×
The internal search function is temporarily non-functional. The current search engine is no longer viable and we are researching alternatives.
As a stop gap measure, we are using Google's custom search engine service.
If you know of an easy to use, open source, search engine ... please contact support@midrange.com.
Hi All
I have a customer who has installed 4 X SSD drives onto a new 740
running V7R1. Getting the hot data is proving somewhat more of a
challenge than the documentation here:
http://www-912.ibm.com/s_dir/slkbase.nsf/1ac66549a21402188625680b0002037e/80a0c71876d5a872862567ca00770cb0
In summary, after running the TRCASPBAL and then running the STRASPBAL
*HSM the drives are left with a good deal less storage used than the
rest of the disk units (a whole bunch of mirrored SAS units). The
figures end up being something like 50% no SAS disks 40% 20% on the
SSDs.
I'm firstly looking for experience anyone else might have had with
moving data onto the SSD's - what worked, what didn't, what strategies
were used. I'm aware that I can identify the data by adding a unit
definition of *SSD or SSD but it would be better if only theoretically
that the system manage what is on the SSD on the basis of usage. The
customer is running JDE and the entire JDE application won't fit on
the SSDs so getting what is h ot onto the SSDs is important.
There is a reference to using a PercentToSSD parameter in SST to set
how much data shoudl be moves to the SSDs but there do not appear to
be any instructions for actually using this feature nor I can I find
any other references to it. Has anyone actually used this and have
some instructions on it ?
Any other experience or suggestions (or references) for optimizing SSD
use woul be most appreciated
d
midrange.com
