Ah ha! Things are not as bad as they seem.
If I do cat /dev/zero | nc -u -p 1666 doris.namkas 1666 and set up doris.namkas to receive correctly then knetload reports around 98000KBit/s which doesn't seem too bad. Doing it the other way round reports the same (ish, though in this case, the sending machine - doris - is only a PII and is also compiling gcc at the same time!). Doing both at the same time (different ports) gives the first host (a PIII) to send at about 100,000KBit/s and doris to send at about 25KBit/s - it doesn't matter who starts - doris always sends slower it seems. This is the first time that I've done testing like this - does anyone have any comments to make about what this shows or doesn't? Thanks for your time, Matthew On Mon, Sep 24, 2001 at 06:27:06AM +0200, Robert Waldner wrote: > > Could you test raw performance? > > Something like running `nc -l -u -p 1666 >/dev/null` on one machine and > `dd if=/dev/zero bs=64k | nc -u -p 1666` on the other, then looking with > `iptraf` how much traffic you?re getting across. > > cheers, > &rw -- Matthew Sackman Nottingham, ENGLAND --------------------------------------------------------------------- The contents of this email are intended for the indicated recipient(s) only. This may or may not be indicated in the above email as it is enormously easy to fake email addresses (see the relevant RFCs). For security reasons this email is likely to be gnupg signed. On the other hand it may not be if I forgot to do so. In any case, if you are reading this on a Windows based computer then there was no point in me doing so (provided that I remembered) as your computer is most likely being used by yourself and 2.8 other people at the same time (normally without your consent). No responsibility will be accepted by anyone for any of the contents of this email. So tough. If in doubt, go compile Mozilla. --------------------------------------------------------------------
pgp56PQuD1MWL.pgp
Description: PGP signature
