Re: Performance of large LF access path builds - SSD vs 10K spinny

Sue,
What you're describing would be akin to the Active/Passive controller
configuration in the DS3/4/5xxx, and in those cases you need to have more
LUNs to fully utilize both controllers. The same applies here, correct? at
least 2 parity sets and the more the merrier?

Best Regards,

Roberto

On Wed, Sep 24, 2014 at 4:39 PM, Sue Baker <sue.baker@xxxxxxxxxx> wrote:

Evan Harris <auctionitis@xxxxxxxxx> wrote on Mon, 22 Sep 2014
18:49:31 GMT:

Could you please expand on that comment a little to explain
why that is ?

I'd just like to understand this a little better.

A single parity set will only utilize one of the paired adapters
a the path to/from storage devices to the system. In other
words, you've set things up so one active adapter and the second
is acting as an auxiliary write cache device. This is not how
the adapter firmware expects things to be and latency is
introduced .... meaning longer disk response times. True for
both SSDs and HDDs, but more noticeable with SSDs.


--
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.