Both code are simply returns {ping:"pong"}, runs on unbantu 12 virtualBox.
Grape on thin
1. Simulate 100 users, 10000 requests
ab -n 10000 -c 100 http://localhost:3000
Result:
Server Software: thin
Server Hostname: localhost
Server Port: 3000
Document Path: /
Document Length: 11 bytes
Concurrency Level: 100
Time taken for tests: 5.368 seconds
Complete requests: 10000
Failed requests: 0
Write errors: 0
Total transferred: 1460000 bytes
HTML transferred: 110000 bytes
Requests per second: 1862.76 [#/sec] (mean)
Time per request: 53.684 [ms] (mean)
Time per request: 0.537 [ms] (mean, across all concurrent requests)
Transfer rate: 265.59 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 0 0.3 0 7
Processing: 31 53 12.8 48 95
Waiting: 27 49 12.4 44 92
Total: 31 53 12.8 48 96
Percentage of the requests served within a certain time (ms)
50% 48
66% 49
75% 51
80% 54
90% 82
95% 84
98% 87
99% 89
100% 96 (longest request)
Grape on goliath
1. Simulate 100 users, 10000 requests
ab -n 10000 -c 100 http://localhost:9000
Result:
Server Software: Goliath
Server Hostname: localhost
Server Port: 9000
Document Path: /api/ping
Document Length: 15 bytes
Concurrency Level: 100
Time taken for tests: 12.329 seconds
Complete requests: 10000
Failed requests: 0
Write errors: 0
Total transferred: 1540000 bytes
HTML transferred: 150000 bytes
Requests per second: 811.07 [#/sec] (mean)
Time per request: 123.294 [ms] (mean)
Time per request: 1.233 [ms] (mean, across all concurrent requests)
Transfer rate: 121.98 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 0 0.3 0 8
Processing: 54 123 17.7 134 158
Waiting: 44 111 17.9 124 149
Total: 59 123 17.6 134 159
Percentage of the requests served within a certain time (ms)
50% 134
66% 135
75% 136
80% 137
90% 140
95% 143
98% 147
99% 157
100% 159 (longest request)
Conclusion: Grape on thin seems much better than grape on goliath.
Grape on thin
1. Simulate 100 users, 10000 requests
ab -n 10000 -c 100 http://localhost:3000
Result:
Server Software: thin
Server Hostname: localhost
Server Port: 3000
Document Path: /
Document Length: 11 bytes
Concurrency Level: 100
Time taken for tests: 5.368 seconds
Complete requests: 10000
Failed requests: 0
Write errors: 0
Total transferred: 1460000 bytes
HTML transferred: 110000 bytes
Requests per second: 1862.76 [#/sec] (mean)
Time per request: 53.684 [ms] (mean)
Time per request: 0.537 [ms] (mean, across all concurrent requests)
Transfer rate: 265.59 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 0 0.3 0 7
Processing: 31 53 12.8 48 95
Waiting: 27 49 12.4 44 92
Total: 31 53 12.8 48 96
Percentage of the requests served within a certain time (ms)
50% 48
66% 49
75% 51
80% 54
90% 82
95% 84
98% 87
99% 89
100% 96 (longest request)
Grape on goliath
1. Simulate 100 users, 10000 requests
ab -n 10000 -c 100 http://localhost:9000
Result:
Server Software: Goliath
Server Hostname: localhost
Server Port: 9000
Document Path: /api/ping
Document Length: 15 bytes
Concurrency Level: 100
Time taken for tests: 12.329 seconds
Complete requests: 10000
Failed requests: 0
Write errors: 0
Total transferred: 1540000 bytes
HTML transferred: 150000 bytes
Requests per second: 811.07 [#/sec] (mean)
Time per request: 123.294 [ms] (mean)
Time per request: 1.233 [ms] (mean, across all concurrent requests)
Transfer rate: 121.98 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 0 0.3 0 8
Processing: 54 123 17.7 134 158
Waiting: 44 111 17.9 124 149
Total: 59 123 17.6 134 159
Percentage of the requests served within a certain time (ms)
50% 134
66% 135
75% 136
80% 137
90% 140
95% 143
98% 147
99% 157
100% 159 (longest request)
Conclusion: Grape on thin seems much better than grape on goliath.
