On Aug 12, 2010, at 10:29 AM, mdipierro wrote: > The "fail" requests are due to the fact that dynamical pages may have > different length at each time and ab reports them as failure. It is > not an issue. > > http://groups.google.com/group/web2py/msg/e6509b1d543696b3
But why the erratic transfer-encoding: chunked? > > > > On Aug 12, 11:13 am, Thadeus Burgess <[email protected]> wrote: >> Thank god I'm not the only one =) >> >> -- >> Thadeus >> >> On Thu, Aug 12, 2010 at 10:35 AM, mdipierro <[email protected]> wrote: >>> There numbers are more typical. Consider that those example page also >>> have a db connection and load/store sessions. >> >>> I do not understand the 30% fail requests on form page. Can you >>> reproduce the problem using Rocket instead of Apache? >>> what is the exact "ab" statement. I want to try reproduce the problem. >> >>> Massimo >> >>> On Aug 12, 10:29 am, David Marko <[email protected]> wrote: >>>> I just tried to bechmark standard web2py examples on the same >>>> machine. >>>> This example /examples/simple_examples/hello3.html gives me 70 req/sec >>>> and it also returns almost 7kB of page data. >> >>>> and /examples/form_examples/form gives me 25 req/sec but with 30% of >>>> fail requests and this returns of 25kB of data, so its very nice. (I >>>> have reporetd this previously .. its strange that pages woth forms >>>> causes failed requests) >> >>>> David >> >>>> On 12 srp, 17:13, mdipierro <[email protected]> wrote: >> >>>>> It seems that it takes 600ms to serve a page when you are serving 10 >>>>> at the time. Considering that Python because of the GIL probably not >>>>> taking advantage of multiple cores you may have this is an effective >>>>> time per request of 600/10=60ms. I still think it is too high >>>>> considering you have a fast CPU. Can you check memory and cpu usage >>>>> wit top? Do you have many model files? What is in there? What is the >>>>> apache configuration (processes or threads)? >> >>>>> Massimo >> >>>>> On Aug 12, 10:05 am, David Marko <[email protected]> wrote: >> >>>>>> This is what I can see in log. The first two lines are when served >>>>>> just one request = simple page reload. The rest is with apache >>>>>> benchmark with concurrency set to 10. >> >>>>>> 192.168.2.62, 2010-08-12 19:00:35, GET, /init/default/index, HTTP/1.0, >>>>>> 200, 0.082553 >>>>>> 192.168.2.62, 2010-08-12 19:01:02, GET, /init/default/index, HTTP/1.0, >>>>>> 200, 0.086724 >> >>>>>> 192.168.2.62, 2010-08-12 19:01:31, GET, /init/default/index, HTTP/1.0, >>>>>> 200, 0.504790 >>>>>> 192.168.2.62, 2010-08-12 19:01:31, GET, /init/default/index, HTTP/1.0, >>>>>> 200, 0.506875 >>>>>> 192.168.2.62, 2010-08-12 19:01:31, GET, /init/default/index, HTTP/1.0, >>>>>> 200, 0.516474 >>>>>> 192.168.2.62, 2010-08-12 19:01:31, GET, /init/default/index, HTTP/1.0, >>>>>> 200, 0.599019 >>>>>> 192.168.2.62, 2010-08-12 19:01:31, GET, /init/default/index, HTTP/1.0, >>>>>> 200, 0.597636 >>>>>> 192.168.2.62, 2010-08-12 19:01:31, GET, /init/default/index, HTTP/1.0, >>>>>> 200, 0.622482 >>>>>> 192.168.2.62, 2010-08-12 19:01:31, GET, /init/default/index, HTTP/1.0, >>>>>> 200, 0.629780 >>>>>> 192.168.2.62, 2010-08-12 19:01:31, GET, /init/default/index, HTTP/1.0, >>>>>> 200, 0.660393 >>>>>> 192.168.2.62, 2010-08-12 19:01:31, GET, /init/default/index, HTTP/1.0, >>>>>> 200, 0.677426 >>>>>> 192.168.2.62, 2010-08-12 19:01:31, GET, /init/default/index, HTTP/1.0, >>>>>> 200, 0.712054 >> >>>>>> On 12 srp, 16:56, mdipierro <[email protected]> wrote: >> >>>>>>> Here are the logs for my web server running web2py.com. The log only >>>>>>> shows dynamic pages most of which (like the book) use db. >> >>>>>>> http://web2py.com/examples/static/logs.txt >> >>>>>>> Most pages take around ~20ms but this is a 600MHz VPS with 384MB Ram. >> >>>>>>> On Aug 12, 9:48 am, mdipierro <[email protected]> wrote: >> >>>>>>>> Something is wrong. In wsgiserver.py set >> >>>>>>>> LOGGING = True >> >>>>>>>> and look at web2py/httpserver.log >>>>>>>> what times do you get? >>>>>>>> do you have very large model files? >> >>>>>>>> Massimo >> >>>>>>>> On Aug 12, 9:43 am, David Marko <[email protected]> wrote: >> >>>>>>>>> I just moved my first real-life app into production (its a private app >>>>>>>>> so I cant share screens etc.). Its running latest stable web2py on >>>>>>>>> Debian 5 + Python 2.6.5 + modwsgi 3.3 . When testing application home >>>>>>>>> page, where are no sql commands, session is disabled (by >>>>>>>>> session.forget()) and migration is disabled, I can get, using apache >>>>>>>>> benchmark, only 12 req/sec. When I compile app, it increases up to 16 >>>>>>>>> req/sec, but both numbers seems to me very low. Can you share some >>>>>>>>> your experience what one can get from web2py? >> >>>>>>>>> Using browser, the application feels very responsive, but I'm just >>>>>>>>> scared (a bit) how this will change when all users start using the >>>>>>>>> app. >> >>>>>>>>> My server HW is one processor 3GHz, 1.5 GB RAM. >> >>>>>>>>> David
