tigrawap / goader Goto Github PK
View Code? Open in Web Editor NEWUniversal benchmark utility (s3, http, file, syscalls)
License: Other
Universal benchmark utility (s3, http, file, syscalls)
License: Other
Результат запуска, если директории tmp нет:
Maximum requests count
Writes
Total requests: 300072
Total errors: 300072
Average OP/s: 9170
Average good OP/s: 1
Почему в виртуалке результат выше, чем на физическом сервере? Не кэширование ли помогает?
Тест в виртуалке:
test@virtualhost:~$ ./goader_linux_amd64 -rpw 2 -max-latency 5ms -requests-engine=disk -url=tmp/RRRRRRR -body-size=4k -max-requests=300000 -show-progress=0
Writes
Average response time: 1.114432ms
Percentile 30 - 50.11µs
Percentile 40 - 55.643µs
Percentile 50 - 61.054µs
Percentile 60 - 66.768µs
Percentile 70 - 73.759µs
Percentile 80 - 84.431µs
Percentile 90 - 111.857µs
Percentile 95 - 3.759657ms
Percentile 99 - 26.63181ms
TopTen latencies: 198.10275ms 203.438435ms 225.246525ms 236.767418ms 241.148235ms 241.450739ms 241.518367ms 242.036285ms 242.163162ms 242.603885ms
Threads with latency below 5ms: 32
Total requests: 100152
Total errors: 0
Average OP/s: 17936
Average good OP/s: 17936
Reads
Average response time: 191.474µs
Percentile 30 - 10.108µs
Percentile 40 - 12.02µs
Percentile 50 - 13.3µs
Percentile 60 - 15.209µs
Percentile 70 - 17.061µs
Percentile 80 - 20.369µs
Percentile 90 - 24.932µs
Percentile 95 - 31.304µs
Percentile 99 - 6.478751ms
TopTen latencies: 61.655905ms 61.695015ms 61.946065ms 62.356578ms 62.772547ms 62.802959ms 63.46258ms 65.705002ms 69.661284ms 80.488723ms
Threads with latency below 5ms: 1
Total requests: 200272
Total errors: 0
Average OP/s: 35532
Average good OP/s: 35532
Тест на сервере:
test@host:~$ /ssdsdc/test/goader_linux_amd64 -rpw 2 -max-latency 5ms -requests-engine=disk -url=/ssdsdd/test/tmp/RRRRRRR -body-size=4k -max-requests=300000 -show-progress=0
Writes
Average response time: 2.055671ms
Percentile 30 - 116.458µs
Percentile 40 - 131.335µs
Percentile 50 - 146.395µs
Percentile 60 - 162.461µs
Percentile 70 - 190.041µs
Percentile 80 - 243.472µs
Percentile 90 - 1.02021ms
Percentile 95 - 18.732525ms
Percentile 99 - 30.520401ms
TopTen latencies: 59.081984ms 59.57073ms 59.939992ms 60.179189ms 60.620015ms 61.073503ms 61.450208ms 61.466306ms 61.541489ms 62.755466ms
Threads with latency below 5ms: 32
Total requests: 100253
Total errors: 0
Average OP/s: 13601
Average good OP/s: 13601
Reads
Average response time: 165.988µs
Percentile 30 - 32.68µs
Percentile 40 - 34.791µs
Percentile 50 - 36.846µs
Percentile 60 - 39.249µs
Percentile 70 - 43.053µs
Percentile 80 - 56.993µs
Percentile 90 - 105.291µs
Percentile 95 - 160.119µs
Percentile 99 - 3.461669ms
TopTen latencies: 28.855339ms 29.082389ms 30.023422ms 30.097268ms 30.694055ms 30.832772ms 30.984025ms 32.897706ms 33.492911ms 33.744299ms
Threads with latency below 5ms: 1
Total requests: 199878
Total errors: 0
Average OP/s: 26880
Average good OP/s: 26880
В одном и том же отчёте перемешаны масштабные коэффициенты. Как сравнивать ? Лучше бы использовался везде только ms, как наиболее актуальный. Сравнение разных отчётов разных серверов так же упростилось бы.
Writes
Average response time: 2.899882ms
Percentile 30 - 24.342µs
Percentile 40 - 26.108µs
Percentile 50 - 29.441µs
Percentile 60 - 37.536µs
Percentile 70 - 42.473µs
Percentile 80 - 48.796µs
Percentile 90 - 80.513µs
Percentile 95 - 21.534907ms
Percentile 99 - 67.219535ms
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.