MIDRANGE dot COM Mailing List Archive



Home » MIDRANGE-L » March 2014

Re: 8205 Disk Drive errors 19A3FFF9 - Drive type 19A3



fixed

I second this. We have a BUNCH of customers running with just the drives in the CEC and they soundly trounce the performance of the POWER5 CEC drives and controller. It also has redundant paths and batteries unlike POWER5.

But to be real, if you are going to license 2 or more cores and stuff in 32 or 64GB Of memory you WILL rapidly find that DASD IOPS are a bottleneck.

I know for a fact you CAN show horn a 460CiD big block Ford into a Pinto but the rear end just goes 'snap' without a comparable upgrade!

- Larry "DrFranken" Bolhuis

www.frankeni.com
www.iDevCloud.com
www.iInTheCloud.com

On 3/18/2014 11:06 PM, Pete Massiello - ML wrote:

Yes, it is true that the cards are not hot swappable, and definitely a backward step. What is not true is the performance of the internal disk controller. That is pretty much a 5805, which is a really good disk controller to control those 8 drives. It can even handle some solid state drives in the CEC. While the internal disk controller of the Power5 was a dog, the internal disk controller of the Power7 machines is pretty good. It isn't the performance of a 5913 or ESA3, but it is good.

Pete


--
Pete Massiello
iTech Solutions
http://www.itechsol.com
http://www.iInTheCloud.com




-----Original Message-----
From: midrange-l-bounces@xxxxxxxxxxxx [mailto:midrange-l-bounces@xxxxxxxxxxxx] On Behalf Of Steinmetz, Paul
Sent: Tuesday, March 18, 2014 3:17 PM
To: 'Midrange Systems Technical Discussion'
Subject: RE: 8205 Disk Drive errors 19A3FFF9 - Drive type 19A3

This partition is only used for testing OS upgrades and hosting, utilized the CEC and its disk drive slots for something useful.
From past experience, we know the CEC is poor for production, P7 slots not hot swappable, only the disks, and gives poor performance, poor is actually being too kind.
Why doesn't IBM include a decent disk controller in the CEC, and why did they take a step backwards, Power5 slots were hot swappable.

-----Original Message-----
From: midrange-l-bounces@xxxxxxxxxxxx [mailto:midrange-l-bounces@xxxxxxxxxxxx] On Behalf Of Pete Massiello - ML
Sent: Tuesday, March 18, 2014 1:29 PM
To: Midrange Systems Technical Discussion
Subject: RE: 8205 Disk Drive errors 19A3FFF9 - Drive type 19A3

Paul,

Interesting why you choice a 5901 to drive the disks. I would never think to use a 5901 as it has no cache and would be very slow performance wise.

Pete

--
Pete Massiello
iTech Solutions
http://www.itechsol.com
http://www.iInTheCloud.com




-----Original Message-----
From: midrange-l-bounces@xxxxxxxxxxxx [mailto:midrange-l-bounces@xxxxxxxxxxxx] On Behalf Of Steinmetz, Paul
Sent: Monday, March 17, 2014 6:29 PM
To: 'Midrange Systems Technical Discussion'
Subject: RE: 8205 Disk Drive errors 19A3FFF9 - Drive type 19A3

Drive replaced.
Parity rebuilt - 9 hours,
8 drives in raid set
Model 099 Striping across all drives,
73% full.

-----Original Message-----
From: midrange-l-bounces@xxxxxxxxxxxx [mailto:midrange-l-bounces@xxxxxxxxxxxx] On Behalf Of DrFranken
Sent: Sunday, March 16, 2014 11:40 PM
To: Midrange Systems Technical Discussion
Subject: Re: 8205 Disk Drive errors 19A3FFF9 - Drive type 19A3

Ooooh yeah that 5901 is 'small of brain' (and cache too) so you are right, likely closer to the 12 than the 6 hours I'd bet.

Good thing it's a test partition eh?? :-)

- Larry "DrFranken" Bolhuis

www.frankeni.com
www.iDevCloud.com
www.iInTheCloud.com

On 3/16/2014 11:37 PM, Steinmetz, Paul wrote:
Larry,

The CEC 5901 disk controller will make it worse. Back when 1st built this LPAR, it was long and slow.
If I had an extra disk slot, I would include hot spare.
Here are some times IBM sent me a while back.
I'm thinking 6 to 12 hours.

Inputs:

Description Values Values Values
Disk Drive CCIN 58B4 19B3 19A3
IOA CCIN 57B5 57B5 57B3
RAID Type 5 5 5
DPH devices? n n n
# of Drives per IOA 18 24 8

Process Time (hrs)
Initialize load source 1 14 14
(scratch install)
Start RAID (no drives config'd) 1 11 11 Add to ASP 1 2 2

-----Original Message-----
From: midrange-l-bounces@xxxxxxxxxxxx
[mailto:midrange-l-bounces@xxxxxxxxxxxx] On Behalf Of DrFranken
Sent: Sunday, March 16, 2014 10:52 PM
To: Midrange Systems Technical Discussion
Subject: Re: 8205 Disk Drive errors 19A3FFF9 - Drive type 19A3

Well as a 10K RPM disk it should take 50% longer to fail than a 15K
RPM Disk, right? :-)

Just a suggestion that Hot Spare would be a great idea with these vary large and somewhat slower disks. I'm going to peg rebuild time on a drive that size at 6 Hours or more from the time IBM physically replaces the disk unit.

- Larry "DrFranken" Bolhuis

www.frankeni.com
www.iDevCloud.com
www.iInTheCloud.com

On 3/16/2014 10:15 PM, Steinmetz, Paul wrote:

One of my disk drives on my software test partition called home.
Drive type 19A3 571GB 10k RPM, 120+ temp failures , beginning at 6:15 this morning.
Drive is being replaced tomorrow morning, Raid5 protection.
This is our 1st disk failure on our Power7, installed 3/2012 _____
Paul Steinmetz IBM i Systems Administrator

Pencor Services, Inc.
462 Delaware Ave
Palmerton Pa 18071

610-826-9117 work
610-826-9188 fax
610-349-0913 cell
610-377-6012 home

psteinmetz@xxxxxxxxxx
http://www.pencor.com/


--
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.

--
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.

--
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.

--
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.

--
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.






Return to Archive home page | Return to MIDRANGE.COM home page

This mailing list archive is Copyright 1997-2014 by MIDRANGE dot 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 here. If you have questions about this, please contact