Hi Jan, thank you for your quick reply :) When you say that "There are a few benchmarks around on the web, many in German only :-/", do you mean that (1) there are systems running RTnet which have been benchmarked (in which case a link or two would be fantastic) or (2) there are benchmarks for which to measure RTnet against?
And thanks for clearing up the Twente issue. It's an especially bad case of name collision since the two are so similar in the high-level approach. Thanks! Lei On 3/26/07, Jan Kiszka <[EMAIL PROTECTED]> wrote: > Lei Zhao wrote: > > Hi, I've been looking into a variety of Real-Time Ethernet protocols > > and was delighted to find an open source project on Sourceforge. I > > have two questions in mind: > > > > > > (1) I have not seen any performance results for RTnet, is there any > > available or under way? Or would I have to do that myself? > > As RTnet is a software solution, performance (whatever one means with it > precisely) heavily depends on the execution platform AND the system > setup (real-time task schedule, IRQ schedule). Yes, if you plan to use > RTnet for some concrete scenario, it is mandatory to do your own > benchmarks on YOUR platform. > > There are a few benchmarks around on the web, many in German only :-/. > But I heard rumours there are more on the way, also in English. I can > only motivate anyone having written a paper, a thesis, or whatever > publicly accessible document about RTnet evaluations to drop a note and > attach a link etc. so that we can collect those references (e.g. in the > wiki). > > > > > (2) In conducting a literature search, I found a paper published by > > Fred Hanssen and others at the University of Twente, entitled "RTnet: > > a distributed real-time protocol for broadcast-capable networks." In > > it, they describe a protocol which is software-only on top of standard > > COTS Ethernet, but uses a token passing method. From what I've read on > > the website and Kiszka's paper in 2005, it seems that Sourceforge's > > RTnet employs a master-slave TDMA method. Am I missing something here? > > Hanssen's paper is here: > > > > http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1559870 > > > > Yes, we are very aware of this unfortunate name collision. The open > source project RTnet dates back to 2000, but in 2003 the Twente group > decided to rename their multimedia soft-realtime protocol to "RTnet" as > well. I informed them about the clash and the history of this name, but > I never received any reply nor did they changed their naming. > > Jan > > > ------------------------------------------------------------------------- Take Surveys. Earn Cash. Influence the Future of IT Join SourceForge.net's Techsay panel and you'll get the chance to share your opinions on IT & business topics through brief surveys-and earn cash http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV _______________________________________________ RTnet-users mailing list RTnet-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/rtnet-users
