##// END OF EJS Templates
narrow: intersect provided matcher with narrowmatcher in `hg diff`...
narrow: intersect provided matcher with narrowmatcher in `hg diff` This provides significant speedups when running diff, and no change in behavior that I'm aware of (or that the tests found). I tested with a repo that I started using narrow in after it was created and attempted to run `hg diff -c .` and similar commands in it on a commit that had files not in the narrowspec. Timing numbers below, using a similar setup as my previous commits. before=9db85644, m-u is mozilla-unified at eb39298e432d (flatmanifest) and 0553b7f29eaf (treemanifest). l-d-r is a repo simulating a situation I've encountered where there's one directory with 30k+ subdirectories. N means narrow, T means treemanifest. The narrowspec is pretty small when in use, and importantly the narrowspec is applied *after* doing the initial checkout (without narrowing), so all of these files exist in the filesystem, which is not normally the case if someone has been using narrow for the entire life of the clone. Anything less than a 5% difference in performance is most likely noise. diff --git: repo | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before ------+---+---+------------------------+-----------------------+------------ m-u | | | 1.292 s +- 0.009 s | 1.295 s +- 0.010 s | 100.2% m-u | | x | 1.296 s +- 0.042 s | 1.299 s +- 0.026 s | 100.2% m-u | x | | 1.292 s +- 0.010 s | 1.297 s +- 0.021 s | 100.4% m-u | x | x | 84.2 ms +- 1.2 ms | 83.6 ms +- 0.2 ms | 99.3% l-d-r | | | 188.7 ms +- 2.7 ms | 188.8 ms +- 2.0 ms | 100.1% l-d-r | | x | 189.9 ms +- 1.5 ms | 189.4 ms +- 1.2 ms | 99.7% l-d-r | x | | 97.1 ms +- 1.0 ms | 87.1 ms +- 1.0 ms | 89.7% <-- l-d-r | x | x | 96.9 ms +- 0.8 ms | 87.2 ms +- 0.7 ms | 90.0% <-- diff -c . --git: repo | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before ------+---+---+------------------------+-----------------------+------------ m-u | | | 231.6 ms +- 3.1 ms | 228.9 ms +- 1.6 ms | 98.8% m-u | | x | 150.5 ms +- 1.7 ms | 150.7 ms +- 1.4 ms | 100.1% m-u | x | | 233.7 ms +- 2.4 ms | 232.2 ms +- 1.9 ms | 99.4% m-u | x | x | 126.1 ms +- 1.2 ms | 126.8 ms +- 1.2 ms | 100.6% l-d-r | | | 82.1 ms +- 2.0 ms | 81.8 ms +- 1.4 ms | 99.6% l-d-r | | x | 3.732 s +- 0.020 s | 3.746 s +- 0.027 s | 100.4% l-d-r | x | | 83.1 ms +- 0.8 ms | 107.6 ms +- 2.4 ms | 129.5% <-- l-d-r | x | x | 758.2 ms +- 38.8 ms | 188.5 ms +- 1.8 ms | 24.9% <-- rebase -r . --keep -d .^^: repo | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before ------+---+---+------------------------+-----------------------+------------ m-u | | | 5.532 s +- 0.087 s | 5.496 s +- 0.016 s | 99.3% m-u | | x | 5.554 s +- 0.061 s | 5.532 s +- 0.013 s | 99.6% m-u | x | | 5.602 s +- 0.134 s | 5.508 s +- 0.035 s | 98.3% m-u | x | x | 582.2 ms +- 15.2 ms | 572.9 ms +- 12.0 ms | 98.4% l-d-r | | | 629.5 ms +- 12.3 ms | 622.5 ms +- 7.3 ms | 98.9% l-d-r | | x | 6.173 s +- 0.062 s | 6.185 s +- 0.076 s | 100.2% l-d-r | x | | 274.5 ms +- 10.0 ms | 272.1 ms +- 6.2 ms | 99.1% l-d-r | x | x | 4.835 s +- 0.056 s | 4.826 s +- 0.034 s | 99.8% status --change . --copies: repo | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before ------+---+---+------------------------+-----------------------+------------ m-u | | | 214.4 ms +- 1.4 ms | 212.2 ms +- 1.7 ms | 99.0% m-u | | x | 130.9 ms +- 1.2 ms | 131.7 ms +- 1.1 ms | 100.6% m-u | x | | 215.0 ms +- 2.1 ms | 214.9 ms +- 2.7 ms | 100.0% m-u | x | x | 109.5 ms +- 2.3 ms | 107.8 ms +- 0.9 ms | 98.4% l-d-r | | | 79.6 ms +- 0.9 ms | 79.8 ms +- 1.6 ms | 100.3% l-d-r | | x | 3.799 s +- 0.037 s | 3.928 s +- 0.021 s | 103.4% <--? l-d-r | x | | 82.7 ms +- 0.7 ms | 83.2 ms +- 1.0 ms | 100.6% l-d-r | x | x | 746.8 ms +- 6.1 ms | 739.0 ms +- 4.2 ms | 99.0% status --copies: repo | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before ------+---+---+------------------------+-----------------------+------------ m-u | | | 1.884 s +- 0.012 s | 1.885 s +- 0.013 s | 100.1% m-u | | x | 1.897 s +- 0.027 s | 1.909 s +- 0.077 s | 100.6% m-u | x | | 1.886 s +- 0.021 s | 1.891 s +- 0.030 s | 100.3% m-u | x | x | 92.0 ms +- 0.7 ms | 92.4 ms +- 0.4 ms | 100.4% l-d-r | | | 570.3 ms +- 18.7 ms | 552.2 ms +- 4.5 ms | 96.8% l-d-r | | x | 568.9 ms +- 16.1 ms | 567.2 ms +- 11.9 ms | 99.7% l-d-r | x | | 171.1 ms +- 2.5 ms | 170.4 ms +- 1.2 ms | 99.6% l-d-r | x | x | 171.6 ms +- 3.4 ms | 171.5 ms +- 1.7 ms | 99.9% update $rev^; ~/src/hg/hg{hg}/hg update $rev: repo | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before ------+---+---+------------------------+-----------------------+------------ m-u | | | 3.107 s +- 0.017 s | 3.116 s +- 0.012 s | 100.3% m-u | | x | 2.943 s +- 0.010 s | 2.945 s +- 0.019 s | 100.1% m-u | x | | 3.116 s +- 0.033 s | 3.118 s +- 0.027 s | 100.1% m-u | x | x | 318.5 ms +- 2.7 ms | 320.8 ms +- 4.8 ms | 100.7% l-d-r | | | 428.9 ms +- 4.4 ms | 429.5 ms +- 4.0 ms | 100.1% l-d-r | | x | 9.593 s +- 0.081 s | 9.869 s +- 0.043 s | 102.9% l-d-r | x | | 253.2 ms +- 3.6 ms | 254.0 ms +- 2.8 ms | 100.3% l-d-r | x | x | 1.613 s +- 0.009 s | 1.630 s +- 0.017 s | 101.1% Differential Revision: https://phab.mercurial-scm.org/D4587

File last commit:

r34436:5326e4ef default
r39663:ee7ee0c5 default
Show More
mpatch.py
128 lines | 3.3 KiB | text/x-python | PythonLexer
# mpatch.py - Python implementation of mpatch.c
#
# Copyright 2009 Matt Mackall <mpm@selenic.com> and others
#
# 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
import struct
from .. import pycompat
stringio = pycompat.bytesio
class mpatchError(Exception):
"""error raised when a delta cannot be decoded
"""
# This attempts to apply a series of patches in time proportional to
# the total size of the patches, rather than patches * len(text). This
# means rather than shuffling strings around, we shuffle around
# pointers to fragments with fragment lists.
#
# When the fragment lists get too long, we collapse them. To do this
# efficiently, we do all our operations inside a buffer created by
# mmap and simply use memmove. This avoids creating a bunch of large
# temporary string buffers.
def _pull(dst, src, l): # pull l bytes from src
while l:
f = src.pop()
if f[0] > l: # do we need to split?
src.append((f[0] - l, f[1] + l))
dst.append((l, f[1]))
return
dst.append(f)
l -= f[0]
def _move(m, dest, src, count):
"""move count bytes from src to dest
The file pointer is left at the end of dest.
"""
m.seek(src)
buf = m.read(count)
m.seek(dest)
m.write(buf)
def _collect(m, buf, list):
start = buf
for l, p in reversed(list):
_move(m, buf, p, l)
buf += l
return (buf - start, start)
def patches(a, bins):
if not bins:
return a
plens = [len(x) for x in bins]
pl = sum(plens)
bl = len(a) + pl
tl = bl + bl + pl # enough for the patches and two working texts
b1, b2 = 0, bl
if not tl:
return a
m = stringio()
# load our original text
m.write(a)
frags = [(len(a), b1)]
# copy all the patches into our segment so we can memmove from them
pos = b2 + bl
m.seek(pos)
for p in bins:
m.write(p)
for plen in plens:
# if our list gets too long, execute it
if len(frags) > 128:
b2, b1 = b1, b2
frags = [_collect(m, b1, frags)]
new = []
end = pos + plen
last = 0
while pos < end:
m.seek(pos)
try:
p1, p2, l = struct.unpack(">lll", m.read(12))
except struct.error:
raise mpatchError("patch cannot be decoded")
_pull(new, frags, p1 - last) # what didn't change
_pull([], frags, p2 - p1) # what got deleted
new.append((l, pos + 12)) # what got added
pos += l + 12
last = p2
frags.extend(reversed(new)) # what was left at the end
t = _collect(m, b2, frags)
m.seek(t[1])
return m.read(t[0])
def patchedsize(orig, delta):
outlen, last, bin = 0, 0, 0
binend = len(delta)
data = 12
while data <= binend:
decode = delta[bin:bin + 12]
start, end, length = struct.unpack(">lll", decode)
if start > end:
break
bin = data + length
data = bin + 12
outlen += start - last
last = end
outlen += length
if bin != binend:
raise mpatchError("patch cannot be decoded")
outlen += orig - last
return outlen