HP3000-L Archives

August 1997, Week 4

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:
Neil Harvey <[log in to unmask]>
Reply To:
Neil Harvey <[log in to unmask]>
Date:
Fri, 22 Aug 1997 16:28:57 +0200
Content-Type:
text/plain
Parts/Attachments:
text/plain (37 lines)
Well, my testing is done. I reported that hardware compression was
better, but in fact Stan pointed out that I had misread my own
benchmarks.

I must conclude that on a 969/200, it is better to use turbostore's
software compression over the drives hardware compression to save time.

The software compression on turbostore reports compression as follows:-

             FILE DATA    COMPRESSED   RATIO     PERCENTAGE
MEDIA  1     9913835530   2935662168   3.4:1     70%


Not bad. The largest files (60% of data) are TurboImage datasets (fairly
full).

So I guess that with 12GB before compression at 3.4:1, I could look
forward to getting about 4 times as much data on the DAT i.e. 12GB of
pre compressed data, or almost 40GB of uncompressed Data.

This is impressive stuff.

I tried to get the results of the hardware compression using SCSIDDS
utilities, but apparently, I'm not capable of deciding for myself
whether to run these diagnostics, and I must apply for a suplicen
password, so that'll have to wait.

I hope that early next year, I'll be able to report on four DDS3 drives
in parallel on a 959/400 :)

Now, if only the DDS3 drives turn out to be more reliable than the DDS2
drives...........................

Regards

Neil (see you in Chicago) Harvey

ATOM RSS1 RSS2