Sue,
During the IDX build, I did notice multiple threads being used, even with unit *all instead vs unit *SSD..
All other production jobs/processes with SSD show 4x improvement compare to 10k spinny.
Could this be due to 5913, 0 read cache?
Is there anything else I'm missing?
We normally don't do many IDX build on production LPAR.
Following our yearly purges, I do rgzpfm while active.
These are still quite lengthy for the large files.
I would like to improve these times, if possible.
Paul
-----Original Message-----
From: MIDRANGE-L [mailto:midrange-l-bounces@xxxxxxxxxxxx] On Behalf Of Sue Baker
Sent: Thursday, September 18, 2014 4:43 PM
To: midrange-l@xxxxxxxxxxxx
Subject: RE: Performance of large LF access path builds - SSD vs 10K spinny
"Steinmetz, Paul" <PSteinmetz@xxxxxxxxxx> wrote on Tue, 16 Sep
2014 19:59:28 GMT:
Am I missing something?
Shouldn't the SSD be faster?
Hard to tell. There are lots of variables. The only way to really understand is to get some pretty detailed performance statistics. With elapsed time being 16 minutes, it's likely analyzing PEX traces would be the only way.
--
Sue
IBM Americas Advanced Technical Sales Support (ATS) Power Systems Rochester, MN
--
This is the Midrange Systems Technical Discussion (MIDRANGE-L) mailing list To post a message email: MIDRANGE-L@xxxxxxxxxxxx To subscribe, unsubscribe, or change list options,
visit:
http://lists.midrange.com/mailman/listinfo/midrange-l
or email: MIDRANGE-L-request@xxxxxxxxxxxx Before posting, please take a moment to review the archives at
http://archive.midrange.com/midrange-l.
midrange.com
