hgdemandimport: apply lazy module loading to sys.meta_path finders
authorGregory Szorc <gregory.szorc@gmail.com>
Mon, 20 Jan 2020 23:51:25 -0800
changeset 44118 f81c17ec303c
parent 44117 c5e0a9b97b8a
child 44119 5b38c2ab6ad3
hgdemandimport: apply lazy module loading to sys.meta_path finders Python's `sys.meta_path` finders are the primary objects whose job it is to find a module at import time. When `import` is called, Python iterates objects in this list and calls `o.find_spec(...)` to find a `ModuleSpec` (or None if the module couldn't be found by that finder). If no meta path finder can find a module, import fails. One of the default meta path finders is `PathFinder`. Its job is to import modules from the filesystem and is probably the most important importer. This finder looks at `sys.path` and `sys.path_hooks` to do its job. The `ModuleSpec` returned by `MetaPathImporter.find_spec()` has a `loader` attribute, which defines the concrete module loader to use. `sys.path_hooks` is a hook point for teaching `PathFinder` to instantiate custom loader types. Previously, we injected a custom `sys.path_hook` that told `PathFinder` to wrap the default loaders with a loader that creates a module object that is lazy. This approach worked. But its main limitation was that it only applied to the `PathFinder` meta path importer. There are other meta path importers that are registered. And in the case of PyOxidizer loading modules from memory, `PathFinder` doesn't come into play since PyOxidizer's own meta path importer was handling all imports. This commit changes our approach to lazy module loading by proxying all meta path importers. Specifically, we overload the `find_spec()` method to swap in a wrapped loader on the `ModuleSpec` before it is returned. The end result of this is all meta path importers should be lazy. As much as I would have loved to utilize .__class__ manipulation to achieve this, some meta path importers are implemented in C/Rust in such a way that they cannot be monkeypatched. This is why we use __getattribute__ to define a proxy. Also, this change could theoretically open us up to regressions in meta path importers whose loader is creating module objects which can't be monkeypatched. But I'm not aware of any of these in the wild. So I think we'll be safe. According to hyperfine, this change yields a decent startup time win of 5-6ms: ``` Benchmark #1: ~/.pyenv/versions/3.6.10/bin/python ./hg version Time (mean ± σ): 86.8 ms ± 0.5 ms [User: 78.0 ms, System: 8.7 ms] Range (min … max): 86.0 ms … 89.1 ms 50 runs Time (mean ± σ): 81.1 ms ± 2.7 ms [User: 74.5 ms, System: 6.5 ms] Range (min … max): 77.8 ms … 90.5 ms 50 runs Benchmark #2: ~/.pyenv/versions/3.7.6/bin/python ./hg version Time (mean ± σ): 78.9 ms ± 0.6 ms [User: 70.2 ms, System: 8.7 ms] Range (min … max): 78.1 ms … 81.2 ms 50 runs Time (mean ± σ): 73.4 ms ± 0.6 ms [User: 65.3 ms, System: 8.0 ms] Range (min … max): 72.4 ms … 75.7 ms 50 runs Benchmark #3: ~/.pyenv/versions/3.8.1/bin/python ./hg version Time (mean ± σ): 78.1 ms ± 0.6 ms [User: 70.2 ms, System: 7.9 ms] Range (min … max): 77.4 ms … 80.9 ms 50 runs Time (mean ± σ): 72.1 ms ± 0.4 ms [User: 64.4 ms, System: 7.6 ms] Range (min … max): 71.4 ms … 74.1 ms 50 runs ``` Differential Revision: https://phab.mercurial-scm.org/D7954
hgdemandimport/demandimportpy3.py
tests/test-demandimport.py
--- a/hgdemandimport/demandimportpy3.py	Mon Jan 20 23:42:19 2020 -0800
+++ b/hgdemandimport/demandimportpy3.py	Mon Jan 20 23:51:25 2020 -0800
@@ -27,8 +27,6 @@
 from __future__ import absolute_import
 
 import contextlib
-import importlib.abc
-import importlib.machinery
 import importlib.util
 import sys
 
@@ -57,23 +55,61 @@
                 super().exec_module(module)
 
 
-_extensions_loader = _lazyloaderex.factory(
-    importlib.machinery.ExtensionFileLoader
-)
-_bytecode_loader = _lazyloaderex.factory(
-    importlib.machinery.SourcelessFileLoader
-)
-_source_loader = _lazyloaderex.factory(importlib.machinery.SourceFileLoader)
+class LazyFinder(object):
+    """A wrapper around a ``MetaPathFinder`` that makes loaders lazy.
+
+    ``sys.meta_path`` finders have their ``find_spec()`` called to locate a
+    module. This returns a ``ModuleSpec`` if found or ``None``. The
+    ``ModuleSpec`` has a ``loader`` attribute, which is called to actually
+    load a module.
+
+    Our class wraps an existing finder and overloads its ``find_spec()`` to
+    replace the ``loader`` with our lazy loader proxy.
 
+    We have to use __getattribute__ to proxy the instance because some meta
+    path finders don't support monkeypatching.
+    """
+
+    __slots__ = ("_finder",)
+
+    def __init__(self, finder):
+        object.__setattr__(self, "_finder", finder)
+
+    def __repr__(self):
+        return "<LazyFinder for %r>" % object.__getattribute__(self, "_finder")
+
+    # __bool__ is canonical Python 3. But check-code insists on __nonzero__ being
+    # defined via `def`.
+    def __nonzero__(self):
+        return bool(object.__getattribute__(self, "_finder"))
 
-def _makefinder(path):
-    return importlib.machinery.FileFinder(
-        path,
-        # This is the order in which loaders are passed in in core Python.
-        (_extensions_loader, importlib.machinery.EXTENSION_SUFFIXES),
-        (_source_loader, importlib.machinery.SOURCE_SUFFIXES),
-        (_bytecode_loader, importlib.machinery.BYTECODE_SUFFIXES),
-    )
+    __bool__ = __nonzero__
+
+    def __getattribute__(self, name):
+        if name in ("_finder", "find_spec"):
+            return object.__getattribute__(self, name)
+
+        return getattr(object.__getattribute__(self, "_finder"), name)
+
+    def __delattr__(self, name):
+        return delattr(object.__getattribute__(self, "_finder"))
+
+    def __setattr__(self, name, value):
+        return setattr(object.__getattribute__(self, "_finder"), name, value)
+
+    def find_spec(self, *args, **kwargs):
+        finder = object.__getattribute__(self, "_finder")
+        spec = finder.find_spec(*args, **kwargs)
+
+        # Lazy loader requires exec_module().
+        if (
+            spec is not None
+            and spec.loader is not None
+            and getattr(spec.loader, "exec_module")
+        ):
+            spec.loader = _lazyloaderex(spec.loader)
+
+        return spec
 
 
 ignores = set()
@@ -85,22 +121,30 @@
 
 
 def isenabled():
-    return _makefinder in sys.path_hooks and not _deactivated
+    return not _deactivated and any(
+        isinstance(finder, LazyFinder) for finder in sys.meta_path
+    )
 
 
 def disable():
-    try:
-        while True:
-            sys.path_hooks.remove(_makefinder)
-    except ValueError:
-        pass
+    new_finders = []
+    for finder in sys.meta_path:
+        new_finders.append(
+            finder._finder if isinstance(finder, LazyFinder) else finder
+        )
+    sys.meta_path[:] = new_finders
 
 
 def enable():
     if not _supported:
         return
 
-    sys.path_hooks.insert(0, _makefinder)
+    new_finders = []
+    for finder in sys.meta_path:
+        new_finders.append(
+            LazyFinder(finder) if not isinstance(finder, LazyFinder) else finder
+        )
+    sys.meta_path[:] = new_finders
 
 
 @contextlib.contextmanager
--- a/tests/test-demandimport.py	Mon Jan 20 23:42:19 2020 -0800
+++ b/tests/test-demandimport.py	Mon Jan 20 23:51:25 2020 -0800
@@ -137,7 +137,7 @@
 from mercurial import hgweb
 
 if ispy3:
-    assert not isinstance(hgweb, _LazyModule)
+    assert isinstance(hgweb, _LazyModule)
     assert f(hgweb) == "<module 'mercurial.hgweb' from '?'>", f(hgweb)
     assert isinstance(hgweb.hgweb_mod, _LazyModule)
     assert (
@@ -210,7 +210,7 @@
 import telnetlib
 
 if ispy3:
-    assert not isinstance(telnetlib, _LazyModule)
+    assert isinstance(telnetlib, _LazyModule)
     assert f(telnetlib) == "<module 'telnetlib' from '?'>"
 else:
     assert f(telnetlib) == "<unloaded module 'telnetlib'>", f(telnetlib)