RE: Disk issue

["Carley, Neil" <carleyn1@xxxxxxxxxxxxxxxx>]

Thanks guys for the reply, and now for the next bit of the equation :
I'm drawing up a spec for upgrade (mainly DASD) and knowing that the 4gig
disks are discontinued I was thinking about using the 8gig ones. The new
disks will go into the main ASP also but would it be a bad idea to add a
further different type of disk into the config ? I will be adding probably
another 80+gig to our existing setup. 
Any further suggestions comments ?

thanks again for your advice on this matter

Neil       

> -----Original Message-----
> From: Larry Bolhuis [SMTP:lbolhuis@arbsol.com]
> Sent: Monday, February 26, 2001 12:33 PM
> To:   MIDRANGE-L@midrange.com; Carley, Neil
> Subject:      Re: Disk issue
> 
> Carley,
> 
>   Amazing how the math works out here here just as it should! Let me
> explain: Your 6607 drives are 4G units, the 6714's are 17G or just about
> 4 times larger. Since they contain about 4 times as much of your 'stuff'
> than the 4G units and are the same speed they will normally be about 4
> times busier. (40% -vs- 10%)
> 
>   This is why IBM (and many others) recommend against putting disks of
> different sizes in the same ASP. Certainly this cannot be avoided
> completely but you skipped one size (8.5G) in between and you can see
> the problem it creates. If you were to get the 4G units up to 20% busy
> (1/2 of recommended maximum) the 17G units would be around 80% busy!
> (Twice recommended maximum).
> 
>   Best thing you could do: Replace all of them with 10K RPM 8.5G drives.
> OK, That's likely not practical (budget wise) but you may want to add
> more arms to off-load those 17's as they are at the recommended maximum
> utilization already.  
> 
>   Also at V4R4 and up there is a storage pool balance function that can
> balance by access that may smooth this out for you some by putting
> lesser used data on the 17G drives. (STRASPBAL).
> 
>   HTH
> 
>     - Larry
> 
> "Carley, Neil" wrote:
> > 
> > Hi,
> > 
> > Hopefully someone can offer me some advice on this. I have a system here
> > (720 V4R3) with 25 disks in the main ASP 18 x 6607's & 7 x 6714's. A
> couple
> > of weeks ago I noticed a few messages in qsysopr reporting problems with
> the
> > disks and recommending contacting service before any serious problems
> > occurred, the machine was IPL'd that day and I have not seen any similar
> > messages since. Using wrkdsksts I notice that the 6607's are only
> running at
> > about 10% busy whereas the 6714's are running at about 40% busy, is it
> > normal to have two different types of disks running like this or could
> this
> > difference be causing a bottleneck on the system as we do tend to push
> our
> > system fairly hard ?
> 
> -- 
> Larry Bolhuis         | Cogito Ergo Vendo iSeries 
> Arbor Solutions, Inc. |
> (616) 451-2500                |               (I think, therefore I buy
> iSeries.)
> (616) 451-2571 -fax   |
> lbolhuis@arbsol.com   |        #3  1951-2001
> +---
> | This is the Midrange System Mailing List!
> | To submit a new message, send your mail to MIDRANGE-L@midrange.com.
> | To subscribe to this list send email to MIDRANGE-L-SUB@midrange.com.
> | To unsubscribe from this list send email to
> MIDRANGE-L-UNSUB@midrange.com.
> | Questions should be directed to the list owner/operator:
> david@midrange.com
> +---
+---
| This is the Midrange System Mailing List!
| To submit a new message, send your mail to MIDRANGE-L@midrange.com.
| To subscribe to this list send email to MIDRANGE-L-SUB@midrange.com.
| To unsubscribe from this list send email to MIDRANGE-L-UNSUB@midrange.com.
| Questions should be directed to the list owner/operator: david@midrange.com
+---