view contrib/undumprevlog @ 40999:dcac24ec935b

commandserver: preload repository in master server and reuse its file cache

This greatly speeds up repository operation with lots of obsolete markers:

  $ ls -lh .hg/store/obsstore
  -rw-r--r-- 1 yuya yuya 21M Dec  2 17:55 .hg/store/obsstore
  $ time hg log -G -l10 --pager no
  (hg)           1.79s user 0.13s system 99% cpu 1.919 total
  (chg uncached) 0.00s user 0.01s system 0% cpu 1.328 total
  (chg cached)   0.00s user 0.00s system 3% cpu 0.180 total

As you can see, the implementation of the preloader function is highly
experimental. It works, but I'm yet to be sure how things can be organized.
So I don't want to formalize the API at this point.

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

from __future__ import absolute_import, print_function

import sys
from mercurial import (
    encoding,
    node,
    pycompat,
    revlog,
    transaction,
    vfs as vfsmod,
)
from mercurial.utils import (
    procutil,
)

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

opener = vfsmod.vfs(b'.', False)
tr = transaction.transaction(sys.stderr.write, opener, {b'store': opener},
                             b"undump.journal")
while True:
    l = sys.stdin.readline()
    if not l:
        break
    if l.startswith("file:"):
        f = encoding.strtolocal(l[6:-1])
        r = revlog.revlog(opener, f)
        pycompat.stdout.write(b'%s\n' % 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 = encoding.strtolocal(sys.stdin.read(length))
        sys.stdin.readline() # end marker
        r.addrevision(d, tr, lr, p1, p2)

tr.close()