Re: [ns] werid delay between enqueue and dequeue

[Bo Wen <bowen@mail.wsu.edu>]

Thanks for your hints.  But I checked out the queue code, that it seems there is
no scheduled time related code.  You know, ns uses the relative time, so how
is this delay implemented?  Since I am simulating the circuit switching,which
assumes that there is no extra delay on the link except the link propagation
delay,
How can I remove this sort of queuing delay?

Thanks,
Bo Wen

Tarik Alj wrote:

> >Date: Thu, 6 Jul 2000 01:10:06 -0700 (PDT)
> >From: Bo  Wen <bowen@mail.wsu.edu>
> >X-Sender: bowen@cougar.it.wsu.edu
> >To: ns-users@isi.edu
> >Subject: [ns] werid delay between enqueue and dequeue
> >MIME-Version: 1.0
> >
> >Hi, can anyone help me figure out this problem?
> >
> >The following is "grepped" trace file for a particular packet.
> >Why is there a small delay between enqueue and dequeue
> >(0.012394-0.0115 = 0.000894)?  Where is it from?  From queue delay?
>
> well, yes. That's what happens when a packet gets enqueued while other packets
> are already in there...
>
> >
> >I used droptail queue, but traffic rate did not exceed the link
> >bandwidth.  however, when I test some small simulation scenario,
> >the enqueue and dequeue time are exactly same.  Why?
>
> There is a limit to the precision you can obtain, if your scenario was small no
> delay probably means negligible delay, that is the delay was to small to be
> recorded, given the precision.
>
> >
> >Thanks a lot.
> >
> >+ 0 0 3 cbr 500 ------- 2 0.3 6.0 0 2
> >- 0.001 0 3 cbr 500 ------- 2 0.3 6.0 0 2
> >r 0.0115 0 3 cbr 500 ------- 2 0.3 6.0 0 2
> >+ 0.0115 3 4 cbr 500 ------- 2 0.3 6.0 0 2
> >^^^^^^^^^
> >- 0.012394 3 4 cbr 500 ------- 2 0.3 6.0 0 2
> >^^^^^^^^^^
> >r 0.022894 3 4 cbr 500 ------- 2 0.3 6.0 0 2
> >+ 0.022894 4 6 cbr 500 ------- 2 0.3 6.0 0 2
> >- 0.023394 4 6 cbr 500 ------- 2 0.3 6.0 0 2
> >r 0.033894 4 6 cbr 500 ------- 2 0.3 6.0 0 2
>
> Tarik