make sure to bench in terms of concurrency and try to send a long term cache control header.
the problem i experienced years ago under similar setups (mod_perl and mod_python) was this: the render/etc times were really nothing or the items were served 'raw' by the app -- but all the js / css / img etc items resulted in dozens of requests to the apps per page viewed. because the apps had inherent overhead and would max out at , for example , 20 concurrent requests instead of thousands like nginx could easily handle, once person viewing a page could essentially lock up the server for a 30-90 seconds. i believe this was one of the larger issues affecting the performance of trac installs a while back as well. -- You received this message because you are subscribed to the Google Groups "pylons-discuss" 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/pylons-discuss?hl=en.
