I would never use T3 or T3+ for my Solaris 8 TSM servers. T3 is just not a
good performer. It's pretty decent for redundancy and availability and lots
of disk in a small foot print. I'm using D2 arrays on one of my TSM servers
and think the disk throughput is great. We use raw volumes and multiple
HBA's and don't have any issues with throughput or being I/O bound. U160
JBOD (like the D2) seems to be a good solution for TSM.

Eric Cowperthwaite
EDS

 -----Original Message-----
From:   Chetan H. Ravnikar [mailto:Chetan.Ravnikar AT SYNOPSYS DOT COM]
Sent:   Thursday, September 26, 2002 3:48 PM
To:     ADSM-L AT VM.MARIST DOT EDU
Subject:        Re: Disk volumes

On Thu, 26 Sep 2002, Johnn D. Tan wrote:
> Ours are SCSI-attached external subsystem (2104). Wow... from 1
> MB/min to 20 MB/sec! We are definitely going to investigate raw
> devices!

wait this did not just come from moving to raw volumes, there were more
issues. We had the Recover logs on the system disk, which got moved to
external SCSI D130s and the striping parameter was tunned to be optimal
on the T3+ storge. Again beleive it or not I am looking into JBOD (D2
arrays) for spools and getting better faster speeds than T3+

Cheers..


>
> johnn
>
> >can I just ask, are these drives external attached on a SCSI array types
> >or internal to the box, (I mean internal bays) depending on the server!?
> >
> >'cause I have similar situation, when we went into using T3 storage for
db
> >and spools. The inherent limitation to configure T3's as raw or JBOD
> >there was as significant slowness in performance. Yes at first we were
using
> >filesystems.  we saw 1meg a min :(
> >
> >After going to raw disks we saw 20 - 25 MB /sec writes. Which
> >is still way less than what a T3 is advertized to do though (80MB
> >sustained). Oh well may be T3 's were not a right storage for TSM is what
> >I have learnt. Offcourse with 256MB cache and write ahead enabled.
> >
> >I was told that the TSM server uses variable 4 to 64k and the T3 with 64K
> >fixed block size was also the cause for the  low performance ..
> >
> >-Chetan
> >
> >
> >
> >
> >
> >On Thu, 26 Sep 2002, Johnn D. Tan wrote:
> >
> >>  Date: Thu, 26 Sep 2002 12:42:45 -0400
> >>  From: Johnn D. Tan <jdtan AT med.cornell DOT edu>
> >>  Reply-To: "ADSM: Dist Stor Manager" <ADSM-L AT vm.marist DOT edu>
> >>  To: ADSM-L AT vm.marist DOT edu
> >>  Subject: Re: Disk volumes
> >>
> >>  I have 12 36-GB drives available for spool.
> >>
> >>  Based on recommendations made to this list earlier this year, I went
> >>  with 12 mirrored disk spools of 16 GB each (keep in mind disk
> >>  overhead).
> >>
> >>  As I understood it, the issue was you want many spools so that, as
> >>  Allen mentioned, you can have many threads for backups and even
> >>  migrations (assuming you have a good number of tape drives).
> >>
> >>  However, you don't want so many spools per disk, otherwise there is
> >>  contention for head movement on the drive which would result in
> >>  poorer performance.
> >>
> >>  johnn
> >>
> >>
> >>
> >>  >=> On Thu, 26 Sep 2002 08:54:01 -0400, Mahesh Tailor
> >>  ><MTailor AT CARILION DOT COM> said:
> >>  >
> >>  >>  Hopefully this is a simple question: I have fourteen 36GB
> >>drives that are
> >>  >>  available for the diskpool and I was wondering whether it is
> >>better to have
> >>  >>  seven 5GB files or three 10GB files or one 35GB file or
> >>something else?  The
> >>  >>  drives are mounted in two IBM-2014 Ultra-Wide SCSI disk drawers
with
> >>  >>  separate Ultra-Wide contollers.  The other 14 drives are used
> >>for DB, LOG,
> >>  >>  and spare.
> >>  >
> >>  >You have a total of 28 spindles, 14 each on two busses, right?
> >>  >
> >>  >I'd suggest making a RAID-5 out of the fourteen free spindles,
> >>and then make
> >>  >the individual volumes "A reasonable size".  What's a reasonable
size?
> >>  >Uh... ;)
> >>  >
> >>  >I just did this with a drawer of 36G SSA, and I chose 10G
> >>volumes, because I
> >>  >have about a dozen (and growing) disk pools amongst which I need to
divide
> >>  >things up.
> >>  >
> >>  >Even if you only have one or two disk pools, it's useful to have
> >>more than a
> >>  >few volumes per pool, because instantaneously only on thing can write
to a
> >  > >volume at a time.  So, for example, if you have 12 clients
> >backing up, and one
> >  > >70G disk volume, there is contention for the thread controlling that
one
> >>  >volume.
> >>  >
> >>  >So calculate the size so that you'll have as many volumes as you feel
like
> >>  >keeping track of, but not many more than that.
> >>  >
> >>  >
> >>  >- Allen S. Rout
> >>
>