Thank you Ian. If any one has report of such experiments, I don't need to do the same work. gavin On Jan 17, 2008 2:24 PM, Ian McDonald <ian.mcdonald@xxxxxxxxxxx> wrote: > > On Jan 17, 2008 5:17 PM, maillist ifiaas <maillist.ifiaas@xxxxxxxxx> wrote: > > Hi friends,, > > > > Where can we find CCID2 (latest Linux release) test against TCP ? > > There seems no measurement study to validate the TCP friendliness on > > any existing implementation yet, including BSD. > > > > Emmanuel Lochin has did some test before, showing the BSD > > implementation was not very well: > > http://manu.lochin.org/dccp/tests/dccp_eval.html > > > > Any similar test for Linux CCID2 out there? > > > > Thank you very much! > > > > gavin > > Easy enough to do a test with modified iperf. Gerrit and I both have > patches for iperf to run it continuously, use dccp and select the TCP > congestion mechanism - use Reno in particular. > > I used to do this with simultaneous CCID3 and TCP to see that they > matched the rate, you could do the same for CCID2. You can use netem > also to constrain link or introduce loss also. > > Regards > > Ian > -- > Web: http://wand.net.nz/~iam4/ > Blog: http://iansblog.jandi.co.nz > - To unsubscribe from this list: send the line "unsubscribe dccp" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
