##// END OF EJS Templates
revbranchcache: populate cache incrementally...
revbranchcache: populate cache incrementally Previously the cache would populate completely the first time it was accessed. This could take over a minute on larger repos. This patch changes it to update incrementally. Only values that are read will be written, and it will only rewrite as much of the file as strictly necessary. This adds a magic value of '\0\0\0\0' to represent an empty cache entry. The probability of this matching an actual commit hash prefix is tiny, so it's ok if that's always considered a cache miss. This is also BC safe since any existing entries with '\0\0\0\0' will just be considered misses. Perf numbers: Mozilla-central: hg --time log -r 'branch(mobile)' -T. Cold Cache: 14.7s -> 15.1s (3% worse) Warm Cache: 1.6s -> 2.1s (30% worse) Mozilla-cental: hg perfbranchmap 2s -> 2.4s (20% worse) hg: hg log -r 'branch(stable) & branch(default)' Cold Cache: 3.1s -> 1.9s (40% better - because the old code missed the cache on both branch() revset iterations, so it did twice the work) Warm Cache: 0.2 -> 0.26 (30% worse) internal huge repo: hg --time log -r 'tip & branch(default)' Cold Cache: 65.4s -> 0.2s (327x better) While this change introduces minor regressions when iterating over every commit in a branch, it massively improves the cold cache time for operations which touch a single commit. I feel the better O() is worth it in this case.

File last commit:

r24215:feddc528 default
r24376:203a078d default
Show More
parsers.py
112 lines | 3.2 KiB | text/x-python | PythonLexer
# parsers.py - Python implementation of parsers.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 mercurial.node import nullid
from mercurial import util
import struct, zlib, cStringIO
_pack = struct.pack
_unpack = struct.unpack
_compress = zlib.compress
_decompress = zlib.decompress
_sha = util.sha1
# Some code below makes tuples directly because it's more convenient. However,
# code outside this module should always use dirstatetuple.
def dirstatetuple(*x):
# x is a tuple
return x
def parse_index2(data, inline):
def gettype(q):
return int(q & 0xFFFF)
def offset_type(offset, type):
return long(long(offset) << 16 | type)
indexformatng = ">Qiiiiii20s12x"
s = struct.calcsize(indexformatng)
index = []
cache = None
off = 0
l = len(data) - s
append = index.append
if inline:
cache = (0, data)
while off <= l:
e = _unpack(indexformatng, data[off:off + s])
append(e)
if e[1] < 0:
break
off += e[1] + s
else:
while off <= l:
e = _unpack(indexformatng, data[off:off + s])
append(e)
off += s
if off != len(data):
raise ValueError('corrupt index file')
if index:
e = list(index[0])
type = gettype(e[0])
e[0] = offset_type(0, type)
index[0] = tuple(e)
# add the magic null revision at -1
index.append((0, 0, 0, -1, -1, -1, -1, nullid))
return index, cache
def parse_dirstate(dmap, copymap, st):
parents = [st[:20], st[20: 40]]
# dereference fields so they will be local in loop
format = ">cllll"
e_size = struct.calcsize(format)
pos1 = 40
l = len(st)
# the inner loop
while pos1 < l:
pos2 = pos1 + e_size
e = _unpack(">cllll", st[pos1:pos2]) # a literal here is faster
pos1 = pos2 + e[4]
f = st[pos2:pos1]
if '\0' in f:
f, c = f.split('\0')
copymap[f] = c
dmap[f] = e[:4]
return parents
def pack_dirstate(dmap, copymap, pl, now):
now = int(now)
cs = cStringIO.StringIO()
write = cs.write
write("".join(pl))
for f, e in dmap.iteritems():
if e[0] == 'n' and e[3] == now:
# The file was last modified "simultaneously" with the current
# write to dirstate (i.e. within the same second for file-
# systems with a granularity of 1 sec). This commonly happens
# for at least a couple of files on 'update'.
# The user could change the file without changing its size
# within the same second. Invalidate the file's mtime in
# dirstate, forcing future 'status' calls to compare the
# contents of the file if the size is the same. This prevents
# mistakenly treating such files as clean.
e = dirstatetuple(e[0], e[1], e[2], -1)
dmap[f] = e
if f in copymap:
f = "%s\0%s" % (f, copymap[f])
e = _pack(">cllll", e[0], e[1], e[2], e[3], len(f))
write(e)
write(f)
return cs.getvalue()