Changes between Version 3 and Version 4 of GeniTmix

10/12/12 13:49:39 (7 years ago)
Ben Newton



  • GeniTmix

    v3 v4  
    1 = Tmix on Geni =
    2 Placeholder for Tmix on Geni page
     1= Tmix on ProtoGeni =
     2Information about Running experiments using the Tmix traffic generation system on ProtoGENI nodes.
     3== What is Tmix? ==
     4In order to perform realistic network simulations, one needs a traffic generator that is capable of generating realistic synthetic traffic in a closed-loop fashion that "looks like" traffic found on an actual network.
     6The Tmix system takes as input a packet header trace file captured from a network link of interest (such as the link between the UNC campus and the rest of the internet). This trace is reverse-compiled into a connection vector (or cvec) file, which is a source-level characterization of each TCP connection present in the trace. Tmix then uses this information to emulate the socket-level behavior of the source application that created the corresponding connection in the trace. The resulting traffic generation is statistically representative of the traffic measured on the real link.
     8== Traffic Generation ==
     9One of the most complex components of empirical evaluations is modeling and generating
     10realistic Internet traffic. The mix of the ever changing and varied applications that constitute the
     11actual Internet traffic makes this a daunting task. Moreover, Internet traffic is different when
     12sampled at different times and in different parts of the globe. Networking researchers have
     13grappled with this problem by taking snapshots of Internet traffic at different times and at various
     14points in the network, and modeling the same for generating traffic in the lab. The generally held 3
     15belief is that the more realistic the traffic used, the more reliable are the results of the empirical
     16evaluations using that traffic. Practice, however, does not adhere to this principle. So, although
     17laboratory testbeds and methods for simulations have evolved over the years, the question about
     18what constitutes essential components for modeling realistic traffic remains open for debate. For
     19example, networking researchers agree that realistic traffic generation for empirical research is
     20best accomplished by capturing traffic on a production link and then using source-level models to
     21generate this traffic in the laboratory or simulator. Source-level models capture the application
     22exchanges and application behavior on the ends (sources) of the TCP connections. But how do
     23you go from the original captured traffic to an acceptable source-level model? Which of the
     24several measures derived from the traffic sources should you model in your workload for your
     25experiments? Would your modeling choices for traffic generation impact the outcome of your
     26experiments? If yes, how significant would the impact be? These remain open questions. 
     28== Tmix Experiments on ProtoGeni ==
     291. Experiment 1
     302. Experiment 2
     313. Experiment 3