HP3000-L Archives

September 1998, Week 2

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:
Gavin Scott <[log in to unmask]>
Reply To:
Gavin Scott <[log in to unmask]>
Date:
Fri, 11 Sep 1998 10:42:16 -0700
Content-Type:
text/plain
Parts/Attachments:
text/plain (34 lines)
Bob writes:
> I've done quite a bit of TCP related work on the 3000 if you can send me a
> spec. of the 'Standard' TCP Benchmark I'll try to knock out the necessary
> code.

If anyone's seriously interested in doing TPC benchmarks, I recommend the
book "The Benchmark Handbook" Edited by Jim Grey, published by Morgan
Kaufmann, ISBN 1-55860-292-5.  It contains information on the TPC A, B,
and C benchmarks (among others) and includes the official TPC specifications
for these benchmarks.

The benchmark which would probably make sense for the 3000 at this point
would be TPC-C, which is an online transaction processing benchmark.

I took a look through the spec, and while it appears to me that it would
only be a medium amount of work to design and implement a good version of
TPC-C, it would be a large effort to meet all of the reporting and auditing
requirements.  One possibility would be for one person or a consortium of
users to write the benchmark and show that it has the potential to produce
good numbers, then HP could take over the actual running of the benchmark
along with all of the paperwork and whatnot required to get the benchmark
certified by the TPC.

A common excuse for not doing TPC-C that I've heard is that the benchmark
requires an SQL database.  This is clearly not the case reading the specs,
and as far as I can tell Image has all of the database functionality
required to implement TPC-C.  There are also plenty of opportunities for
clever coding.

Keep in mind though that the other operating systems and DBMS vendors
have been tuning against this benchmark for years.

G.

ATOM RSS1 RSS2