Oh yes, sorry for misunderstanding. We actually had issues with KernelTun. We ended up adding a BURST parameter to it. There are weird interactions between selected() and tasks where selected() does not get called as often as one might hope. You could also try changing the _tasks_per_iter to be much much lower (like 2) and see if it helps...
I can look into giving you an updated KernelTun with a BURST param if you are interested, but it might take me a few days to get to it. Cliff On Wed, Apr 20, 2011 at 9:50 AM, Roberto Riggio < [email protected]> wrote: > Packets are not coming from a fromdevice element, but rather are injected > from a > kerneltun element. Traffic is generated in user space by iperf. > > The generation rate is 10 mbps so it cannot be transmitted over the > wireless > link that is running at the static rate of 6 mbps. However, the packets are > not > lost on the link, but somewhere between kerneltun and iperf. > > R. > > Il 20/04/2011 18:17, Cliff Frey ha scritto: > > I would expect that you are _not_ CPU limited. This is what I would expect > to see if FromDevice is just only rarely scheduled. > > If you are still worried about fairness, you can set the BURST parameter > on FromDevice to be higher, but I really think that the issue is that > FromDevice's task is not active, because the device has not received any > more packets. > > You can also check FromDevice's "drops" handler to make sure that > FromDevice is not being starved. > > Cliff > > On Wed, Apr 20, 2011 at 1:55 AM, Roberto Riggio < > [email protected]> wrote: > >> Hi, >> >> I have some doubts about how push and pull are scheduled. >> >> I'm running click on two wireless routers and I'm generating some >> traffic between them using iPerf. Wireless interfaces are operating in >> monitor mode and click is running in userspace. >> >> The configuration essentially consist of: >> >> KernelTun >> -> CheckIPHeader >> -> ... other push elements that set route etc. ... >> -> FullNoteQueue >> -> WifiEncap, SetTXRate, Radiotapencap >> -> ToDevice >> >> The tx rate is statically set to 6 mbps. The strange this is that if >> I generate traffic with Iperf at a very high rate (e.g. 10Mbps) I >> do get an high packet loss as expected, but there is only one packet >> in the queue. >> >> I've added some debug message to the Queue' push and pull method >> and this is what I get: >> >> push >> pull >> pull >> pull >> pull >> pull >> pull >> pull >> pull >> pull >> pull >> pull >> push >> pull >> pull >> pull >> pull >> pull >> pull >> pull >> pull >> pull >> pull >> pull >> push >> >> basically it seems that the driver is alway trying to pull from the >> queue, until the >> _empty_note is put to sleep and only then a packet is pushed into the >> queue. >> >> What I would expect is that incoming packet should be pushed in to the >> queue >> and then eventually dropped if todevice cannot pull them all. Am I >> missing somthing? >> >> R. >> >> -- >> -------------------------------------------------------- >> Roberto Riggio, Ph.D. >> CREATE-NET >> Network& Security Solutions for Pervasive Computing Systems (iNSPIRE) >> Senior Researcher >> Via alla Cascata 56/D - 38123 Povo Trento (Italy) >> e-mail: [email protected] >> Tel: (+39) 0461 408400 - interno/extension 708 >> Fax: (+39) 0461 421157 >> www.create-net.org/~rriggio <http://www.create-net.org/%7Erriggio> >> -------------------------------------------------------- >> >> The information transmitted is intended only for the person or entity to >> which it is addressed and may contain confidential and/or privileged >> material. Any review, retransmission, dissemination or other use of, or >> taking of any action in reliance upon, this information by persons or >> entities other than the intended recipient is prohibited according to >> the Italian Law 196/2003 of the Legislature. If you received this in >> error, please contact the sender and delete the material from any >> computer. >> >> Le informazioni contenute in questo messaggio di posta elettronica e nei >> file allegati sono da considerarsi strettamente riservate. Il loro >> utilizzo e' consentito esclusivamente al destinatario del messaggio, per >> le finalita' indicate nel messaggio stesso. Qualora riceveste questo >> messaggio senza esserne il destinatario, Vi preghiamo cortesemente di >> darcene notizia via e-mail e di procedere alla cancellazione del >> messaggio stesso dal Vostro sistema. Trattenere il messaggio stesso, >> divulgarlo anche in parte, distribuirlo ad altri soggetti, copiarlo, >> od utilizzarlo per finalita' diverse, costituisce comportamento >> contrario ai principi dettati dal D. Lgs. 196/2003. >> >> _______________________________________________ >> click mailing list >> [email protected] >> https://amsterdam.lcs.mit.edu/mailman/listinfo/click >> > > > > -- > -------------------------------------------------------- > Roberto Riggio, Ph.D. > CREATE-NET > Network & Security Solutions for Pervasive Computing Systems (iNSPIRE) > Senior Researcher > Via alla Cascata 56/D - 38123 Povo Trento (Italy) > e-mail: [email protected] > > Tel: (+39) 0461 408400 - interno/extension 708 > Fax: (+39) 0461 421157www.create-net.org/~rriggio > -------------------------------------------------------- > > The information transmitted is intended only for the person or entity to > which it is addressed and may contain confidential and/or privileged > material. Any review, retransmission, dissemination or other use of, or > taking of any action in reliance upon, this information by persons or > entities other than the intended recipient is prohibited according to > the Italian Law 196/2003 of the Legislature. If you received this in > error, please contact the sender and delete the material from any > computer. > > Le informazioni contenute in questo messaggio di posta elettronica e nei > file allegati sono da considerarsi strettamente riservate. Il loro > utilizzo e' consentito esclusivamente al destinatario del messaggio, per > le finalita' indicate nel messaggio stesso. Qualora riceveste questo > messaggio senza esserne il destinatario, Vi preghiamo cortesemente di > darcene notizia via e-mail e di procedere alla cancellazione del > messaggio stesso dal Vostro sistema. Trattenere il messaggio stesso, > divulgarlo anche in parte, distribuirlo ad altri soggetti, copiarlo, > od utilizzarlo per finalita' diverse, costituisce comportamento > contrario ai principi dettati dal D. Lgs. 196/2003. > > _______________________________________________ click mailing list [email protected] https://amsterdam.lcs.mit.edu/mailman/listinfo/click
