Mercurial > public > mercurial-scm > hg
annotate mercurial/pvec.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 | a89aa2d7b34d |
| children | d4ba4d51f85f |
| rev | line source |
|---|---|
| 16249 | 1 # pvec.py - probabilistic vector clocks for Mercurial |
| 2 # | |
| 3 # Copyright 2012 Matt Mackall <mpm@selenic.com> | |
| 4 # | |
| 5 # This software may be used and distributed according to the terms of the | |
| 6 # GNU General Public License version 2 or any later version. | |
| 7 | |
| 8 ''' | |
| 9 A "pvec" is a changeset property based on the theory of vector clocks | |
| 10 that can be compared to discover relatedness without consulting a | |
| 11 graph. This can be useful for tasks like determining how a | |
| 12 disconnected patch relates to a repository. | |
| 13 | |
| 14 Currently a pvec consist of 448 bits, of which 24 are 'depth' and the | |
| 15 remainder are a bit vector. It is represented as a 70-character base85 | |
| 16 string. | |
| 17 | |
| 18 Construction: | |
| 19 | |
| 20 - a root changeset has a depth of 0 and a bit vector based on its hash | |
| 21 - a normal commit has a changeset where depth is increased by one and | |
| 22 one bit vector bit is flipped based on its hash | |
| 23 - a merge changeset pvec is constructed by copying changes from one pvec into | |
| 24 the other to balance its depth | |
| 25 | |
| 26 Properties: | |
| 27 | |
| 28 - for linear changes, difference in depth is always <= hamming distance | |
| 29 - otherwise, changes are probably divergent | |
| 30 - when hamming distance is < 200, we can reliably detect when pvecs are near | |
| 31 | |
| 32 Issues: | |
| 33 | |
| 34 - hamming distance ceases to work over distances of ~ 200 | |
| 35 - detecting divergence is less accurate when the common ancestor is very close | |
| 36 to either revision or total distance is high | |
| 37 - this could probably be improved by modeling the relation between | |
| 38 delta and hdist | |
| 39 | |
| 40 Uses: | |
| 41 | |
| 42 - a patch pvec can be used to locate the nearest available common ancestor for | |
| 43 resolving conflicts | |
| 44 - ordering of patches can be established without a DAG | |
| 45 - two head pvecs can be compared to determine whether push/pull/merge is needed | |
| 46 and approximately how many changesets are involved | |
| 47 - can be used to find a heuristic divergence measure between changesets on | |
| 48 different branches | |
| 49 ''' | |
| 50 | |
|
44602
a89aa2d7b34d
pvec: drop an unused `from __future__ import division`
Martin von Zweigbergk <martinvonz@google.com>
parents:
43793
diff
changeset
|
51 from __future__ import absolute_import |
|
27501
983e93d88193
pvec: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
24339
diff
changeset
|
52 |
|
983e93d88193
pvec: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
24339
diff
changeset
|
53 from .node import nullrev |
|
983e93d88193
pvec: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
24339
diff
changeset
|
54 from . import ( |
|
38783
e7aa113b14f7
global: use pycompat.xrange()
Gregory Szorc <gregory.szorc@gmail.com>
parents:
32201
diff
changeset
|
55 pycompat, |
|
27501
983e93d88193
pvec: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
24339
diff
changeset
|
56 util, |
|
983e93d88193
pvec: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
24339
diff
changeset
|
57 ) |
| 16249 | 58 |
|
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
38783
diff
changeset
|
59 _size = 448 # 70 chars b85-encoded |
|
43465
90aac60b6697
pvec: migrate to modern integer division
Augie Fackler <augie@google.com>
parents:
43463
diff
changeset
|
60 _bytes = _size // 8 |
| 16249 | 61 _depthbits = 24 |
|
43465
90aac60b6697
pvec: migrate to modern integer division
Augie Fackler <augie@google.com>
parents:
43463
diff
changeset
|
62 _depthbytes = _depthbits // 8 |
| 16249 | 63 _vecbytes = _bytes - _depthbytes |
| 64 _vecbits = _vecbytes * 8 | |
|
43465
90aac60b6697
pvec: migrate to modern integer division
Augie Fackler <augie@google.com>
parents:
43463
diff
changeset
|
65 _radius = (_vecbits - 30) // 2 # high probability vectors are related |
|
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
38783
diff
changeset
|
66 |
| 16249 | 67 |
| 68 def _bin(bs): | |
| 69 '''convert a bytestring to a long''' | |
| 70 v = 0 | |
| 71 for b in bs: | |
| 72 v = v * 256 + ord(b) | |
| 73 return v | |
| 74 | |
|
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
38783
diff
changeset
|
75 |
| 16249 | 76 def _str(v, l): |
|
43479
8e89b6e1e0cd
pvec: add an explicit type hint to help pytype
Augie Fackler <augie@google.com>
parents:
43465
diff
changeset
|
77 # type: (int, int) -> bytes |
|
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
78 bs = b"" |
|
38783
e7aa113b14f7
global: use pycompat.xrange()
Gregory Szorc <gregory.szorc@gmail.com>
parents:
32201
diff
changeset
|
79 for p in pycompat.xrange(l): |
|
43463
271af23d01a9
pvec: fix overlooked chr() call
Augie Fackler <augie@google.com>
parents:
43115
diff
changeset
|
80 bs = pycompat.bytechr(v & 255) + bs |
| 16249 | 81 v >>= 8 |
| 82 return bs | |
| 83 | |
|
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
38783
diff
changeset
|
84 |
| 16249 | 85 def _split(b): |
| 86 '''depth and bitvec''' | |
| 87 return _bin(b[:_depthbytes]), _bin(b[_depthbytes:]) | |
| 88 | |
|
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
38783
diff
changeset
|
89 |
| 16249 | 90 def _join(depth, bitvec): |
| 91 return _str(depth, _depthbytes) + _str(bitvec, _vecbytes) | |
| 92 | |
|
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
38783
diff
changeset
|
93 |
| 16249 | 94 def _hweight(x): |
| 95 c = 0 | |
| 96 while x: | |
| 97 if x & 1: | |
| 98 c += 1 | |
| 99 x >>= 1 | |
| 100 return c | |
|
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
38783
diff
changeset
|
101 |
|
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
38783
diff
changeset
|
102 |
|
38783
e7aa113b14f7
global: use pycompat.xrange()
Gregory Szorc <gregory.szorc@gmail.com>
parents:
32201
diff
changeset
|
103 _htab = [_hweight(x) for x in pycompat.xrange(256)] |
| 16249 | 104 |
|
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
38783
diff
changeset
|
105 |
| 16249 | 106 def _hamming(a, b): |
| 107 '''find the hamming distance between two longs''' | |
| 108 d = a ^ b | |
| 109 c = 0 | |
| 110 while d: | |
|
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
38783
diff
changeset
|
111 c += _htab[d & 0xFF] |
| 16249 | 112 d >>= 8 |
| 113 return c | |
| 114 | |
|
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
38783
diff
changeset
|
115 |
| 16249 | 116 def _mergevec(x, y, c): |
| 117 # Ideally, this function would be x ^ y ^ ancestor, but finding | |
| 118 # ancestors is a nuisance. So instead we find the minimal number | |
| 119 # of changes to balance the depth and hamming distance | |
| 120 | |
| 121 d1, v1 = x | |
| 122 d2, v2 = y | |
| 123 if d1 < d2: | |
| 124 d1, d2, v1, v2 = d2, d1, v2, v1 | |
| 125 | |
| 126 hdist = _hamming(v1, v2) | |
| 127 ddist = d1 - d2 | |
| 128 v = v1 | |
|
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
38783
diff
changeset
|
129 m = v1 ^ v2 # mask of different bits |
| 16249 | 130 i = 1 |
| 131 | |
| 132 if hdist > ddist: | |
| 133 # if delta = 10 and hdist = 100, then we need to go up 55 steps | |
| 134 # to the ancestor and down 45 | |
|
43465
90aac60b6697
pvec: migrate to modern integer division
Augie Fackler <augie@google.com>
parents:
43463
diff
changeset
|
135 changes = (hdist - ddist + 1) // 2 |
| 16249 | 136 else: |
| 137 # must make at least one change | |
| 138 changes = 1 | |
| 139 depth = d1 + changes | |
| 140 | |
| 141 # copy changes from v2 | |
| 142 if m: | |
| 143 while changes: | |
| 144 if m & i: | |
| 145 v ^= i | |
| 146 changes -= 1 | |
| 147 i <<= 1 | |
| 148 else: | |
| 149 v = _flipbit(v, c) | |
| 150 | |
| 151 return depth, v | |
| 152 | |
|
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
38783
diff
changeset
|
153 |
| 16249 | 154 def _flipbit(v, node): |
| 155 # converting bit strings to longs is slow | |
|
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
38783
diff
changeset
|
156 bit = (hash(node) & 0xFFFFFFFF) % _vecbits |
|
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
38783
diff
changeset
|
157 return v ^ (1 << bit) |
|
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
38783
diff
changeset
|
158 |
| 16249 | 159 |
| 160 def ctxpvec(ctx): | |
| 161 '''construct a pvec for ctx while filling in the cache''' | |
|
24339
bcc319d936a3
pvec: replace 'ctx._repo' with 'ctx.repo()'
Matt Harbison <matt_harbison@yahoo.com>
parents:
18918
diff
changeset
|
162 r = ctx.repo() |
|
43115
4aa72cdf616f
py3: delete b'' prefix from safehasattr arguments
Martin von Zweigbergk <martinvonz@google.com>
parents:
43077
diff
changeset
|
163 if not util.safehasattr(r, "_pveccache"): |
| 16249 | 164 r._pveccache = {} |
| 165 pvc = r._pveccache | |
| 166 if ctx.rev() not in pvc: | |
| 167 cl = r.changelog | |
|
38783
e7aa113b14f7
global: use pycompat.xrange()
Gregory Szorc <gregory.szorc@gmail.com>
parents:
32201
diff
changeset
|
168 for n in pycompat.xrange(ctx.rev() + 1): |
| 16249 | 169 if n not in pvc: |
| 170 node = cl.node(n) | |
| 171 p1, p2 = cl.parentrevs(n) | |
| 172 if p1 == nullrev: | |
| 173 # start with a 'random' vector at root | |
| 174 pvc[n] = (0, _bin((node * 3)[:_vecbytes])) | |
| 175 elif p2 == nullrev: | |
| 176 d, v = pvc[p1] | |
| 177 pvc[n] = (d + 1, _flipbit(v, node)) | |
| 178 else: | |
| 179 pvc[n] = _mergevec(pvc[p1], pvc[p2], node) | |
| 180 bs = _join(*pvc[ctx.rev()]) | |
|
32201
4462a981e8df
base85: proxy through util module
Yuya Nishihara <yuya@tcha.org>
parents:
27501
diff
changeset
|
181 return pvec(util.b85encode(bs)) |
| 16249 | 182 |
|
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
38783
diff
changeset
|
183 |
| 16249 | 184 class pvec(object): |
| 185 def __init__(self, hashorctx): | |
|
43746
10662ac7849e
pvec: fix a `str` type conditional for py3
Matt Harbison <matt_harbison@yahoo.com>
parents:
43115
diff
changeset
|
186 if isinstance(hashorctx, bytes): |
| 16249 | 187 self._bs = hashorctx |
|
32201
4462a981e8df
base85: proxy through util module
Yuya Nishihara <yuya@tcha.org>
parents:
27501
diff
changeset
|
188 self._depth, self._vec = _split(util.b85decode(hashorctx)) |
| 16249 | 189 else: |
|
18918
5093d2a87ff6
pvec: use the correct name for an identifier
Bryan O'Sullivan <bryano@fb.com>
parents:
17424
diff
changeset
|
190 self._vec = ctxpvec(hashorctx) |
| 16249 | 191 |
| 192 def __str__(self): | |
| 193 return self._bs | |
| 194 | |
| 195 def __eq__(self, b): | |
| 196 return self._vec == b._vec and self._depth == b._depth | |
| 197 | |
| 198 def __lt__(self, b): | |
| 199 delta = b._depth - self._depth | |
| 200 if delta < 0: | |
|
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
38783
diff
changeset
|
201 return False # always correct |
| 16249 | 202 if _hamming(self._vec, b._vec) > delta: |
| 203 return False | |
| 204 return True | |
| 205 | |
| 206 def __gt__(self, b): | |
| 207 return b < self | |
| 208 | |
| 209 def __or__(self, b): | |
| 210 delta = abs(b._depth - self._depth) | |
| 211 if _hamming(self._vec, b._vec) <= delta: | |
| 212 return False | |
| 213 return True | |
| 214 | |
| 215 def __sub__(self, b): | |
| 216 if self | b: | |
|
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
217 raise ValueError(b"concurrent pvecs") |
| 16249 | 218 return self._depth - b._depth |
| 219 | |
| 220 def distance(self, b): | |
| 221 d = abs(b._depth - self._depth) | |
| 222 h = _hamming(self._vec, b._vec) | |
| 223 return max(d, h) | |
| 224 | |
| 225 def near(self, b): | |
| 226 dist = abs(b.depth - self._depth) | |
| 227 if dist > _radius or _hamming(self._vec, b._vec) > _radius: | |
| 228 return False |