They (Netapp) spent a fair amount time in the Netapp 202 class teaching about how it is best to keep a RAID group on one controller.  If you have a single RAID group that spans more than one FC-AL interface, it is called a fractured RAID group, and there was even a lab in the class where they went through how to correct a fractured RAID group and put the disks back on one FC-AL controller. 
 
It looks like the configuration that was used in the benchmark was a single volume that had 2 RAID groups (RAID group 0, and RAID group 1, presumably), and each of these RAID groups was cabled up to separate interfaces.  I'm guessing that this configuration would yield a filesystem that is striped across both FC-AL interfaces.  Since the RAID calculations are done at the RAID group level rather than at the volume level it makes sense that more than one RAID calculation can be done in parallel.  Based on that assumption, splitting a volume across 2 controllers (while preventing RAID group fracturing) should improve performance.
 
Rick Hulsey
Southwest Airlines
2425 Wyman
Mail Stop 4DC
Dallas, Tx., 75235
rick.hulsey@wnco.com
(214) 792-7188 Office
(972) 880-6882 Cell
(800) 915-3747 Pager


>>> Graydon Dodson <grdodson@lexmark.com> 10/09/00 04:22PM >>>

> I also had a 760 survive doing 17,000 nfs ops/second once.  ...

  When running compiles, it is not unusual for us to see numbers over 22,000 on
the op-panel of our 760.    Anyone know where the top end of an 840 is?
Support has been unable to answer that one for us.

  So in our move to an 840 I want to configure it's volume for maximum
performance.  The ground rules are two FC-AL adapters, seven full trays of 18G
drives.  All one volume is very desirable.

  Now the SPECsfs97 benchmark on the 840 states:

    * The F1 filesystem was composed of two RAID groups, each containing 17 data
      disks and one parity disk.  Two spare disks were present

    * The F1 filesystem was striped across both disk controllers


  Since I have to assume that NetApp would use a high performance architecture
for the benchmark I am guessing that this is the way to go, but there is quite
a bit of detail missing.

  Is it a good or bad idea to split a raid group over two FC-AL interfaces?
 
  What does "striped across both disk controllers" mean?
 
  If there are spare disks (same size) on both FC-AL interfaces and a disk fails
  Which one is used to rebuild?  (Same FC-AL or random choice)

  Is it a good or bad idea to split a volume over multiple FC-AL interfaces?
 



The need for speed

Graydon Dodson          (606) 232-6483        grdodson@lexmark.com
Lexmark International Inc.