[Twisted-Python] I found an interisting comment about Twisted vs. Erlang

Jamu Kakar jkakar at kakar.ca
Tue Sep 29 15:48:17 EDT 2009


Hi Alec,

On Tue, Sep 29, 2009 at 12:36 PM, Alec Matusis <matusis at yahoo.com> wrote:
> As you can see from the %CPU column, I have my reasons for concern ;) This
> is current copy and paste from a node with 2x quad core xeon L5420  @
> 2.50GHz - 1 twistd process per core.
>
>  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND
>
> 24448 nobody     20   0  991m 607m 2452 R   99  4.3  24764:37 twistd
>
> 28553 nobody     20   0  909m 453m 2412 R   95  3.2   1346:51 twistd
>
> 24640 nobody     20   0 1092m 676m 2452 R   93  4.8  32750:14 twistd
>
> 29900 nobody     20   0  802m 362m 2412 R   93  2.6   1180:53 twistd
>
> 24279 nobody     20   0  761m 277m 2424 R   42  2.0  13891:58 twistd
>
> 32422 nobody     20   0 1381m 962m 2372 R   10  6.9  13241:54 twistd
>
> 24210 nobody     20   0  599m 236m 2396 S    4  1.7   9063:29 twistd
>
> 29862 nobody     20   0  323m  14m 2384 S    2  0.1  71:53.50 twistd

What was your application doing at the time?  Was it idle, heavily
loaded, somewhere in the middle?  What is the QoS for each client
connecting to your service?  Are requests being handled in a timely
fashion?  Do the users of your service perceive a performance
problem or do you just not like seeing big numbers in the %CPU
column?  Are performance problems really in Twisted, or are they
because of suboptimal decisions in application logic/factoring?

Posting a list like that and suggesting that something is wrong (or
right, even) with Twisted isn't really productive: there's nowhere
obvious to go from here to make it better.

My first glance at those numbers made me think Twisted is awesome
because it lets you write an application that can actually make full
use of the CPU power you have, but I'm guessing that's not what
you're getting at. :)

Thanks,
J.



More information about the Twisted-Python mailing list