Bencher::Scenario::CloneModules - Benchmark various data cloning modules
This document describes version 0.050 of Bencher::Scenario::CloneModules (from Perl distribution Bencher-Scenarios-CloneModules), released on 2021-07-31.
To run benchmark with default option:
% bencher -m CloneModules
To run module startup overhead benchmark:
% bencher --module-startup -m CloneModules
For more options (dump scenario, list/include/exclude/add participants, list/include/exclude/add datasets, etc), see bencher or run bencher --help.
bencher --help
Packaging a benchmark script as a Bencher scenario makes it convenient to include/exclude/add participants/datasets (either via CLI or Perl code), send the result to a central repository, among others . See Bencher and bencher (CLI) for more details.
Version numbers shown below are the versions used when running the sample benchmark.
Clone 0.45
Clone::PP 1.08
Data::Clone 0.004
Sereal::Dclone 0.003
Storable 3.23
Clone::clone (perl_code)
Function call template:
Clone::clone(<data>)
Clone::PP::clone (perl_code)
Clone::PP::clone(<data>)
Data::Clone::clone (perl_code)
Data::Clone::clone(<data>)
Sereal::Dclone::dclone (perl_code)
Sereal::Dclone::dclone(<data>)
Storable::dclone (perl_code)
Storable::dclone(<data>)
array0
array1
array10
array100
array1k
array10k
hash1k
hash10k
Run on: perl: v5.34.0, CPU: Intel(R) Core(TM) i7-4770 CPU @ 3.40GHz (4 cores), OS: GNU/Linux LinuxMint version 19, OS kernel: Linux version 5.3.0-68-generic.
Benchmark command (cloning a 10k-element array):
% bencher -m CloneModules --include-datasets array10k
Result formatted as table:
#table1# +------------------------+-----------+-----------+-----------------------+-----------------------+---------+---------+ | participant | rate (/s) | time (ms) | pct_faster_vs_slowest | pct_slower_vs_fastest | errors | samples | +------------------------+-----------+-----------+-----------------------+-----------------------+---------+---------+ | Clone::clone | 480 | 2.1 | 0.00% | 528.98% | 5.1e-06 | 20 | | Clone::PP::clone | 1200 | 0.81 | 158.13% | 143.66% | 2.5e-06 | 20 | | Storable::dclone | 1400 | 0.71 | 194.00% | 113.94% | 3.5e-06 | 21 | | Sereal::Dclone::dclone | 2800 | 0.36 | 482.25% | 8.03% | 6.9e-07 | 20 | | Data::Clone::clone | 3000 | 0.33 | 528.98% | 0.00% | 4.3e-07 | 20 | +------------------------+-----------+-----------+-----------------------+-----------------------+---------+---------+
The above result formatted in Benchmark.pm style:
Rate C:c CP:c S:d SD:d DC:c C:c 480/s -- -61% -66% -82% -84% CP:c 1200/s 159% -- -12% -55% -59% S:d 1400/s 195% 14% -- -49% -53% SD:d 2800/s 483% 125% 97% -- -8% DC:c 3000/s 536% 145% 115% 9% -- Legends: C:c: participant=Clone::clone CP:c: participant=Clone::PP::clone DC:c: participant=Data::Clone::clone S:d: participant=Storable::dclone SD:d: participant=Sereal::Dclone::dclone
The above result presented as chart:
#IMAGE: share/images/bencher-result-1.png|/tmp/8FUibnYqSi/bencher-result-1.png
Benchmark command (cloning a 10k-pair hash):
% bencher -m CloneModules --include-datasets hash10k
#table2# +------------------------+-----------+-----------+-----------------------+-----------------------+---------+---------+ | participant | rate (/s) | time (ms) | pct_faster_vs_slowest | pct_slower_vs_fastest | errors | samples | +------------------------+-----------+-----------+-----------------------+-----------------------+---------+---------+ | Clone::clone | 190 | 5.2 | 0.00% | 126.46% | 8.9e-06 | 21 | | Clone::PP::clone | 210 | 4.7 | 11.08% | 103.87% | 5.8e-06 | 20 | | Storable::dclone | 340 | 2.9 | 76.92% | 28.00% | 3.8e-06 | 20 | | Data::Clone::clone | 360 | 2.8 | 88.69% | 20.02% | 3.1e-06 | 20 | | Sereal::Dclone::dclone | 440 | 2.3 | 126.46% | 0.00% | 4.3e-06 | 20 | +------------------------+-----------+-----------+-----------------------+-----------------------+---------+---------+
Rate C:c CP:c S:d DC:c SD:d C:c 190/s -- -9% -44% -46% -55% CP:c 210/s 10% -- -38% -40% -51% S:d 340/s 79% 62% -- -3% -20% DC:c 360/s 85% 67% 3% -- -17% SD:d 440/s 126% 104% 26% 21% -- Legends: C:c: participant=Clone::clone CP:c: participant=Clone::PP::clone DC:c: participant=Data::Clone::clone S:d: participant=Storable::dclone SD:d: participant=Sereal::Dclone::dclone
#IMAGE: share/images/bencher-result-2.png|/tmp/8FUibnYqSi/bencher-result-2.png
Benchmark command (benchmarking module startup overhead):
% bencher -m CloneModules --module-startup
#table3# +---------------------+-----------+-------------------+-----------------------+-----------------------+-----------+---------+ | participant | time (ms) | mod_overhead_time | pct_faster_vs_slowest | pct_slower_vs_fastest | errors | samples | +---------------------+-----------+-------------------+-----------------------+-----------------------+-----------+---------+ | Sereal::Dclone | 10 | 4.6 | 0.00% | 131.01% | 0.00024 | 20 | | Storable | 12 | 6.6 | 5.42% | 119.13% | 5.8e-05 | 20 | | Clone | 10 | 4.6 | 26.44% | 82.70% | 0.00021 | 20 | | Clone::PP | 9 | 3.6 | 42.26% | 62.39% | 0.00019 | 20 | | Data::Clone | 7.3 | 1.9 | 71.61% | 34.62% | 4e-05 | 21 | | perl -e1 (baseline) | 5.4 | 0 | 131.01% | 0.00% | 2.2e-05 | 23 | +---------------------+-----------+-------------------+-----------------------+-----------------------+-----------+---------+
Rate S S:D C C:P D:C perl -e1 (baseline) S 83.3/s -- -16% -16% -25% -39% -55% S:D 100.0/s 19% -- 0% -9% -27% -46% C 100.0/s 19% 0% -- -9% -27% -46% C:P 111.1/s 33% 11% 11% -- -18% -39% D:C 137.0/s 64% 36% 36% 23% -- -26% perl -e1 (baseline) 185.2/s 122% 85% 85% 66% 35% -- Legends: C: mod_overhead_time=4.6 participant=Clone C:P: mod_overhead_time=3.6 participant=Clone::PP D:C: mod_overhead_time=1.9 participant=Data::Clone S: mod_overhead_time=6.6 participant=Storable S:D: mod_overhead_time=4.6 participant=Sereal::Dclone perl -e1 (baseline): mod_overhead_time=0 participant=perl -e1 (baseline)
#IMAGE: share/images/bencher-result-3.png|/tmp/8FUibnYqSi/bencher-result-3.png
To display as an interactive HTML table on a browser, you can add option --format html+datatables.
--format html+datatables
Please visit the project's homepage at https://metacpan.org/release/Bencher-Scenarios-CloneModules.
Source repository is at https://github.com/perlancar/perl-Bencher-Scenarios-CloneModules.
Please report any bugs or feature requests on the bugtracker website https://rt.cpan.org/Public/Dist/Display.html?Name=Bencher-Scenarios-CloneModules
When submitting a bug or request, please include a test-file or a patch to an existing test-file that illustrates the bug or desired feature.
perlancar <perlancar@cpan.org>
This software is copyright (c) 2021, 2017, 2016 by perlancar@cpan.org.
This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself.
To install Bencher::Scenarios::CloneModules, copy and paste the appropriate command in to your terminal.
cpanm
cpanm Bencher::Scenarios::CloneModules
CPAN shell
perl -MCPAN -e shell install Bencher::Scenarios::CloneModules
For more information on module installation, please visit the detailed CPAN module installation guide.