> Date: Sun, 02 Dec 2012 22:16:52 +0100 > From: Magnus Danielson <mag...@rubidium.dyndns.org> > > On 12/02/2012 08:54 PM, Erich Heine wrote: >> Examining the time "in switch" for various packets at the microsecond level >> was needed to understand various delay curves for different network loads, >> with an ultimate goal of proper statistical modeling reflecting reality as >> close as possible. > > This is a bold challenge, it's a difficult task (clear speak: there is a > reason for this to be a research field, industry never *really* got it > under control).
I agree with Magus, but measuring in-host (or in-switch) timing is still possible. The research team I am with presented a paper at ISPCS this year on the measuring of in-host latencies and looking at where packet timestamps take place, such as SO_TIMESTAMP as Magnus mentions below. I will point you to a link to our docs, email me off the list if you do not have access to the IEEE online journals. The paper is mainly focused on BSD systems; however, BSD is not unheard of in the switch world so maybe it can give you a few tricks for what you want to accomplish regarding your in-switch timing. Paper: "Probing the Latencies of Software Timestamping" http://www.synclab.org/docs/ >> I personally have also used endace products to measure packet timings for >> research, but I didn't need so much precision for that work - however I can >> say they have a good API and decent tech support for interacting with their >> cards and products. > > Is there native support with Linux kernels? > It would be very nice to have the support using SO_TIMESTAMP and friends. Our team also uses Endace. But we only host the Endcace DAG cards on our BSD boxes. -Matt _______________________________________________ time-nuts mailing list -- time-nuts@febo.com To unsubscribe, go to https://www.febo.com/cgi-bin/mailman/listinfo/time-nuts and follow the instructions there.