hgext/pager.py
author Siddharth Agarwal <sid0@fb.com>
Wed, 25 Mar 2015 15:55:31 -0700
changeset 24461 05ccfe6763f1
parent 24067 0baf41e02a4d
child 25186 80c5b2666a96
permissions -rw-r--r--
osutil: use getdirentriesattr on OS X if possible This is a significant win for large repositories on OS X, especially with a cold cache. Unfortunately we need to keep the lstat-based implementation around for two reasons: - Not all filesystems support this call. - There's an edge case in which it's best to fall back to avoid a retry loop. More about this in the comments. The below tests are all performed on a Mac with an SSD running OS X 10.9, on a repository with over 200k files. The results are best of 5 with simulated best-effort conditions. The gains with a hot cache are pretty impressive: 'hg status' goes from 5.18 seconds to 3.79 seconds. However, a repository that large will probably already be using something like hgwatchman [1], which helps much more (for this repo, 'hg status' with hgwatchman is approximately 1 second). Where this really helps is when the cache is cold [2]: hg status goes from 31.0 seconds to 9.66. See http://lists.apple.com/archives/filesystem-dev/2014/Dec/msg00002.html for some more discussion about this function. This is based on a patch by Sean Farley <sean@farley.io>. [1] https://bitbucket.org/facebook/hgwatchman [2] There appears to be no easy way to clear the file cache (aka "vnodes") on OS X short of rebooting. purge(8) purportedly does that but in my testing had little effect. The workaround I came up with was to assume that vnode eviction was LRU, make sure the kern.maxvnodes sysctl is smaller than the size of the repository, then make sure we'd always miss the cache by running 'hg status' in another clone of the repository before running it in the test repository.

# pager.py - display output using a pager
#
# Copyright 2008 David Soria Parra <dsp@php.net>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
#
# To load the extension, add it to your configuration file:
#
#   [extension]
#   pager =
#
# Run "hg help pager" to get info on configuration.

'''browse command output with an external pager

To set the pager that should be used, set the application variable::

  [pager]
  pager = less -FRX

If no pager is set, the pager extensions uses the environment variable
$PAGER. If neither pager.pager, nor $PAGER is set, no pager is used.

You can disable the pager for certain commands by adding them to the
pager.ignore list::

  [pager]
  ignore = version, help, update

You can also enable the pager only for certain commands using
pager.attend. Below is the default list of commands to be paged::

  [pager]
  attend = annotate, cat, diff, export, glog, log, qdiff

Setting pager.attend to an empty value will cause all commands to be
paged.

If pager.attend is present, pager.ignore will be ignored.

Lastly, you can enable and disable paging for individual commands with
the attend-<command> option. This setting takes precedence over
existing attend and ignore options and defaults::

  [pager]
  attend-cat = false

To ignore global commands like :hg:`version` or :hg:`help`, you have
to specify them in your user configuration file.

The --pager=... option can also be used to control when the pager is
used. Use a boolean value like yes, no, on, off, or use auto for
normal behavior.

'''

import atexit, sys, os, signal, subprocess, errno, shlex
from mercurial import commands, dispatch, util, extensions, cmdutil
from mercurial.i18n import _

testedwith = 'internal'

def _pagerfork(ui, p):
    if not util.safehasattr(os, 'fork'):
        sys.stdout = util.popen(p, 'wb')
        if ui._isatty(sys.stderr):
            sys.stderr = sys.stdout
        return
    fdin, fdout = os.pipe()
    pid = os.fork()
    if pid == 0:
        os.close(fdin)
        os.dup2(fdout, sys.stdout.fileno())
        if ui._isatty(sys.stderr):
            os.dup2(fdout, sys.stderr.fileno())
        os.close(fdout)
        return
    os.dup2(fdin, sys.stdin.fileno())
    os.close(fdin)
    os.close(fdout)
    try:
        os.execvp('/bin/sh', ['/bin/sh', '-c', p])
    except OSError, e:
        if e.errno == errno.ENOENT:
            # no /bin/sh, try executing the pager directly
            args = shlex.split(p)
            os.execvp(args[0], args)
        else:
            raise

def _pagersubprocess(ui, p):
    pager = subprocess.Popen(p, shell=True, bufsize=-1,
                             close_fds=util.closefds, stdin=subprocess.PIPE,
                             stdout=sys.stdout, stderr=sys.stderr)

    stdout = os.dup(sys.stdout.fileno())
    stderr = os.dup(sys.stderr.fileno())
    os.dup2(pager.stdin.fileno(), sys.stdout.fileno())
    if ui._isatty(sys.stderr):
        os.dup2(pager.stdin.fileno(), sys.stderr.fileno())

    @atexit.register
    def killpager():
        if util.safehasattr(signal, "SIGINT"):
            signal.signal(signal.SIGINT, signal.SIG_IGN)
        pager.stdin.close()
        os.dup2(stdout, sys.stdout.fileno())
        os.dup2(stderr, sys.stderr.fileno())
        pager.wait()

def _runpager(ui, p):
    # The subprocess module shipped with Python <= 2.4 is buggy (issue3533).
    # The compat version is buggy on Windows (issue3225), but has been shipping
    # with hg for a long time.  Preserve existing functionality.
    if sys.version_info >= (2, 5):
        _pagersubprocess(ui, p)
    else:
        _pagerfork(ui, p)

def uisetup(ui):
    if '--debugger' in sys.argv or not ui.formatted():
        return

    def pagecmd(orig, ui, options, cmd, cmdfunc):
        p = ui.config("pager", "pager", os.environ.get("PAGER"))
        usepager = False
        always = util.parsebool(options['pager'])
        auto = options['pager'] == 'auto'

        if not p:
            pass
        elif always:
            usepager = True
        elif not auto:
            usepager = False
        else:
            attend = ui.configlist('pager', 'attend', attended)
            ignore = ui.configlist('pager', 'ignore')
            cmds, _ = cmdutil.findcmd(cmd, commands.table)

            for cmd in cmds:
                var = 'attend-%s' % cmd
                if ui.config('pager', var):
                    usepager = ui.configbool('pager', var)
                    break
                if (cmd in attend or
                     (cmd not in ignore and not attend)):
                    usepager = True
                    break

        setattr(ui, 'pageractive', usepager)

        if usepager:
            ui.setconfig('ui', 'formatted', ui.formatted(), 'pager')
            ui.setconfig('ui', 'interactive', False, 'pager')
            if util.safehasattr(signal, "SIGPIPE"):
                signal.signal(signal.SIGPIPE, signal.SIG_DFL)
            _runpager(ui, p)
        return orig(ui, options, cmd, cmdfunc)

    # Wrap dispatch._runcommand after color is loaded so color can see
    # ui.pageractive. Otherwise, if we loaded first, color's wrapped
    # dispatch._runcommand would run without having access to ui.pageractive.
    def afterloaded(loaded):
        extensions.wrapfunction(dispatch, '_runcommand', pagecmd)
    extensions.afterloaded('color', afterloaded)

def extsetup(ui):
    commands.globalopts.append(
        ('', 'pager', 'auto',
         _("when to paginate (boolean, always, auto, or never)"),
         _('TYPE')))

attended = ['annotate', 'cat', 'diff', 'export', 'glog', 'log', 'qdiff']