× 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.



VERY big difference 10K vs 15K but of course in this case it's also exacerbated by the 1.1TB size vs the 'usual' 300GB or occasional 600GB 15K Drives. Round numbers whatever the 15K Drives take, double that for 10K Drives.

If you watch the drives during init of the LS you will see this:

With RAID:

The Load Source LED is pretty much solid on. One other drive is also solid on. Which drive that is changes as to where the RAID stripe data is for the sectors being initialized on the LS.

Remember that for RAID there is a READ READ and then a WRITE WRITE for every sector updated. Four operations.

Before RAID:

The Load Source LED is solid on.

Before RAID there is only WRITE. Meaning 75% less I/Os to initialize the disk here.

However if RAID is already there, once the LS is initialized you may simply add the other disks to the ASP. If RAID is not present then you need to start it and since the LS already has data you pay the penalty then. We have found the graph to correspond approximately as this:

NO RAID:
|-a----+-b----------------------------------------+-c-|

RAID:
|-b--|-a-----------------------------------+-c--------|

a: Init Load Source
b: Start RAID
c: Add drives to ASP.

So as the man with the oil filter said: "You can pay me now or pay me later!"

As to initializing SAN disks we have NOT seen performance boost there. In fact much slower. First there is the time to create the volumes on the SAN and then the time for IBM i to initialize them!

- Larry "DrFranken" Bolhuis

www.Frankeni.com
www.iDevCloud.com - Personal Development IBM i timeshare service.
www.iInTheCloud.com - Commercial IBM i Cloud Hosting.

On 8/31/2017 12:09 PM, Roberto José Etcheverry Romero wrote:
Dr,
10k or 15k I think the problem there lies in the RAID code. Most
controllers from IBM i I've worked with have the same problem. If you are
initializing the LS BEFORE starting raid, it goes fast enough. After RAID?
slow as heck. Don't know why since it's just writing 0 to the disk. One of
the reasons I love external SAN, 0 writes are detected by the controller
and ignored...
Have you seen a big difference between 10k and 15k on this matter?

Roberto

On Thu, Aug 31, 2017 at 1:05 PM, DrFranken <midrange@xxxxxxxxxxxx> wrote:

Currently initializing the load source on a set of 10K RPM 1.1TB Drives
that are already in a RAID5 configuration.

764 minutes and counting.......

That's just one of the 'why nots' :-)

--

- Larry "DrFranken" Bolhuis

www.Frankeni.com
www.iDevCloud.com - Personal Development IBM i timeshare service.
www.iInTheCloud.com - Commercial IBM i Cloud Hosting.
--
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.

Please contact support@xxxxxxxxxxxx for any subscription related
questions.

Help support midrange.com by shopping at amazon.com with our affiliate
link: http://amzn.to/2dEadiD


As an Amazon Associate we earn from qualifying purchases.

This thread ...

Replies:

Follow On AppleNews
Return to Archive home page | Return to MIDRANGE.COM home page

This mailing list archive is Copyright 1997-2024 by midrange.com and David Gibbs as a compilation work. Use of the archive is restricted to research of a business or technical nature. Any other uses are prohibited. Full details are available on our policy page. If you have questions about this, please contact [javascript protected email address].

Operating expenses for this site are earned using the Amazon Associate program and Google Adsense.