tests/check-perf-code.py

phases: invalidate the phases set less often on retract boundary

We already have the information to update the phase set, so we do so directly
instead of invalidating the cache.

This show a sizeable speedup in our `perf::unbundle` benchmark on the
many-draft mozilla-try repository.

### data-env-vars.name            = mozilla-try-2023-03-22-zstd-sparse-revlog
  # benchmark.name                = hg.perf.perf-unbundle
  # bin-env-vars.hg.flavor        = no-rust
  # bin-env-vars.hg.py-re2-module = default
  # benchmark.variants.issue6528  = disabled

  # benchmark.variants.revs = last-10
before: 2.055259 seconds
after:  1.887064 seconds (-8.18%)
  # benchmark.variants.revs = last-100
before: 2.409239 seconds
after:  2.222429 seconds (-7.75%)
  # benchmark.variants.revs = last-1000
before: 3.945648 seconds
after:  3.762480 seconds (-4.64%)

#!/usr/bin/env python3
#
# check-perf-code - (historical) portability checker for contrib/perf.py


import os
import sys

# write static check patterns here
perfpypats = [
    [
        (
            r'(branchmap|repoview|repoviewutil)\.subsettable',
            "use getbranchmapsubsettable() for early Mercurial",
        ),
        (
            r'\.(vfs|svfs|opener|sopener)',
            "use getvfs()/getsvfs() for early Mercurial",
        ),
        (
            r'ui\.configint',
            "use getint() instead of ui.configint() for early Mercurial",
        ),
    ],
    # warnings
    [],
]


def modulewhitelist(names):
    replacement = [
        ('.py', ''),
        ('.c', ''),  # trim suffix
        ('mercurial%s' % '/', ''),  # trim "mercurial/" path
    ]
    ignored = {'__init__'}
    modules = {}

    # convert from file name to module name, and count # of appearances
    for name in names:
        name = name.strip()
        for old, new in replacement:
            name = name.replace(old, new)
        if name not in ignored:
            modules[name] = modules.get(name, 0) + 1

    # list up module names, which appear multiple times
    whitelist = []
    for name, count in modules.items():
        if count > 1:
            whitelist.append(name)

    return whitelist


if __name__ == "__main__":
    # in this case, it is assumed that result of "hg files" at
    # multiple revisions is given via stdin
    whitelist = modulewhitelist(sys.stdin)
    assert whitelist, "module whitelist is empty"

    # build up module whitelist check from file names given at runtime
    perfpypats[0].append(
        # this matching pattern assumes importing modules from
        # "mercurial" package in the current style below, for simplicity
        #
        #    from mercurial import (
        #        foo,
        #        bar,
        #        baz
        #    )
        (
            (
                r'from mercurial import [(][a-z0-9, \n#]*\n(?! *%s,|^[ #]*\n|[)])'
                % ',| *'.join(whitelist)
            ),
            "import newer module separately in try clause for early Mercurial",
        )
    )

    # import contrib/check-code.py as checkcode
    assert 'RUNTESTDIR' in os.environ, "use check-perf-code.py in *.t script"
    contribpath = os.path.join(os.environ['RUNTESTDIR'], '..', 'contrib')
    sys.path.insert(0, contribpath)
    checkcode = __import__('check-code')

    # register perf.py specific entry with "checks" in check-code.py
    checkcode.checks.append(
        ('perf.py', r'contrib/perf.py$', '', checkcode.pyfilters, perfpypats)
    )

    sys.exit(checkcode.main())