contrib/check-py3-compat.py

perf: add command to benchmark bundle reading

Upcoming commits will be refactoring bundle2 I/O code.

This commit establishes a `hg perfbundleread` command that measures
how long it takes to read a bundle using various mechanisms.

As a baseline, here's output from an uncompressed bundle1
bundle of my Firefox repo (7,098,622,890 bytes):

! read(8k)
! wall 0.763481 comb 0.760000 user 0.160000 sys 0.600000 (best of 6)
! read(16k)
! wall 0.644512 comb 0.640000 user 0.110000 sys 0.530000 (best of 16)
! read(32k)
! wall 0.581172 comb 0.590000 user 0.060000 sys 0.530000 (best of 18)
! read(128k)
! wall 0.535183 comb 0.530000 user 0.010000 sys 0.520000 (best of 19)
! cg1 deltaiter()
! wall 0.873500 comb 0.880000 user 0.840000 sys 0.040000 (best of 12)
! cg1 getchunks()
! wall 6.283797 comb 6.270000 user 5.570000 sys 0.700000 (best of 3)
! cg1 read(8k)
! wall 1.097173 comb 1.100000 user 0.400000 sys 0.700000 (best of 10)
! cg1 read(16k)
! wall 0.810750 comb 0.800000 user 0.200000 sys 0.600000 (best of 13)
! cg1 read(32k)
! wall 0.671215 comb 0.670000 user 0.110000 sys 0.560000 (best of 15)
! cg1 read(128k)
! wall 0.597857 comb 0.600000 user 0.020000 sys 0.580000 (best of 15)

And from an uncompressed bundle2 bundle (6,070,036,163 bytes):

! read(8k)
! wall 0.676997 comb 0.680000 user 0.160000 sys 0.520000 (best of 15)
! read(16k)
! wall 0.592706 comb 0.590000 user 0.080000 sys 0.510000 (best of 17)
! read(32k)
! wall 0.529395 comb 0.530000 user 0.050000 sys 0.480000 (best of 16)
! read(128k)
! wall 0.491270 comb 0.490000 user 0.010000 sys 0.480000 (best of 19)
! bundle2 forwardchunks()
! wall 2.997131 comb 2.990000 user 2.270000 sys 0.720000 (best of 4)
! bundle2 iterparts()
! wall 12.247197 comb 10.670000 user 8.170000 sys 2.500000 (best of 3)
! bundle2 part seek()
! wall 11.761675 comb 10.500000 user 8.240000 sys 2.260000 (best of 3)
! bundle2 part read(8k)
! wall 9.116163 comb 9.110000 user 8.240000 sys 0.870000 (best of 3)
! bundle2 part read(16k)
! wall 8.984362 comb 8.970000 user 8.110000 sys 0.860000 (best of 3)
! bundle2 part read(32k)
! wall 8.758364 comb 8.740000 user 7.860000 sys 0.880000 (best of 3)
! bundle2 part read(128k)
! wall 8.749040 comb 8.730000 user 7.830000 sys 0.900000 (best of 3)

We already see some interesting data. Notably that bundle2 has
significant overhead compared to bundle1. This matters for e.g. stream
clone bundles, which can be applied at >1Gbps.

Differential Revision: https://phab.mercurial-scm.org/D1385

#!/usr/bin/env python
#
# check-py3-compat - check Python 3 compatibility of Mercurial files
#
# Copyright 2015 Gregory Szorc <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import, print_function

import ast
import importlib
import os
import sys
import traceback

def check_compat_py2(f):
    """Check Python 3 compatibility for a file with Python 2"""
    with open(f, 'rb') as fh:
        content = fh.read()
    root = ast.parse(content)

    # Ignore empty files.
    if not root.body:
        return

    futures = set()
    haveprint = False
    for node in ast.walk(root):
        if isinstance(node, ast.ImportFrom):
            if node.module == '__future__':
                futures |= set(n.name for n in node.names)
        elif isinstance(node, ast.Print):
            haveprint = True

    if 'absolute_import' not in futures:
        print('%s not using absolute_import' % f)
    if haveprint and 'print_function' not in futures:
        print('%s requires print_function' % f)

def check_compat_py3(f):
    """Check Python 3 compatibility of a file with Python 3."""
    with open(f, 'rb') as fh:
        content = fh.read()

    try:
        ast.parse(content)
    except SyntaxError as e:
        print('%s: invalid syntax: %s' % (f, e))
        return

    # Try to import the module.
    # For now we only support modules in packages because figuring out module
    # paths for things not in a package can be confusing.
    if (f.startswith(('hgdemandimport/', 'hgext/', 'mercurial/'))
        and not f.endswith('__init__.py')):
        assert f.endswith('.py')
        name = f.replace('/', '.')[:-3]
        try:
            importlib.import_module(name)
        except Exception as e:
            exc_type, exc_value, tb = sys.exc_info()
            # We walk the stack and ignore frames from our custom importer,
            # import mechanisms, and stdlib modules. This kinda/sorta
            # emulates CPython behavior in import.c while also attempting
            # to pin blame on a Mercurial file.
            for frame in reversed(traceback.extract_tb(tb)):
                if frame.name == '_call_with_frames_removed':
                    continue
                if 'importlib' in frame.filename:
                    continue
                if 'mercurial/__init__.py' in frame.filename:
                    continue
                if frame.filename.startswith(sys.prefix):
                    continue
                break

            if frame.filename:
                filename = os.path.basename(frame.filename)
                print('%s: error importing: <%s> %s (error at %s:%d)' % (
                      f, type(e).__name__, e, filename, frame.lineno))
            else:
                print('%s: error importing module: <%s> %s (line %d)' % (
                      f, type(e).__name__, e, frame.lineno))

if __name__ == '__main__':
    if sys.version_info[0] == 2:
        fn = check_compat_py2
    else:
        fn = check_compat_py3

    for f in sys.argv[1:]:
        fn(f)

    sys.exit(0)