contrib/hg-ssh
author Pierre-Yves David <pierre-yves.david@octobus.net>
Sat, 13 Apr 2024 23:40:28 +0200
changeset 51592 24844407fa0d
parent 48875 6000f5b25c9b
permissions -rwxr-xr-x
perf: clear vfs audit_cache before each run When generating a stream clone, we spend a large amount of time auditing path. Before this changes, the first run was warming the vfs cache for the other runs, leading to a large runtime difference and a "faulty" reported timing for the operation. We now clear this important cache between run to get a more realistic timing. Below are some example of median time change when clearing these cases. The maximum time for a run did not changed significantly. ### data-env-vars.name = mozilla-central-2018-08-01-zstd-sparse-revlog # benchmark.name = hg.perf.exchange.stream.generate # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.version = latest no-clearing: 17.289905 cache-clearing: 21.587965 (+24.86%, +4.30) ## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog no-clearing: 32.670748 cache-clearing: 40.467095 (+23.86%, +7.80) ## data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog no-clearing: 37.838858 cache-clearing: 46.072749 (+21.76%, +8.23) ## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog no-clearing: 32.969395 cache-clearing: 39.646209 (+20.25%, +6.68) In addition, this significantly reduce the timing difference between the performance command, from the perf extensions and a `real `hg bundle` call producing a stream bundle. Some significant differences remain especially on the "mozilla-try" repositories, but they are now smaller. Note that some of that difference will actually not be attributable to the stream generation (like maybe phases or branch map computation). Below are some benchmarks done on a currently draft changeset fixing some unrelated slowness in `hg bundle` (34a78972af409d1ff37c29e60f6ca811ad1a457d) ### data-env-vars.name = mozilla-central-2018-08-01-zstd-sparse-revlog # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default hg.perf.exchange.stream.generate: 21.587965 hg.command.bundle: 24.301799 (+12.57%, +2.71) ## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog hg.perf.exchange.stream.generate: 40.467095 hg.command.bundle: 44.831317 (+10.78%, +4.36) ## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog hg.perf.exchange.stream.generate: 39.646209 hg.command.bundle: 45.395258 (+14.50%, +5.75) ## data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog hg.perf.exchange.stream.generate: 46.072749 hg.command.bundle: 55.882608 (+21.29%, +9.81) ## data-env-vars.name = mozilla-try-2023-03-22-zlib-general-delta hg.perf.exchange.stream.generate: 334.716708 hg.command.bundle: 377.856767 (+12.89%, +43.14) ## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog hg.perf.exchange.stream.generate: 302.972301 hg.command.bundle: 326.098755 (+7.63%, +23.13)

#!/usr/bin/env python3
#
# Copyright 2005-2007 by Intevation GmbH <intevation@intevation.de>
#
# Author(s):
# Thomas Arendsen Hein <thomas@intevation.de>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

"""
hg-ssh - a wrapper for ssh access to a limited set of mercurial repos

To be used in ~/.ssh/authorized_keys with the "command" option, see sshd(8):
command="hg-ssh path/to/repo1 /path/to/repo2 ~/repo3 ~user/repo4" ssh-dss ...
(probably together with these other useful options:
 no-port-forwarding,no-X11-forwarding,no-agent-forwarding)

This allows pull/push over ssh from/to the repositories given as arguments.

If all your repositories are subdirectories of a common directory, you can
allow shorter paths with:
command="cd path/to/my/repositories && hg-ssh repo1 subdir/repo2"

You can use pattern matching of your normal shell, e.g.:
command="cd repos && hg-ssh user/thomas/* projects/{mercurial,foo}"

You can also add a --read-only flag to allow read-only access to a key, e.g.:
command="hg-ssh --read-only repos/*"
"""

import os
import re
import shlex
import sys

# enable importing on demand to reduce startup time
import hgdemandimport

hgdemandimport.enable()

from mercurial import (
    dispatch,
    pycompat,
    ui as uimod,
)


def main():
    # Prevent insertion/deletion of CRs
    dispatch.initstdio()

    cwd = os.getcwd()
    if os.name == 'nt':
        # os.getcwd() is inconsistent on the capitalization of the drive
        # letter, so adjust it. see https://bugs.python.org/issue40368
        if re.match('^[a-z]:', cwd):
            cwd = cwd[0:1].upper() + cwd[1:]

    readonly = False
    args = sys.argv[1:]
    while len(args):
        if args[0] == '--read-only':
            readonly = True
            args.pop(0)
        else:
            break
    allowed_paths = [
        os.path.normpath(os.path.join(cwd, os.path.expanduser(path)))
        for path in args
    ]
    orig_cmd = os.getenv('SSH_ORIGINAL_COMMAND', '?')
    try:
        cmdargv = shlex.split(orig_cmd)
    except ValueError as e:
        sys.stderr.write('Illegal command "%s": %s\n' % (orig_cmd, e))
        sys.exit(255)

    if cmdargv[:2] == ['hg', '-R'] and cmdargv[3:] == ['serve', '--stdio']:
        path = cmdargv[2]
        repo = os.path.normpath(os.path.join(cwd, os.path.expanduser(path)))
        if repo in allowed_paths:
            cmd = [b'-R', pycompat.fsencode(repo), b'serve', b'--stdio']
            req = dispatch.request(cmd)
            if readonly:
                if not req.ui:
                    req.ui = uimod.ui.load()
                req.ui.setconfig(
                    b'hooks',
                    b'pretxnopen.hg-ssh',
                    b'python:__main__.rejectpush',
                    b'hg-ssh',
                )
                req.ui.setconfig(
                    b'hooks',
                    b'prepushkey.hg-ssh',
                    b'python:__main__.rejectpush',
                    b'hg-ssh',
                )
            dispatch.dispatch(req)
        else:
            sys.stderr.write('Illegal repository "%s"\n' % repo)
            sys.exit(255)
    else:
        sys.stderr.write('Illegal command "%s"\n' % orig_cmd)
        sys.exit(255)


def rejectpush(ui, **kwargs):
    ui.warn((b"Permission denied\n"))
    # mercurial hooks use unix process conventions for hook return values
    # so a truthy return means failure
    return True


if __name__ == '__main__':
    main()