tests/md5sum.py

merge: apply non-interactive working dir updates in parallel

This has a big effect on the performance of working dir updates.

Here are the results of update from null to the given rev in several
repos, on a Linux 3.2 system with 32 cores running ext4, with the progress
extension enabled.

repo             rev           plain  parallel   speedup
hg               7068089c95a2    0.9       0.3       3
mozilla-central  fe1600b22c77   42.8       7.7       5.5
linux-2.6        9ef4b770e069   31.4       4.9       6.4

#!/usr/bin/env python
#
# Based on python's Tools/scripts/md5sum.py
#
# This software may be used and distributed according to the terms
# of the PYTHON SOFTWARE FOUNDATION LICENSE VERSION 2, which is
# GPL-compatible.

import sys, os

try:
    from hashlib import md5
except ImportError:
    from md5 import md5

try:
    import msvcrt
    msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
    msvcrt.setmode(sys.stderr.fileno(), os.O_BINARY)
except ImportError:
    pass

for filename in sys.argv[1:]:
    try:
        fp = open(filename, 'rb')
    except IOError, msg:
        sys.stderr.write('%s: Can\'t open: %s\n' % (filename, msg))
        sys.exit(1)

    m = md5()
    try:
        while True:
            data = fp.read(8192)
            if not data:
                break
            m.update(data)
    except IOError, msg:
        sys.stderr.write('%s: I/O error: %s\n' % (filename, msg))
        sys.exit(1)
    sys.stdout.write('%s  %s\n' % (m.hexdigest(), filename))

sys.exit(0)