HP3000-L Archives

July 2001, Week 3

HP3000-L@RAVEN.UTC.EDU

Options: Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
"HOFMEISTER,JAMES (HP-USA,ex1)" <[log in to unmask]>
Reply To:
HOFMEISTER,JAMES (HP-USA,ex1)
Date:
Wed, 18 Jul 2001 13:49:02 -0400
Content-Type:
text/plain
Parts/Attachments:
text/plain (59 lines)
Hello Andrew, @

Re: Telnet performance

------------------------------------------------------------------------
Further to the details regarding poor performance of Telnet. We are
looking at converting out current DTC users (possibly upto 800 users) to
Telnet.  Could anyone confirm if there are any performance problems with
Telnet, or if Telnet is not a problem. We are running on 2 different
hardware platforms, all running the same software level.

2 x HP979/400, 1 X HP989/650.

The 800 users will be split across the systems, with the majority on the
HP989/650, and one of the HP979/400's. Both have sufficient memory and
disc space.  I would be grateful of any responses.
------------------------------------------------------------------------

I would not characterize Telnet as having "performance problems", but I
would suggest that by "the standards, design and architecture" that
Telnet is significantly slower than the DTC connections.

HP has not done performance bench marks with Telnet v.s. DTC connections
so I really can not give you hard numbers on the performance difference
but if I was a marketing guy I would sell Telnet as being 1/2 as fast
(or twice as slow) as a DTC connection and with that expectation set I
think you would find for the most part that number would be conservative.

Note: The feed back I have heard from the folks out here on the 3000-l
news group is that Telnet performance is great.

The performance for the Telnet on the HPe3k from a design stand point
was evaluated and measured against the performance of NS-VT VTSERVER as
a goal and my understanding is that with the exception of specific
corner cases that goal was met.

One possible test/bench mark would be to build a monster WRQ recording
of a repeatable keystroke sequence and then to play that recording with
connections to DTC's, Telnet and NS-VT and use that data as your
performance benchmark.  Note: It is important to first run this test on
an idle system to capture a measurement and then later to run this same
test in a production load environment.

I hope this helps.

P.S. As other of the 3000-l folks out here will attest to, it is very
important to install the latest General Release NST, PTD and INT
patches to be successful in using Telnet.

Regards,

James Hofmeister
Hewlett Packard
Worldwide Technology Network Expert Center
P.S. My Ideals are my own, not necessarily my employers.

* To join/leave the list, search archives, change list settings, *
* etc., please visit http://raven.utc.edu/archives/hp3000-l.html *

ATOM RSS1 RSS2