view tests/test-lrucachedict.py @ 44118:f81c17ec303c

hgdemandimport: apply lazy module loading to sys.meta_path finders

Python's `sys.meta_path` finders are the primary objects whose job it
is to find a module at import time. When `import` is called, Python
iterates objects in this list and calls `o.find_spec(...)` to find
a `ModuleSpec` (or None if the module couldn't be found by that
finder). If no meta path finder can find a module, import fails.

One of the default meta path finders is `PathFinder`. Its job is to
import modules from the filesystem and is probably the most important
importer. This finder looks at `sys.path` and `sys.path_hooks` to do
its job.

The `ModuleSpec` returned by `MetaPathImporter.find_spec()` has a
`loader` attribute, which defines the concrete module loader to use.
`sys.path_hooks` is a hook point for teaching `PathFinder` to
instantiate custom loader types.

Previously, we injected a custom `sys.path_hook` that told `PathFinder`
to wrap the default loaders with a loader that creates a module object
that is lazy.

This approach worked. But its main limitation was that it only applied
to the `PathFinder` meta path importer. There are other meta path
importers that are registered. And in the case of PyOxidizer loading
modules from memory, `PathFinder` doesn't come into play since
PyOxidizer's own meta path importer was handling all imports.

This commit changes our approach to lazy module loading by proxying
all meta path importers. Specifically, we overload the `find_spec()`
method to swap in a wrapped loader on the `ModuleSpec` before it
is returned. The end result of this is all meta path importers should
be lazy.

As much as I would have loved to utilize .__class__ manipulation to
achieve this, some meta path importers are implemented in C/Rust
in such a way that they cannot be monkeypatched. This is why we
use __getattribute__ to define a proxy.

Also, this change could theoretically open us up to regressions in
meta path importers whose loader is creating module objects which
can't be monkeypatched. But I'm not aware of any of these in the
wild. So I think we'll be safe.

According to hyperfine, this change yields a decent startup time win of
5-6ms:

```
Benchmark #1: ~/.pyenv/versions/3.6.10/bin/python ./hg version
  Time (mean ± σ):      86.8 ms ±   0.5 ms    [User: 78.0 ms, System: 8.7 ms]
  Range (min … max):    86.0 ms …  89.1 ms    50 runs

  Time (mean ± σ):      81.1 ms ±   2.7 ms    [User: 74.5 ms, System: 6.5 ms]
  Range (min … max):    77.8 ms …  90.5 ms    50 runs

Benchmark #2: ~/.pyenv/versions/3.7.6/bin/python ./hg version
  Time (mean ± σ):      78.9 ms ±   0.6 ms    [User: 70.2 ms, System: 8.7 ms]
  Range (min … max):    78.1 ms …  81.2 ms    50 runs

  Time (mean ± σ):      73.4 ms ±   0.6 ms    [User: 65.3 ms, System: 8.0 ms]
  Range (min … max):    72.4 ms …  75.7 ms    50 runs

Benchmark #3: ~/.pyenv/versions/3.8.1/bin/python ./hg version
  Time (mean ± σ):      78.1 ms ±   0.6 ms    [User: 70.2 ms, System: 7.9 ms]
  Range (min … max):    77.4 ms …  80.9 ms    50 runs

  Time (mean ± σ):      72.1 ms ±   0.4 ms    [User: 64.4 ms, System: 7.6 ms]
  Range (min … max):    71.4 ms …  74.1 ms    50 runs
```

Differential Revision: https://phab.mercurial-scm.org/D7954

from __future__ import absolute_import, print_function

import unittest

import silenttestrunner

from mercurial import util


class testlrucachedict(unittest.TestCase):
    def testsimple(self):
        d = util.lrucachedict(4)
        self.assertEqual(d.capacity, 4)
        d.insert('a', 'va', cost=2)
        d['b'] = 'vb'
        d['c'] = 'vc'
        d.insert('d', 'vd', cost=42)

        self.assertEqual(d['a'], 'va')
        self.assertEqual(d['b'], 'vb')
        self.assertEqual(d['c'], 'vc')
        self.assertEqual(d['d'], 'vd')

        self.assertEqual(d.totalcost, 44)

        # 'a' should be dropped because it was least recently used.
        d['e'] = 've'
        self.assertNotIn('a', d)
        self.assertIsNone(d.get('a'))
        self.assertEqual(d.totalcost, 42)

        self.assertEqual(d['b'], 'vb')
        self.assertEqual(d['c'], 'vc')
        self.assertEqual(d['d'], 'vd')
        self.assertEqual(d['e'], 've')

        # Replacing item with different cost adjusts totalcost.
        d.insert('e', 've', cost=4)
        self.assertEqual(d.totalcost, 46)

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

        # 'e' should be dropped now
        d['f'] = 'vf'
        self.assertNotIn('e', d)
        self.assertEqual(d['b'], 'vb2')
        self.assertEqual(d['c'], 'vc2')
        self.assertEqual(d['d'], 'vd')
        self.assertEqual(d['f'], 'vf')

        d.clear()
        for key in ('a', 'b', 'c', 'd', 'e', 'f'):
            self.assertNotIn(key, d)

    def testunfull(self):
        d = util.lrucachedict(4)
        d['a'] = 1
        d['b'] = 2
        d['a']
        d['b']

        for key in ('a', 'b'):
            self.assertIn(key, d)

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

        self.assertIsNone(d.get('missing'))
        self.assertEqual(list(d), ['c', 'b', 'a'])

        self.assertEqual(d.get('a'), 'va')
        self.assertEqual(list(d), ['a', 'c', 'b'])

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

        with self.assertRaises(KeyError):
            d.peek('missing')
        self.assertEqual(list(d), ['c', 'b', 'a'])
        self.assertIsNone(d.peek('missing', None))
        self.assertEqual(list(d), ['c', 'b', 'a'])

        self.assertEqual(d.peek('a'), 'va')
        self.assertEqual(list(d), ['c', 'b', 'a'])

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

        with self.assertRaises(KeyError):
            d.pop('missing')
        self.assertEqual(list(d), ['c', 'b', 'a'])
        self.assertIsNone(d.pop('missing', None))
        self.assertEqual(list(d), ['c', 'b', 'a'])

        self.assertEqual(d.pop('b'), 'vb')
        self.assertEqual(list(d), ['c', 'a'])

    def testcopypartial(self):
        d = util.lrucachedict(4)
        d.insert('a', 'va', cost=4)
        d.insert('b', 'vb', cost=2)

        dc = d.copy()

        self.assertEqual(len(dc), 2)
        self.assertEqual(dc.totalcost, 6)
        for key in ('a', 'b'):
            self.assertIn(key, dc)
            self.assertEqual(dc[key], 'v%s' % key)

        self.assertEqual(len(d), 2)
        for key in ('a', 'b'):
            self.assertIn(key, d)
            self.assertEqual(d[key], 'v%s' % key)

        d['c'] = 'vc'
        del d['b']
        self.assertEqual(d.totalcost, 4)
        dc = d.copy()
        self.assertEqual(len(dc), 2)
        self.assertEqual(dc.totalcost, 4)
        for key in ('a', 'c'):
            self.assertIn(key, dc)
            self.assertEqual(dc[key], 'v%s' % key)

    def testcopyempty(self):
        d = util.lrucachedict(4)
        dc = d.copy()
        self.assertEqual(len(dc), 0)

    def testcopyfull(self):
        d = util.lrucachedict(4)
        d.insert('a', 'va', cost=42)
        d['b'] = 'vb'
        d['c'] = 'vc'
        d['d'] = 'vd'

        dc = d.copy()

        for key in ('a', 'b', 'c', 'd'):
            self.assertIn(key, dc)
            self.assertEqual(dc[key], 'v%s' % key)

        self.assertEqual(d.totalcost, 42)
        self.assertEqual(dc.totalcost, 42)

        # 'a' should be dropped because it was least recently used.
        dc['e'] = 've'
        self.assertNotIn('a', dc)
        for key in ('b', 'c', 'd', 'e'):
            self.assertIn(key, dc)
            self.assertEqual(dc[key], 'v%s' % key)

        self.assertEqual(d.totalcost, 42)
        self.assertEqual(dc.totalcost, 0)

        # Contents and order of original dict should remain unchanged.
        dc['b'] = 'vb_new'

        self.assertEqual(list(iter(d)), ['d', 'c', 'b', 'a'])
        for key in ('a', 'b', 'c', 'd'):
            self.assertEqual(d[key], 'v%s' % key)

        d = util.lrucachedict(4, maxcost=42)
        d.insert('a', 'va', cost=5)
        d.insert('b', 'vb', cost=4)
        d.insert('c', 'vc', cost=3)
        dc = d.copy()
        self.assertEqual(dc.maxcost, 42)
        self.assertEqual(len(dc), 3)

        # Max cost can be lowered as part of copy.
        dc = d.copy(maxcost=10)
        self.assertEqual(dc.maxcost, 10)
        self.assertEqual(len(dc), 2)
        self.assertEqual(dc.totalcost, 7)
        self.assertIn('b', dc)
        self.assertIn('c', dc)

    def testcopydecreasecapacity(self):
        d = util.lrucachedict(5)
        d.insert('a', 'va', cost=4)
        d.insert('b', 'vb', cost=2)
        d['c'] = 'vc'
        d['d'] = 'vd'

        dc = d.copy(2)
        self.assertEqual(dc.totalcost, 0)
        for key in ('a', 'b'):
            self.assertNotIn(key, dc)
        for key in ('c', 'd'):
            self.assertIn(key, dc)
            self.assertEqual(dc[key], 'v%s' % key)

        dc.insert('e', 've', cost=7)
        self.assertEqual(dc.totalcost, 7)
        self.assertNotIn('c', dc)
        for key in ('d', 'e'):
            self.assertIn(key, dc)
            self.assertEqual(dc[key], 'v%s' % key)

        # Original should remain unchanged.
        self.assertEqual(d.totalcost, 6)
        for key in ('a', 'b', 'c', 'd'):
            self.assertIn(key, d)
            self.assertEqual(d[key], 'v%s' % key)

    def testcopyincreasecapacity(self):
        d = util.lrucachedict(5)
        d['a'] = 'va'
        d['b'] = 'vb'
        d['c'] = 'vc'
        d['d'] = 'vd'

        dc = d.copy(6)
        for key in ('a', 'b', 'c', 'd'):
            self.assertIn(key, dc)
            self.assertEqual(dc[key], 'v%s' % key)

        dc['e'] = 've'
        dc['f'] = 'vf'
        for key in ('a', 'b', 'c', 'd', 'e', 'f'):
            self.assertIn(key, dc)
            self.assertEqual(dc[key], 'v%s' % key)

        dc['g'] = 'vg'
        self.assertNotIn('a', dc)
        for key in ('b', 'c', 'd', 'e', 'f', 'g'):
            self.assertIn(key, dc)
            self.assertEqual(dc[key], 'v%s' % key)

        # Original should remain unchanged.
        for key in ('a', 'b', 'c', 'd'):
            self.assertIn(key, d)
            self.assertEqual(d[key], 'v%s' % key)

    def testpopoldest(self):
        d = util.lrucachedict(4)
        d.insert('a', 'va', cost=10)
        d.insert('b', 'vb', cost=5)

        self.assertEqual(len(d), 2)
        self.assertEqual(d.popoldest(), ('a', 'va'))
        self.assertEqual(len(d), 1)
        self.assertEqual(d.totalcost, 5)
        self.assertEqual(d.popoldest(), ('b', 'vb'))
        self.assertEqual(len(d), 0)
        self.assertEqual(d.totalcost, 0)
        self.assertIsNone(d.popoldest())

        d['a'] = 'va'
        d['b'] = 'vb'
        d['c'] = 'vc'
        d['d'] = 'vd'

        self.assertEqual(d.popoldest(), ('a', 'va'))
        self.assertEqual(len(d), 3)
        for key in ('b', 'c', 'd'):
            self.assertEqual(d[key], 'v%s' % key)

        d['a'] = 'va'
        self.assertEqual(d.popoldest(), ('b', 'vb'))

    def testmaxcost(self):
        # Item cost is zero by default.
        d = util.lrucachedict(6, maxcost=10)
        d['a'] = 'va'
        d['b'] = 'vb'
        d['c'] = 'vc'
        d['d'] = 'vd'
        self.assertEqual(len(d), 4)
        self.assertEqual(d.totalcost, 0)

        d.clear()

        # Insertion to exact cost threshold works without eviction.
        d.insert('a', 'va', cost=6)
        d.insert('b', 'vb', cost=4)

        self.assertEqual(len(d), 2)
        self.assertEqual(d['a'], 'va')
        self.assertEqual(d['b'], 'vb')

        # Inserting a new element with 0 cost works.
        d['c'] = 'vc'
        self.assertEqual(len(d), 3)

        # Inserting a new element with cost putting us above high
        # water mark evicts oldest single item.
        d.insert('d', 'vd', cost=1)
        self.assertEqual(len(d), 3)
        self.assertEqual(d.totalcost, 5)
        self.assertNotIn('a', d)
        for key in ('b', 'c', 'd'):
            self.assertEqual(d[key], 'v%s' % key)

        # Inserting a new element with enough room for just itself
        # evicts all items before.
        d.insert('e', 've', cost=10)
        self.assertEqual(len(d), 1)
        self.assertEqual(d.totalcost, 10)
        self.assertIn('e', d)

        # Inserting a new element with cost greater than threshold
        # still retains that item.
        d.insert('f', 'vf', cost=11)
        self.assertEqual(len(d), 1)
        self.assertEqual(d.totalcost, 11)
        self.assertIn('f', d)

        # Inserting a new element will evict the last item since it is
        # too large.
        d['g'] = 'vg'
        self.assertEqual(len(d), 1)
        self.assertEqual(d.totalcost, 0)
        self.assertIn('g', d)

        d.clear()

        d.insert('a', 'va', cost=7)
        d.insert('b', 'vb', cost=3)
        self.assertEqual(len(d), 2)

        # Replacing a value with smaller cost won't result in eviction.
        d.insert('b', 'vb2', cost=2)
        self.assertEqual(len(d), 2)

        # Replacing a value with a higher cost will evict when threshold
        # exceeded.
        d.insert('b', 'vb3', cost=4)
        self.assertEqual(len(d), 1)
        self.assertNotIn('a', d)

    def testmaxcostcomplex(self):
        d = util.lrucachedict(100, maxcost=100)
        d.insert('a', 'va', cost=9)
        d.insert('b', 'vb', cost=21)
        d.insert('c', 'vc', cost=7)
        d.insert('d', 'vc', cost=50)
        self.assertEqual(d.totalcost, 87)

        # Inserting new element should free multiple elements so we hit
        # low water mark.
        d.insert('e', 'vd', cost=25)
        self.assertEqual(len(d), 2)
        self.assertNotIn('a', d)
        self.assertNotIn('b', d)
        self.assertNotIn('c', d)
        self.assertIn('d', d)
        self.assertIn('e', d)


if __name__ == '__main__':
    silenttestrunner.main(__name__)