Well I've compiled pypy-1.8 from source (without jit) and found that is slower than python whyle executing web2py here are my test results
*PYPY* ab -n 10 -c 5 http://127.0.0.1:8000/ This is ApacheBench, Version 2.3 <$Revision: 655654 $> Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/ Licensed to The Apache Software Foundation, http://www.apache.org/ Benchmarking 127.0.0.1 (be patient).....done Server Software: Rocket Server Hostname: 127.0.0.1 Server Port: 8000 Document Path: / Document Length: 18071 bytes Concurrency Level: 5 Time taken for tests: 5.257 seconds Complete requests: 10 Failed requests: 0 Write errors: 0 Total transferred: 184880 bytes HTML transferred: 180710 bytes Requests per second: 1.90 [#/sec] (mean) Time per request: 2628.322 [ms] (mean) Time per request: 525.664 [ms] (mean, across all concurrent requests) Transfer rate: 34.35 [Kbytes/sec] received Connection Times (ms) min mean[+/-sd] median max Connect: 0 0 0.1 0 0 Processing: 1851 2465 277.7 2583 2731 Waiting: 1849 2461 275.6 2583 2705 Total: 1851 2465 277.7 2583 2731 Percentage of the requests served within a certain time (ms) 50% 2583 66% 2610 75% 2671 80% 2671 90% 2731 95% 2731 98% 2731 99% 2731 100% 2731 (longest request) *PYTHON* ab -n 10 -c 5 http://127.0.0.1:8181/ This is ApacheBench, Version 2.3 <$Revision: 655654 $> Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/ Licensed to The Apache Software Foundation, http://www.apache.org/ Benchmarking 127.0.0.1 (be patient).....done Server Software: Rocket Server Hostname: 127.0.0.1 Server Port: 8181 Document Path: / Document Length: 18071 bytes Concurrency Level: 5 Time taken for tests: 1.920 seconds Complete requests: 10 Failed requests: 0 Write errors: 0 Total transferred: 184890 bytes HTML transferred: 180710 bytes Requests per second: 5.21 [#/sec] (mean) Time per request: 960.005 [ms] (mean) Time per request: 192.001 [ms] (mean, across all concurrent requests) Transfer rate: 94.04 [Kbytes/sec] received Connection Times (ms) min mean[+/-sd] median max Connect: 0 0 0.2 0 0 Processing: 694 883 107.4 885 1031 Waiting: 693 880 104.2 885 1030 Total: 694 883 107.6 885 1031 Percentage of the requests served within a certain time (ms) 50% 885 66% 889 75% 995 80% 1017 90% 1031 95% 1031 98% 1031 99% 1031 100% 1031 (longest request) This app uses lots of modules like pymongo, Image, stripogram, dateutil, pygeoip,tornado, tornadio, pycurl I've manage to easy_install all them in pypy, but I couldn't install pycurl, so I've commented it for the ab testing I've also tried with the welcome app and the results were similar: pypy was 2.5x slower Any other tests are truly appreciated
