##// END OF EJS Templates
util: optimize cost auditing on insert...
util: optimize cost auditing on insert Calling popoldest() on insert with cost auditing enabled introduces significant overhead. The primary reason for this overhead is that popoldest() needs to walk the linked list to find the first non-empty node. When we call popoldest() within a loop, this can become quadratic. The performance impact is more pronounced on caches with large capacities. This commit effectively inlines the popoldest() call into _enforcecostlimit(). By doing so, we only do the backwards walk to find the first empty node once. However, we still may still perform this work on insert when the cache is near cost capacity. So this is only a partial performance win. $ hg perflrucachedict --size 4 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 100 ! gets w/ cost limit ! wall 0.598737 comb 0.590000 user 0.590000 sys 0.000000 (best of 17) ! inserts w/ cost limit ! wall 1.694282 comb 1.700000 user 1.700000 sys 0.000000 (best of 6) ! wall 1.659181 comb 1.650000 user 1.650000 sys 0.000000 (best of 7) ! mixed w/ cost limit ! wall 1.157655 comb 1.150000 user 1.150000 sys 0.000000 (best of 9) ! wall 1.139955 comb 1.140000 user 1.140000 sys 0.000000 (best of 9) $ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000 ! gets w/ cost limit ! wall 0.598526 comb 0.600000 user 0.600000 sys 0.000000 (best of 17) ! wall 0.601993 comb 0.600000 user 0.600000 sys 0.000000 (best of 17) ! inserts w/ cost limit ! wall 37.838315 comb 37.840000 user 37.840000 sys 0.000000 (best of 3) ! wall 25.105273 comb 25.080000 user 25.080000 sys 0.000000 (best of 3) ! mixed w/ cost limit ! wall 18.060198 comb 18.060000 user 18.060000 sys 0.000000 (best of 3) ! wall 12.104470 comb 12.070000 user 12.070000 sys 0.000000 (best of 3) $ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000 --mixedgetfreq 90 ! gets w/ cost limit ! wall 0.600024 comb 0.600000 user 0.600000 sys 0.000000 (best of 17) ! wall 0.614439 comb 0.620000 user 0.620000 sys 0.000000 (best of 17) ! inserts w/ cost limit ! wall 37.154547 comb 37.120000 user 37.120000 sys 0.000000 (best of 3) ! wall 25.963028 comb 25.960000 user 25.960000 sys 0.000000 (best of 3) ! mixed w/ cost limit ! wall 4.381602 comb 4.380000 user 4.370000 sys 0.010000 (best of 3) ! wall 3.174256 comb 3.170000 user 3.170000 sys 0.000000 (best of 4) Differential Revision: https://phab.mercurial-scm.org/D4504

File last commit:

r34436:5326e4ef default
r39605:cc23c09b 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