Something is wrong. Cherrypy cannot take 40x longer. Moreover you are not benchmarking the web server but a web2py app. And the time spent in web2py is more than the time spent in the web server by a factor 10. You need to benchmark a bare bone (non-web2py) hello world wsgi application (such as the one provided).
I would also try change the number of min threads (num thread) the size of the listening queue and try benchmark with different values of ab -c option. On Sep 18, 1:45 pm, Alex Fanjul <[email protected]> wrote: > Sorry my results are very inconsistent... and I dont know why... > m4400 notebook, windows7 rtm, t9400, 4gb, 500gb, fx770 > > ---------------------------------------------------------------------------------- > [[[[[[HELLOWORLD WITH WEB2PY IN APACHE+WSGI AND WITHOUT SSL (EVEN IF ITS > IN DOMAIN NAME)]]]]]] > ---------------------------------------------------------------------------------- > E:\wamp\bin\apache\Apache2.2.11\bin>ab -n > 10000http://ssl.localhost/HelloWorld/ > default/index > > Benchmarking ssl.localhost (be patient) > > Server Software: Apache/2.2.11 > Server Hostname: ssl.localhost > Server Port: 80 > > Document Path: /HelloWorld/default/index > Document Length: 22 bytes > > Concurrency Level: 1 > Time taken for tests: 55.751 seconds > Complete requests: 10000 > Failed requests: 0 > Write errors: 0 > Total transferred: 4320000 bytes > HTML transferred: 220000 bytes > Requests per second: 179.37 [#/sec] (mean) > Time per request: 5.575 [ms] (mean) > Time per request: 5.575 [ms] (mean, across all concurrent requests) > Transfer rate: 75.67 [Kbytes/sec] received > > Connection Times (ms) > min mean[+/-sd] median max > Connect: 0 0 0.4 0 3 > Processing: 4 5 9.3 5 541 > Waiting: 3 5 8.2 4 540 > Total: 4 6 9.3 5 541 > > Percentage of the requests served within a certain time (ms) > 50% 5 > 66% 5 > 75% 5 > 80% 5 > 90% 6 > 95% 13 > 98% 14 > 99% 16 > 100% 541 (longest request) > > ---------------------------------------------------------------------------------- > [[[[[[HELLOWORLD WITH WEB2PY IN WEB2PYSERVER]]]]]] > ---------------------------------------------------------------------------------- > > E:\wamp\bin\apache\Apache2.2.11\bin>ab -n > 10000http://127.0.0.1:8000/HelloWorld/default/index > This is ApacheBench, Version 2.3 <$Revision: 655654 $> > Copyright 1996 Adam Twiss, Zeus Technology Ltd,http://www.zeustech.net/ > Licensed to The Apache Software Foundation,http://www.apache.org/ > > Benchmarking 127.0.0.1 (be patient) > Completed 1000 requests > Completed 2000 requests > Completed 3000 requests > Completed 4000 requests > Completed 5000 requests > Completed 6000 requests > Completed 7000 requests > Completed 8000 requests > Completed 9000 requests > Completed 10000 requests > Finished 10000 requests > > Server Software: PBartoloNt > Server Hostname: 127.0.0.1 > Server Port: 8000 > > Document Path: /HelloWorld/default/index > Document Length: 22 bytes > > Concurrency Level: 1 > Time taken for tests: 50.371 seconds > Complete requests: 10000 > Failed requests: 0 > Write errors: 0 > Total transferred: 3850000 bytes > HTML transferred: 220000 bytes > Requests per second: 198.53 [#/sec] (mean) > Time per request: 5.037 [ms] (mean) > Time per request: 5.037 [ms] (mean, across all concurrent requests) > Transfer rate: 74.64 [Kbytes/sec] received > > Connection Times (ms) > min mean[+/-sd] median max > Connect: 0 0 0.4 0 3 > Processing: 3 5 9.2 4 404 > Waiting: 3 4 9.2 4 401 > Total: 4 5 9.2 4 404 > > Percentage of the requests served within a certain time (ms) > 50% 4 > 66% 4 > 75% 5 > 80% 5 > 90% 5 > 95% 11 > 98% 13 > 99% 15 > 100% 404 (longest request) > > > ---------------------------------------------------------------------------------- > [[[[[[HELLOWORLD WITH WEB2PY IN CHERRYPY]]]]]] > ---------------------------------------------------------------------------------- > > E:\wamp\bin\apache\Apache2.2.11\bin>ab -n > 10000http://127.0.0.1:8000/HelloWorld > > This is ApacheBench, Version 2.3 <$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) > Completed 1000 requests > Completed 2000 requests > Completed 3000 requests > Completed 4000 requests > Completed 5000 requests > Completed 6000 requests > Completed 7000 requests > Completed 8000 requests > Completed 9000 requests > Completed 10000 requests > Finished 10000 requests > > Server Software: CherryPy/3.2.0beta > Server Hostname: 127.0.0.1 > Server Port: 8000 > > Document Path: /HelloWorld > Document Length: 22 bytes > > Concurrency Level: 1 > Time taken for tests: 2342.605 seconds > Complete requests: 10000 > Failed requests: 0 > Write errors: 0 > Total transferred: 3860000 bytes > HTML transferred: 220000 bytes > Requests per second: 4.27 [#/sec] (mean) > Time per request: 234.260 [ms] (mean) > Time per request: 234.260 [ms] (mean, across all concurrent requests) > Transfer rate: 1.61 [Kbytes/sec] received > > Connection Times (ms) > min mean[+/-sd] median max > Connect: 0 0 0.4 0 7 > Processing: 107 234 311.0 218 21304 > Waiting: 107 215 301.4 211 21303 > Total: 107 234 311.0 218 21305 > > Percentage of the requests served within a certain time (ms) > 50% 218 > 66% 245 > 75% 257 > 80% 274 > 90% 317 > 95% 393 > 98% 496 > 99% 523 > 100% 21305 (longest request) > > El 18/09/2009 18:41, mdipierro escribió: > > > > > It would be great if you could run and publish more benchmarks for > > this, cherrypy and apache+mod_wsgi and a couple of different > > hello_world apps. > > I have not been able to test chunked upload since I do not know how > > which clients do it. Firefox does not. The code would be much smaller > > without support for it. > > It would be breat if you could run some more benchmarks as Graham > > suggested. > > > Massimo > > > On Sep 18, 11:29 am, Alex Fanjul<[email protected]> wrote: > > >> Just now I was reviewing, and efectively the init call was wrong... > >> great! > > >> El 18/09/2009 18:23, mdipierro escribió: > > >>> sorry, I tried to make it api compatible with cherrypy and broke the > >>> hello world example. You can find the latest here: > > >>>http://web2py.com/examples/static/web2pyserver.py > > >>> Massimo > > >>> On Sep 18, 11:20 am, Alex Fanjul<[email protected]> wrote: > > >>>> Massimo I tried to run standalone and I recived this: > > >>>> E:\web2py\gluon>python web2pyserver.py 8001 > >>>> Traceback (most recent call last): > >>>> File "web2pyserver.py", line 260, in<module> > > >>>> s=web2pyWSGIServer('127.0.0.1:'+sys.argv[1],test_wsgi_app,min_threads=5,max_ > >>>> threads=10) > >>>> TypeError: __init__() got an unexpected keyword argument 'min_threads' > > >>>> Integrated with web2py it works (not with all apps) but doesnt me allow > >>>> to enter in admin section (typical: Admin is disabled because insecure > >>>> channel) even if I was in localhost. > > >>>> Any clues with this 2 issues? > >>>> Alex F > > >>>> El 18/09/2009 5:50, Massimo Di Pierro escribió: > > >>>>> Please ignore my previous email. I fixed it and it seems to works > >>>>> great (attached) > > >>>>> It is very much modeled on wsgiserver. > >>>>> It fits in 262 lines of code, uses regex and it is a little bit faster > >>>>> than wsgiserver but, > >>>>> it does not perform all checks that wsgiserver performs (do we need > >>>>> them?). > >>>>> I am still trying to figure out if I am missing something important. > > >>>>> Massimo > > >>>> -- > >>>> Alejandro Fanjul Fdez. > >>>> [email protected] > > >> -- > >> Alejandro Fanjul Fdez. > >> [email protected] > > -- > Alejandro Fanjul Fdez. > [email protected] --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "web2py-users" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/web2py?hl=en -~----------~----~----~----~------~----~------~--~---
