HP3000-L Archives

February 1995, 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:
Eric Schubert <[log in to unmask]>
Reply To:
Eric Schubert <[log in to unmask]>
Date:
Thu, 16 Feb 1995 15:25:34 -0500
Content-Type:
text/plain
Parts/Attachments:
text/plain (41 lines)
HP3000-L:
 
 Anyone have a benchmark comparing NS/VT performance to DTC performance?
 
 It is always stated in general terms that NS/VT costs more CPU cycles, etc.
per session than DTC connection - I need to know how much difference so we
can recommend either a network solution or a DTC solution for session
connectivity of a new building.
 
 Our 992 currently averages 250 sessions and 75% CPU utilization and we are
planning 30 additional sessions.  We run on average about 30-40 NS sessions
already.
 
First choice - a factor number.
------------------------------
 
For example,
  20 VT sessions consume the same resources as 30 DTC connections (not a
real number here, just an example of what I want).
 
 
Second choice, pieces of info on:
---------------------------------
(1) What is the difference in memory per session?
 
(2) What is the difference in CPU per session?
 
(3) At what point will my LANIC saturate?
 
(4) How does socket configuration equate?
 
(5) Other considerations?
---
OR is there a place in HP documentation that I can simply read to answer
such questions?
 
I'm hoping someone has performed a benchmark already.
--------------------------------------------------------------------
Eric J. Schubert                 Administrative Information Services
Senior Data Base Analyst         University of Notre Dame, IN USA

ATOM RSS1 RSS2