Improve performance of inspect.getmodule

getmodule maintains a cache of module names & associated file names.
Whenever it encounters a module filename not in its cache, it iterates
over sys.modules and repopulates its cache.

An object which has no associated module filename will trigger this
repopulation loop every time getmodule is called.  The cost is easily
seen with inspect.getstack

def run_test(module):
    # cols have stack depths
    # rows have len(sys.modules)

    def print_line(h, *vals):
        if not h:
            print("%5s" % h, *["%6i" % v for v in vals])
        else:
            print("%5s" % h, *["%6.1f" % v for v in vals])

    def add_modules(n):
        import random
        import sys
        for _ in range(n):
            sys.modules[f"foo_{random.randint(0,2**64)}"] = module

    def measure(depth):
        import inspect
        import timeit

        def nest(level):
            if level > 0:
                return nest(level-1)
            else:
                dur = timeit.timeit(lambda: inspect.stack(), number=1)
                return dur * 1000

        return nest(depth)

    import sys
    print_line("", *[2**e for e in range(7)])
    for i in range(1, 5):
        add_modules(n=10**i)
        times = [measure(depth=2**e) for e in range(7)]
        print_line(len(sys.modules), *times)

python 3.11.0a7+ optimized build ====

# sys has no __file__ and doesn't enter getmodule cache
>>> import sys
>>> run_test(sys)
           1      2      4      8     16     32     64
   87    2.1    0.8    1.0    1.3    2.0    3.3    6.1
  187    2.0    2.5    2.7    3.6    5.5    9.5   16.8
 1187   13.6   15.7   19.1   26.3   39.6   67.4  123.3
11187  134.1  150.3  183.4  252.0  383.5  750.3 1189.8
>>> exit()

>>> import random
>>> run_test(random)
           1      2      4      8     16     32     64
   87    2.1    0.7    0.9    1.2    1.7    2.9    5.6
  187    2.3    1.1    1.5    1.8    2.5    4.3    7.8
 1187   17.0    4.3    5.6    7.1   11.1   18.6   33.9
11187  164.6   37.4   45.7   61.6   94.7  161.0  297.7
>>> exit()

python 3.11.0a7+ optimized build, with changes ====

>>> import sys
>>> run_test(sys)
           1      2      4      8     16     32     64
   87    1.7    0.2    0.2    0.3    0.4    0.6    1.2
  187    0.2    0.2    0.2    0.2    0.3    0.5    0.9
 1187    0.2    0.2    0.2    0.3    0.3    0.5    0.9
11187    0.3    0.3    0.3    0.3    0.5    0.8    1.3
>>> exit()

>>> import random
>>> run_test(random)
           1      2      4      8     16     32     64
   87    1.8    0.2    0.2    0.3    0.4    0.6    1.2
  187    0.2    0.2    0.2    0.3    0.3    0.6    0.9
 1187    0.2    0.2    0.2    0.3    0.4    0.5    0.9
11187    0.3    0.2    0.2    0.3    0.3    0.6    1.0
>>> exit()

Author: mdeck

Lib/inspect.py

@@ -907,6 +907,14 @@ def getfile(object):
             if object.__module__ == '__main__':
                 raise OSError('source code not available')
         raise TypeError('{!r} is a built-in class'.format(object))
+    if code := _getcode(object):
+        return code.co_filename
+    raise TypeError('module, class, method, function, traceback, frame, or '
+                    'code object was expected, got {}'.format(
+                    type(object).__name__))
+
+def _getcode(object):
+    """Get the code an object was defined in, if available."""
     if ismethod(object):
         object = object.__func__
     if isfunction(object):
@@ -916,10 +924,7 @@ def getfile(object):
     if isframe(object):
         object = object.f_code
     if iscode(object):
-        return object.co_filename
-    raise TypeError('module, class, method, function, traceback, frame, or '
-                    'code object was expected, got {}'.format(
-                    type(object).__name__))
+        return object
 
 def getmodulename(path):
     """Return the module name for a given file, or None."""
@@ -969,20 +974,27 @@ def getabsfile(object, _filename=None):
 
 modulesbyfile = {}
 _filesbymodname = {}
+_moduleless = set()
 
 def getmodule(object, _filename=None):
     """Return the module an object was defined in, or None if not found."""
     if ismodule(object):
         return object
     if hasattr(object, '__module__'):
         return sys.modules.get(object.__module__)
+    code = _getcode(object)
+    if code and hash(code) in _moduleless:
+        return None
     # Try the filename to modulename cache
     if _filename is not None and _filename in modulesbyfile:
         return sys.modules.get(modulesbyfile[_filename])
     # Try the cache again with the absolute file name
     try:
         file = getabsfile(object, _filename)
     except (TypeError, FileNotFoundError):
+        _moduleless.add(hash(code))
+        return None
+    if code and hash(code) in _moduleless:
         return None
     if file in modulesbyfile:
         return sys.modules.get(modulesbyfile[file])
@@ -1004,6 +1016,7 @@ def getmodule(object, _filename=None):
     # Check the main module
     main = sys.modules['__main__']
     if not hasattr(object, '__name__'):
+        _moduleless.add(hash(code))
         return None
     if hasattr(main, object.__name__):
         mainobject = getattr(main, object.__name__)
@@ -1015,6 +1028,8 @@ def getmodule(object, _filename=None):
         builtinobject = getattr(builtin, object.__name__)
         if builtinobject is object:
             return builtin
+    _moduleless.add(hash(code))
+    return None
 
 
 class ClassFoundException(Exception):