On Tue, Mar 02, 2004 at 03:00:15PM +0100, Andre Oppermann wrote: > Brooks Davis wrote: > > > > On Tue, Mar 02, 2004 at 10:37:41AM +0900, Lars Eggert wrote: > > > Hi, > > > > > > Wes Peters wrote: > > > >On Monday 01 March 2004 14:18, Andre Oppermann wrote: > > > > > > > >>[] establish a testbed for testing and qualification of TCP performance > > > >> and optimizations over a wide range of network conditions (types, > > > >> speeds, packet loss ratios, out of order, etc). (started) > > > > > > > >Be sure to coordinate with the donations officer for help in getting > > > >equipment you may need. > > > > > > this sounds like something you could do with planetlab > > > (http://planet-lab.org/). Do you have access? (Or maybe I misunderstood > > > what you meant by "testbed".) > > > > From the list of metrics, Emulab (http://www.emulab.net/) is probably > > more what he's thinking, but we probably ought to let Andre speak for > > him self. :-) > > No, I want to have something that emulates real-world line conditions. > For example ADSL connections and so on. Or links Europe-USA etc. This > is not about performance of server applications like apache benchmarking. This is definatly something you could do with Emulab (that's why we have one), but if you just need to simulate agrigate link characteristics, Emulab would be massive overkill. -- Brooks -- Any statement of the form "X is the one, true Y" is FALSE. PGP fingerprint 655D 519C 26A7 82E7 2529 9BF0 5D8E 8BE9 F238 1AD4
This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:37:45 UTC