Setting RTT for networked experiement - TCP-IP

This is a discussion on Setting RTT for networked experiement - TCP-IP ; While going through papers detailing experiments on network traffic, I have come across experiments set up as "We vary the RTT from 16ms to 324ms. The buffer size of the bottleneck router is fixed to 2Mbytes". [from paper: http://www.csc.ncsu.edu/faculty/rhee...steppaper.htm] I ...

+ Reply to Thread
Results 1 to 3 of 3

Thread: Setting RTT for networked experiement

  1. Setting RTT for networked experiement

    While going through papers detailing experiments on network traffic, I
    have come across experiments set up as "We vary the RTT from 16ms to
    324ms. The buffer size of the bottleneck router is fixed to 2Mbytes".
    [from paper:
    http://www.csc.ncsu.edu/faculty/rhee...steppaper.htm]

    I could not understand, how we can vary RTT.

    RTT, round trip time, is usually defined as the time since transmission
    of the packet till the reception of its acknowledgement.

    Thus, RTT should be function of the media which carries the data plus
    the background traffic at that instant.

    That makes me wonder how can we vary RTT for experimental purpose? How
    do we have control over that?

    Thanks a lot in advance,
    Shri


  2. Re: Setting RTT for networked experiement

    In article <1155079378.344518.307020@b28g2000cwb.googlegroups. com>,
    "Shrikrishna Khare" wrote:

    > While going through papers detailing experiments on network traffic, I
    > have come across experiments set up as "We vary the RTT from 16ms to
    > 324ms. The buffer size of the bottleneck router is fixed to 2Mbytes".
    > [from paper:
    > http://www.csc.ncsu.edu/faculty/rhee...steppaper.htm]
    >
    > I could not understand, how we can vary RTT.
    >
    > RTT, round trip time, is usually defined as the time since transmission
    > of the packet till the reception of its acknowledgement.
    >
    > Thus, RTT should be function of the media which carries the data plus
    > the background traffic at that instant.
    >
    > That makes me wonder how can we vary RTT for experimental purpose? How
    > do we have control over that?


    You modify the stack sending the acknowledgements so that it delays
    sending them. Or you modify a router in between so that it holds onto
    packets rather than forwarding them immediately.

    --
    Barry Margolin, barmar@alum.mit.edu
    Arlington, MA
    *** PLEASE post questions in newsgroups, not directly to me ***
    *** PLEASE don't copy me on replies, I'll read them in the group ***

  3. Re: Setting RTT for networked experiement

    Shrikrishna Khare wrote:

    > While going through papers detailing experiments on network traffic, I
    > have come across experiments set up as "We vary the RTT from 16ms to
    > 324ms. The buffer size of the bottleneck router is fixed to 2Mbytes".
    >
    > I could not understand, how we can vary RTT.
    >
    > RTT, round trip time, is usually defined as the time since transmission
    > of the packet till the reception of its acknowledgement.
    >
    > Thus, RTT should be function of the media which carries the data plus
    > the background traffic at that instant.
    >
    > That makes me wonder how can we vary RTT for experimental purpose? How
    > do we have control over that?


    You can use a network emulator.

    e.g. the netem component in Linux 2.6

    http://linux-net.osdl.org/index.php/Netem

    Regards.

+ Reply to Thread