copies-rust: tokenize all paths into integer
authorPierre-Yves David <pierre-yves.david@octobus.net>
Sat, 25 Apr 2020 12:37:46 +0200
changeset 46151 c6bc77f7e593
parent 46150 a132aa5979ec
child 46152 e166e8a035a7
copies-rust: tokenize all paths into integer Copy information for each changesets tend to affect a small new number of path. However, each of these path might be handled a large number of time. Handling HgPathBuf (aka `Vec<u8>`) is expensive. Handling integer is cheap. With this patch we: - turn any input path into an integer "token" early, - do all the internal logic using such "token", - turn "token" back into path right before returning a result. This gives use a quite significant performance boost in our slower cases. Repo Case Source-Rev Dest-Rev # of revisions old time new time Difference Factor time per rev --------------------------------------------------------------------------------------------------------------------------------------------------------------- pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 6780 revs, 0.092828 s, 0.081225 s, -0.011603 s, × 0.8750, 11 µs/rev pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 43645 revs, 0.711975 s, 0.586011 s, -0.125964 s, × 0.8231, 13 µs/rev pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 11316 revs, 0.124505 s, 0.114173 s, -0.010332 s, × 0.9170, 10 µs/rev netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 5750 revs, 0.072072 s, 0.061004 s, -0.011068 s, × 0.8464, 10 µs/rev netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 66949 revs, 0.682732 s, 0.535874 s, -0.146858 s, × 0.7849, 8 µs/rev mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 153721 revs, 1.935918 s, 1.781383 s, -0.154535 s, × 0.9202, 11 µs/rev mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 204976 revs, 2.827320 s, 2.603867 s, -0.223453 s, × 0.9210, 12 µs/rev mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 97052 revs, 3.243010 s, 1.529120 s, -1.713890 s, × 0.4715, 15 µs/rev mozilla-try x00000_revs_x_added_0_copies 6a320851d377 1ebb79acd503 : 363753 revs, 5.693818 s, 4.842699 s, -0.851119 s, × 0.8505, 13 µs/rev mozilla-try x00000_revs_x_added_x_copies 5173c4b6f97c 95d83ee7242d : 362229 revs, 5.677655 s, 4.761732 s, -0.915923 s, × 0.8387, 13 µs/rev mozilla-try x00000_revs_x000_added_x_copies 9126823d0e9c ca82787bb23c : 359344 revs, 5.563370 s, 4.733912 s, -0.829458 s, × 0.8509, 13 µs/rev mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 192665 revs, 2.864099 s, 2.593410 s, -0.270689 s, × 0.9055, 13 µs/rev mozilla-try x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 228985 revs, 113.297287 s, 41.041198 s, -72.256089 s, × 0.3622, 179 µs/rev mozilla-try x00000_revs_x00000_added_x000_copies 9b2a99adc05e 8e29777b48e6 : 382065 revs, 59.498652 s, 27.915689 s, -31.582963 s, × 0.4692, 73 µs/rev Full timing comparison between this revision and the previous one: Repo Case Source-Rev Dest-Rev # of revisions old time new time Difference Factor time per rev --------------------------------------------------------------------------------------------------------------------------------------------------------------- mercurial x_revs_x_added_0_copies ad6b123de1c7 39cfcef4f463 : 1 revs, 0.000042 s, 0.000042 s, +0.000000 s, × 1.0000, 42 µs/rev mercurial x_revs_x_added_x_copies 2b1c78674230 0c1d10351869 : 6 revs, 0.000104 s, 0.000110 s, +0.000006 s, × 1.0577, 18 µs/rev mercurial x000_revs_x000_added_x_copies 81f8ff2a9bf2 dd3267698d84 : 1032 revs, 0.004913 s, 0.004918 s, +0.000005 s, × 1.0010, 4 µs/rev pypy x_revs_x_added_0_copies aed021ee8ae8 099ed31b181b : 9 revs, 0.000191 s, 0.000195 s, +0.000004 s, × 1.0209, 21 µs/rev pypy x_revs_x000_added_0_copies 4aa4e1f8e19a 359343b9ac0e : 1 revs, 0.000050 s, 0.000049 s, -0.000001 s, × 0.9800, 49 µs/rev pypy x_revs_x_added_x_copies ac52eb7bbbb0 72e022663155 : 7 revs, 0.000112 s, 0.000112 s, +0.000000 s, × 1.0000, 16 µs/rev pypy x_revs_x00_added_x_copies c3b14617fbd7 ace7255d9a26 : 1 revs, 0.000288 s, 0.000324 s, +0.000036 s, × 1.1250, 324 µs/rev pypy x_revs_x000_added_x000_copies df6f7a526b60 a83dc6a2d56f : 6 revs, 0.010411 s, 0.010611 s, +0.000200 s, × 1.0192, 1768 µs/rev pypy x000_revs_xx00_added_0_copies 89a76aede314 2f22446ff07e : 4785 revs, 0.052852 s, 0.050835 s, -0.002017 s, × 0.9618, 10 µs/rev pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 6780 revs, 0.092828 s, 0.081225 s, -0.011603 s, × 0.8750, 11 µs/rev pypy x000_revs_x000_added_x000_copies 89a76aede314 7b3dda341c84 : 5441 revs, 0.063269 s, 0.061291 s, -0.001978 s, × 0.9687, 11 µs/rev pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 43645 revs, 0.711975 s, 0.586011 s, -0.125964 s, × 0.8231, 13 µs/rev pypy x0000_revs_xx000_added_0_copies bf2c629d0071 4ffed77c095c : 2 revs, 0.012771 s, 0.012824 s, +0.000053 s, × 1.0042, 6412 µs/rev pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 11316 revs, 0.124505 s, 0.114173 s, -0.010332 s, × 0.9170, 10 µs/rev netbeans x_revs_x_added_0_copies fb0955ffcbcd a01e9239f9e7 : 2 revs, 0.000082 s, 0.000085 s, +0.000003 s, × 1.0366, 42 µs/rev netbeans x_revs_x000_added_0_copies 6f360122949f 20eb231cc7d0 : 2 revs, 0.000111 s, 0.000108 s, -0.000003 s, × 0.9730, 54 µs/rev netbeans x_revs_x_added_x_copies 1ada3faf6fb6 5a39d12eecf4 : 3 revs, 0.000171 s, 0.000175 s, +0.000004 s, × 1.0234, 58 µs/rev netbeans x_revs_x00_added_x_copies 35be93ba1e2c 9eec5e90c05f : 9 revs, 0.000708 s, 0.000719 s, +0.000011 s, × 1.0155, 79 µs/rev netbeans x000_revs_xx00_added_0_copies eac3045b4fdd 51d4ae7f1290 : 1421 revs, 0.010608 s, 0.010175 s, -0.000433 s, × 0.9592, 7 µs/rev netbeans x000_revs_x000_added_x_copies e2063d266acd 6081d72689dc : 1533 revs, 0.015635 s, 0.015569 s, -0.000066 s, × 0.9958, 10 µs/rev netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 5750 revs, 0.072072 s, 0.061004 s, -0.011068 s, × 0.8464, 10 µs/rev netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 66949 revs, 0.682732 s, 0.535874 s, -0.146858 s, × 0.7849, 8 µs/rev mozilla-central x_revs_x_added_0_copies 3697f962bb7b 7015fcdd43a2 : 2 revs, 0.000090 s, 0.000090 s, +0.000000 s, × 1.0000, 45 µs/rev mozilla-central x_revs_x000_added_0_copies dd390860c6c9 40d0c5bed75d : 8 revs, 0.000210 s, 0.000281 s, +0.000071 s, × 1.3381, 35 µs/rev mozilla-central x_revs_x_added_x_copies 8d198483ae3b 14207ffc2b2f : 9 revs, 0.000182 s, 0.000187 s, +0.000005 s, × 1.0275, 20 µs/rev mozilla-central x_revs_x00_added_x_copies 98cbc58cc6bc 446a150332c3 : 7 revs, 0.000594 s, 0.000660 s, +0.000066 s, × 1.1111, 94 µs/rev mozilla-central x_revs_x000_added_x000_copies 3c684b4b8f68 0a5e72d1b479 : 3 revs, 0.003102 s, 0.003385 s, +0.000283 s, × 1.0912, 1128 µs/rev mozilla-central x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 0.060234 s, 0.069812 s, +0.009578 s, × 1.1590, 11635 µs/rev mozilla-central x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.006300 s, 0.006503 s, +0.000203 s, × 1.0322, 4 µs/rev mozilla-central x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.004817 s, 0.004988 s, +0.000171 s, × 1.0355, 121 µs/rev mozilla-central x000_revs_x000_added_x000_copies 7c97034feb78 4407bd0c6330 : 7839 revs, 0.065451 s, 0.063963 s, -0.001488 s, × 0.9773, 8 µs/rev mozilla-central x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 0.026282 s, 0.026225 s, -0.000057 s, × 0.9978, 42 µs/rev mozilla-central x0000_revs_xx000_added_x000_copies f78c615a656c 96a38b690156 : 30263 revs, 0.206873 s, 0.201377 s, -0.005496 s, × 0.9734, 6 µs/rev mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 153721 revs, 1.935918 s, 1.781383 s, -0.154535 s, × 0.9202, 11 µs/rev mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 204976 revs, 2.827320 s, 2.603867 s, -0.223453 s, × 0.9210, 12 µs/rev mozilla-try x_revs_x_added_0_copies aaf6dde0deb8 9790f499805a : 2 revs, 0.000842 s, 0.000845 s, +0.000003 s, × 1.0036, 422 µs/rev mozilla-try x_revs_x000_added_0_copies d8d0222927b4 5bb8ce8c7450 : 2 revs, 0.000870 s, 0.000862 s, -0.000008 s, × 0.9908, 431 µs/rev mozilla-try x_revs_x_added_x_copies 092fcca11bdb 936255a0384a : 4 revs, 0.000165 s, 0.000161 s, -0.000004 s, × 0.9758, 40 µs/rev mozilla-try x_revs_x00_added_x_copies b53d2fadbdb5 017afae788ec : 2 revs, 0.001145 s, 0.001163 s, +0.000018 s, × 1.0157, 581 µs/rev mozilla-try x_revs_x000_added_x000_copies 20408ad61ce5 6f0ee96e21ad : 1 revs, 0.026500 s, 0.032414 s, +0.005914 s, × 1.2232, 32414 µs/rev mozilla-try x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 0.059407 s, 0.070149 s, +0.010742 s, × 1.1808, 11691 µs/rev mozilla-try x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.006325 s, 0.006526 s, +0.000201 s, × 1.0318, 4 µs/rev mozilla-try x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.005171 s, 0.005187 s, +0.000016 s, × 1.0031, 126 µs/rev mozilla-try x000_revs_x000_added_x000_copies 1346fd0130e4 4c65cbdabc1f : 6657 revs, 0.066837 s, 0.065047 s, -0.001790 s, × 0.9732, 9 µs/rev mozilla-try x0000_revs_x_added_0_copies 63519bfd42ee a36a2a865d92 : 40314 revs, 0.314252 s, 0.301129 s, -0.013123 s, × 0.9582, 7 µs/rev mozilla-try x0000_revs_x_added_x_copies 9fe69ff0762d bcabf2a78927 : 38690 revs, 0.304160 s, 0.280683 s, -0.023477 s, × 0.9228, 7 µs/rev mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 8598 revs, 0.089223 s, 0.084897 s, -0.004326 s, × 0.9515, 9 µs/rev mozilla-try x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 0.026711 s, 0.026620 s, -0.000091 s, × 0.9966, 43 µs/rev mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 97052 revs, 3.243010 s, 1.529120 s, -1.713890 s, × 0.4715, 15 µs/rev mozilla-try x0000_revs_x0000_added_x0000_copies e928c65095ed e951f4ad123a : 52031 revs, 0.756500 s, 0.738709 s, -0.017791 s, × 0.9765, 14 µs/rev mozilla-try x00000_revs_x_added_0_copies 6a320851d377 1ebb79acd503 : 363753 revs, 5.693818 s, 4.842699 s, -0.851119 s, × 0.8505, 13 µs/rev mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 34414 revs, 0.590904 s, 0.596946 s, +0.006042 s, × 1.0102, 17 µs/rev mozilla-try x00000_revs_x_added_x_copies 5173c4b6f97c 95d83ee7242d : 362229 revs, 5.677655 s, 4.761732 s, -0.915923 s, × 0.8387, 13 µs/rev mozilla-try x00000_revs_x000_added_x_copies 9126823d0e9c ca82787bb23c : 359344 revs, 5.563370 s, 4.733912 s, -0.829458 s, × 0.8509, 13 µs/rev mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 192665 revs, 2.864099 s, 2.593410 s, -0.270689 s, × 0.9055, 13 µs/rev mozilla-try x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 228985 revs, 113.297287 s, 41.041198 s, -72.256089 s, × 0.3622, 179 µs/rev mozilla-try x00000_revs_x00000_added_x000_copies 9b2a99adc05e 8e29777b48e6 : 382065 revs, 59.498652 s, 27.915689 s, -31.582963 s, × 0.4692, 73 µs/rev Full timing comparison between this revision and the filelog copy tracing. Repo Case Source-Rev Dest-Rev # of revisions filelog sidedata Difference Factor time per rev --------------------------------------------------------------------------------------------------------------------------------------------------------------- mercurial x_revs_x_added_0_copies ad6b123de1c7 39cfcef4f463 : 1 revs, 0.000903 s, 0.000042 s, -0.000861 s, × 0.0465, 41 µs/rev mercurial x_revs_x_added_x_copies 2b1c78674230 0c1d10351869 : 6 revs, 0.001861 s, 0.000110 s, -0.001751 s, × 0.0591, 18 µs/rev mercurial x000_revs_x000_added_x_copies 81f8ff2a9bf2 dd3267698d84 : 1032 revs, 0.018577 s, 0.004918 s, -0.013659 s, × 0.2647, 4 µs/rev pypy x_revs_x_added_0_copies aed021ee8ae8 099ed31b181b : 9 revs, 0.001519 s, 0.000195 s, -0.001324 s, × 0.1283, 21 µs/rev pypy x_revs_x000_added_0_copies 4aa4e1f8e19a 359343b9ac0e : 1 revs, 0.213855 s, 0.000049 s, -0.350d73 s, × 0.0002, 48 µs/rev pypy x_revs_x_added_x_copies ac52eb7bbbb0 72e022663155 : 7 revs, 0.017022 s, 0.000112 s, -0.016910 s, × 0.0065, 15 µs/rev pypy x_revs_x00_added_x_copies c3b14617fbd7 ace7255d9a26 : 1 revs, 0.019398 s, 0.000324 s, -0.019074 s, × 0.0167, 323 µs/rev pypy x_revs_x000_added_x000_copies df6f7a526b60 a83dc6a2d56f : 6 revs, 0.769467 s, 0.010611 s, -0.758856 s, × 0.0137, 1768 µs/rev pypy x000_revs_xx00_added_0_copies 89a76aede314 2f22446ff07e : 4785 revs, 1.221952 s, 0.050835 s, -1.171117 s, × 0.0416, 10 µs/rev pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 6780 revs, 1.304007 s, 0.081225 s, -1.222782 s, × 0.0622, 11 µs/rev pypy x000_revs_x000_added_x000_copies 89a76aede314 7b3dda341c84 : 5441 revs, 1.686610 s, 0.061291 s, -1.625319 s, × 0.0363, 11 µs/rev pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 43645 revs, 0.001107 s, 0.586011 s, +0.584904 s, × 529.36, 13 µs/rev pypy x0000_revs_xx000_added_0_copies bf2c629d0071 4ffed77c095c : 2 revs, 1.100760 s, 0.012824 s, -1.087936 s, × 0.0116, 6408 µs/rev pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 11316 revs, 1.350547 s, 0.114173 s, -1.236374 s, × 0.0845, 10 µs/rev netbeans x_revs_x_added_0_copies fb0955ffcbcd a01e9239f9e7 : 2 revs, 0.027864 s, 0.000085 s, -0.027779 s, × 0.0030, 42 µs/rev netbeans x_revs_x000_added_0_copies 6f360122949f 20eb231cc7d0 : 2 revs, 0.132479 s, 0.000108 s, -0.132371 s, × 0.0008, 53 µs/rev netbeans x_revs_x_added_x_copies 1ada3faf6fb6 5a39d12eecf4 : 3 revs, 0.025405 s, 0.000175 s, -0.025230 s, × 0.0068, 58 µs/rev netbeans x_revs_x00_added_x_copies 35be93ba1e2c 9eec5e90c05f : 9 revs, 0.053244 s, 0.000719 s, -0.052525 s, × 0.0135, 79 µs/rev netbeans x000_revs_xx00_added_0_copies eac3045b4fdd 51d4ae7f1290 : 1421 revs, 0.038017 s, 0.010175 s, -0.027842 s, × 0.2676, 7 µs/rev netbeans x000_revs_x000_added_x_copies e2063d266acd 6081d72689dc : 1533 revs, 0.198308 s, 0.015569 s, -0.182739 s, × 0.0785, 10 µs/rev netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 5750 revs, 0.949749 s, 0.061004 s, -0.888745 s, × 0.0642, 10 µs/rev netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 66949 revs, 3.932262 s, 0.535874 s, -3.396388 s, × 0.1362, 8 µs/rev mozilla-central x_revs_x_added_0_copies 3697f962bb7b 7015fcdd43a2 : 2 revs, 0.024490 s, 0.000090 s, -0.024400 s, × 0.0036, 44 µs/rev mozilla-central x_revs_x000_added_0_copies dd390860c6c9 40d0c5bed75d : 8 revs, 0.143885 s, 0.000281 s, -0.143604 s, × 0.0019, 35 µs/rev mozilla-central x_revs_x_added_x_copies 8d198483ae3b 14207ffc2b2f : 9 revs, 0.025471 s, 0.000187 s, -0.025284 s, × 0.0073, 20 µs/rev mozilla-central x_revs_x00_added_x_copies 98cbc58cc6bc 446a150332c3 : 7 revs, 0.086013 s, 0.000660 s, -0.085353 s, × 0.0076, 94 µs/rev mozilla-central x_revs_x000_added_x000_copies 3c684b4b8f68 0a5e72d1b479 : 3 revs, 0.200726 s, 0.003385 s, -0.197341 s, × 0.0168, 1127 µs/rev mozilla-central x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 2.224171 s, 0.069812 s, -2.154359 s, × 0.0313, 11633 µs/rev mozilla-central x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.090780 s, 0.006503 s, -0.084277 s, × 0.0716, 4 µs/rev mozilla-central x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.764805 s, 0.004988 s, -0.759817 s, × 0.0065, 121 µs/rev mozilla-central x000_revs_x000_added_x000_copies 7c97034feb78 4407bd0c6330 : 7839 revs, 1.161405 s, 0.063963 s, -1.097442 s, × 0.0550, 8 µs/rev mozilla-central x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 6.816186 s, 0.026225 s, -6.789961 s, × 0.0038, 42 µs/rev mozilla-central x0000_revs_xx000_added_x000_copies f78c615a656c 96a38b690156 : 30263 revs, 3.374819 s, 0.201377 s, -3.173442 s, × 0.0596, 6 µs/rev mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 153721 revs, 16.285469 s, 1.781383 s, -14.504086 s, × 0.1093, 11 µs/rev mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 204976 revs, 21.207733 s, 2.603867 s, -18.603866 s, × 0.1227, 12 µs/rev mozilla-try x_revs_x_added_0_copies aaf6dde0deb8 9790f499805a : 2 revs, 0.080843 s, 0.000845 s, -0.079998 s, × 0.0104, 422 µs/rev mozilla-try x_revs_x000_added_0_copies d8d0222927b4 5bb8ce8c7450 : 2 revs, 0.511068 s, 0.000862 s, -0.510206 s, × 0.0016, 430 µs/rev mozilla-try x_revs_x_added_x_copies 092fcca11bdb 936255a0384a : 4 revs, 0.021573 s, 0.000161 s, -0.021412 s, × 0.0074, 40 µs/rev mozilla-try x_revs_x00_added_x_copies b53d2fadbdb5 017afae788ec : 2 revs, 0.227726 s, 0.001163 s, -0.226563 s, × 0.0051, 581 µs/rev mozilla-try x_revs_x000_added_x000_copies 20408ad61ce5 6f0ee96e21ad : 1 revs, 1.120448 s, 0.032414 s, -1.088034 s, × 0.0289, 32381 µs/rev mozilla-try x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 2.241713 s, 0.070149 s, -2.171564 s, × 0.0312, 11689 µs/rev mozilla-try x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.090633 s, 0.006526 s, -0.084107 s, × 0.0720, 4 µs/rev mozilla-try x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.770403 s, 0.005187 s, -0.765216 s, × 0.0067, 126 µs/rev mozilla-try x000_revs_x000_added_x000_copies 1346fd0130e4 4c65cbdabc1f : 6657 revs, 1.184557 s, 0.065047 s, -1.119510 s, × 0.0549, 9 µs/rev mozilla-try x0000_revs_x_added_0_copies 63519bfd42ee a36a2a865d92 : 40314 revs, 0.085790 s, 0.301129 s, +0.215339 s, × 3.5100, 7 µs/rev mozilla-try x0000_revs_x_added_x_copies 9fe69ff0762d bcabf2a78927 : 38690 revs, 0.080616 s, 0.280683 s, +0.200067 s, × 3.4817, 7 µs/rev mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 8598 revs, 7.712554 s, 0.084897 s, -7.627657 s, × 0.0110, 9 µs/rev mozilla-try x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 6.937294 s, 0.026620 s, -6.910674 s, × 0.0038, 43 µs/rev mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 97052 revs, 7.712313 s, 1.529120 s, -6.183193 s, × 0.1982, 15 µs/rev mozilla-try x0000_revs_x0000_added_x0000_copies e928c65095ed e951f4ad123a : 52031 revs, 9.966910 s, 0.738709 s, -9.228201 s, × 0.0741, 14 µs/rev mozilla-try x00000_revs_x_added_0_copies 6a320851d377 1ebb79acd503 : 363753 revs, 0.090397 s, 4.842699 s, +4.752302 s, × 53.571, 13 µs/rev mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 34414 revs, 27.817167 s, 0.596946 s, -27.220221 s, × 0.0214, 17 µs/rev mozilla-try x00000_revs_x_added_x_copies 5173c4b6f97c 95d83ee7242d : 362229 revs, 0.091305 s, 4.761732 s, +4.670427 s, × 52.151, 13 µs/rev mozilla-try x00000_revs_x000_added_x_copies 9126823d0e9c ca82787bb23c : 359344 revs, 0.231183 s, 4.733912 s, +4.502729 s, × 20.476, 13 µs/rev mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 192665 revs, 19.830617 s, 2.593410 s, -17.237207 s, × 0.1307, 13 µs/rev mozilla-try x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 228985 revs, 21.743873 s, 41.041198 s, +19.297325 s, × 1.8874, 179 µs/rev mozilla-try x00000_revs_x00000_added_x000_copies 9b2a99adc05e 8e29777b48e6 : 382065 revs, 25.935037 s, 27.915689 s, +1.980652 s, × 1.0763, 73 µs/rev Differential Revision: https://phab.mercurial-scm.org/D9493
rust/hg-core/src/copy_tracing.rs
--- a/rust/hg-core/src/copy_tracing.rs	Fri Nov 20 13:46:14 2020 +0100
+++ b/rust/hg-core/src/copy_tracing.rs	Sat Apr 25 12:37:46 2020 +0200
@@ -12,9 +12,9 @@
 
 pub type PathCopies = HashMap<HgPathBuf, HgPathBuf>;
 
-type PathToken = HgPathBuf;
+type PathToken = usize;
 
-#[derive(Clone, Debug, PartialEq)]
+#[derive(Clone, Debug, PartialEq, Copy)]
 struct TimeStampedPathCopy {
     /// revision at which the copy information was added
     rev: Revision,
@@ -314,6 +314,37 @@
     SecondParent,
 }
 
+/// A small "tokenizer" responsible of turning full HgPath into lighter
+/// PathToken
+///
+/// Dealing with small object, like integer is much faster, so HgPath input are
+/// turned into integer "PathToken" and converted back in the end.
+#[derive(Clone, Debug, Default)]
+struct TwoWayPathMap {
+    token: HashMap<HgPathBuf, PathToken>,
+    path: Vec<HgPathBuf>,
+}
+
+impl TwoWayPathMap {
+    fn tokenize(&mut self, path: &HgPath) -> PathToken {
+        match self.token.get(path) {
+            Some(a) => *a,
+            None => {
+                let a = self.token.len();
+                let buf = path.to_owned();
+                self.path.push(buf.clone());
+                self.token.insert(buf, a);
+                a
+            }
+        }
+    }
+
+    fn untokenize(&self, token: PathToken) -> &HgPathBuf {
+        assert!(token < self.path.len(), format!("Unknown token: {}", token));
+        &self.path[token]
+    }
+}
+
 /// Same as mercurial.copies._combine_changeset_copies, but in Rust.
 ///
 /// Arguments are:
@@ -337,6 +368,8 @@
     let mut all_copies = HashMap::new();
     let mut oracle = AncestorOracle::new(is_ancestor);
 
+    let mut path_map = TwoWayPathMap::default();
+
     for rev in revs {
         let mut d: DataHolder<D> = DataHolder { data: None };
         let (p1, p2, changes) = rev_info(rev, &mut d);
@@ -355,6 +388,7 @@
             if let Some(parent_copies) = parent_copies {
                 // combine it with data for that revision
                 let vertex_copies = add_from_changes(
+                    &mut path_map,
                     &parent_copies,
                     &changes,
                     Parent::FirstParent,
@@ -374,6 +408,7 @@
             if let Some(parent_copies) = parent_copies {
                 // combine it with data for that revision
                 let vertex_copies = add_from_changes(
+                    &mut path_map,
                     &parent_copies,
                     &changes,
                     Parent::SecondParent,
@@ -388,6 +423,7 @@
                     // If we got data from both parents, We need to combine
                     // them.
                     Some(copies) => Some(merge_copies_dict(
+                        &path_map,
                         vertex_copies,
                         copies,
                         &changes,
@@ -412,7 +448,9 @@
     let mut result = PathCopies::default();
     for (dest, tt_source) in tt_result {
         if let Some(path) = tt_source.path {
-            result.insert(dest, path);
+            let path_dest = path_map.untokenize(dest).to_owned();
+            let path_path = path_map.untokenize(path).to_owned();
+            result.insert(path_dest, path_path);
         }
     }
     result
@@ -447,6 +485,7 @@
 /// Combine ChangedFiles with some existing PathCopies information and return
 /// the result
 fn add_from_changes(
+    path_map: &mut TwoWayPathMap,
     base_copies: &TimeStampedPathCopies,
     changes: &ChangedFiles,
     parent: Parent,
@@ -455,9 +494,11 @@
     let mut copies = base_copies.clone();
     for action in changes.iter_actions(parent) {
         match action {
-            Action::Copied(dest, source) => {
+            Action::Copied(path_dest, path_source) => {
+                let dest = path_map.tokenize(path_dest);
+                let source = path_map.tokenize(path_source);
                 let entry;
-                if let Some(v) = base_copies.get(source) {
+                if let Some(v) = base_copies.get(&source) {
                     entry = match &v.path {
                         Some(path) => Some((*(path)).to_owned()),
                         None => Some(source.to_owned()),
@@ -475,18 +516,19 @@
                 };
                 copies.insert(dest.to_owned(), ttpc);
             }
-            Action::Removed(f) => {
+            Action::Removed(deleted_path) => {
                 // We must drop copy information for removed file.
                 //
                 // We need to explicitly record them as dropped to
                 // propagate this information when merging two
                 // TimeStampedPathCopies object.
-                if copies.contains_key(f.as_ref()) {
+                let deleted = path_map.tokenize(deleted_path);
+                if copies.contains_key(&deleted) {
                     let ttpc = TimeStampedPathCopy {
                         rev: current_rev,
                         path: None,
                     };
-                    copies.insert(f.to_owned(), ttpc);
+                    copies.insert(deleted, ttpc);
                 }
             }
         }
@@ -499,6 +541,7 @@
 /// In case of conflict, value from "major" will be picked, unless in some
 /// cases. See inline documentation for details.
 fn merge_copies_dict<A: Fn(Revision, Revision) -> bool>(
+    path_map: &TwoWayPathMap,
     mut minor: TimeStampedPathCopies,
     mut major: TimeStampedPathCopies,
     changes: &ChangedFiles,
@@ -511,7 +554,9 @@
         |dest: &PathToken,
          src_minor: &TimeStampedPathCopy,
          src_major: &TimeStampedPathCopy| {
-            compare_value(changes, oracle, dest, src_minor, src_major)
+            compare_value(
+                path_map, changes, oracle, dest, src_minor, src_major,
+            )
         };
     if minor.is_empty() {
         major
@@ -641,6 +686,7 @@
 /// decide which side prevails in case of conflicting values
 #[allow(clippy::if_same_then_else)]
 fn compare_value<A: Fn(Revision, Revision) -> bool>(
+    path_map: &TwoWayPathMap,
     changes: &ChangedFiles,
     oracle: &mut AncestorOracle<A>,
     dest: &PathToken,
@@ -664,7 +710,8 @@
             "conflict information from p1 and p2 in the same revision"
         );
     } else {
-        let action = changes.get_merge_case(&dest);
+        let dest_path = path_map.untokenize(*dest);
+        let action = changes.get_merge_case(dest_path);
         if src_major.path.is_none() && action == MergeCase::Salvaged {
             // If the file is "deleted" in the major side but was
             // salvaged by the merge, we keep the minor side alive