tests/test-filelog.py
author Gregory Szorc <gregory.szorc@gmail.com>
Sun, 20 Nov 2016 16:56:21 -0800
changeset 30461 d195fa651b51
parent 29205 a0939666b836
child 30559 d83ca854fa21
permissions -rwxr-xr-x
bdiff: don't check border condition in loop This is pretty much a copy of d500ddae7494, just to a different loop. The condition `p == plast` (`plast == a + len - 1`) was only true on the final iteration of the loop. So it was wasteful to check for it on every iteration. We decrease the iteration count by 1 and add an explicit check for `p == plast` after the loop. Again, we see modest wins. From the mozilla-unified repository: $ perfbdiff -m 3041e4d59df2 ! wall 0.035502 comb 0.040000 user 0.040000 sys 0.000000 (best of 100) ! wall 0.030480 comb 0.030000 user 0.030000 sys 0.000000 (best of 100) $ perfbdiff 0e9928989e9c --alldata --count 100 ! wall 4.097394 comb 4.100000 user 4.100000 sys 0.000000 (best of 3) ! wall 3.597798 comb 3.600000 user 3.600000 sys 0.000000 (best of 3) The 2nd example throws a total of ~3.3GB of data at bdiff. This change increases the throughput from ~811 MB/s to ~924 MB/s.

#!/usr/bin/env python
"""
Tests the behavior of filelog w.r.t. data starting with '\1\n'
"""
from __future__ import absolute_import, print_function

from mercurial.node import (
    hex,
    nullid,
)
from mercurial import (
    hg,
    ui as uimod,
)

myui = uimod.ui()
repo = hg.repository(myui, path='.', create=True)

fl = repo.file('foobar')

def addrev(text, renamed=False):
    if renamed:
        # data doesn't matter. Just make sure filelog.renamed() returns True
        meta = {'copyrev': hex(nullid), 'copy': 'bar'}
    else:
        meta = {}

    lock = t = None
    try:
        lock = repo.lock()
        t = repo.transaction('commit')
        node = fl.add(text, meta, t, 0, nullid, nullid)
        return node
    finally:
        if t:
            t.close()
        if lock:
            lock.release()

def error(text):
    print('ERROR: ' + text)

textwith = '\1\nfoo'
without = 'foo'

node = addrev(textwith)
if not textwith == fl.read(node):
    error('filelog.read for data starting with \\1\\n')
if fl.cmp(node, textwith) or not fl.cmp(node, without):
    error('filelog.cmp for data starting with \\1\\n')
if fl.size(0) != len(textwith):
    error('FIXME: This is a known failure of filelog.size for data starting '
        'with \\1\\n')

node = addrev(textwith, renamed=True)
if not textwith == fl.read(node):
    error('filelog.read for a renaming + data starting with \\1\\n')
if fl.cmp(node, textwith) or not fl.cmp(node, without):
    error('filelog.cmp for a renaming + data starting with \\1\\n')
if fl.size(1) != len(textwith):
    error('filelog.size for a renaming + data starting with \\1\\n')

print('OK.')