Sir, These are numbers of my app. I've rebooted my Ubuntu this time, with no other program running, these are the results.
Config: 2.16 GHZ Dual Core, 2GB RAM *************Without SSL*************** va...@varun-laptop:~$ ab -c 20 -n 500 http://10.1.65.114/init/default/login This is ApacheBench, Version 2.3 <$Revision: 655654 $> Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/ Licensed to The Apache Software Foundation, http://www.apache.org/ Benchmarking 10.1.65.114 (be patient) Completed 100 requests Completed 200 requests Completed 300 requests Completed 400 requests Completed 500 requests Finished 500 requests Server Software: Apache/2.2.12 Server Hostname: 10.1.65.114 Server Port: 80 Document Path: /init/default/login Document Length: 5595 bytes Concurrency Level: 20 Time taken for tests: 15.632 seconds Complete requests: 500 Failed requests: 0 Write errors: 0 Total transferred: 2994418 bytes HTML transferred: 2797500 bytes Requests per second: 31.99 [#/sec] (mean) Time per request: 625.284 [ms] (mean) Time per request: 31.264 [ms] (mean, across all concurrent requests) Transfer rate: 187.07 [Kbytes/sec] received Connection Times (ms) min mean[+/-sd] median max Connect: 0 0 0.2 0 1 Processing: 92 619 149.4 609 1288 Waiting: 80 612 149.0 604 1270 Total: 93 619 149.3 609 1288 Percentage of the requests served within a certain time (ms) 50% 609 66% 675 75% 719 80% 748 90% 806 95% 864 98% 969 99% 1015 100% 1288 (longest request) ************** With SSL ********************** va...@varun-laptop:~$ ab -c 20 -n 500 https://10.1.65.114/welcome/default/ This is ApacheBench, Version 2.3 <$Revision: 655654 $> Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/ Licensed to The Apache Software Foundation, http://www.apache.org/ Benchmarking 10.1.65.114 (be patient) ^C Server Software: Server Hostname: 10.1.65.114 Server Port: 443 Document Path: /welcome/default/ Document Length: 0 bytes Concurrency Level: 20 Time taken for tests: 0.213 seconds Complete requests: 0 Failed requests: 0 Write errors: 0 Total transferred: 0 bytes HTML transferred: 0 bytes va...@varun-laptop:~$ ab -c 20 -n 500 https://10.1.65.114/init/default/login This is ApacheBench, Version 2.3 <$Revision: 655654 $> Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/ Licensed to The Apache Software Foundation, http://www.apache.org/ Benchmarking 10.1.65.114 (be patient) Completed 100 requests Completed 200 requests Completed 300 requests Completed 400 requests Completed 500 requests Finished 500 requests Server Software: Apache/2.2.12 Server Hostname: 10.1.65.114 Server Port: 443 SSL/TLS Protocol: TLSv1/SSLv3,DHE-RSA-AES256-SHA,1024,256 Document Path: /init/default/login Document Length: 5595 bytes Concurrency Level: 20 Time taken for tests: 17.456 seconds Complete requests: 500 Failed requests: 0 Write errors: 0 Total transferred: 3005532 bytes HTML transferred: 2803095 bytes Requests per second: 28.64 [#/sec] (mean) Time per request: 698.229 [ms] (mean) Time per request: 34.911 [ms] (mean, across all concurrent requests) Transfer rate: 168.14 [Kbytes/sec] received Connection Times (ms) min mean[+/-sd] median max Connect: 37 253 118.5 257 719 Processing: 53 436 191.9 397 1348 Waiting: 49 397 188.9 366 1336 Total: 237 690 232.6 683 1859 Percentage of the requests served within a certain time (ms) 50% 683 66% 743 75% 771 80% 806 90% 924 95% 1173 98% 1381 99% 1547 100% 1859 (longest request) On Jan 10, 8:25 pm, mdipierro <mdipie...@cs.depaul.edu> wrote: > These number are high. What is in the app? Are you testing ssl? What > are the same numbers without ssl? > > On Jan 10, 5:12 am, vvk <varunk.ap...@gmail.com> wrote: > > > Thanks massimo sir, > > > At first, I was getting mean response time of 200 ms per request (ab - > > n 500 -c 20) > > I did compile (link "compile" in admin page), mean time per request > > reduced to 61 ms. > > After that I did, migrate=False for all tables, mean time came down to > > 57.1 ms. > > I'll try caching today and post that results also. > > > ----- > > > va...@varun-laptop:~$ ab -c 20 -n 500https://localhost/lsilab/default/login > > This is ApacheBench, Version 2.3 <$Revision: 655654 $> > > Copyright 1996 Adam Twiss, Zeus Technology Ltd,http://www.zeustech.net/ > > Licensed to The Apache Software Foundation,http://www.apache.org/ > > > Benchmarking localhost (be patient) > > Completed 100 requests > > Completed 200 requests > > Completed 300 requests > > Completed 400 requests > > Completed 500 requests > > Finished 500 requests > > > Server Software: Apache/2.2.12 > > Server Hostname: localhost > > Server Port: 443 > > SSL/TLS Protocol: TLSv1/SSLv3,DHE-RSA-AES256-SHA,1024,256 > > > Document Path: /lsilab/default/login > > Document Length: 5611 bytes > > > Concurrency Level: 20 > > Time taken for tests: 28.633 seconds > > Complete requests: 500 > > Failed requests: 0 > > Write errors: 0 > > Total transferred: 3005798 bytes > > HTML transferred: 2805500 bytes > > Requests per second: 17.46 [#/sec] (mean) > > Time per request: 1145.315 [ms] (mean) > > Time per request: 57.266 [ms] (mean, across all concurrent > > requests) > > Transfer rate: 102.52 [Kbytes/sec] received > > > Connection Times (ms) > > min mean[+/-sd] median max > > Connect: 41 423 151.1 450 976 > > Processing: 129 705 228.8 662 1589 > > Waiting: 129 651 215.9 609 1588 > > Total: 471 1128 249.1 1093 1829 > > > Percentage of the requests served within a certain time (ms) > > 50% 1093 > > 66% 1195 > > 75% 1277 > > 80% 1322 > > 90% 1502 > > 95% 1577 > > 98% 1693 > > 99% 1724 > > 100% 1829 (longest request) > > va...@varun-laptop:~$ > > > On Jan 2, 3:15 pm, waTR <r...@devshell.org> wrote: > > > > I agree. The bottleneck would likely be the DB, not web2py or Django > > > or any other framework/language. Therefore, the key here is to use > > > caching and smart db design (plus some ajax to break big DB load tasks > > > down to smaller ones). > > > > On Jan 1, 6:27 pm, mdipierro <mdipie...@cs.depaul.edu> wrote: > > > > > It really depends on what "Can this handle requests from 100 users > > > > every moment?" means. > > > > The bottleneck is probably the db. > > > > > Before youbenchmarkand/or go to production make sure you: > > > > - bytecode compile your app > > > > - set all your models to migrate = False > > > > > Massimo > > > > > On Dec 31 2009, 9:00 pm, vvk <varunk.ap...@gmail.com> wrote: > > > > > > Hi all, > > > > > > I've to write a portal for my college in next semester. I want to > > > > > discuss regarding scalabilty of web2py. > > > > > > Configuration of Deployment: > > > > > Apache + Mod WSGI + Postgresql + https only > > > > > > Can this handle requests from 100 users every moment? > > > > > What might be expected load on system given that machines here are of > > > > > server class, can they handle this load, kindly suggest minimum > > > > > configuration for this to work ? > > > > > My application is a small one, having ten tables and conforms to 3NF, > > > > > any suggestions here, regarding controllers or DB ? > > > > > I'm testing my Inventory application today for scalability on a > > > > > machine (AMD Athlon Processor 3000+, 512 MB RAM), will post results > > > > > today. > > > > > > ---- > > > > > Varun
-- You received this message because you are subscribed to the Google Groups "web2py-users" group. To post to this group, send email to web...@googlegroups.com. To unsubscribe from this group, send email to web2py+unsubscr...@googlegroups.com. For more options, visit this group at http://groups.google.com/group/web2py?hl=en.
