Thanks for the great work; I think these were pretty great results.

On Thu, May 14, 2009 at 10:41 AM, Ben Gidley <b...@gidley.co.uk> wrote:
> Hi,
> As I posted a few weeks back I have been running a series of load tests and
> have come to the following key conslusions
>
>   - *Tapestry is fast* - the response times even under load are low. It
>   isn't alway's fastest solution but it is sufficiently fast for me to focus
>   my tuning attention elsewhere
>   - *Tapestry does not leak memory *- One of the concerns I have heard
>   raised about tapestry's approach is that it is likely to be heavy on memory.
>   In fact I found the opposite. It was lower than struts/jsp and in the
>   extended run the memory was pretty flat
>   - *Tapestry is faster than struts for forms apps* - Tapestry seems to
>   excel as the application complexity gets significant. This is probably a
>   feature of its pooling model.
>   - *Tapestry doesn't break easily and when it does it recovers* - Tapestry
>   does slow down under extreme load, but it does break or hit bottlenecks.
>   This is a really positive thing. It also recovers when the load goes away.
>   - *More CPU's doesn't always equal better* - in a number of tests
>   performance didn't increase linearly. 2 CPU's did double throughput but 4
>   didn't. This is often a feature of the OS/platform but would suggest in a
>   virtualised environment that running more dual core instances is better than
>   running fewer quad core instances
>   - *64bit is faster than 32 bit* - This one surprised me a bit - I had
>   heard and thought that 64bit was a bit slower as it pushes more data around.
>   However it seems that using a 64bit JVM on a 64bit OS makes a positive
>   difference on both Solaris and Linux.
>   - *Linux is faster than Open Solaris X86* - This one also surprised me a
>   bit - I expected them to be pretty near the same whereas in fact is was
>   nearly 25% better on linux. I can't explain it - but the numbers speak for
>   themselves.
>
> The full details of the load tests and a longer write up is at
> http://blog.gidley.co.uk/2009/05/tapestry-load-testing-round-up.html
>
>
> Ben Gidley
>
> www.gidley.co.uk
> b...@gidley.co.uk
>



-- 
Howard M. Lewis Ship

Creator of Apache Tapestry
Director of Open Source Technology at Formos

---------------------------------------------------------------------
To unsubscribe, e-mail: users-unsubscr...@tapestry.apache.org
For additional commands, e-mail: users-h...@tapestry.apache.org

Reply via email to