Frank Schwede, LSY wrote:
I think the performance of an M9 disk isnt important. We benchmarked striped M3 and M9 pvs, same LVM-layout, had 4 and 8 phys. escon-channels. Nearly Same perf-values.
If you feel you can get the same amount of bandwidth from a -9 as from a -3, then that only means that seek time is not a significant factor. But you've just lost a factor of 3 if you compute the GB per MB/s. If you triple the data because the volume of processing tripled, then that may be an issue.
The paths to your ESS is what you share for all volumes behind that control unit. If you have 100 x 3390-3, these 100 compete for 4 chpids. When you only have 33 x 3390-9 then I would say you still need number of paths per 100 devices, not per GB ?
Aren't the DASDs virtual in the storage boxes?? Tracks are living anywhere!?
No, that was RVA. It's not for ESS. A number of S/390 volumes sit on the same set of disks. Look at the discussion at http://www10.software.ibm.com/developerworks/opensource/linux390/perf/tuning_rec_dasd_optimizedisk.shtml#begin
Rob
---------------------------------------------------------------------- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
