ADSM-L

Re: [ADSM-L] TSM 6 database space performance question

2010-05-12 08:19:59
Subject: Re: [ADSM-L] TSM 6 database space performance question
From: Richard Rhodes <rrhodes AT FIRSTENERGYCORP DOT COM>
To: ADSM-L AT VM.MARIST DOT EDU
Date: Wed, 12 May 2010 08:19:11 -0400
While they are getting the advantage of the disk subsystem spreading the
lun over many drives, they are not getting an advantage at the OS level of
balanced I/O between the luns unless they are using some kind of OS level
stripping.  I'm not really familiar with Linux . . . are they using LVM and
spreading the physical partitions across both luns, or, some kind of true
striping across the luns?

A lun is not just capacity, but also X amount of iops.  If the 2 luns are
simply concatinated then the iops of the new lun is going to be way under
utilizied until the db grows into the space, and even then it will probably
be unbalanced.  This is also true for the disks in the storage system - the
drives represent capacity (mb) as well as iops.  A disk iin the array not
carrying it's share of the i/o load is being wasted.

Rick






             "John D.
             Schneider"
             <john.schneider@C                                          To
             OMPUTERCOACHINGCO         ADSM-L AT VM.MARIST DOT EDU
             MMUNITY.COM>                                               cc
             Sent by: "ADSM:
             Dist Stor                                             Subject
             Manager"                  TSM 6 database space performance
             <[email protected]         question
             .EDU>


             05/11/2010 04:21
             PM


             Please respond to
             "ADSM: Dist Stor
                 Manager"
             <[email protected]
                   .EDU>






Greetings,
   I have a customer running TSM 6.1.3 on a Linux RedHat 5.4 server.
They are using high-performance SAN attached disk for the TSM database
and logs.  They have created the TSM database all in one directory under
one filesystem.  Recently then needed to add more space, and they carved
out a lun from another RAID group, and then added that lun to the
existing filesystem.  TSM shows that it now has the additional space,
but it is still all under one directory.
   In reading the Performance Guide and Admin Guide, they both recommend
spreading the data out over multiple directories, putting each directory
behind separate disks/luns.  This certainly makes sense to spread the
I/O out over multiple luns, and I get that.  But is there anything wrong
with the way my customer has done it?  They are using multiple luns from
different RAID groups, but they are all put together behind one
directory.  Is this going to become a problem as they add more and more
load to this instance?  If TSM has lots of separate directories and they
are across multiple luns, does TSM do it's database I/O differently?

Best Regards,

John D. Schneider
The Computer Coaching Community, LLC
Cell: (314) 750-8721


-----------------------------------------
The information contained in this message is intended only for the
personal and confidential use of the recipient(s) named above. If
the reader of this message is not the intended recipient or an
agent responsible for delivering it to the intended recipient, you
are hereby notified that you have received this document in error
and that any review, dissemination, distribution, or copying of
this message is strictly prohibited. If you have received this
communication in error, please notify us immediately, and delete
the original message.

<Prev in Thread] Current Thread [Next in Thread>