Mercurial > hg > mercurial-crew-with-dirclash
view tests/test-parseindex @ 2577:fa76c5d609c9
bdiff: improve worst case behavior by 100x.
on 5.8MB (244.000 lines) text file with similar lines, hash before
this change made diff against empty file take 75 seconds. this change
improves performance to 0.6 seconds. result is that clone of smallish
repo (137MB) with some files like this takes 1 minute instead of 10
minutes.
common case of diff is 10% slower now, probably because of worse cache
locality. but diff does not affect overall performance in common case
(less than 1% of runtime is in diff when it is working ok), so this
tradeoff looks good.
author | Vadim Gelfer <vadim.gelfer@gmail.com> |
---|---|
date | Fri, 07 Jul 2006 15:02:55 -0700 |
parents | 6563438219e3 |
children | c0b449154a90 |
line wrap: on
line source
#!/bin/sh # # revlog.parseindex must be able to parse the index file even if # an index entry is split between two 64k blocks. The ideal test # would be to create an index file with inline data where # 64k < size < 64k + 64 (64k is the size of the read buffer, 64 is # the size of an index entry) and with an index entry starting right # before the 64k block boundary, and try to read it. # # We approximate that by reducing the read buffer to 1 byte. # hg init a cd a echo abc > foo hg add foo hg commit -m 'add foo' -d '1000000 0' echo >> foo hg commit -m 'change foo' -d '1000001 0' hg log -r 0: cat >> test.py << EOF from mercurial import changelog, util from mercurial.node import * class singlebyteread(object): def __init__(self, real): self.real = real def read(self, size=-1): if size == 65536: size = 1 return self.real.read(size) def __getattr__(self, key): return getattr(self.real, key) def opener(*args): o = util.opener(*args) def wrapper(*a): f = o(*a) return singlebyteread(f) return wrapper cl = changelog.changelog(opener('.hg')) print cl.count(), 'revisions:' for r in xrange(cl.count()): print short(cl.node(r)) EOF python test.py