Hi,
I'm having a nginx / uwsgi / django server and wanted to get some
profiling data to identify bottle necks. (80% dynamic difficult to cache
contents, so don't worry too much about serving static contents)
What would be recommended strategies to create decent reports, that can
help to pinpoint potentially critical code.
I posted another message in the django group for django specific profiling.
Here I'd be mostly interested in uwsgi specic tools.
I could add specific profiling features to the server even if they would
slow down the system. I'd just enable them for a few days, gather the
data and would disable them afterwards.
What statistics do you normally use to identify such issues and how
could you get them?
Some measures I can think of:
Number of held back uwsgi requests
--------------------------------------
How could I identify all requests, that are blocked due to the fact,
that I don't have enough uwsgi processes spawned.
report of Django requests and their execution time
-----------------------------------------------------
Just use the uwsgi logs?
Any other nginx / uwsgi specific tricks to get a feeling where the time
(and memory) is spent?
Thanks for any suggestions
_______________________________________________
uWSGI mailing list
[email protected]
http://lists.unbit.it/cgi-bin/mailman/listinfo/uwsgi
