Use more aggressive gc thresholds, and tune earlier

In some cases gc was consuming a significant fraction of CPU, so run
gc less often. Also tune gc very early, to run gc less during import
time -- not sure if this has any significant impact, but in an
unrelated project this was somewhat helpful.

This makes incremental checking of torch 27% faster (based on 100
measurements), and also speeds up self check by about 10% (both
incremental and non-incremental).

Author: JukkaL

mypy/__main__.py

@@ -2,6 +2,11 @@
 
 from __future__ import annotations
 
+from mypy.gctune import tune_gc
+
+# Tune GC as early as possible, before most imports
+tune_gc()
+
 import os
 import sys
 import traceback

mypy/build.py

@@ -16,10 +16,8 @@
 import collections
 import contextlib
 import errno
-import gc
 import json
 import os
-import platform
 import re
 import stat
 import sys
@@ -46,6 +44,7 @@
 from mypy.checker import TypeChecker
 from mypy.error_formatter import OUTPUT_CHOICES, ErrorFormatter
 from mypy.errors import CompileError, ErrorInfo, Errors, report_internal_error
+from mypy.gctune import tune_gc
 from mypy.graph_utils import prepare_sccs, strongly_connected_components, topsort
 from mypy.indirection import TypeIndirectionVisitor
 from mypy.messages import MessageBuilder
@@ -217,9 +216,9 @@ def _build(
     stderr: TextIO,
     extra_plugins: Sequence[Plugin],
 ) -> BuildResult:
-    if platform.python_implementation() == "CPython":
-        # This seems the most reasonable place to tune garbage collection.
-        gc.set_threshold(150 * 1000)
+    # We tune gc in __main__, but also do it here in case we are called from
+    # another entry point such as a test.
+    tune_gc()
 
     data_dir = default_data_dir()
     fscache = fscache or FileSystemCache()

mypy/gctune.py

@@ -0,0 +1,15 @@
+"""Tuning cyclic garbage collector (GC) parameters for better performance.
+
+Since this is called very early, before most imports, don't add new import
+dependencies!
+"""
+
+import gc
+import platform
+
+
+def tune_gc() -> None:
+    if platform.python_implementation() == "CPython":
+        # Run gc less frequently, as otherwise we can spent a large fraction of
+        # cpu in gc.
+        gc.set_threshold(200 * 1000, 30, 30)

mypyc/__main__.py

@@ -12,6 +12,11 @@
 
 from __future__ import annotations
 
+from mypy.gctune import tune_gc
+
+# Tune GC as early as possible, before most imports
+tune_gc()
+
 import os
 import os.path
 import subprocess