bpo-29585: optimize site.py startup time (GH-136)

Avoid importing `sysconfig` from `site` by copying minimum code.
Python startup is 5% faster on Linux and 30% faster on macOS

8 files changed, 96 insertions, 43 deletions

diff --git a/Lib/site.py b/Lib/site.py
index 8797938358..fcf7dde411 100644
--- a/Lib/site.py
+++ b/Lib/site.py
@@ -124,7 +124,7 @@ def removeduppaths():
         # if they only differ in case); turn relative paths into absolute
         # paths.
         dir, dircase = makepath(dir)
-        if not dircase in known_paths:
+        if dircase not in known_paths:
             L.append(dir)
             known_paths.add(dircase)
     sys.path[:] = L
@@ -234,6 +234,46 @@ def check_enableusersite():
 
     return True
 
+
+# NOTE: sysconfig and it's dependencies are relatively large but site module
+# needs very limited part of them.
+# To speedup startup time, we have copy of them.
+#
+# See https://bugs.python.org/issue29585
+
+# Copy of sysconfig._getuserbase()
+def _getuserbase():
+    env_base = os.environ.get("PYTHONUSERBASE", None)
+    if env_base:
+        return env_base
+
+    def joinuser(*args):
+        return os.path.expanduser(os.path.join(*args))
+
+    if os.name == "nt":
+        base = os.environ.get("APPDATA") or "~"
+        return joinuser(base, "Python")
+
+    if sys.platform == "darwin" and sys._framework:
+        return joinuser("~", "Library", sys._framework,
+                        "%d.%d" % sys.version_info[:2])
+
+    return joinuser("~", ".local")
+
+
+# Same to sysconfig.get_path('purelib', os.name+'_user')
+def _get_path(userbase):
+    version = sys.version_info
+
+    if os.name == 'nt':
+        return f'{userbase}/Python{version[0]}{version[1]}/site-packages'
+
+    if sys.platform == 'darwin' and sys._framework:
+        return f'{userbase}/lib/python/site-packages'
+
+    return f'{userbase}/lib/python{version[0]}.{version[1]}/site-packages'
+
+
 def getuserbase():
     """Returns the `user base` directory path.
 
@@ -242,12 +282,11 @@ def getuserbase():
     it.
     """
     global USER_BASE
-    if USER_BASE is not None:
-        return USER_BASE
-    from sysconfig import get_config_var
-    USER_BASE = get_config_var('userbase')
+    if USER_BASE is None:
+        USER_BASE = _getuserbase()
     return USER_BASE
 
+
 def getusersitepackages():
     """Returns the user-specific site-packages directory path.
 
@@ -255,20 +294,11 @@ def getusersitepackages():
     function will also set it.
     """
     global USER_SITE
-    user_base = getuserbase() # this will also set USER_BASE
-
-    if USER_SITE is not None:
-        return USER_SITE
-
-    from sysconfig import get_path
+    userbase = getuserbase() # this will also set USER_BASE
 
-    if sys.platform == 'darwin':
-        from sysconfig import get_config_var
-        if get_config_var('PYTHONFRAMEWORK'):
-            USER_SITE = get_path('purelib', 'osx_framework_user')
-            return USER_SITE
+    if USER_SITE is None:
+        USER_SITE = _get_path(userbase)
 
-    USER_SITE = get_path('purelib', '%s_user' % os.name)
     return USER_SITE
 
 def addusersitepackages(known_paths):
@@ -310,15 +340,11 @@ def getsitepackages(prefixes=None):
         else:
             sitepackages.append(prefix)
             sitepackages.append(os.path.join(prefix, "lib", "site-packages"))
-        if sys.platform == "darwin":
-            # for framework builds *only* we add the standard Apple
-            # locations.
-            from sysconfig import get_config_var
-            framework = get_config_var("PYTHONFRAMEWORK")
-            if framework:
-                sitepackages.append(
-                        os.path.join("/Library", framework,
-                            '%d.%d' % sys.version_info[:2], "site-packages"))
+        # for framework builds *only* we add the standard Apple locations.
+        if sys.platform == "darwin" and sys._framework:
+            sitepackages.append(
+                    os.path.join("/Library", framework,
+                        '%d.%d' % sys.version_info[:2], "site-packages"))
     return sitepackages
 
 def addsitepackages(known_paths, prefixes=None):
diff --git a/Lib/sysconfig.py b/Lib/sysconfig.py
index ed0a34d662..e6618b1d51 100644
--- a/Lib/sysconfig.py
+++ b/Lib/sysconfig.py
@@ -51,6 +51,7 @@ _INSTALL_SCHEMES = {
         'scripts': '{base}/Scripts',
         'data': '{base}',
         },
+    # NOTE: When modifying "purelib" scheme, update site._get_path() too.
     'nt_user': {
         'stdlib': '{userbase}/Python{py_version_nodot}',
         'platstdlib': '{userbase}/Python{py_version_nodot}',
@@ -177,32 +178,25 @@ def _get_default_scheme():
     return os.name
 
 
+# NOTE: site.py has copy of this function.
+# Sync it when modify this function.
 def _getuserbase():
     env_base = os.environ.get("PYTHONUSERBASE", None)
+    if env_base:
+        return env_base
 
     def joinuser(*args):
         return os.path.expanduser(os.path.join(*args))
 
     if os.name == "nt":
         base = os.environ.get("APPDATA") or "~"
-        if env_base:
-            return env_base
-        else:
-            return joinuser(base, "Python")
+        return joinuser(base, "Python")
 
-    if sys.platform == "darwin":
-        framework = get_config_var("PYTHONFRAMEWORK")
-        if framework:
-            if env_base:
-                return env_base
-            else:
-                return joinuser("~", "Library", framework, "%d.%d" %
-                                sys.version_info[:2])
+    if sys.platform == "darwin" and sys._framework:
+        return joinuser("~", "Library", sys._framework,
+                        "%d.%d" % sys.version_info[:2])
 
-    if env_base:
-        return env_base
-    else:
-        return joinuser("~", ".local")
+    return joinuser("~", ".local")
 
 
 def _parse_makefile(filename, vars=None):
diff --git a/Lib/test/test_site.py b/Lib/test/test_site.py
index 150162279e..bf7be4ec1c 100644
--- a/Lib/test/test_site.py
+++ b/Lib/test/test_site.py
@@ -180,6 +180,13 @@ class HelperFunctionsTests(unittest.TestCase):
         finally:
             pth_file.cleanup()
 
+    def test_getuserbase(self):
+        self.assertEqual(site._getuserbase(), sysconfig._getuserbase())
+
+    def test_get_path(self):
+        self.assertEqual(site._get_path(site._getuserbase()),
+                         sysconfig.get_path('purelib', os.name + '_user'))
+
     @unittest.skipUnless(site.ENABLE_USER_SITE, "requires access to PEP 370 "
                           "user-site (site.ENABLE_USER_SITE)")
     def test_s_option(self):
diff --git a/Misc/NEWS.d/next/Library/2017-06-29-00-17-38.bpo-29585.x2V0my.rst b/Misc/NEWS.d/next/Library/2017-06-29-00-17-38.bpo-29585.x2V0my.rst
new file mode 100644
index 0000000000..c841f1b225
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2017-06-29-00-17-38.bpo-29585.x2V0my.rst
@@ -0,0 +1,2 @@
+Avoid importing ``sysconfig`` from ``site`` to improve startup speed. Python
+startup is about 5% faster on Linux and 30% faster on macOS.
diff --git a/Python/sysmodule.c b/Python/sysmodule.c
index 424a88f708..84673e3fed 100644
--- a/Python/sysmodule.c
+++ b/Python/sysmodule.c
@@ -1965,6 +1965,7 @@ _PySys_BeginInit(void)
     SET_SYS_FROM_STRING("_git",
                         Py_BuildValue("(szz)", "CPython", _Py_gitidentifier(),
                                       _Py_gitversion()));
+    SET_SYS_FROM_STRING("_framework", PyUnicode_FromString(PYTHONFRAMEWORK));
     SET_SYS_FROM_STRING("api_version",
                         PyLong_FromLong(PYTHON_API_VERSION));
     SET_SYS_FROM_STRING("copyright",
diff --git a/configure b/configure
index ec42e08f89..ff8152d7d1 100755
--- a/configure
+++ b/configure
@@ -783,6 +783,7 @@ infodir
 docdir
 oldincludedir
 includedir
+runstatedir
 localstatedir
 sharedstatedir
 sysconfdir
@@ -896,6 +897,7 @@ datadir='${datarootdir}'
 sysconfdir='${prefix}/etc'
 sharedstatedir='${prefix}/com'
 localstatedir='${prefix}/var'
+runstatedir='${localstatedir}/run'
 includedir='${prefix}/include'
 oldincludedir='/usr/include'
 docdir='${datarootdir}/doc/${PACKAGE_TARNAME}'
@@ -1148,6 +1150,15 @@ do
   | -silent | --silent | --silen | --sile | --sil)
     silent=yes ;;
 
+  -runstatedir | --runstatedir | --runstatedi | --runstated \
+  | --runstate | --runstat | --runsta | --runst | --runs \
+  | --run | --ru | --r)
+    ac_prev=runstatedir ;;
+  -runstatedir=* | --runstatedir=* | --runstatedi=* | --runstated=* \
+  | --runstate=* | --runstat=* | --runsta=* | --runst=* | --runs=* \
+  | --run=* | --ru=* | --r=*)
+    runstatedir=$ac_optarg ;;
+
   -sbindir | --sbindir | --sbindi | --sbind | --sbin | --sbi | --sb)
     ac_prev=sbindir ;;
   -sbindir=* | --sbindir=* | --sbindi=* | --sbind=* | --sbin=* \
@@ -1285,7 +1296,7 @@ fi
 for ac_var in	exec_prefix prefix bindir sbindir libexecdir datarootdir \
 		datadir sysconfdir sharedstatedir localstatedir includedir \
 		oldincludedir docdir infodir htmldir dvidir pdfdir psdir \
-		libdir localedir mandir
+		libdir localedir mandir runstatedir
 do
   eval ac_val=\$$ac_var
   # Remove trailing slashes.
@@ -1438,6 +1449,7 @@ Fine tuning of the installation directories:
   --sysconfdir=DIR        read-only single-machine data [PREFIX/etc]
   --sharedstatedir=DIR    modifiable architecture-independent data [PREFIX/com]
   --localstatedir=DIR     modifiable single-machine data [PREFIX/var]
+  --runstatedir=DIR       modifiable per-process data [LOCALSTATEDIR/run]
   --libdir=DIR            object code libraries [EPREFIX/lib]
   --includedir=DIR        C header files [PREFIX/include]
   --oldincludedir=DIR     C header files for non-gcc [/usr/include]
@@ -3231,6 +3243,12 @@ fi
 
 
 
+
+cat >>confdefs.h <<_ACEOF
+#define PYTHONFRAMEWORK "${PYTHONFRAMEWORK}"
+_ACEOF
+
+
 ##AC_ARG_WITH(dyld,
 ##            AS_HELP_STRING([--with-dyld],
 ##                           [Use (OpenStep|Rhapsody) dynamic linker]))
diff --git a/configure.ac b/configure.ac
index 18b940ab32..815769f534 100644
--- a/configure.ac
+++ b/configure.ac
@@ -355,6 +355,8 @@ AC_SUBST(FRAMEWORKPYTHONW)
 AC_SUBST(FRAMEWORKUNIXTOOLSPREFIX)
 AC_SUBST(FRAMEWORKINSTALLAPPSPREFIX)
 
+AC_DEFINE_UNQUOTED(PYTHONFRAMEWORK, "${PYTHONFRAMEWORK}", [framework name])
+
 ##AC_ARG_WITH(dyld,
 ##            AS_HELP_STRING([--with-dyld],
 ##                           [Use (OpenStep|Rhapsody) dynamic linker]))
diff --git a/pyconfig.h.in b/pyconfig.h.in
index fa2792b18a..f7c50eadca 100644
--- a/pyconfig.h.in
+++ b/pyconfig.h.in
@@ -1247,6 +1247,9 @@
 /* Define as the preferred size in bits of long digits */
 #undef PYLONG_BITS_IN_DIGIT
 
+/* framework name */
+#undef PYTHONFRAMEWORK
+
 /* Define if you want to coerce the C locale to a UTF-8 based locale */
 #undef PY_COERCE_C_LOCALE