HP3000-L Archives

February 2005, 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:
Denys Beauchemin <[log in to unmask]>
Reply To:
[log in to unmask][log in to unmask], 25 Feb 2005 17:56:07 -0000400_us-ascii Good idea. I'll experiment with one of the files to see what
compression I get. (I have a 7 day cycle of logfiles based on HPDAY no
so I could each day just compress the previous day's logfile .

-----Original Message-----
From: Brian Donaldson [mailto:[log in to unmask]]
Sent: 25 February 2005 17:52
To: HP3000 List; Tony Summers
Subject: Re: Compressing data [...]57_25Feb200517:56:[log in to unmask]
Date:
Wed, 23 Feb 2005 18:04:14 -0600
Content-Type:
text/plain
Parts/Attachments:
text/plain (33 lines)
I think I'm going to disagree with you, even though I fell badly about doing
that.

If you look in HP document A6183-96005, on page 17, you will find some
performance numbers listed there.  They are much higher than 8MB/second,
even for the write.

Also, on my ProLiant, I have a Compaq Smartarray with two partitions; one of
them has 15k drives, the other has 10k drive.  Back a few years when I was
doing backup performance studies, I was approaching speeds of 55 MB/second
on reads to an LTO drive from the 15k partition and around 45MB/second on
the 10K partition.  Of course, it's just a little twin-CPU ML370 with LVD
drives and array, no fiber here.



Denys

-----Original Message-----
From: HP-3000 Systems Discussion [mailto:[log in to unmask]] On Behalf
Of steve macsisak
Sent: Tuesday, February 22, 2005 3:17 PM
To: [log in to unmask]
Subject: Re: [HP3000-L] Moving from XP512 to VA71xx

 More useless numbers. It looks like the 10k drives in the VA7100 can do
about 8mb per second per drive using 64kb write size.  The VA71xx
probably adds some latency of its own independent of the disk.
Who knows what the effective  I/O rate of the device is???

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

ATOM RSS1 RSS2