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

Re: cessna (fwd)


===============================================================================
Robb Kambic                                Unidata Program Center
Software Engineer III                      Univ. Corp for Atmospheric Research
address@hidden             WWW: http://www.unidata.ucar.edu/
===============================================================================

---------- Forwarded message ----------
Date: Wed, 24 Feb 1999 17:20:58 -0700
From: Tres Hofmeister <address@hidden>
To: Peter Neilley <address@hidden>
    Frank Hage <address@hidden>
Subject: Re: cessna

On 1999.02.24, Peter Neilley wrote:
: 
: I believe cessena is pulling in the NIDS data, which by volume
: represents about 80% of the data fed through the iita machine.
: What's the cost of that workstation?   Is it Pentium Xeon processors?
: We have iita connected to the FIDI ring to (supposively) make the
: redistribution of the data from iita to the rest of UCAR sites
: more efficient.  Do you have any comments on that vs. the 100 Mbps
: switch connected to cessna?

Peter,

        cessna was about $5000.  The processors are generic Pentium
II's.  The Xeon isn't worth the money; it's only about 10% faster at
the same clock rates.  While we're on the topic, the new Pentium III
isn't much better for general purpose computing.  It may be available
at higher clock rates (and higher cost), though.

        As for the FDDI issue, I'd be very curious to see how cessna
does given its 10Mbps switched (dedicated) connection.  FDDI is a bus
topology, so the 100Mbps bandwidth is shared, in this case with everyone
else on the FDDI ring at FL.  If 10Mbps switched isn't adequate, we
could probably arrange for a dedicated 100Mbps switched Ethernet link
to the big FL router upstairs.

-- 
Tres Hofmeister <address@hidden>  http://www.rap.ucar.edu/staff/tres/
Research Applications Program   National Center for Atmospheric Research