view mercurial/cffi/osutil.py @ 39270:37e56607cbb9

lfs: add a progress bar when searching for blobs to upload

The search itself can take an extreme amount of time if there are a lot of
revisions involved.  I've got a local repo that took 6 minutes to push 1850
commits, and 60% of that time was spent here (there are ~70K files):

     \ 58.1%  wrapper.py:     extractpointers      line 297:  pointers = extractpointers(...
       | 57.7%  wrapper.py:     pointersfromctx    line 352:  for p in pointersfromctx(ct...
       | 57.4%  wrapper.py:     pointerfromctx     line 397:  p = pointerfromctx(ctx, f, ...
         \ 38.7%  context.py:     __contains__     line 368:  if f not in ctx:
           | 38.7%  util.py:        __get__        line 82:  return key in self._manifest
           | 38.7%  context.py:     _manifest      line 1416:  result = self.func(obj)
           | 38.7%  manifest.py:    read           line 472:  return self._manifestctx.re...
             \ 25.6%  revlog.py:      revision     line 1562:  text = rl.revision(self._node)
               \ 12.8%  revlog.py:      _chunks    line 2217:  bins = self._chunks(chain, ...
                 | 12.0%  revlog.py:      decompressline 2112:  ladd(decomp(buffer(data, ch...
               \  7.8%  revlog.py:      checkhash  line 2232:  self.checkhash(text, node, ...
                 |  7.8%  revlog.py:      hash     line 2315:  if node != self.hash(text, ...
                 |  7.8%  revlog.py:      hash     line 2242:  return hash(text, p1, p2)
             \ 12.0%  manifest.py:    __init__     line 1565:  self._data = manifestdict(t...
         \ 16.8%  context.py:     filenode         line 378:  if not _islfs(fctx.filelog(...
           | 15.7%  util.py:        __get__        line 706:  return self._filelog
           | 14.8%  context.py:     _filelog       line 1416:  result = self.func(obj)
           | 14.8%  localrepo.py:   file           line 629:  return self._repo.file(self...
           | 14.8%  filelog.py:     __init__       line 1134:  return filelog.filelog(self...
           | 14.5%  revlog.py:      __init__       line 24:  censorable=True)

# osutil.py - CFFI version of osutil.c
#
# Copyright 2016 Maciej Fijalkowski <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import os
import stat as statmod

from ..pure.osutil import *

from .. import (
    pycompat,
)

if pycompat.isdarwin:
    from . import _osutil

    ffi = _osutil.ffi
    lib = _osutil.lib

    listdir_batch_size = 4096
    # tweakable number, only affects performance, which chunks
    # of bytes do we get back from getattrlistbulk

    attrkinds = [None] * 20 # we need the max no for enum VXXX, 20 is plenty

    attrkinds[lib.VREG] = statmod.S_IFREG
    attrkinds[lib.VDIR] = statmod.S_IFDIR
    attrkinds[lib.VLNK] = statmod.S_IFLNK
    attrkinds[lib.VBLK] = statmod.S_IFBLK
    attrkinds[lib.VCHR] = statmod.S_IFCHR
    attrkinds[lib.VFIFO] = statmod.S_IFIFO
    attrkinds[lib.VSOCK] = statmod.S_IFSOCK

    class stat_res(object):
        def __init__(self, st_mode, st_mtime, st_size):
            self.st_mode = st_mode
            self.st_mtime = st_mtime
            self.st_size = st_size

    tv_sec_ofs = ffi.offsetof("struct timespec", "tv_sec")
    buf = ffi.new("char[]", listdir_batch_size)

    def listdirinternal(dfd, req, stat, skip):
        ret = []
        while True:
            r = lib.getattrlistbulk(dfd, req, buf, listdir_batch_size, 0)
            if r == 0:
                break
            if r == -1:
                raise OSError(ffi.errno, os.strerror(ffi.errno))
            cur = ffi.cast("val_attrs_t*", buf)
            for i in range(r):
                lgt = cur.length
                assert lgt == ffi.cast('uint32_t*', cur)[0]
                ofs = cur.name_info.attr_dataoffset
                str_lgt = cur.name_info.attr_length
                base_ofs = ffi.offsetof('val_attrs_t', 'name_info')
                name = str(ffi.buffer(ffi.cast("char*", cur) + base_ofs + ofs,
                           str_lgt - 1))
                tp = attrkinds[cur.obj_type]
                if name == "." or name == "..":
                    continue
                if skip == name and tp == statmod.S_ISDIR:
                    return []
                if stat:
                    mtime = cur.mtime.tv_sec
                    mode = (cur.accessmask & ~lib.S_IFMT)| tp
                    ret.append((name, tp, stat_res(st_mode=mode, st_mtime=mtime,
                                st_size=cur.datalength)))
                else:
                    ret.append((name, tp))
                cur = ffi.cast("val_attrs_t*", int(ffi.cast("intptr_t", cur))
                    + lgt)
        return ret

    def listdir(path, stat=False, skip=None):
        req = ffi.new("struct attrlist*")
        req.bitmapcount = lib.ATTR_BIT_MAP_COUNT
        req.commonattr = (lib.ATTR_CMN_RETURNED_ATTRS |
                          lib.ATTR_CMN_NAME |
                          lib.ATTR_CMN_OBJTYPE |
                          lib.ATTR_CMN_ACCESSMASK |
                          lib.ATTR_CMN_MODTIME)
        req.fileattr = lib.ATTR_FILE_DATALENGTH
        dfd = lib.open(path, lib.O_RDONLY, 0)
        if dfd == -1:
            raise OSError(ffi.errno, os.strerror(ffi.errno))

        try:
            ret = listdirinternal(dfd, req, stat, skip)
        finally:
            try:
                lib.close(dfd)
            except BaseException:
                pass # we ignore all the errors from closing, not
                # much we can do about that
        return ret