view contrib/undumprevlog @ 47346:f27f2afb15da

dirstate-tree: Skip readdir() in `hg status -mard`

When running the status algorithm in a mode where we don’t list unknown
or ignored files, all we care about are files that are listed in the dirstate.
We can there for skip making expensive calls to readdir() to list the contents
of filesystem directories, and instead only run stat() to get the filesystem
state of files listed in the dirstate. (This state may be an error for files
that don’t exist anymore on the filesystem.)

On 16 CPU threads, this reduces the time spent in the `status()` function for
`hg status -mard` on an old snapshot of mozilla-central from ~70ms to ~50ms.

Differential Revision: https://phab.mercurial-scm.org/D10752

#!/usr/bin/env python3
# Undump a dump from dumprevlog
# $ hg init
# $ undumprevlog < repo.dump

from __future__ import absolute_import, print_function

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

from mercurial.revlogutils import (
    constants as revlog_constants,
)

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])
        assert f.endswith(b'.i')
        r = revlog.revlog(
            opener,
            target=(revlog_constants.KIND_OTHER, b'undump-revlog'),
            radix=f[:-2],
        )
        procutil.stdout.write(b'%s\n' % f)
    elif l.startswith("node:"):
        n = bin(l[6:-1])
    elif l.startswith("linkrev:"):
        lr = int(l[9:-1])
    elif l.startswith("parents:"):
        p = l[9:-1].split()
        p1 = bin(p[0])
        p2 = 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()