is_tracked(gc))
+        self.assertTrue(gc.is_tracked(UserClass))
+        self.assertTrue(gc.is_tracked(UserClass()))
+        self.assertTrue(gc.is_tracked([]))
+        self.assertTrue(gc.is_tracked(set()))
+
     def test_bug1055820b(self):
         # Corresponds to temp2b.py in the bug report.
 
diff --git a/Lib/test/test_tuple.py b/Lib/test/test_tuple.py
index de08131..f82af31 100644
--- a/Lib/test/test_tuple.py
+++ b/Lib/test/test_tuple.py
@@ -1,5 +1,7 @@
 from test import support, seq_tests
 
+import gc
+
 class TupleTest(seq_tests.CommonTest):
     type2test = tuple
 
@@ -82,6 +84,69 @@ class TupleTest(seq_tests.CommonTest):
         self.assertEqual(repr(a0), "()")
         self.assertEqual(repr(a2), "(0, 1, 2)")
 
+    def _not_tracked(self, t):
+        # Nested tuples can take several collections to untrack
+        gc.collect()
+        gc.collect()
+        self.assertFalse(gc.is_tracked(t), t)
+
+    def _tracked(self, t):
+        self.assertTrue(gc.is_tracked(t), t)
+        gc.collect()
+        gc.collect()
+        self.assertTrue(gc.is_tracked(t), t)
+
+    def test_track_literals(self):
+        # Test GC-optimization of tuple literals
+        x, y, z = 1.5, "a", []
+
+        self._not_tracked(())
+        self._not_tracked((1,))
+        self._not_tracked((1, 2))
+        self._not_tracked((1, 2, "a"))
+        self._not_tracked((1, 2, (None, True, False, ()), int))
+        self._not_tracked((object(),))
+        self._not_tracked(((1, x), y, (2, 3)))
+
+        # Tuples with mutable elements are always tracked, even if those
+        # elements are not tracked right now.
+        self._tracked(([],))
+        self._tracked(([1],))
+        self._tracked(({},))
+        self._tracked((set(),))
+        self._tracked((x, y, z))
+
+    def check_track_dynamic(self, tp, always_track):
+        x, y, z = 1.5, "a", []
+
+        check = self._tracked if always_track else self._not_tracked
+        check(tp())
+        check(tp([]))
+        check(tp(set()))
+        check(tp([1, x, y]))
+        check(tp(obj for obj in [1, x, y]))
+        check(tp(set([1, x, y])))
+        check(tp(tuple([obj]) for obj in [1, x, y]))
+        check(tuple(tp([obj]) for obj in [1, x, y]))
+
+        self._tracked(tp([z]))
+        self._tracked(tp([[x, y]]))
+        self._tracked(tp([{x: y}]))
+        self._tracked(tp(obj for obj in [x, y, z]))
+        self._tracked(tp(tuple([obj]) for obj in [x, y, z]))
+        self._tracked(tuple(tp([obj]) for obj in [x, y, z]))
+
+    def test_track_dynamic(self):
+        # Test GC-optimization of dynamically constructed tuples.
+        self.check_track_dynamic(tuple, False)
+
+    def test_track_subtypes(self):
+        # Tuple subtypes must always be tracked
+        class MyTuple(tuple):
+            pass
+        self.check_track_dynamic(MyTuple, True)
+
+
 def test_main():
     support.run_unittest(TupleTest)