HP3000-L Archives

December 1998, 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:
Overman_James <[log in to unmask]>
Reply To:
Overman_James <[log in to unmask]>
Date:
Fri, 18 Dec 1998 23:35:18 GMT
Content-Type:
text/plain
Parts/Attachments:
text/plain (23 lines)
Bruce Toback ([log in to unmask]) wrote:
: James Overman writes:
: >Maybe I'll get to play with DLT's someday.  But right now, dual DDS-3's do
: >the job on our biggest system of 36.7G with 60% compression in 4 hours 24
: >minutes with an average transfer rate of 431 to 483 K/S.

: This transfer rate seems *really* low for DDS-3. Are you using DDS-3
: tapes? On our Macintosh network, I see >1.5MB/S transfer rate to DDS-3,
: and that's using the SCSI-1 port on the Mac, not its SCSI-2 port. In
: fact, checking your math (36.7GB / 264*60 seconds), it looks like you're
: getting 2.3MB/S.

You're right.  I just copied the thruput rate from the STATISTICS report
from TurboStore.  I think the thruput value is for the actual bytes written
to the tape after compression.  Thus 2.3MB/S times .40 (after compression)
gives .926 MB/S which is roughly the sum of 431 and 483 KB/S reported for the
two drives.  Comparing rates of data written before compression will vary
depending upon the degree of compression.  Actual rates written to tape
should be relatively equal for all DDS drives of the same basic flavor barring
significant tape movement speeds of various manufacuters drives.
--
 [log in to unmask] HP CSBU R&D  Roseville, CA

ATOM RSS1 RSS2