[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

20030624: 20030623: HDS feed to/from seistan (cont.)

This archive contains answers to questions sent to Unidata support through mid-2025. Note that the archive is no longer being updated. We provide the archive for reference; many of the answers presented here remain technically correct, even if somewhat outdated. For the most up-to-date information on the use of NSF Unidata software and data services, please consult the Software Documentation first.

  • Subject: 20030624: 20030623: HDS feed to/from seistan (cont.)
  • Date: Tue, 24 Jun 2003 10:53:49 -0600
>From: Robert Leche <address@hidden>
>Organization: LSU
>Keywords: 200306161954.h5GJs2Ld016710 LDM-6 IDD

Hi Bob,

>I am in the process of arranging a meeting with the telecommunications
>group on campus.

This is music to my ears! :-)

>The first issue is that needs to be made is who 'owns' these routers:
>
>  lsubr1-118-6509-dsw-1.g2.lsu.edu    
>  laNoc-lsubr.LEARN.la.net   
>
>My guess is LSU. That being the case, issue two is, why are these
>routers causing delays in transfering large packets.

As kind of a last check we are planning on doing scp transfer tests
using the 132 MB image file I mentioned last night, but this time
using port 388.  This should tell us if there is any limiting being
done on this specific port.  That is the most likely scenario _if_
some sort of a packet shaper is being used.

>My best guess is
>it has something to do with fragmentation of the packets traversing the
>routers.  Any other thoughts at this point would be conjecture.

I have to admit that several of us have been sitting here scratching
our heads about this strange problem.  It is understandable that I
might not be able to come up with a scenario that would cause the
large latencies, but for our system administrator to also be stumped
attests to the strange nature of the problem (he is one of the best).

>I'll let you know how 'things' go.

Thanks!

>By the way.........
>
>I want to thank you and  the others who have worked to resolve the
>problems that have  spanned two universities. I realize much effort has
>gone into understanding the  problems.

I appreciate the comment.  It is our desire to see the problem get resolved
so that LSU/SRCC can act as an effective top level node in the IDD.

Cheers,

Tom