In my experience, it's very difficult to tie profiling data from generic profilers to specific requests, then to the specific lines-of-code triggering the problems.
This is important because many performance conditions don't reveal themselves all of the time: for example, it's very common that an issue might only be a problem for your largest customers. The context is really important.
This is important because many performance conditions don't reveal themselves all of the time: for example, it's very common that an issue might only be a problem for your largest customers. The context is really important.
Scout has a production-safe profiler for Ruby apps that builds on the wonderful StackProf gem that does this: http://help.apm.scoutapp.com/#scoutprof