##// END OF EJS Templates
perf: benchmark command for revlog indexes...
perf: benchmark command for revlog indexes We didn't have explicit microbenchmark coverage for loading revlog indexes. That seems like a useful thing to have, so let's add it. We currently measure the low-level nodemap APIs. There is room to hook in at the actual revlog layer. This could be done as a follow-up. The hackiest thing about this patch is specifying revlog paths. Other commands have arguments that allow resolution of changelog, manifest, and filelog. I needed to hook in at a lower level of the revlog API than what the existing helper functions to resolve revlogs allowed. I was too lazy to write some new APIs. This could be done as a follow-up easily enough. Example output for `hg perfrevlogindex 00changelog.i` on my Firefox repo (404418 revisions): ! revlog constructor ! wall 0.003106 comb 0.000000 user 0.000000 sys 0.000000 (best of 912) ! read ! wall 0.003077 comb 0.000000 user 0.000000 sys 0.000000 (best of 924) ! create index object ! wall 0.000000 comb 0.000000 user 0.000000 sys 0.000000 (best of 1803994) ! retrieve index entry for rev 0 ! wall 0.000193 comb 0.000000 user 0.000000 sys 0.000000 (best of 14037) ! look up missing node ! wall 0.003313 comb 0.000000 user 0.000000 sys 0.000000 (best of 865) ! look up node at rev 0 ! wall 0.003295 comb 0.010000 user 0.010000 sys 0.000000 (best of 858) ! look up node at 1/4 len ! wall 0.002598 comb 0.010000 user 0.010000 sys 0.000000 (best of 1103) ! look up node at 1/2 len ! wall 0.001909 comb 0.000000 user 0.000000 sys 0.000000 (best of 1507) ! look up node at 3/4 len ! wall 0.001213 comb 0.000000 user 0.000000 sys 0.000000 (best of 2275) ! look up node at tip ! wall 0.000453 comb 0.000000 user 0.000000 sys 0.000000 (best of 5697) ! look up all nodes (forward) ! wall 0.094615 comb 0.100000 user 0.100000 sys 0.000000 (best of 100) ! look up all nodes (reverse) ! wall 0.045889 comb 0.050000 user 0.050000 sys 0.000000 (best of 100) ! retrieve all index entries (forward) ! wall 0.078398 comb 0.080000 user 0.060000 sys 0.020000 (best of 100) ! retrieve all index entries (reverse) ! wall 0.079376 comb 0.080000 user 0.070000 sys 0.010000 (best of 100)

File last commit:

r32512:0e8b0b9a default
r32532:e4f51462 default
Show More
mpatch.py
127 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.stringio
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