> So I am wondering if this is an anomaly of both the way latency-test and > emc > / realtime start up, or if the results are really that bad. The max > interval > values are consistently better, plus watching last interval generally > gives > values approximately averaging 991000 and 24750 respectively which are > better than when run on the non-smp kernel.
The max interval values are usually less relevant. You should only care about max jitter. Try to really abuse your system when doing a latency test. And I would run the RTAI latency test aswell (the one in /usr/realtime*/testsuite/latency/kern/), check the wiki there's an instruction how to do that. Regards, Alex ------------------------------------------------------------------------------ Create and Deploy Rich Internet Apps outside the browser with Adobe(R)AIR(TM) software. With Adobe AIR, Ajax developers can use existing skills and code to build responsive, highly engaging applications that combine the power of local resources and data with the reach of the web. Download the Adobe AIR SDK and Ajax docs to start building applications today-http://p.sf.net/sfu/adobe-com _______________________________________________ Emc-developers mailing list Emc-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-developers
