view contrib/undumprevlog @ 17962:4c29668ca316 stable

util: make chunkbuffer non-quadratic on Windows

The old str-based += collector performed very nicely on Linux, but
turns out to be quadratically expensive on Windows, causing
chunkbuffer to dominate in profiles.

This list-based version has been measured to significantly improve
performance with large chunks on Windows, with negligible overall
overhead on Linux (though microbenchmarks show it to be about 50% slower).

This may increase memory overhead where += didn't behave quadratically. If we
want to gather up 1G of data to join, we temporarily have 1G in our
list and 1G in our string.

#!/usr/bin/env python
# Undump a dump from dumprevlog
# $ hg init
# $ undumprevlog < repo.dump

import sys
from mercurial import revlog, node, scmutil, util, transaction

for fp in (sys.stdin, sys.stdout, sys.stderr):
    util.setbinary(fp)

opener = scmutil.opener('.', False)
tr = transaction.transaction(sys.stderr.write, opener, "undump.journal")
while 1:
    l = sys.stdin.readline()
    if not l:
        break
    if l.startswith("file:"):
        f = l[6:-1]
        r = revlog.revlog(opener, f)
        print f
    elif l.startswith("node:"):
        n = node.bin(l[6:-1])
    elif l.startswith("linkrev:"):
        lr = int(l[9:-1])
    elif l.startswith("parents:"):
        p = l[9:-1].split()
        p1 = node.bin(p[0])
        p2 = node.bin(p[1])
    elif l.startswith("length:"):
        length = int(l[8:-1])
        sys.stdin.readline() # start marker
        d = sys.stdin.read(length)
        sys.stdin.readline() # end marker
        r.addrevision(d, tr, lr, p1, p2)

tr.close()