mercurial/vfs.py
| author |
Pierre-Yves David <pierre-yves.david@octobus.net> |
|
Mon, 02 Nov 2020 11:03:56 +0100 |
| changeset 45907 |
06b64fabf91c |
| parent 44575 |
77d48738b8e0
|
| child 45957 |
89a2afe31e82 |
| permissions |
-rw-r--r-- |
copies: cache the ancestor checking call when tracing copy
A good share of the time spent in this function is spent doing ancestors
checking. To avoid spending time in duplicated call, we cache the result of
calls.
In the slower case, this provide a quite significant performance boost. Below
are the result for a set of selected pairs (many of them pathological):
(And further down is another table that summarize the current state of filelog
based vs changeset base copy tracing)
The benchmark have been configured to be killed after 6 minutes of runtime,
which mean that any detect slower than 2 minutes will be marked as "killed".
This drop some useful information about how much slower these case are… but also
prevent 99% of the benchmark time to be spent on case that can be labelled "very
slow" anyway.
Repo Case Source-Rev Dest-Rev Old-Time New-Time Difference Factor
------------------------------------------------------------------------------------------------------------------------------------
mercurial x_revs_x_added_0_copies ad6b123de1c7 39cfcef4f463 : 0.000044 s, 0.000044 s, +0.000000 s, × 1.0000
mercurial x_revs_x_added_x_copies 2b1c78674230 0c1d10351869 : 0.000138 s, 0.000138 s, +0.000000 s, × 1.0000
mercurial x000_revs_x000_added_x_copies 81f8ff2a9bf2 dd3267698d84 : 0.005067 s, 0.005052 s, -0.000015 s, × 0.9970
pypy x_revs_x_added_0_copies aed021ee8ae8 099ed31b181b : 0.000218 s, 0.000219 s, +0.000001 s, × 1.0046
pypy x_revs_x000_added_0_copies 4aa4e1f8e19a 359343b9ac0e : 0.000053 s, 0.000055 s, +0.000002 s, × 1.0377
pypy x_revs_x_added_x_copies ac52eb7bbbb0 72e022663155 : 0.000125 s, 0.000128 s, +0.000003 s, × 1.0240
pypy x_revs_x00_added_x_copies c3b14617fbd7 ace7255d9a26 : 0.001098 s, 0.001089 s, -0.000009 s, × 0.9918
pypy x_revs_x000_added_x000_copies df6f7a526b60 a83dc6a2d56f : 0.017546 s, 0.017407 s, -0.000139 s, × 0.9921
pypy x000_revs_xx00_added_0_copies 89a76aede314 2f22446ff07e : 0.096723 s, 0.094175 s, -0.002548 s, × 0.9737
pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 0.271796 s, 0.238009 s, -0.033787 s, × 0.8757
pypy x000_revs_x000_added_x000_copies 89a76aede314 7b3dda341c84 : 0.128602 s, 0.125876 s, -0.002726 s, × 0.9788
pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 7.086742 s, 3.581556 s, -3.505186 s, × 0.5054
pypy x0000_revs_xx000_added_0_copies bf2c629d0071 4ffed77c095c : 0.016634 s, 0.016721 s, +0.000087 s, × 1.0052
pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 0.254225 s, 0.242367 s, -0.011858 s, × 0.9534
netbeans x_revs_x_added_0_copies fb0955ffcbcd a01e9239f9e7 : 0.000166 s, 0.000165 s, -0.000001 s, × 0.9940
netbeans x_revs_x000_added_0_copies 6f360122949f 20eb231cc7d0 : 0.000118 s, 0.000114 s, -0.000004 s, × 0.9661
netbeans x_revs_x_added_x_copies 1ada3faf6fb6 5a39d12eecf4 : 0.000296 s, 0.000296 s, +0.000000 s, × 1.0000
netbeans x_revs_x00_added_x_copies 35be93ba1e2c 9eec5e90c05f : 0.001137 s, 0.001124 s, -0.000013 s, × 0.9886
netbeans x000_revs_xx00_added_0_copies eac3045b4fdd 51d4ae7f1290 : 0.014133 s, 0.013060 s, -0.001073 s, × 0.9241
netbeans x000_revs_x000_added_x_copies e2063d266acd 6081d72689dc : 0.016988 s, 0.017112 s, +0.000124 s, × 1.0073
netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 0.676361 s, 0.660350 s, -0.016011 s, × 0.9763
netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 12.515149 s, 10.032499 s, -2.482650 s, × 0.8016
mozilla-central x_revs_x_added_0_copies 3697f962bb7b 7015fcdd43a2 : 0.000186 s, 0.000189 s, +0.000003 s, × 1.0161
mozilla-central x_revs_x000_added_0_copies dd390860c6c9 40d0c5bed75d : 0.000459 s, 0.000462 s, +0.000003 s, × 1.0065
mozilla-central x_revs_x_added_x_copies 8d198483ae3b 14207ffc2b2f : 0.000273 s, 0.000270 s, -0.000003 s, × 0.9890
mozilla-central x_revs_x00_added_x_copies 98cbc58cc6bc 446a150332c3 : 0.001503 s, 0.001474 s, -0.000029 s, × 0.9807
mozilla-central x_revs_x000_added_x000_copies 3c684b4b8f68 0a5e72d1b479 : 0.004862 s, 0.004806 s, -0.000056 s, × 0.9885
mozilla-central x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 0.088291 s, 0.085150 s, -0.003141 s, × 0.9644
mozilla-central x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 0.007113 s, 0.007064 s, -0.000049 s, × 0.9931
mozilla-central x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 0.004687 s, 0.004741 s, +0.000054 s, × 1.0115
mozilla-central x000_revs_x000_added_x000_copies 7c97034feb78 4407bd0c6330 : 0.198710 s, 0.190133 s, -0.008577 s, × 0.9568
mozilla-central x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 0.036068 s, 0.035651 s, -0.000417 s, × 0.9884
mozilla-central x0000_revs_xx000_added_x000_copies f78c615a656c 96a38b690156 : 0.465362 s, 0.440694 s, -0.024668 s, × 0.9470
mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 24.519684 s, 18.454163 s, -6.065521 s, × 0.7526
mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 42.711897 s, 31.562719 s, -11.149178 s, × 0.7390
mozilla-try x_revs_x_added_0_copies aaf6dde0deb8 9790f499805a : 0.001201 s, 0.001189 s, -0.000012 s, × 0.9900
mozilla-try x_revs_x000_added_0_copies d8d0222927b4 5bb8ce8c7450 : 0.001216 s, 0.001204 s, -0.000012 s, × 0.9901
mozilla-try x_revs_x_added_x_copies 092fcca11bdb 936255a0384a : 0.000595 s, 0.000586 s, -0.000009 s, × 0.9849
mozilla-try x_revs_x00_added_x_copies b53d2fadbdb5 017afae788ec : 0.001856 s, 0.001845 s, -0.000011 s, × 0.9941
mozilla-try x_revs_x000_added_x000_copies 20408ad61ce5 6f0ee96e21ad : 0.064936 s, 0.063822 s, -0.001114 s, × 0.9828
mozilla-try x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 0.090601 s, 0.088038 s, -0.002563 s, × 0.9717
mozilla-try x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 0.007510 s, 0.007389 s, -0.000121 s, × 0.9839
mozilla-try x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 0.004911 s, 0.004868 s, -0.000043 s, × 0.9912
mozilla-try x000_revs_x000_added_x000_copies 1346fd0130e4 4c65cbdabc1f : 0.233231 s, 0.222450 s, -0.010781 s, × 0.9538
mozilla-try x0000_revs_x_added_0_copies 63519bfd42ee a36a2a865d92 : 0.419989 s, 0.370675 s, -0.049314 s, × 0.8826
mozilla-try x0000_revs_x_added_x_copies 9fe69ff0762d bcabf2a78927 : 0.401521 s, 0.358020 s, -0.043501 s, × 0.8917
mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 0.179555 s, 0.145235 s, -0.034320 s, × 0.8089
mozilla-try x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 0.038004 s, 0.037606 s, -0.000398 s, × 0.9895
mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 52.838482 s, 7.382439 s, -45.456043 s, × 0.1397
mozilla-try x0000_revs_x0000_added_x0000_copies e928c65095ed e951f4ad123a : 8.705874 s, 7.273506 s, -1.432368 s, × 0.8355
mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 1.126708 s, 1.074593 s, -0.052115 s, × 0.9537
mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 83.854020 s, 27.746195 s, -56.107825 s, × 0.3309
Below is a table comparing the runtime of the current "filelog centric"
algorithm, with the "changeset centric" one, we just modified.
The changeset centric algorithm is a significant win in many scenario, but they
are still various cases where it is quite slower. When many revision has to be
considered the cost of retrieving the copy information, creating new
dictionaries, merging dictionaries and checking if revision are ancestors of
each other can slow things down.
The rest of this series, will introduce a rust version of the copy tracing code
to deal with most of theses issues.
Repo Case Source-Rev Dest-Rev filelog sidedata Difference Factor
---------------------------------------------------------------------------------------------------------------------------------------
mercurial x_revs_x_added_0_copies ad6b123de1c7 39cfcef4f463 : 0.000914 s, 0.000044 s, - 0.000870 s, × 0.048140
mercurial x_revs_x_added_x_copies 2b1c78674230 0c1d10351869 : 0.001812 s, 0.000138 s, - 0.001674 s, × 0.076159
mercurial x000_revs_x000_added_x_copies 81f8ff2a9bf2 dd3267698d84 : 0.017954 s, 0.005052 s, - 0.012902 s, × 0.281386
pypy x_revs_x_added_0_copies aed021ee8ae8 099ed31b181b : 0.001509 s, 0.000219 s, - 0.001290 s, × 0.145129
pypy x_revs_x000_added_0_copies 4aa4e1f8e19a 359343b9ac0e : 0.206881 s, 0.000055 s, - 0.206826 s, × 0.000266
pypy x_revs_x_added_x_copies ac52eb7bbbb0 72e022663155 : 0.016951 s, 0.000128 s, - 0.016823 s, × 0.007551
pypy x_revs_x00_added_x_copies c3b14617fbd7 ace7255d9a26 : 0.019096 s, 0.001089 s, - 0.018007 s, × 0.057028
pypy x_revs_x000_added_x000_copies df6f7a526b60 a83dc6a2d56f : 0.762506 s, 0.017407 s, - 0.745099 s, × 0.022829
pypy x000_revs_xx00_added_0_copies 89a76aede314 2f22446ff07e : 1.179211 s, 0.094175 s, - 1.085036 s, × 0.079863
pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 1.249058 s, 0.238009 s, - 1.011049 s, × 0.190551
pypy x000_revs_x000_added_x000_copies 89a76aede314 7b3dda341c84 : 1.614107 s, 0.125876 s, - 1.488231 s, × 0.077985
pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 0.001064 s, 3.581556 s, + 3.580492 s, × 3366.124060
pypy x0000_revs_xx000_added_0_copies bf2c629d0071 4ffed77c095c : 1.061275 s, 0.016721 s, - 1.044554 s, × 0.015756
pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 1.341119 s, 0.242367 s, - 1.098752 s, × 0.180720
netbeans x_revs_x_added_0_copies fb0955ffcbcd a01e9239f9e7 : 0.027803 s, 0.000165 s, - 0.027638 s, × 0.005935
netbeans x_revs_x000_added_0_copies 6f360122949f 20eb231cc7d0 : 0.130014 s, 0.000114 s, - 0.129900 s, × 0.000877
netbeans x_revs_x_added_x_copies 1ada3faf6fb6 5a39d12eecf4 : 0.024990 s, 0.000296 s, - 0.024694 s, × 0.011845
netbeans x_revs_x00_added_x_copies 35be93ba1e2c 9eec5e90c05f : 0.052201 s, 0.001124 s, - 0.051077 s, × 0.021532
netbeans x000_revs_xx00_added_0_copies eac3045b4fdd 51d4ae7f1290 : 0.037642 s, 0.013060 s, - 0.024582 s, × 0.346953
netbeans x000_revs_x000_added_x_copies e2063d266acd 6081d72689dc : 0.197086 s, 0.017112 s, - 0.179974 s, × 0.086825
netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 0.935148 s, 0.660350 s, - 0.274798 s, × 0.706145
netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 3.920674 s, 10.032499 s, + 6.111825 s, × 2.558871
mozilla-central x_revs_x_added_0_copies 3697f962bb7b 7015fcdd43a2 : 0.024232 s, 0.000189 s, - 0.024043 s, × 0.007800
mozilla-central x_revs_x000_added_0_copies dd390860c6c9 40d0c5bed75d : 0.141483 s, 0.000462 s, - 0.141021 s, × 0.003265
mozilla-central x_revs_x_added_x_copies 8d198483ae3b 14207ffc2b2f : 0.025775 s, 0.000270 s, - 0.025505 s, × 0.010475
mozilla-central x_revs_x00_added_x_copies 98cbc58cc6bc 446a150332c3 : 0.084922 s, 0.001474 s, - 0.083448 s, × 0.017357
mozilla-central x_revs_x000_added_x000_copies 3c684b4b8f68 0a5e72d1b479 : 0.194784 s, 0.004806 s, - 0.189978 s, × 0.024673
mozilla-central x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 2.161103 s, 0.085150 s, - 2.075953 s, × 0.039401
mozilla-central x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 0.089347 s, 0.007064 s, - 0.082283 s, × 0.079063
mozilla-central x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 0.732171 s, 0.004741 s, - 0.727430 s, × 0.006475
mozilla-central x000_revs_x000_added_x000_copies 7c97034feb78 4407bd0c6330 : 1.157287 s, 0.190133 s, - 0.967154 s, × 0.164292
mozilla-central x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 6.726568 s, 0.035651 s, - 6.690917 s, × 0.005300
mozilla-central x0000_revs_xx000_added_x000_copies f78c615a656c 96a38b690156 : 3.266229 s, 0.440694 s, - 2.825535 s, × 0.134924
mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 15.860534 s, 18.454163 s, + 2.593629 s, × 1.163527
mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 20.450475 s, 31.562719 s, +11.112244 s, × 1.543373
mozilla-try x_revs_x_added_0_copies aaf6dde0deb8 9790f499805a : 0.080442 s, 0.001189 s, - 0.079253 s, × 0.014781
mozilla-try x_revs_x000_added_0_copies d8d0222927b4 5bb8ce8c7450 : 0.497672 s, 0.001204 s, - 0.496468 s, × 0.002419
mozilla-try x_revs_x_added_x_copies 092fcca11bdb 936255a0384a : 0.021183 s, 0.000586 s, - 0.020597 s, × 0.027664
mozilla-try x_revs_x00_added_x_copies b53d2fadbdb5 017afae788ec : 0.230991 s, 0.001845 s, - 0.229146 s, × 0.007987
mozilla-try x_revs_x000_added_x000_copies 20408ad61ce5 6f0ee96e21ad : 1.118461 s, 0.063822 s, - 1.054639 s, × 0.057062
mozilla-try x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 2.206083 s, 0.088038 s, - 2.118045 s, × 0.039907
mozilla-try x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 0.089404 s, 0.007389 s, - 0.082015 s, × 0.082647
mozilla-try x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 0.733043 s, 0.004868 s, - 0.728175 s, × 0.006641
mozilla-try x000_revs_x000_added_x000_copies 1346fd0130e4 4c65cbdabc1f : 1.163367 s, 0.222450 s, - 0.940917 s, × 0.191212
mozilla-try x0000_revs_x_added_0_copies 63519bfd42ee a36a2a865d92 : 0.085456 s, 0.370675 s, + 0.285219 s, × 4.337612
mozilla-try x0000_revs_x_added_x_copies 9fe69ff0762d bcabf2a78927 : 0.083601 s, 0.358020 s, + 0.274419 s, × 4.282485
mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 7.366614 s, 0.145235 s, - 7.221379 s, × 0.019715
mozilla-try x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 6.664464 s, 0.037606 s, - 6.626858 s, × 0.005643
mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 7.467836 s, 7.382439 s, - 0.085397 s, × 0.988565
mozilla-try x0000_revs_x0000_added_x0000_copies e928c65095ed e951f4ad123a : 9.801294 s, 7.273506 s, - 2.527788 s, × 0.742097
mozilla-try x00000_revs_x_added_0_copies 6a320851d377 1ebb79acd503 : 0.091886 s, killed
mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 26.491140 s, 1.074593 s, -25.416547 s, × 0.040564
mozilla-try x00000_revs_x_added_x_copies 5173c4b6f97c 95d83ee7242d : 0.092863 s, killed
mozilla-try x00000_revs_x000_added_x_copies 9126823d0e9c ca82787bb23c : 0.226823 s, killed
mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 18.914630 s, 27.746195 s, + 8.831565 s, × 1.466917
mozilla-try x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 21.198903 s, killed
mozilla-try x00000_revs_x00000_added_x000_copies 9b2a99adc05e 8e29777b48e6 : 24.952268 s, killed
Differential Revision: https://phab.mercurial-scm.org/D9296
# vfs.py - Mercurial 'vfs' classes
#
# Copyright Matt Mackall <mpm@selenic.com>
#
# 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 contextlib
import errno
import os
import shutil
import stat
import threading
from .i18n import _
from .pycompat import (
delattr,
getattr,
setattr,
)
from . import (
encoding,
error,
pathutil,
pycompat,
util,
)
def _avoidambig(path, oldstat):
"""Avoid file stat ambiguity forcibly
This function causes copying ``path`` file, if it is owned by
another (see issue5418 and issue5584 for detail).
"""
def checkandavoid():
newstat = util.filestat.frompath(path)
# return whether file stat ambiguity is (already) avoided
return not newstat.isambig(oldstat) or newstat.avoidambig(path, oldstat)
if not checkandavoid():
# simply copy to change owner of path to get privilege to
# advance mtime (see issue5418)
util.rename(util.mktempcopy(path), path)
checkandavoid()
class abstractvfs(object):
"""Abstract base class; cannot be instantiated"""
def __init__(self, *args, **kwargs):
'''Prevent instantiation; don't call this from subclasses.'''
raise NotImplementedError('attempted instantiating ' + str(type(self)))
def __call__(self, path, mode=b'rb', **kwargs):
raise NotImplementedError
def _auditpath(self, path, mode):
raise NotImplementedError
def join(self, path, *insidef):
raise NotImplementedError
def tryread(self, path):
'''gracefully return an empty string for missing files'''
try:
return self.read(path)
except IOError as inst:
if inst.errno != errno.ENOENT:
raise
return b""
def tryreadlines(self, path, mode=b'rb'):
'''gracefully return an empty array for missing files'''
try:
return self.readlines(path, mode=mode)
except IOError as inst:
if inst.errno != errno.ENOENT:
raise
return []
@util.propertycache
def open(self):
'''Open ``path`` file, which is relative to vfs root.
Newly created directories are marked as "not to be indexed by
the content indexing service", if ``notindexed`` is specified
for "write" mode access.
'''
return self.__call__
def read(self, path):
with self(path, b'rb') as fp:
return fp.read()
def readlines(self, path, mode=b'rb'):
with self(path, mode=mode) as fp:
return fp.readlines()
def write(self, path, data, backgroundclose=False, **kwargs):
with self(path, b'wb', backgroundclose=backgroundclose, **kwargs) as fp:
return fp.write(data)
def writelines(self, path, data, mode=b'wb', notindexed=False):
with self(path, mode=mode, notindexed=notindexed) as fp:
return fp.writelines(data)
def append(self, path, data):
with self(path, b'ab') as fp:
return fp.write(data)
def basename(self, path):
"""return base element of a path (as os.path.basename would do)
This exists to allow handling of strange encoding if needed."""
return os.path.basename(path)
def chmod(self, path, mode):
return os.chmod(self.join(path), mode)
def dirname(self, path):
"""return dirname element of a path (as os.path.dirname would do)
This exists to allow handling of strange encoding if needed."""
return os.path.dirname(path)
def exists(self, path=None):
return os.path.exists(self.join(path))
def fstat(self, fp):
return util.fstat(fp)
def isdir(self, path=None):
return os.path.isdir(self.join(path))
def isfile(self, path=None):
return os.path.isfile(self.join(path))
def islink(self, path=None):
return os.path.islink(self.join(path))
def isfileorlink(self, path=None):
'''return whether path is a regular file or a symlink
Unlike isfile, this doesn't follow symlinks.'''
try:
st = self.lstat(path)
except OSError:
return False
mode = st.st_mode
return stat.S_ISREG(mode) or stat.S_ISLNK(mode)
def reljoin(self, *paths):
"""join various elements of a path together (as os.path.join would do)
The vfs base is not injected so that path stay relative. This exists
to allow handling of strange encoding if needed."""
return os.path.join(*paths)
def split(self, path):
"""split top-most element of a path (as os.path.split would do)
This exists to allow handling of strange encoding if needed."""
return os.path.split(path)
def lexists(self, path=None):
return os.path.lexists(self.join(path))
def lstat(self, path=None):
return os.lstat(self.join(path))
def listdir(self, path=None):
return os.listdir(self.join(path))
def makedir(self, path=None, notindexed=True):
return util.makedir(self.join(path), notindexed)
def makedirs(self, path=None, mode=None):
return util.makedirs(self.join(path), mode)
def makelock(self, info, path):
return util.makelock(info, self.join(path))
def mkdir(self, path=None):
return os.mkdir(self.join(path))
def mkstemp(self, suffix=b'', prefix=b'tmp', dir=None):
fd, name = pycompat.mkstemp(
suffix=suffix, prefix=prefix, dir=self.join(dir)
)
dname, fname = util.split(name)
if dir:
return fd, os.path.join(dir, fname)
else:
return fd, fname
def readdir(self, path=None, stat=None, skip=None):
return util.listdir(self.join(path), stat, skip)
def readlock(self, path):
return util.readlock(self.join(path))
def rename(self, src, dst, checkambig=False):
"""Rename from src to dst
checkambig argument is used with util.filestat, and is useful
only if destination file is guarded by any lock
(e.g. repo.lock or repo.wlock).
To avoid file stat ambiguity forcibly, checkambig=True involves
copying ``src`` file, if it is owned by another. Therefore, use
checkambig=True only in limited cases (see also issue5418 and
issue5584 for detail).
"""
self._auditpath(dst, b'w')
srcpath = self.join(src)
dstpath = self.join(dst)
oldstat = checkambig and util.filestat.frompath(dstpath)
if oldstat and oldstat.stat:
ret = util.rename(srcpath, dstpath)
_avoidambig(dstpath, oldstat)
return ret
return util.rename(srcpath, dstpath)
def readlink(self, path):
return util.readlink(self.join(path))
def removedirs(self, path=None):
"""Remove a leaf directory and all empty intermediate ones
"""
return util.removedirs(self.join(path))
def rmdir(self, path=None):
"""Remove an empty directory."""
return os.rmdir(self.join(path))
def rmtree(self, path=None, ignore_errors=False, forcibly=False):
"""Remove a directory tree recursively
If ``forcibly``, this tries to remove READ-ONLY files, too.
"""
if forcibly:
def onerror(function, path, excinfo):
if function is not os.remove:
raise
# read-only files cannot be unlinked under Windows
s = os.stat(path)
if (s.st_mode & stat.S_IWRITE) != 0:
raise
os.chmod(path, stat.S_IMODE(s.st_mode) | stat.S_IWRITE)
os.remove(path)
else:
onerror = None
return shutil.rmtree(
self.join(path), ignore_errors=ignore_errors, onerror=onerror
)
def setflags(self, path, l, x):
return util.setflags(self.join(path), l, x)
def stat(self, path=None):
return os.stat(self.join(path))
def unlink(self, path=None):
return util.unlink(self.join(path))
def tryunlink(self, path=None):
"""Attempt to remove a file, ignoring missing file errors."""
util.tryunlink(self.join(path))
def unlinkpath(self, path=None, ignoremissing=False, rmdir=True):
return util.unlinkpath(
self.join(path), ignoremissing=ignoremissing, rmdir=rmdir
)
def utime(self, path=None, t=None):
return os.utime(self.join(path), t)
def walk(self, path=None, onerror=None):
"""Yield (dirpath, dirs, files) tuple for each directories under path
``dirpath`` is relative one from the root of this vfs. This
uses ``os.sep`` as path separator, even you specify POSIX
style ``path``.
"The root of this vfs" is represented as empty ``dirpath``.
"""
root = os.path.normpath(self.join(None))
# when dirpath == root, dirpath[prefixlen:] becomes empty
# because len(dirpath) < prefixlen.
prefixlen = len(pathutil.normasprefix(root))
for dirpath, dirs, files in os.walk(self.join(path), onerror=onerror):
yield (dirpath[prefixlen:], dirs, files)
@contextlib.contextmanager
def backgroundclosing(self, ui, expectedcount=-1):
"""Allow files to be closed asynchronously.
When this context manager is active, ``backgroundclose`` can be passed
to ``__call__``/``open`` to result in the file possibly being closed
asynchronously, on a background thread.
"""
# Sharing backgroundfilecloser between threads is complex and using
# multiple instances puts us at risk of running out of file descriptors
# only allow to use backgroundfilecloser when in main thread.
if not isinstance(
threading.currentThread(),
threading._MainThread, # pytype: disable=module-attr
):
yield
return
vfs = getattr(self, 'vfs', self)
if getattr(vfs, '_backgroundfilecloser', None):
raise error.Abort(
_(b'can only have 1 active background file closer')
)
with backgroundfilecloser(ui, expectedcount=expectedcount) as bfc:
try:
vfs._backgroundfilecloser = (
bfc # pytype: disable=attribute-error
)
yield bfc
finally:
vfs._backgroundfilecloser = (
None # pytype: disable=attribute-error
)
class vfs(abstractvfs):
'''Operate files relative to a base directory
This class is used to hide the details of COW semantics and
remote file access from higher level code.
'cacheaudited' should be enabled only if (a) vfs object is short-lived, or
(b) the base directory is managed by hg and considered sort-of append-only.
See pathutil.pathauditor() for details.
'''
def __init__(
self,
base,
audit=True,
cacheaudited=False,
expandpath=False,
realpath=False,
):
if expandpath:
base = util.expandpath(base)
if realpath:
base = os.path.realpath(base)
self.base = base
self._audit = audit
if audit:
self.audit = pathutil.pathauditor(self.base, cached=cacheaudited)
else:
self.audit = lambda path, mode=None: True
self.createmode = None
self._trustnlink = None
self.options = {}
@util.propertycache
def _cansymlink(self):
return util.checklink(self.base)
@util.propertycache
def _chmod(self):
return util.checkexec(self.base)
def _fixfilemode(self, name):
if self.createmode is None or not self._chmod:
return
os.chmod(name, self.createmode & 0o666)
def _auditpath(self, path, mode):
if self._audit:
if os.path.isabs(path) and path.startswith(self.base):
path = os.path.relpath(path, self.base)
r = util.checkosfilename(path)
if r:
raise error.Abort(b"%s: %r" % (r, path))
self.audit(path, mode=mode)
def __call__(
self,
path,
mode=b"r",
atomictemp=False,
notindexed=False,
backgroundclose=False,
checkambig=False,
auditpath=True,
makeparentdirs=True,
):
'''Open ``path`` file, which is relative to vfs root.
By default, parent directories are created as needed. Newly created
directories are marked as "not to be indexed by the content indexing
service", if ``notindexed`` is specified for "write" mode access.
Set ``makeparentdirs=False`` to not create directories implicitly.
If ``backgroundclose`` is passed, the file may be closed asynchronously.
It can only be used if the ``self.backgroundclosing()`` context manager
is active. This should only be specified if the following criteria hold:
1. There is a potential for writing thousands of files. Unless you
are writing thousands of files, the performance benefits of
asynchronously closing files is not realized.
2. Files are opened exactly once for the ``backgroundclosing``
active duration and are therefore free of race conditions between
closing a file on a background thread and reopening it. (If the
file were opened multiple times, there could be unflushed data
because the original file handle hasn't been flushed/closed yet.)
``checkambig`` argument is passed to atomictempfile (valid
only for writing), and is useful only if target file is
guarded by any lock (e.g. repo.lock or repo.wlock).
To avoid file stat ambiguity forcibly, checkambig=True involves
copying ``path`` file opened in "append" mode (e.g. for
truncation), if it is owned by another. Therefore, use
combination of append mode and checkambig=True only in limited
cases (see also issue5418 and issue5584 for detail).
'''
if auditpath:
self._auditpath(path, mode)
f = self.join(path)
if b"b" not in mode:
mode += b"b" # for that other OS
nlink = -1
if mode not in (b'r', b'rb'):
dirname, basename = util.split(f)
# If basename is empty, then the path is malformed because it points
# to a directory. Let the posixfile() call below raise IOError.
if basename:
if atomictemp:
if makeparentdirs:
util.makedirs(dirname, self.createmode, notindexed)
return util.atomictempfile(
f, mode, self.createmode, checkambig=checkambig
)
try:
if b'w' in mode:
util.unlink(f)
nlink = 0
else:
# nlinks() may behave differently for files on Windows
# shares if the file is open.
with util.posixfile(f):
nlink = util.nlinks(f)
if nlink < 1:
nlink = 2 # force mktempcopy (issue1922)
except (OSError, IOError) as e:
if e.errno != errno.ENOENT:
raise
nlink = 0
if makeparentdirs:
util.makedirs(dirname, self.createmode, notindexed)
if nlink > 0:
if self._trustnlink is None:
self._trustnlink = nlink > 1 or util.checknlink(f)
if nlink > 1 or not self._trustnlink:
util.rename(util.mktempcopy(f), f)
fp = util.posixfile(f, mode)
if nlink == 0:
self._fixfilemode(f)
if checkambig:
if mode in (b'r', b'rb'):
raise error.Abort(
_(
b'implementation error: mode %s is not'
b' valid for checkambig=True'
)
% mode
)
fp = checkambigatclosing(fp)
if backgroundclose and isinstance(
threading.currentThread(),
threading._MainThread, # pytype: disable=module-attr
):
if (
not self._backgroundfilecloser # pytype: disable=attribute-error
):
raise error.Abort(
_(
b'backgroundclose can only be used when a '
b'backgroundclosing context manager is active'
)
)
fp = delayclosedfile(
fp,
self._backgroundfilecloser, # pytype: disable=attribute-error
)
return fp
def symlink(self, src, dst):
self.audit(dst)
linkname = self.join(dst)
util.tryunlink(linkname)
util.makedirs(os.path.dirname(linkname), self.createmode)
if self._cansymlink:
try:
os.symlink(src, linkname)
except OSError as err:
raise OSError(
err.errno,
_(b'could not symlink to %r: %s')
% (src, encoding.strtolocal(err.strerror)),
linkname,
)
else:
self.write(dst, src)
def join(self, path, *insidef):
if path:
return os.path.join(self.base, path, *insidef)
else:
return self.base
opener = vfs
class proxyvfs(abstractvfs):
def __init__(self, vfs):
self.vfs = vfs
def _auditpath(self, path, mode):
return self.vfs._auditpath(path, mode)
@property
def options(self):
return self.vfs.options
@options.setter
def options(self, value):
self.vfs.options = value
class filtervfs(proxyvfs, abstractvfs):
'''Wrapper vfs for filtering filenames with a function.'''
def __init__(self, vfs, filter):
proxyvfs.__init__(self, vfs)
self._filter = filter
def __call__(self, path, *args, **kwargs):
return self.vfs(self._filter(path), *args, **kwargs)
def join(self, path, *insidef):
if path:
return self.vfs.join(self._filter(self.vfs.reljoin(path, *insidef)))
else:
return self.vfs.join(path)
filteropener = filtervfs
class readonlyvfs(proxyvfs):
'''Wrapper vfs preventing any writing.'''
def __init__(self, vfs):
proxyvfs.__init__(self, vfs)
def __call__(self, path, mode=b'r', *args, **kw):
if mode not in (b'r', b'rb'):
raise error.Abort(_(b'this vfs is read only'))
return self.vfs(path, mode, *args, **kw)
def join(self, path, *insidef):
return self.vfs.join(path, *insidef)
class closewrapbase(object):
"""Base class of wrapper, which hooks closing
Do not instantiate outside of the vfs layer.
"""
def __init__(self, fh):
object.__setattr__(self, '_origfh', fh)
def __getattr__(self, attr):
return getattr(self._origfh, attr)
def __setattr__(self, attr, value):
return setattr(self._origfh, attr, value)
def __delattr__(self, attr):
return delattr(self._origfh, attr)
def __enter__(self):
self._origfh.__enter__()
return self
def __exit__(self, exc_type, exc_value, exc_tb):
raise NotImplementedError('attempted instantiating ' + str(type(self)))
def close(self):
raise NotImplementedError('attempted instantiating ' + str(type(self)))
class delayclosedfile(closewrapbase):
"""Proxy for a file object whose close is delayed.
Do not instantiate outside of the vfs layer.
"""
def __init__(self, fh, closer):
super(delayclosedfile, self).__init__(fh)
object.__setattr__(self, '_closer', closer)
def __exit__(self, exc_type, exc_value, exc_tb):
self._closer.close(self._origfh)
def close(self):
self._closer.close(self._origfh)
class backgroundfilecloser(object):
"""Coordinates background closing of file handles on multiple threads."""
def __init__(self, ui, expectedcount=-1):
self._running = False
self._entered = False
self._threads = []
self._threadexception = None
# Only Windows/NTFS has slow file closing. So only enable by default
# on that platform. But allow to be enabled elsewhere for testing.
defaultenabled = pycompat.iswindows
enabled = ui.configbool(b'worker', b'backgroundclose', defaultenabled)
if not enabled:
return
# There is overhead to starting and stopping the background threads.
# Don't do background processing unless the file count is large enough
# to justify it.
minfilecount = ui.configint(b'worker', b'backgroundcloseminfilecount')
# FUTURE dynamically start background threads after minfilecount closes.
# (We don't currently have any callers that don't know their file count)
if expectedcount > 0 and expectedcount < minfilecount:
return
maxqueue = ui.configint(b'worker', b'backgroundclosemaxqueue')
threadcount = ui.configint(b'worker', b'backgroundclosethreadcount')
ui.debug(
b'starting %d threads for background file closing\n' % threadcount
)
self._queue = pycompat.queue.Queue(maxsize=maxqueue)
self._running = True
for i in range(threadcount):
t = threading.Thread(target=self._worker, name='backgroundcloser')
self._threads.append(t)
t.start()
def __enter__(self):
self._entered = True
return self
def __exit__(self, exc_type, exc_value, exc_tb):
self._running = False
# Wait for threads to finish closing so open files don't linger for
# longer than lifetime of context manager.
for t in self._threads:
t.join()
def _worker(self):
"""Main routine for worker thread."""
while True:
try:
fh = self._queue.get(block=True, timeout=0.100)
# Need to catch or the thread will terminate and
# we could orphan file descriptors.
try:
fh.close()
except Exception as e:
# Stash so can re-raise from main thread later.
self._threadexception = e
except pycompat.queue.Empty:
if not self._running:
break
def close(self, fh):
"""Schedule a file for closing."""
if not self._entered:
raise error.Abort(
_(b'can only call close() when context manager active')
)
# If a background thread encountered an exception, raise now so we fail
# fast. Otherwise we may potentially go on for minutes until the error
# is acted on.
if self._threadexception:
e = self._threadexception
self._threadexception = None
raise e
# If we're not actively running, close synchronously.
if not self._running:
fh.close()
return
self._queue.put(fh, block=True, timeout=None)
class checkambigatclosing(closewrapbase):
"""Proxy for a file object, to avoid ambiguity of file stat
See also util.filestat for detail about "ambiguity of file stat".
This proxy is useful only if the target file is guarded by any
lock (e.g. repo.lock or repo.wlock)
Do not instantiate outside of the vfs layer.
"""
def __init__(self, fh):
super(checkambigatclosing, self).__init__(fh)
object.__setattr__(self, '_oldstat', util.filestat.frompath(fh.name))
def _checkambig(self):
oldstat = self._oldstat
if oldstat.stat:
_avoidambig(self._origfh.name, oldstat)
def __exit__(self, exc_type, exc_value, exc_tb):
self._origfh.__exit__(exc_type, exc_value, exc_tb)
self._checkambig()
def close(self):
self._origfh.close()
self._checkambig()