mirror of
https://github.com/sreedevk/deduplicator.git
synced 2026-08-26 02:04:39 +00:00
58e33cc8da
- [x] parallelization
- [x] (scanning) + (processing sw & processing hw & formatting & printing)
- [x] reduce cloning values on the heap
- [x] add a partial hashing mode (--strict)
- [x] add unit tests
- [x] add silent mode
- [x] update documentation
- [x] remove color output
- [x] progress bar improvements
- [x] use progress bar groups
- [x] remove broken json rendering
- [x] add benchmarks
94 lines
2.6 KiB
Ruby
94 lines
2.6 KiB
Ruby
require 'tempfile'
|
||
require 'fileutils'
|
||
require 'securerandom'
|
||
|
||
namespace :benchmark do
|
||
file 'target/release/deduplicator' do
|
||
sh "cargo build --release"
|
||
end
|
||
|
||
task :few_large_files => 'target/release/deduplicator' do
|
||
# Benchmark 1: ./target/release/deduplicator bench_artifacts
|
||
# Time (mean ± σ): 2.5 ms ± 0.6 ms [User: 2.4 ms, System: 4.8 ms]
|
||
# Range (min … max): 1.8 ms … 9.7 ms 1474 runs
|
||
|
||
root = "bench_artifacts"
|
||
Dir.mkdir(root)
|
||
|
||
# files with same size
|
||
2.times.map do |i|
|
||
File.open(File.join(root, "file_#{i}_fwss.bin"), 'wb') do |f|
|
||
f.write(SecureRandom.bytes(4096 * 100_000))
|
||
end
|
||
end
|
||
|
||
# files with different sizes
|
||
2.times.map do |i|
|
||
File.open(File.join(root, "file_#{i}_fwds.bin"), 'wb') do |f|
|
||
f.write(SecureRandom.bytes(4096 * (rand * 100_000).ceil))
|
||
end
|
||
end
|
||
|
||
# files with same content & size
|
||
2.times.each do |i|
|
||
File.open(File.join(root, "file_#{i}_fwscas.bin"), 'wb') do |f|
|
||
f.write("\0" * (4096 * 100_000))
|
||
end
|
||
end
|
||
|
||
# files with different content but same size
|
||
2.times.each do |i|
|
||
File.open(File.join(root, "file_#{i}_fwdcbss.bin"), 'wb') do |f|
|
||
f.write(SecureRandom.bytes(4096 * 100_000))
|
||
end
|
||
end
|
||
|
||
sh("hyperfine -N --warmup 80 './target/release/deduplicator #{root}'")
|
||
sh("dust '#{root}'")
|
||
|
||
FileUtils.rm_rf(root)
|
||
end
|
||
|
||
task :many_small_files => 'target/release/deduplicator' do
|
||
# Benchmark 1: ./target/release/deduplicator bench_artifacts
|
||
# Time (mean ± σ): 10.6 ms ± 1.0 ms [User: 20.0 ms, System: 22.5 ms]
|
||
# Range (min … max): 8.4 ms … 14.2 ms 235 runs
|
||
|
||
root = "bench_artifacts"
|
||
Dir.mkdir(root)
|
||
|
||
# files with same size
|
||
1000.times.each do |i|
|
||
File.open(File.join(root, "file_#{i}_fwss.bin"), 'wb') do |f|
|
||
f.write(SecureRandom.bytes(4096 * 1000))
|
||
end
|
||
end
|
||
|
||
# files with different sizes
|
||
1000.times.each do |i|
|
||
File.open(File.join(root, "file_#{i}_fwds.bin"), 'wb') do |f|
|
||
f.write(SecureRandom.bytes(4096 * (rand * 100).ceil))
|
||
end
|
||
end
|
||
|
||
# files with same content & size
|
||
1000.times.each do |i|
|
||
File.open(File.join(root, "file_#{i}_fwscas.bin"), 'wb') do |f|
|
||
f.write("\0" * (4096 * 1000))
|
||
end
|
||
end
|
||
|
||
# files with different content but same size
|
||
1000.times.each do |i|
|
||
File.open(File.join(root, "file_#{i}_fwdcbss.bin"), 'wb') do |f|
|
||
f.write(SecureRandom.bytes(4096 * 1000))
|
||
end
|
||
end
|
||
|
||
sh("hyperfine --warmup 20 './target/release/deduplicator #{root}'")
|
||
sh("dust '#{root}'")
|
||
|
||
FileUtils.rm_rf(root)
|
||
end
|
||
end
|