[Flent-users] Saturating test with configurable packet-size/MSS?

[Flent-users] Saturating test with configurable packet-size/MSS?

[Sebastian Moeller]

Dear all,

Loganaden remined me of a pet project of mine, deducing the per-packet-overhead from non ATM/AAL5 carriers. Now, I believe I have an approach that might be worth exploring*, but that requires me to saturate my link with packets of different packet sizes. so I wonder is there an easy way inside flent to run a fully saturating TCP or UDP test (multiple flows required to saturate the link are fine) and have control over packetsize from within flent/the specific flent test?

Best Regards
	Sebastian

*) In theory it works but my current approach absolutely requires me to measure the maximum goodput to >= 99.8% correct, which is another challenge in itself ;) The catch is that on a given link both gross-rate and per-packet-overhead are unkown and goodput can only be estimated making the whole endeavor slightly tricky...
_______________________________________________
Flent-users mailing list
Flent-users@flent.org
http://flent.org/mailman/listinfo/flent-users_flent.org