Mercurial > hg
view mercurial/store.py @ 45892:06b64fabf91c
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
author | Pierre-Yves David <pierre-yves.david@octobus.net> |
---|---|
date | Mon, 02 Nov 2020 11:03:56 +0100 |
parents | d252f51ab032 |
children | 89a2afe31e82 |
line wrap: on
line source
# store.py - repository store handling for Mercurial # # Copyright 2008 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 errno import functools import os import stat from .i18n import _ from .pycompat import getattr from . import ( changelog, error, manifest, node, policy, pycompat, util, vfs as vfsmod, ) from .utils import hashutil parsers = policy.importmod('parsers') # how much bytes should be read from fncache in one read # It is done to prevent loading large fncache files into memory fncache_chunksize = 10 ** 6 def _matchtrackedpath(path, matcher): """parses a fncache entry and returns whether the entry is tracking a path matched by matcher or not. If matcher is None, returns True""" if matcher is None: return True path = decodedir(path) if path.startswith(b'data/'): return matcher(path[len(b'data/') : -len(b'.i')]) elif path.startswith(b'meta/'): return matcher.visitdir(path[len(b'meta/') : -len(b'/00manifest.i')]) raise error.ProgrammingError(b"cannot decode path %s" % path) # This avoids a collision between a file named foo and a dir named # foo.i or foo.d def _encodedir(path): ''' >>> _encodedir(b'data/foo.i') 'data/foo.i' >>> _encodedir(b'data/foo.i/bla.i') 'data/foo.i.hg/bla.i' >>> _encodedir(b'data/foo.i.hg/bla.i') 'data/foo.i.hg.hg/bla.i' >>> _encodedir(b'data/foo.i\\ndata/foo.i/bla.i\\ndata/foo.i.hg/bla.i\\n') 'data/foo.i\\ndata/foo.i.hg/bla.i\\ndata/foo.i.hg.hg/bla.i\\n' ''' return ( path.replace(b".hg/", b".hg.hg/") .replace(b".i/", b".i.hg/") .replace(b".d/", b".d.hg/") ) encodedir = getattr(parsers, 'encodedir', _encodedir) def decodedir(path): ''' >>> decodedir(b'data/foo.i') 'data/foo.i' >>> decodedir(b'data/foo.i.hg/bla.i') 'data/foo.i/bla.i' >>> decodedir(b'data/foo.i.hg.hg/bla.i') 'data/foo.i.hg/bla.i' ''' if b".hg/" not in path: return path return ( path.replace(b".d.hg/", b".d/") .replace(b".i.hg/", b".i/") .replace(b".hg.hg/", b".hg/") ) def _reserved(): ''' characters that are problematic for filesystems * ascii escapes (0..31) * ascii hi (126..255) * windows specials these characters will be escaped by encodefunctions ''' winreserved = [ord(x) for x in u'\\:*?"<>|'] for x in range(32): yield x for x in range(126, 256): yield x for x in winreserved: yield x def _buildencodefun(): ''' >>> enc, dec = _buildencodefun() >>> enc(b'nothing/special.txt') 'nothing/special.txt' >>> dec(b'nothing/special.txt') 'nothing/special.txt' >>> enc(b'HELLO') '_h_e_l_l_o' >>> dec(b'_h_e_l_l_o') 'HELLO' >>> enc(b'hello:world?') 'hello~3aworld~3f' >>> dec(b'hello~3aworld~3f') 'hello:world?' >>> enc(b'the\\x07quick\\xADshot') 'the~07quick~adshot' >>> dec(b'the~07quick~adshot') 'the\\x07quick\\xadshot' ''' e = b'_' xchr = pycompat.bytechr asciistr = list(map(xchr, range(127))) capitals = list(range(ord(b"A"), ord(b"Z") + 1)) cmap = {x: x for x in asciistr} for x in _reserved(): cmap[xchr(x)] = b"~%02x" % x for x in capitals + [ord(e)]: cmap[xchr(x)] = e + xchr(x).lower() dmap = {} for k, v in pycompat.iteritems(cmap): dmap[v] = k def decode(s): i = 0 while i < len(s): for l in pycompat.xrange(1, 4): try: yield dmap[s[i : i + l]] i += l break except KeyError: pass else: raise KeyError return ( lambda s: b''.join( [cmap[s[c : c + 1]] for c in pycompat.xrange(len(s))] ), lambda s: b''.join(list(decode(s))), ) _encodefname, _decodefname = _buildencodefun() def encodefilename(s): ''' >>> encodefilename(b'foo.i/bar.d/bla.hg/hi:world?/HELLO') 'foo.i.hg/bar.d.hg/bla.hg.hg/hi~3aworld~3f/_h_e_l_l_o' ''' return _encodefname(encodedir(s)) def decodefilename(s): ''' >>> decodefilename(b'foo.i.hg/bar.d.hg/bla.hg.hg/hi~3aworld~3f/_h_e_l_l_o') 'foo.i/bar.d/bla.hg/hi:world?/HELLO' ''' return decodedir(_decodefname(s)) def _buildlowerencodefun(): ''' >>> f = _buildlowerencodefun() >>> f(b'nothing/special.txt') 'nothing/special.txt' >>> f(b'HELLO') 'hello' >>> f(b'hello:world?') 'hello~3aworld~3f' >>> f(b'the\\x07quick\\xADshot') 'the~07quick~adshot' ''' xchr = pycompat.bytechr cmap = {xchr(x): xchr(x) for x in pycompat.xrange(127)} for x in _reserved(): cmap[xchr(x)] = b"~%02x" % x for x in range(ord(b"A"), ord(b"Z") + 1): cmap[xchr(x)] = xchr(x).lower() def lowerencode(s): return b"".join([cmap[c] for c in pycompat.iterbytestr(s)]) return lowerencode lowerencode = getattr(parsers, 'lowerencode', None) or _buildlowerencodefun() # Windows reserved names: con, prn, aux, nul, com1..com9, lpt1..lpt9 _winres3 = (b'aux', b'con', b'prn', b'nul') # length 3 _winres4 = (b'com', b'lpt') # length 4 (with trailing 1..9) def _auxencode(path, dotencode): ''' Encodes filenames containing names reserved by Windows or which end in period or space. Does not touch other single reserved characters c. Specifically, c in '\\:*?"<>|' or ord(c) <= 31 are *not* encoded here. Additionally encodes space or period at the beginning, if dotencode is True. Parameter path is assumed to be all lowercase. A segment only needs encoding if a reserved name appears as a basename (e.g. "aux", "aux.foo"). A directory or file named "foo.aux" doesn't need encoding. >>> s = b'.foo/aux.txt/txt.aux/con/prn/nul/foo.' >>> _auxencode(s.split(b'/'), True) ['~2efoo', 'au~78.txt', 'txt.aux', 'co~6e', 'pr~6e', 'nu~6c', 'foo~2e'] >>> s = b'.com1com2/lpt9.lpt4.lpt1/conprn/com0/lpt0/foo.' >>> _auxencode(s.split(b'/'), False) ['.com1com2', 'lp~749.lpt4.lpt1', 'conprn', 'com0', 'lpt0', 'foo~2e'] >>> _auxencode([b'foo. '], True) ['foo.~20'] >>> _auxencode([b' .foo'], True) ['~20.foo'] ''' for i, n in enumerate(path): if not n: continue if dotencode and n[0] in b'. ': n = b"~%02x" % ord(n[0:1]) + n[1:] path[i] = n else: l = n.find(b'.') if l == -1: l = len(n) if (l == 3 and n[:3] in _winres3) or ( l == 4 and n[3:4] <= b'9' and n[3:4] >= b'1' and n[:3] in _winres4 ): # encode third letter ('aux' -> 'au~78') ec = b"~%02x" % ord(n[2:3]) n = n[0:2] + ec + n[3:] path[i] = n if n[-1] in b'. ': # encode last period or space ('foo...' -> 'foo..~2e') path[i] = n[:-1] + b"~%02x" % ord(n[-1:]) return path _maxstorepathlen = 120 _dirprefixlen = 8 _maxshortdirslen = 8 * (_dirprefixlen + 1) - 4 def _hashencode(path, dotencode): digest = node.hex(hashutil.sha1(path).digest()) le = lowerencode(path[5:]).split(b'/') # skips prefix 'data/' or 'meta/' parts = _auxencode(le, dotencode) basename = parts[-1] _root, ext = os.path.splitext(basename) sdirs = [] sdirslen = 0 for p in parts[:-1]: d = p[:_dirprefixlen] if d[-1] in b'. ': # Windows can't access dirs ending in period or space d = d[:-1] + b'_' if sdirslen == 0: t = len(d) else: t = sdirslen + 1 + len(d) if t > _maxshortdirslen: break sdirs.append(d) sdirslen = t dirs = b'/'.join(sdirs) if len(dirs) > 0: dirs += b'/' res = b'dh/' + dirs + digest + ext spaceleft = _maxstorepathlen - len(res) if spaceleft > 0: filler = basename[:spaceleft] res = b'dh/' + dirs + filler + digest + ext return res def _hybridencode(path, dotencode): '''encodes path with a length limit Encodes all paths that begin with 'data/', according to the following. Default encoding (reversible): Encodes all uppercase letters 'X' as '_x'. All reserved or illegal characters are encoded as '~xx', where xx is the two digit hex code of the character (see encodefilename). Relevant path components consisting of Windows reserved filenames are masked by encoding the third character ('aux' -> 'au~78', see _auxencode). Hashed encoding (not reversible): If the default-encoded path is longer than _maxstorepathlen, a non-reversible hybrid hashing of the path is done instead. This encoding uses up to _dirprefixlen characters of all directory levels of the lowerencoded path, but not more levels than can fit into _maxshortdirslen. Then follows the filler followed by the sha digest of the full path. The filler is the beginning of the basename of the lowerencoded path (the basename is everything after the last path separator). The filler is as long as possible, filling in characters from the basename until the encoded path has _maxstorepathlen characters (or all chars of the basename have been taken). The extension (e.g. '.i' or '.d') is preserved. The string 'data/' at the beginning is replaced with 'dh/', if the hashed encoding was used. ''' path = encodedir(path) ef = _encodefname(path).split(b'/') res = b'/'.join(_auxencode(ef, dotencode)) if len(res) > _maxstorepathlen: res = _hashencode(path, dotencode) return res def _pathencode(path): de = encodedir(path) if len(path) > _maxstorepathlen: return _hashencode(de, True) ef = _encodefname(de).split(b'/') res = b'/'.join(_auxencode(ef, True)) if len(res) > _maxstorepathlen: return _hashencode(de, True) return res _pathencode = getattr(parsers, 'pathencode', _pathencode) def _plainhybridencode(f): return _hybridencode(f, False) def _calcmode(vfs): try: # files in .hg/ will be created using this mode mode = vfs.stat().st_mode # avoid some useless chmods if (0o777 & ~util.umask) == (0o777 & mode): mode = None except OSError: mode = None return mode _data = [ b'bookmarks', b'narrowspec', b'data', b'meta', b'00manifest.d', b'00manifest.i', b'00changelog.d', b'00changelog.i', b'phaseroots', b'obsstore', b'requires', ] def isrevlog(f, kind, st): return kind == stat.S_IFREG and f[-2:] in (b'.i', b'.d') class basicstore(object): '''base class for local repository stores''' def __init__(self, path, vfstype): vfs = vfstype(path) self.path = vfs.base self.createmode = _calcmode(vfs) vfs.createmode = self.createmode self.rawvfs = vfs self.vfs = vfsmod.filtervfs(vfs, encodedir) self.opener = self.vfs def join(self, f): return self.path + b'/' + encodedir(f) def _walk(self, relpath, recurse, filefilter=isrevlog): '''yields (unencoded, encoded, size)''' path = self.path if relpath: path += b'/' + relpath striplen = len(self.path) + 1 l = [] if self.rawvfs.isdir(path): visit = [path] readdir = self.rawvfs.readdir while visit: p = visit.pop() for f, kind, st in readdir(p, stat=True): fp = p + b'/' + f if filefilter(f, kind, st): n = util.pconvert(fp[striplen:]) l.append((decodedir(n), n, st.st_size)) elif kind == stat.S_IFDIR and recurse: visit.append(fp) l.sort() return l def changelog(self, trypending): return changelog.changelog(self.vfs, trypending=trypending) def manifestlog(self, repo, storenarrowmatch): rootstore = manifest.manifestrevlog(self.vfs) return manifest.manifestlog(self.vfs, repo, rootstore, storenarrowmatch) def datafiles(self, matcher=None): return self._walk(b'data', True) + self._walk(b'meta', True) def topfiles(self): # yield manifest before changelog return reversed(self._walk(b'', False)) def walk(self, matcher=None): '''yields (unencoded, encoded, size) if a matcher is passed, storage files of only those tracked paths are passed with matches the matcher ''' # yield data files first for x in self.datafiles(matcher): yield x for x in self.topfiles(): yield x def copylist(self): return _data def write(self, tr): pass def invalidatecaches(self): pass def markremoved(self, fn): pass def __contains__(self, path): '''Checks if the store contains path''' path = b"/".join((b"data", path)) # file? if self.vfs.exists(path + b".i"): return True # dir? if not path.endswith(b"/"): path = path + b"/" return self.vfs.exists(path) class encodedstore(basicstore): def __init__(self, path, vfstype): vfs = vfstype(path + b'/store') self.path = vfs.base self.createmode = _calcmode(vfs) vfs.createmode = self.createmode self.rawvfs = vfs self.vfs = vfsmod.filtervfs(vfs, encodefilename) self.opener = self.vfs def datafiles(self, matcher=None): for a, b, size in super(encodedstore, self).datafiles(): try: a = decodefilename(a) except KeyError: a = None if a is not None and not _matchtrackedpath(a, matcher): continue yield a, b, size def join(self, f): return self.path + b'/' + encodefilename(f) def copylist(self): return [b'requires', b'00changelog.i'] + [b'store/' + f for f in _data] class fncache(object): # the filename used to be partially encoded # hence the encodedir/decodedir dance def __init__(self, vfs): self.vfs = vfs self.entries = None self._dirty = False # set of new additions to fncache self.addls = set() def ensureloaded(self, warn=None): '''read the fncache file if not already read. If the file on disk is corrupted, raise. If warn is provided, warn and keep going instead.''' if self.entries is None: self._load(warn) def _load(self, warn=None): '''fill the entries from the fncache file''' self._dirty = False try: fp = self.vfs(b'fncache', mode=b'rb') except IOError: # skip nonexistent file self.entries = set() return self.entries = set() chunk = b'' for c in iter(functools.partial(fp.read, fncache_chunksize), b''): chunk += c try: p = chunk.rindex(b'\n') self.entries.update(decodedir(chunk[: p + 1]).splitlines()) chunk = chunk[p + 1 :] except ValueError: # substring '\n' not found, maybe the entry is bigger than the # chunksize, so let's keep iterating pass if chunk: msg = _(b"fncache does not ends with a newline") if warn: warn(msg + b'\n') else: raise error.Abort( msg, hint=_( b"use 'hg debugrebuildfncache' to " b"rebuild the fncache" ), ) self._checkentries(fp, warn) fp.close() def _checkentries(self, fp, warn): """ make sure there is no empty string in entries """ if b'' in self.entries: fp.seek(0) for n, line in enumerate(util.iterfile(fp)): if not line.rstrip(b'\n'): t = _(b'invalid entry in fncache, line %d') % (n + 1) if warn: warn(t + b'\n') else: raise error.Abort(t) def write(self, tr): if self._dirty: assert self.entries is not None self.entries = self.entries | self.addls self.addls = set() tr.addbackup(b'fncache') fp = self.vfs(b'fncache', mode=b'wb', atomictemp=True) if self.entries: fp.write(encodedir(b'\n'.join(self.entries) + b'\n')) fp.close() self._dirty = False if self.addls: # if we have just new entries, let's append them to the fncache tr.addbackup(b'fncache') fp = self.vfs(b'fncache', mode=b'ab', atomictemp=True) if self.addls: fp.write(encodedir(b'\n'.join(self.addls) + b'\n')) fp.close() self.entries = None self.addls = set() def add(self, fn): if self.entries is None: self._load() if fn not in self.entries: self.addls.add(fn) def remove(self, fn): if self.entries is None: self._load() if fn in self.addls: self.addls.remove(fn) return try: self.entries.remove(fn) self._dirty = True except KeyError: pass def __contains__(self, fn): if fn in self.addls: return True if self.entries is None: self._load() return fn in self.entries def __iter__(self): if self.entries is None: self._load() return iter(self.entries | self.addls) class _fncachevfs(vfsmod.proxyvfs): def __init__(self, vfs, fnc, encode): vfsmod.proxyvfs.__init__(self, vfs) self.fncache = fnc self.encode = encode def __call__(self, path, mode=b'r', *args, **kw): encoded = self.encode(path) if mode not in (b'r', b'rb') and ( path.startswith(b'data/') or path.startswith(b'meta/') ): # do not trigger a fncache load when adding a file that already is # known to exist. notload = self.fncache.entries is None and self.vfs.exists(encoded) if notload and b'a' in mode and not self.vfs.stat(encoded).st_size: # when appending to an existing file, if the file has size zero, # it should be considered as missing. Such zero-size files are # the result of truncation when a transaction is aborted. notload = False if not notload: self.fncache.add(path) return self.vfs(encoded, mode, *args, **kw) def join(self, path): if path: return self.vfs.join(self.encode(path)) else: return self.vfs.join(path) class fncachestore(basicstore): def __init__(self, path, vfstype, dotencode): if dotencode: encode = _pathencode else: encode = _plainhybridencode self.encode = encode vfs = vfstype(path + b'/store') self.path = vfs.base self.pathsep = self.path + b'/' self.createmode = _calcmode(vfs) vfs.createmode = self.createmode self.rawvfs = vfs fnc = fncache(vfs) self.fncache = fnc self.vfs = _fncachevfs(vfs, fnc, encode) self.opener = self.vfs def join(self, f): return self.pathsep + self.encode(f) def getsize(self, path): return self.rawvfs.stat(path).st_size def datafiles(self, matcher=None): for f in sorted(self.fncache): if not _matchtrackedpath(f, matcher): continue ef = self.encode(f) try: yield f, ef, self.getsize(ef) except OSError as err: if err.errno != errno.ENOENT: raise def copylist(self): d = ( b'bookmarks', b'narrowspec', b'data', b'meta', b'dh', b'fncache', b'phaseroots', b'obsstore', b'00manifest.d', b'00manifest.i', b'00changelog.d', b'00changelog.i', b'requires', ) return [b'requires', b'00changelog.i'] + [b'store/' + f for f in d] def write(self, tr): self.fncache.write(tr) def invalidatecaches(self): self.fncache.entries = None self.fncache.addls = set() def markremoved(self, fn): self.fncache.remove(fn) def _exists(self, f): ef = self.encode(f) try: self.getsize(ef) return True except OSError as err: if err.errno != errno.ENOENT: raise # nonexistent entry return False def __contains__(self, path): '''Checks if the store contains path''' path = b"/".join((b"data", path)) # check for files (exact match) e = path + b'.i' if e in self.fncache and self._exists(e): return True # now check for directories (prefix match) if not path.endswith(b'/'): path += b'/' for e in self.fncache: if e.startswith(path) and self._exists(e): return True return False