Mercurial > hg > mercurial-crew-with-dirclash
view tests/test-parseindex @ 5451:0a43875677b1
revlog: break up compression of large deltas
Python's zlib apparently makes an internal copy of strings passed to
compress(). To avoid this, compress strings 1M at a time, then join
them at the end if the result would be smaller than the original.
For initial commits of large but compressible files, this cuts peak
memory usage nearly in half.
author | Matt Mackall <mpm@selenic.com> |
---|---|
date | Thu, 11 Oct 2007 00:46:54 -0500 |
parents | c0b449154a90 |
children |
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/store')) print cl.count(), 'revisions:' for r in xrange(cl.count()): print short(cl.node(r)) EOF python test.py