[olug] SAN Information

Mon Sep 30 16:05:25 UTC 2002

Sorry about the delay in replying, I don't do much with my work e-mail on
the weekends.

The way the Magnitude handles data is rather unique.  At the hardware level
the data is striped across all the drives (or spindles as they refer to
them).  This is not really configurable from a user standpoint, and if you
talk to Dell/EMC they'll harp on it as a big problem because it prevents
you from doing any performance tuning at the hardware level.  IMO this
isn't that big of a deal.  Honestly, how many of us bother to performance
tune our server-attached RAID's?  So let's say you've got a Magnitude with
1 Tb of space raw space.  You create a vdisk of 100 Gb with RAID 0.  You
just used 100 Gb of space and there is now a logical stripe set being
presented to your server.  Now lets say you want to change it to RAID 5.
Your space usage goes up to 150 Gb of space and your data now has some
(logical) fault tolerance that it wouldn't have otherwise had.  Then you
change it to RAID 10 (mirrored stripe set).  Your space usage just went up
to 200 Gb but you have the best fault tolerance and the best speed.  All of
this is done a logical rather than hardware level.  Xiotech calls this
"true storage virtualization".  EMC calls it a bad idea or "SAN Lite".  I
call it just what I need.   It's not a solution that I think would work
well for everyone, but since I'm not running a multi-billion dollar
e-business that can have zero downtime it will work for me.  Xiotech
claims, and so far I've found it to be true, that they're the only ones to
fully virtualize the storage.

I'm not sure my understanding of the differing parity levels on RAID 5 is
adequate to explain it.  The short version is that the lower parity version
(3 vs. 5 vs. 9) have better performance.

Bill
****************Reply separator*******************

                      "Rogers, John C NWD02"                                                                                 
                      <John.C.Rogers at nwd02.usac        To:       "'olug at olug.org'" <olug at olug.org>                           
                      e.army.mil>                      cc:                                                                   
                      Sent by:                         Subject:  RE: [olug] SAN Information                                  
                      olug-admin at olug.org                                                                                    

                      09/27/2002 04:51 PM                                                                                    
                      Please respond to olug                                                                                 

<snip>

Changing RAID levels on the fly is a very cool feature, what I am wondering
is if it really changes the physical storage blocks on disk or is it
changing the blocking factors in the controller OS settings only?  Most of
the big smart SANs I have seen and read about really implement RAID in
software and do not ever change the data on the physical disks.  The
algorithms used to place the block to the metal are proprietary and very
specialized to their requirements and SAN OS specifics.

<snip>

I am not familiar with RAID 5 with different parities.  Can you explain
that to the group?  I always knew it as RAID 0-5 with some new versions
like 10 and 7 coming out now.  Is parity RAID changing the parity
calculations or just the striping locations?  When we use RAID 5 or RAID 3
it is physically changing the controller setups and the way the blocks are
put to disk.  Like RAID 3 only stripes parity to one disk instead of 5 as
RAID 5 does.