yup, you're right. I saw the two settings in sipp.hpp
(MAX_RECV_LOOPS_PER_CYCLE and MAX_SCHED_LOOPS_PER_CYCLE). Upping these let
me run, although the max cps turned out to be around 1187. That's enough to
get me by for the load testing I'm doing, and will run 2 or more instances
if I need it.
thanks,
Ean
On Fri, Feb 4, 2011 at 7:35 PM, Greg Henderson <gnhenderso...@gmail.com>wrote:
> I have seen the same thing. I think it has to due to how it's compile. 1K
> per instance is not that few.
>
> You could always start another instance of sipp.
>
> On Feb 4, 2011, at 7: 54, Ean Houts wrote:
>
> I'm unable to create more than 1000 calls per second (no media). I've
> attempted on several linux boxes (Fedora, 32 bit, FC10-13) with several
> versions of SIPP. Is this a known limitation? I can't find anything in the
> documentation/performance pages I've seen.
>
> thanks,
> Ean
> ------------------------------------------------------------------------------
> The modern datacenter depends on network connectivity to access resources
> and provide services. The best practices for maximizing a physical server's
> connectivity to a physical network are well understood - see how these
> rules translate into the virtual world?
>
> http://p.sf.net/sfu/oracle-sfdevnlfb_______________________________________________
> Sipp-users mailing list
> Sipp-users@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/sipp-users
>
>
>
------------------------------------------------------------------------------
The modern datacenter depends on network connectivity to access resources
and provide services. The best practices for maximizing a physical server's
connectivity to a physical network are well understood - see how these
rules translate into the virtual world?
http://p.sf.net/sfu/oracle-sfdevnlfb
_______________________________________________
Sipp-users mailing list
Sipp-users@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/sipp-users
