[erlang-questions] Heavy duty UDP server performance

Ameretat Reith ameretat.reith@REDACTED
Thu Feb 11 20:36:55 CET 2016


On Thu, 11 Feb 2016 15:33:07 +0100
Jesper Louis Andersen <jesper.louis.andersen@REDACTED> wrote:

> 
> This was exactly the same idea I had when I read that. Apart from what
> Lukas is mentioning, you may be able to avoid some TLB shootdowns by
> locking CPU cores to schedulers via +sbt db. For these kinds of
> situations, this can improve the CPU % usage as well since one core
> waiting for the L1,L2,L3 cache to populate counts as active CPU time.
> And if other cores are able to kill the TLB, you will have lots of
> traps to the OS and lots of higher CPU times.

Good idea, Thanks.  I'll test on real application.


> If all the messages you receive have the same rough structure,
> you can win a lot by making it easier for the system to grab memory
> of that size.

I'm not aware of any option to hint VM to grab memory of some size, VM
memory options I found, are mostly about carrier size and the way some
carrier and location being chosen.



More information about the erlang-questions mailing list