[forge-dev] Improving the performance of weld for micro-deployments.

[Luca Masini]

We don't need to recall the Schrödinger cat for this kind of experiments !!
Lincoln do you see that startup time is really higher when you start
YourKit ??

Which version are you using ?? In my experience the last one has a really
good agent that impact not so much on performance in tracing or
instrumentation.



2013/1/30 Thomas Frühbeck <fruehbeck at aon.at>

> IMHO both tools have their up/downsides.
>   - instrumentation gives you a quite precise _relative_ performance
> indicator
>   - sampling gives a _relatively precise_ performance indicator
> both have impact on the runtime, so you always have to account for the
> "uncertainty principle" :-)
>
> Am 29.01.2013 23:33, schrieb Stuart Douglas:
> > Tracing is pretty useless at identifying slow parts, as the overhead it
> > adds distorts the profile too much. The only thing it is really good for
> > is identifying methods that are called too often.
> >
> > Sampling is generally much better.
> >
> _______________________________________________
> forge-dev mailing list
> forge-dev at lists.jboss.org
> https://lists.jboss.org/mailman/listinfo/forge-dev
>



-- 
****************************************
http://www.lucamasini.net
http://twitter.com/lmasini
http://www.linkedin.com/pub/luca-masini/7/10/2b9
****************************************
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.jboss.org/pipermail/forge-dev/attachments/20130130/44945e79/attachment.html