tests/test-lrucachedict.py

perf: add threading capability to perfbdiff

Since we are releasing the GIL during diffing, it is interesting to see how a
thread pool would perform on diffing. We add a new `--threads` argument to
commands. Synchronizing the thread pool is a bit complex because we want to be
able to reuse it from one run to another.

On my computer (i7 with 4 cores + hyperthreading), I get the following data for
about 12000 revisions:
threads wall        comb    wall gain   comb overhead
none    31.596715   31.59    0.00%       0.00%
1       31.621228   31.62   -0.08%       0.09%
2       16.406202   32.8    48.08%       3.83%
3       11.598334   34.76   63.29%      10.03%
4        9.205421   36.77   70.87%      16.40%
5        8.517604   42.51   73.04%      34.57%
6        7.94645    47.58   74.85%      50.62%
7        7.434972   51.92   76.47%      64.36%
8        7.070638   55.34   77.62%      75.18%

Compared to the feature disabled (threads=0), the overhead is negligible with
the threading code (threads=1), and the gain is already 48% with two threads.

from __future__ import absolute_import, print_function

from mercurial import (
    util,
)

def printifpresent(d, xs, name='d'):
    for x in xs:
        present = x in d
        print("'%s' in %s: %s" % (x, name, present))
        if present:
            print("%s['%s']: %s" % (name, x, d[x]))

def test_lrucachedict():
    d = util.lrucachedict(4)
    d['a'] = 'va'
    d['b'] = 'vb'
    d['c'] = 'vc'
    d['d'] = 'vd'

    # all of these should be present
    printifpresent(d, ['a', 'b', 'c', 'd'])

    # 'a' should be dropped because it was least recently used
    d['e'] = 've'
    printifpresent(d, ['a', 'b', 'c', 'd', 'e'])

    assert d.get('a') is None
    assert d.get('e') == 've'

    # touch entries in some order (get or set).
    d['e']
    d['c'] = 'vc2'
    d['d']
    d['b'] = 'vb2'

    # 'e' should be dropped now
    d['f'] = 'vf'
    printifpresent(d, ['b', 'c', 'd', 'e', 'f'])

    d.clear()
    printifpresent(d, ['b', 'c', 'd', 'e', 'f'])

    # Now test dicts that aren't full.
    d = util.lrucachedict(4)
    d['a'] = 1
    d['b'] = 2
    d['a']
    d['b']
    printifpresent(d, ['a', 'b'])

    # test copy method
    d = util.lrucachedict(4)
    d['a'] = 'va3'
    d['b'] = 'vb3'
    d['c'] = 'vc3'
    d['d'] = 'vd3'

    dc = d.copy()

    # all of these should be present
    print("\nAll of these should be present:")
    printifpresent(dc, ['a', 'b', 'c', 'd'], 'dc')

    # 'a' should be dropped because it was least recently used
    print("\nAll of these except 'a' should be present:")
    dc['e'] = 've3'
    printifpresent(dc, ['a', 'b', 'c', 'd', 'e'], 'dc')

    # contents and order of original dict should remain unchanged
    print("\nThese should be in reverse alphabetical order and read 'v?3':")
    dc['b'] = 'vb3_new'
    for k in list(iter(d)):
        print("d['%s']: %s" % (k, d[k]))

if __name__ == '__main__':
    test_lrucachedict()