##// END OF EJS Templates
copies-rust: tokenize all paths into integer...
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

File last commit:

r43207:69de49c4 default
r46766:c6bc77f7 default
Show More
compressionparams.c
572 lines | 17.1 KiB | text/x-c | CLexer
/**
* Copyright (c) 2016-present, Gregory Szorc
* All rights reserved.
*
* This software may be modified and distributed under the terms
* of the BSD license. See the LICENSE file for details.
*/
#include "python-zstandard.h"
extern PyObject* ZstdError;
int set_parameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int value) {
size_t zresult = ZSTD_CCtxParams_setParameter(params, param, value);
if (ZSTD_isError(zresult)) {
PyErr_Format(ZstdError, "unable to set compression context parameter: %s",
ZSTD_getErrorName(zresult));
return 1;
}
return 0;
}
#define TRY_SET_PARAMETER(params, param, value) if (set_parameter(params, param, value)) return -1;
#define TRY_COPY_PARAMETER(source, dest, param) { \
int result; \
size_t zresult = ZSTD_CCtxParams_getParameter(source, param, &result); \
if (ZSTD_isError(zresult)) { \
return 1; \
} \
zresult = ZSTD_CCtxParams_setParameter(dest, param, result); \
if (ZSTD_isError(zresult)) { \
return 1; \
} \
}
int set_parameters(ZSTD_CCtx_params* params, ZstdCompressionParametersObject* obj) {
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_nbWorkers);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_format);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_compressionLevel);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_windowLog);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_hashLog);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_chainLog);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_searchLog);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_minMatch);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_targetLength);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_strategy);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_contentSizeFlag);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_checksumFlag);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_dictIDFlag);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_jobSize);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_overlapLog);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_forceMaxWindow);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_enableLongDistanceMatching);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_ldmHashLog);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_ldmMinMatch);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_ldmBucketSizeLog);
TRY_COPY_PARAMETER(obj->params, params, ZSTD_c_ldmHashRateLog);
return 0;
}
int reset_params(ZstdCompressionParametersObject* params) {
if (params->params) {
ZSTD_CCtxParams_reset(params->params);
}
else {
params->params = ZSTD_createCCtxParams();
if (!params->params) {
PyErr_NoMemory();
return 1;
}
}
return set_parameters(params->params, params);
}
#define TRY_GET_PARAMETER(params, param, value) { \
size_t zresult = ZSTD_CCtxParams_getParameter(params, param, value); \
if (ZSTD_isError(zresult)) { \
PyErr_Format(ZstdError, "unable to retrieve parameter: %s", ZSTD_getErrorName(zresult)); \
return 1; \
} \
}
int to_cparams(ZstdCompressionParametersObject* params, ZSTD_compressionParameters* cparams) {
int value;
TRY_GET_PARAMETER(params->params, ZSTD_c_windowLog, &value);
cparams->windowLog = value;
TRY_GET_PARAMETER(params->params, ZSTD_c_chainLog, &value);
cparams->chainLog = value;
TRY_GET_PARAMETER(params->params, ZSTD_c_hashLog, &value);
cparams->hashLog = value;
TRY_GET_PARAMETER(params->params, ZSTD_c_searchLog, &value);
cparams->searchLog = value;
TRY_GET_PARAMETER(params->params, ZSTD_c_minMatch, &value);
cparams->minMatch = value;
TRY_GET_PARAMETER(params->params, ZSTD_c_targetLength, &value);
cparams->targetLength = value;
TRY_GET_PARAMETER(params->params, ZSTD_c_strategy, &value);
cparams->strategy = value;
return 0;
}
static int ZstdCompressionParameters_init(ZstdCompressionParametersObject* self, PyObject* args, PyObject* kwargs) {
static char* kwlist[] = {
"format",
"compression_level",
"window_log",
"hash_log",
"chain_log",
"search_log",
"min_match",
"target_length",
"compression_strategy",
"strategy",
"write_content_size",
"write_checksum",
"write_dict_id",
"job_size",
"overlap_log",
"overlap_size_log",
"force_max_window",
"enable_ldm",
"ldm_hash_log",
"ldm_min_match",
"ldm_bucket_size_log",
"ldm_hash_rate_log",
"ldm_hash_every_log",
"threads",
NULL
};
int format = 0;
int compressionLevel = 0;
int windowLog = 0;
int hashLog = 0;
int chainLog = 0;
int searchLog = 0;
int minMatch = 0;
int targetLength = 0;
int compressionStrategy = -1;
int strategy = -1;
int contentSizeFlag = 1;
int checksumFlag = 0;
int dictIDFlag = 0;
int jobSize = 0;
int overlapLog = -1;
int overlapSizeLog = -1;
int forceMaxWindow = 0;
int enableLDM = 0;
int ldmHashLog = 0;
int ldmMinMatch = 0;
int ldmBucketSizeLog = 0;
int ldmHashRateLog = -1;
int ldmHashEveryLog = -1;
int threads = 0;
if (!PyArg_ParseTupleAndKeywords(args, kwargs,
"|iiiiiiiiiiiiiiiiiiiiiiii:CompressionParameters",
kwlist, &format, &compressionLevel, &windowLog, &hashLog, &chainLog,
&searchLog, &minMatch, &targetLength, &compressionStrategy, &strategy,
&contentSizeFlag, &checksumFlag, &dictIDFlag, &jobSize, &overlapLog,
&overlapSizeLog, &forceMaxWindow, &enableLDM, &ldmHashLog, &ldmMinMatch,
&ldmBucketSizeLog, &ldmHashRateLog, &ldmHashEveryLog, &threads)) {
return -1;
}
if (reset_params(self)) {
return -1;
}
if (threads < 0) {
threads = cpu_count();
}
/* We need to set ZSTD_c_nbWorkers before ZSTD_c_jobSize and ZSTD_c_overlapLog
* because setting ZSTD_c_nbWorkers resets the other parameters. */
TRY_SET_PARAMETER(self->params, ZSTD_c_nbWorkers, threads);
TRY_SET_PARAMETER(self->params, ZSTD_c_format, format);
TRY_SET_PARAMETER(self->params, ZSTD_c_compressionLevel, compressionLevel);
TRY_SET_PARAMETER(self->params, ZSTD_c_windowLog, windowLog);
TRY_SET_PARAMETER(self->params, ZSTD_c_hashLog, hashLog);
TRY_SET_PARAMETER(self->params, ZSTD_c_chainLog, chainLog);
TRY_SET_PARAMETER(self->params, ZSTD_c_searchLog, searchLog);
TRY_SET_PARAMETER(self->params, ZSTD_c_minMatch, minMatch);
TRY_SET_PARAMETER(self->params, ZSTD_c_targetLength, targetLength);
if (compressionStrategy != -1 && strategy != -1) {
PyErr_SetString(PyExc_ValueError, "cannot specify both compression_strategy and strategy");
return -1;
}
if (compressionStrategy != -1) {
strategy = compressionStrategy;
}
else if (strategy == -1) {
strategy = 0;
}
TRY_SET_PARAMETER(self->params, ZSTD_c_strategy, strategy);
TRY_SET_PARAMETER(self->params, ZSTD_c_contentSizeFlag, contentSizeFlag);
TRY_SET_PARAMETER(self->params, ZSTD_c_checksumFlag, checksumFlag);
TRY_SET_PARAMETER(self->params, ZSTD_c_dictIDFlag, dictIDFlag);
TRY_SET_PARAMETER(self->params, ZSTD_c_jobSize, jobSize);
if (overlapLog != -1 && overlapSizeLog != -1) {
PyErr_SetString(PyExc_ValueError, "cannot specify both overlap_log and overlap_size_log");
return -1;
}
if (overlapSizeLog != -1) {
overlapLog = overlapSizeLog;
}
else if (overlapLog == -1) {
overlapLog = 0;
}
TRY_SET_PARAMETER(self->params, ZSTD_c_overlapLog, overlapLog);
TRY_SET_PARAMETER(self->params, ZSTD_c_forceMaxWindow, forceMaxWindow);
TRY_SET_PARAMETER(self->params, ZSTD_c_enableLongDistanceMatching, enableLDM);
TRY_SET_PARAMETER(self->params, ZSTD_c_ldmHashLog, ldmHashLog);
TRY_SET_PARAMETER(self->params, ZSTD_c_ldmMinMatch, ldmMinMatch);
TRY_SET_PARAMETER(self->params, ZSTD_c_ldmBucketSizeLog, ldmBucketSizeLog);
if (ldmHashRateLog != -1 && ldmHashEveryLog != -1) {
PyErr_SetString(PyExc_ValueError, "cannot specify both ldm_hash_rate_log and ldm_hash_everyLog");
return -1;
}
if (ldmHashEveryLog != -1) {
ldmHashRateLog = ldmHashEveryLog;
}
else if (ldmHashRateLog == -1) {
ldmHashRateLog = 0;
}
TRY_SET_PARAMETER(self->params, ZSTD_c_ldmHashRateLog, ldmHashRateLog);
return 0;
}
PyDoc_STRVAR(ZstdCompressionParameters_from_level__doc__,
"Create a CompressionParameters from a compression level and target sizes\n"
);
ZstdCompressionParametersObject* CompressionParameters_from_level(PyObject* undef, PyObject* args, PyObject* kwargs) {
int managedKwargs = 0;
int level;
PyObject* sourceSize = NULL;
PyObject* dictSize = NULL;
unsigned PY_LONG_LONG iSourceSize = 0;
Py_ssize_t iDictSize = 0;
PyObject* val;
ZSTD_compressionParameters params;
ZstdCompressionParametersObject* result = NULL;
int res;
if (!PyArg_ParseTuple(args, "i:from_level",
&level)) {
return NULL;
}
if (!kwargs) {
kwargs = PyDict_New();
if (!kwargs) {
return NULL;
}
managedKwargs = 1;
}
sourceSize = PyDict_GetItemString(kwargs, "source_size");
if (sourceSize) {
#if PY_MAJOR_VERSION >= 3
iSourceSize = PyLong_AsUnsignedLongLong(sourceSize);
if (iSourceSize == (unsigned PY_LONG_LONG)(-1)) {
goto cleanup;
}
#else
iSourceSize = PyInt_AsUnsignedLongLongMask(sourceSize);
#endif
PyDict_DelItemString(kwargs, "source_size");
}
dictSize = PyDict_GetItemString(kwargs, "dict_size");
if (dictSize) {
#if PY_MAJOR_VERSION >= 3
iDictSize = PyLong_AsSsize_t(dictSize);
#else
iDictSize = PyInt_AsSsize_t(dictSize);
#endif
if (iDictSize == -1) {
goto cleanup;
}
PyDict_DelItemString(kwargs, "dict_size");
}
params = ZSTD_getCParams(level, iSourceSize, iDictSize);
/* Values derived from the input level and sizes are passed along to the
constructor. But only if a value doesn't already exist. */
val = PyDict_GetItemString(kwargs, "window_log");
if (!val) {
val = PyLong_FromUnsignedLong(params.windowLog);
if (!val) {
goto cleanup;
}
PyDict_SetItemString(kwargs, "window_log", val);
Py_DECREF(val);
}
val = PyDict_GetItemString(kwargs, "chain_log");
if (!val) {
val = PyLong_FromUnsignedLong(params.chainLog);
if (!val) {
goto cleanup;
}
PyDict_SetItemString(kwargs, "chain_log", val);
Py_DECREF(val);
}
val = PyDict_GetItemString(kwargs, "hash_log");
if (!val) {
val = PyLong_FromUnsignedLong(params.hashLog);
if (!val) {
goto cleanup;
}
PyDict_SetItemString(kwargs, "hash_log", val);
Py_DECREF(val);
}
val = PyDict_GetItemString(kwargs, "search_log");
if (!val) {
val = PyLong_FromUnsignedLong(params.searchLog);
if (!val) {
goto cleanup;
}
PyDict_SetItemString(kwargs, "search_log", val);
Py_DECREF(val);
}
val = PyDict_GetItemString(kwargs, "min_match");
if (!val) {
val = PyLong_FromUnsignedLong(params.minMatch);
if (!val) {
goto cleanup;
}
PyDict_SetItemString(kwargs, "min_match", val);
Py_DECREF(val);
}
val = PyDict_GetItemString(kwargs, "target_length");
if (!val) {
val = PyLong_FromUnsignedLong(params.targetLength);
if (!val) {
goto cleanup;
}
PyDict_SetItemString(kwargs, "target_length", val);
Py_DECREF(val);
}
val = PyDict_GetItemString(kwargs, "compression_strategy");
if (!val) {
val = PyLong_FromUnsignedLong(params.strategy);
if (!val) {
goto cleanup;
}
PyDict_SetItemString(kwargs, "compression_strategy", val);
Py_DECREF(val);
}
result = PyObject_New(ZstdCompressionParametersObject, &ZstdCompressionParametersType);
if (!result) {
goto cleanup;
}
result->params = NULL;
val = PyTuple_New(0);
if (!val) {
Py_CLEAR(result);
goto cleanup;
}
res = ZstdCompressionParameters_init(result, val, kwargs);
Py_DECREF(val);
if (res) {
Py_CLEAR(result);
goto cleanup;
}
cleanup:
if (managedKwargs) {
Py_DECREF(kwargs);
}
return result;
}
PyDoc_STRVAR(ZstdCompressionParameters_estimated_compression_context_size__doc__,
"Estimate the size in bytes of a compression context for compression parameters\n"
);
PyObject* ZstdCompressionParameters_estimated_compression_context_size(ZstdCompressionParametersObject* self) {
return PyLong_FromSize_t(ZSTD_estimateCCtxSize_usingCCtxParams(self->params));
}
PyDoc_STRVAR(ZstdCompressionParameters__doc__,
"ZstdCompressionParameters: low-level control over zstd compression");
static void ZstdCompressionParameters_dealloc(ZstdCompressionParametersObject* self) {
if (self->params) {
ZSTD_freeCCtxParams(self->params);
self->params = NULL;
}
PyObject_Del(self);
}
#define PARAM_GETTER(name, param) PyObject* ZstdCompressionParameters_get_##name(PyObject* self, void* unused) { \
int result; \
size_t zresult; \
ZstdCompressionParametersObject* p = (ZstdCompressionParametersObject*)(self); \
zresult = ZSTD_CCtxParams_getParameter(p->params, param, &result); \
if (ZSTD_isError(zresult)) { \
PyErr_Format(ZstdError, "unable to get compression parameter: %s", \
ZSTD_getErrorName(zresult)); \
return NULL; \
} \
return PyLong_FromLong(result); \
}
PARAM_GETTER(format, ZSTD_c_format)
PARAM_GETTER(compression_level, ZSTD_c_compressionLevel)
PARAM_GETTER(window_log, ZSTD_c_windowLog)
PARAM_GETTER(hash_log, ZSTD_c_hashLog)
PARAM_GETTER(chain_log, ZSTD_c_chainLog)
PARAM_GETTER(search_log, ZSTD_c_searchLog)
PARAM_GETTER(min_match, ZSTD_c_minMatch)
PARAM_GETTER(target_length, ZSTD_c_targetLength)
PARAM_GETTER(compression_strategy, ZSTD_c_strategy)
PARAM_GETTER(write_content_size, ZSTD_c_contentSizeFlag)
PARAM_GETTER(write_checksum, ZSTD_c_checksumFlag)
PARAM_GETTER(write_dict_id, ZSTD_c_dictIDFlag)
PARAM_GETTER(job_size, ZSTD_c_jobSize)
PARAM_GETTER(overlap_log, ZSTD_c_overlapLog)
PARAM_GETTER(force_max_window, ZSTD_c_forceMaxWindow)
PARAM_GETTER(enable_ldm, ZSTD_c_enableLongDistanceMatching)
PARAM_GETTER(ldm_hash_log, ZSTD_c_ldmHashLog)
PARAM_GETTER(ldm_min_match, ZSTD_c_ldmMinMatch)
PARAM_GETTER(ldm_bucket_size_log, ZSTD_c_ldmBucketSizeLog)
PARAM_GETTER(ldm_hash_rate_log, ZSTD_c_ldmHashRateLog)
PARAM_GETTER(threads, ZSTD_c_nbWorkers)
static PyMethodDef ZstdCompressionParameters_methods[] = {
{
"from_level",
(PyCFunction)CompressionParameters_from_level,
METH_VARARGS | METH_KEYWORDS | METH_STATIC,
ZstdCompressionParameters_from_level__doc__
},
{
"estimated_compression_context_size",
(PyCFunction)ZstdCompressionParameters_estimated_compression_context_size,
METH_NOARGS,
ZstdCompressionParameters_estimated_compression_context_size__doc__
},
{ NULL, NULL }
};
#define GET_SET_ENTRY(name) { #name, ZstdCompressionParameters_get_##name, NULL, NULL, NULL }
static PyGetSetDef ZstdCompressionParameters_getset[] = {
GET_SET_ENTRY(format),
GET_SET_ENTRY(compression_level),
GET_SET_ENTRY(window_log),
GET_SET_ENTRY(hash_log),
GET_SET_ENTRY(chain_log),
GET_SET_ENTRY(search_log),
GET_SET_ENTRY(min_match),
GET_SET_ENTRY(target_length),
GET_SET_ENTRY(compression_strategy),
GET_SET_ENTRY(write_content_size),
GET_SET_ENTRY(write_checksum),
GET_SET_ENTRY(write_dict_id),
GET_SET_ENTRY(threads),
GET_SET_ENTRY(job_size),
GET_SET_ENTRY(overlap_log),
/* TODO remove this deprecated attribute */
{ "overlap_size_log", ZstdCompressionParameters_get_overlap_log, NULL, NULL, NULL },
GET_SET_ENTRY(force_max_window),
GET_SET_ENTRY(enable_ldm),
GET_SET_ENTRY(ldm_hash_log),
GET_SET_ENTRY(ldm_min_match),
GET_SET_ENTRY(ldm_bucket_size_log),
GET_SET_ENTRY(ldm_hash_rate_log),
/* TODO remove this deprecated attribute */
{ "ldm_hash_every_log", ZstdCompressionParameters_get_ldm_hash_rate_log, NULL, NULL, NULL },
{ NULL }
};
PyTypeObject ZstdCompressionParametersType = {
PyVarObject_HEAD_INIT(NULL, 0)
"ZstdCompressionParameters", /* tp_name */
sizeof(ZstdCompressionParametersObject), /* tp_basicsize */
0, /* tp_itemsize */
(destructor)ZstdCompressionParameters_dealloc, /* tp_dealloc */
0, /* tp_print */
0, /* tp_getattr */
0, /* tp_setattr */
0, /* tp_compare */
0, /* tp_repr */
0, /* tp_as_number */
0, /* tp_as_sequence */
0, /* tp_as_mapping */
0, /* tp_hash */
0, /* tp_call */
0, /* tp_str */
0, /* tp_getattro */
0, /* tp_setattro */
0, /* tp_as_buffer */
Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE, /* tp_flags */
ZstdCompressionParameters__doc__, /* tp_doc */
0, /* tp_traverse */
0, /* tp_clear */
0, /* tp_richcompare */
0, /* tp_weaklistoffset */
0, /* tp_iter */
0, /* tp_iternext */
ZstdCompressionParameters_methods, /* tp_methods */
0, /* tp_members */
ZstdCompressionParameters_getset, /* tp_getset */
0, /* tp_base */
0, /* tp_dict */
0, /* tp_descr_get */
0, /* tp_descr_set */
0, /* tp_dictoffset */
(initproc)ZstdCompressionParameters_init, /* tp_init */
0, /* tp_alloc */
PyType_GenericNew, /* tp_new */
};
void compressionparams_module_init(PyObject* mod) {
Py_TYPE(&ZstdCompressionParametersType) = &PyType_Type;
if (PyType_Ready(&ZstdCompressionParametersType) < 0) {
return;
}
Py_INCREF(&ZstdCompressionParametersType);
PyModule_AddObject(mod, "ZstdCompressionParameters",
(PyObject*)&ZstdCompressionParametersType);
/* TODO remove deprecated alias. */
Py_INCREF(&ZstdCompressionParametersType);
PyModule_AddObject(mod, "CompressionParameters",
(PyObject*)&ZstdCompressionParametersType);
}