messure performance

[matsumotory]

from https://gist.github.com/matsumoto-r/9702123.

[sawanoboly]

同環境でnginx 1.5のHTTP1.1

ENV

• Server: Ubuntu12.04 on virtualbox (10.33.35.201)

# cat /proc/cpuinfo 
processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 69
model name      : Intel(R) Core(TM) i7-4558U CPU @ 2.80GHz
stepping        : 1
microcode       : 0x19
cpu MHz         : 2762.728
cache size      : 6144 KB
fpu             : yes
fpu_exception   : yes
cpuid level     : 5
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 syscall nx rdtscp lm constant_tsc up rep_good nopl pni monitor ssse3 lahf_lm
bogomips        : 5525.45
clflush size    : 64
cache_alignment : 64
address sizes   : 39 bits physical, 48 bits virtual
power management:

# nginx -V
nginx version: nginx/1.5.0
TLS SNI support enabled
configure arguments: --prefix=/usr/share/nginx --conf-path=/etc/nginx/nginx.conf --error-log-path=/var/log/nginx/error.log --http-client-body-temp-path=/var/lib/nginx/body --http-fastcgi-temp-path=/var/lib/nginx/fastcgi --http-log-path=/var/log/nginx/access.log --http-proxy-temp-path=/var/lib/nginx/proxy --http-scgi-temp-path=/var/lib/nginx/scgi --http-uwsgi-temp-path=/var/lib/nginx/uwsgi --lock-path=/var/lock/nginx.lock --pid-path=/run/nginx.pid --with-pcre-jit --with-debug --with-http_addition_module --with-http_dav_module --with-http_geoip_module --with-http_gzip_static_module --with-http_image_filter_module --with-http_realip_module --with-http_stub_status_module --with-http_ssl_module --with-http_sub_module --with-http_xslt_module --with-ipv6 --with-mail --with-mail_ssl_module --add-module=/build/buildd/nginx-1.5.0/debian/modules/nginx-auth-pam --add-module=/build/buildd/nginx-1.5.0/debian/modules/nginx-dav-ext-module --add-module=/build/buildd/nginx-1.5.0/debian/modules/nginx-echo --add-module=/build/buildd/nginx-1.5.0/debian/modules/nginx-upstream-fair --add-module=/build/buildd/nginx-1.5.0/debian/modules/ngx_http_substitutions_filter_module

# ./build/default/weighttp -c 100 -n 100000 -k http://127.0.0.1:80/index.html
weighttp - a lightweight and simple webserver benchmarking tool

starting benchmark...
spawning thread #1: 100 concurrent requests, 100000 total requests
progress:  10% done
progress:  20% done
progress:  30% done
progress:  40% done
progress:  50% done
progress:  60% done
progress:  70% done
progress:  80% done
progress:  90% done
progress: 100% done

finished in 6 sec, 135 millisec and 940 microsec, 16297 req/s, 4137 kbyte/s
requests: 100000 total, 100000 started, 100000 done, 100000 succeeded, 0 failed, 0 errored
status codes: 100000 2xx, 0 3xx, 0 4xx, 0 5xx
traffic: 25995015 bytes total, 23495015 bytes http, 2500000 bytes data

[matsumotory]

おおー、確かmruby-http2は10並列で14万でしたよね？100並列（-c 100 -m 100）という上記と同じ条件だとどうなりますか？

上記と同環境のmruby-http2の情報を下記の「ここから」以下にコピペ(refs: https://gist.github.com/matsumoto-r/9702123#comment-1197493 )

ここから↓

---

VirtualBoxでTLSなしをやってみた。146232 req/s

index.htmlをtmpfsにしてみたらちょっと(+30,000)早くなった。

ENV

• Ubuntu12.04 on virtualbox

# cat /proc/cpuinfo 
processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 69
model name      : Intel(R) Core(TM) i7-4558U CPU @ 2.80GHz
stepping        : 1
microcode       : 0x19
cpu MHz         : 2762.728
cache size      : 6144 KB
fpu             : yes
fpu_exception   : yes
cpuid level     : 5
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 syscall nx rdtscp lm constant_tsc up rep_good nopl pni monitor ssse3 lahf_lm
bogomips        : 5525.45
clflush size    : 64
cache_alignment : 64
address sizes   : 39 bits physical, 48 bits virtual
power management:

build

• build mruby with cookbook[mruby]

Before build

apt-get install autoconf automake autotools-dev libtool pkg-config zlib1g-dev libcunit1-dev libssl-dev libxml2-dev libevent-dev libjansson-dev libjemalloc-dev
mount -t tmpfs -o size=64m /dev/shm /var/tmp

Server

root_dir = "/var/tmp/www"  # tmpfs

s = HTTP2::Server.new({
  :port           => 8080,
  :document_root  => "#{root_dir}/htdocs",
  :server_name    => "mruby-http2 server",
  :tls => false,
})

s.run

Result

# ./h2load -n100000 -c10 -m10 http://127.0.0.1:8080/index.html
-t: warning: the number of threads is greater than hardware cores.
starting benchmark...
spawning thread #0: 10 concurrent clients, 100000 total requests
progress: 10% done
progress: 20% done
progress: 30% done
progress: 40% done
progress: 50% done
progress: 60% done
progress: 70% done
progress: 80% done
progress: 90% done
progress: 100% done

finished in 0 sec, 683 millisec and 844 microsec, 146232 req/s, 6997 kbytes/s
requests: 100000 total, 100000 started, 100000 done, 100000 succeeded, 0 failed, 0 errored
status codes: 100000 2xx, 0 3xx, 0 4xx, 0 5xx
traffic: 4900370 bytes total, 160 bytes headers, 2500000 bytes data

---

ここまで↑

[sawanoboly]

こうなるねえ。

# ./h2load -n100000 -c100 -m100 http://127.0.0.1:8080/index.html
-t: warning: the number of threads is greater than hardware cores.
starting benchmark...
spawning thread #0: 100 concurrent clients, 100000 total requests
progress: 10% done
progress: 20% done
progress: 30% done
progress: 40% done
progress: 50% done
progress: 60% done
progress: 70% done
progress: 80% done
progress: 90% done
progress: 100% done

finished in 0 sec, 884 millisec and 519 microsec, 113055 req/s, 5413 kbytes/s
requests: 100000 total, 100000 started, 100000 done, 100000 succeeded, 0 failed, 0 errored
status codes: 100000 2xx, 0 3xx, 0 4xx, 0 5xx
traffic: 4903700 bytes total, 1600 bytes headers, 2500000 bytes data

[matsumotory]

なるほどー。これらをみるとnginxの10倍くらいですかね。

[matsumotory]

Current commit: 49d213b

$ h2load -w30 -W30 -n5000000 -c100 -m 100 http://127.0.0.1:8080/index.html
starting benchmark...
spawning thread #0: 100 concurrent clients, 5000000 total requests
progress: 10% done
progress: 20% done
progress: 30% done
progress: 40% done
progress: 50% done
progress: 60% done
progress: 70% done
progress: 80% done
progress: 90% done
progress: 100% done

finished in 21 sec, 840 millisec and 430 microsec, 228933 req/s, 5815 kbytes/s
requests: 5000000 total, 5000000 started, 5000000 done, 5000000 succeeded, 0 failed, 0 errored
status codes: 5000000 2xx, 0 3xx, 0 4xx, 0 5xx
traffic: 250069900 bytes total, 20067800 bytes headers, 110000000 bytes data

[matsumotory]

Local hello world benchmark: conccurency 30000

$ h2load -n1000000 -c30000 -m30000 http://127.0.0.1:8080/index.html
starting benchmark...
spawning thread #0: 30000 concurrent clients, 1000000 total requests
progress: 10% done
progress: 20% done
progress: 30% done
progress: 40% done
progress: 50% done
progress: 60% done
progress: 70% done
progress: 80% done
progress: 90% done
progress: 100% done

finished in 7 sec, 467 millisec and 749 microsec, 133909 req/s, 3656 kbytes/s
requests: 1000000 total, 1000000 started, 1000000 done, 1000000 succeeded, 0 failed, 0 errored
status codes: 1000000 2xx, 0 3xx, 0 4xx, 0 5xx
traffic: 52588235 bytes total, 5958235 bytes headers, 22000000 bytes data

[matsumotory]

done