contrib/casesmash.py

revlog: read/cache chunks in fixed windows of 64 KB

When reading a revlog chunk, instead of reading up to 64 KB ahead of the
request offset and caching that, this change caches a fixed window before
and after the requested data that falls on 64 KB boundaries. This increases
cache hits when reading revlogs backwards.

Running perfmoonwalk on the Mercurial repo (with almost 20,000 changesets) on
Mac OS X with an SSD, before this change:

$ hg perfmoonwalk
! wall 2.307994 comb 2.310000 user 2.120000 sys 0.190000 (best of 5)

(Each run has 10,668 cache hits and 9,304 misses.)

After this change:

$ hg perfmoonwalk
! wall 1.814117 comb 1.810000 user 1.810000 sys 0.000000 (best of 6)

(19,931 cache hits, 62 misses.)

On a busy NFS share, before this change:

$ hg perfmoonwalk
! wall 17.000034 comb 4.100000 user 3.270000 sys 0.830000 (best of 3)

After:

$ hg perfmoonwalk
! wall 1.746115 comb 1.670000 user 1.660000 sys 0.010000 (best of 5)

import os, __builtin__
from mercurial import util

def lowerwrap(scope, funcname):
    f = getattr(scope, funcname)
    def wrap(fname, *args, **kwargs):
        d, base = os.path.split(fname)
        try:
            files = os.listdir(d or '.')
        except OSError:
            files = []
        if base in files:
            return f(fname, *args, **kwargs)
        for fn in files:
            if fn.lower() == base.lower():
                return f(os.path.join(d, fn), *args, **kwargs)
        return f(fname, *args, **kwargs)
    scope.__dict__[funcname] = wrap

def normcase(path):
    return path.lower()

os.path.normcase = normcase

for f in 'file open'.split():
    lowerwrap(__builtin__, f)

for f in "chmod chown open lstat stat remove unlink".split():
    lowerwrap(os, f)

for f in "exists lexists".split():
    lowerwrap(os.path, f)

lowerwrap(util, 'posixfile')