|
I have MPG licensed, but virtually never use it because there's never any
performance issue.
I brought the data up to date. The only graph related to Disk that's not
grayed out is Disk Space Utilization. Guess I'll have to read up on it.
But not today or tomorrow because we have a DR machine set up remotely and
I have the rest of today and tomorrow to test.
On Thu, Mar 20, 2014 at 2:00 PM, Steinmetz, Paul <PSteinmetz@xxxxxxxxxx>wrote:
Jeff,
Do a WRKDSKSTS during a save or any batch job, you'll see a huge
difference.
Better yet, use MPG (free demo available), check your disk response time,
service times and wait times.
MPG also has a what if option, you can compare your numbers between Raid5
and Raid6
Paul
-----Original Message-----
From: midrange-l-bounces@xxxxxxxxxxxx [mailto:
midrange-l-bounces@xxxxxxxxxxxx] On Behalf Of rob@xxxxxxxxx
Sent: Thursday, March 20, 2014 12:58 PM
To: Midrange Systems Technical Discussion
Subject: Re: RAID 6 rebuild time - can I slash it?
Tell you salesforce you want them to start selling until you get a
constant 40% busy.
Then again, maybe we should also...
Size % I/O Request Read Write Read Write %
Type (M) Used Rqs Size (K) Rqs Rqs (K) (K) Busy
433C 127892 80.1 14.8 17.7 6.2 8.5 25.3 12.1 2
433C 127892 78.5 11.0 18.4 6.5 4.5 19.2 17.3 2
433C 127892 78.5 19.4 15.4 6.8 12.6 23.5 11.0 3
433C 127892 78.5 24.9 9.7 7.3 17.5 18.9 5.9 4
433C 127892 78.5 20.2 18.3 9.8 10.4 19.9 16.8 4
433C 127892 78.5 23.2 11.4 6.7 16.4 19.3 8.1 3
433C 127892 78.5 18.0 13.2 7.2 10.7 19.9 8.6 3
433C 127892 78.5 14.9 13.8 6.2 8.6 18.1 10.7 2
433C 127892 78.5 22.3 11.7 8.4 13.9 17.6 8.2 3
433C 127892 78.5 16.3 19.3 10.1 6.1 24.2 11.2 4
433C 127892 78.5 33.9 12.7 6.8 27.1 18.8 11.2 2
433C 127892 78.5 21.2 14.1 6.0 15.2 20.6 11.5 3
433C 127892 78.5 12.7 21.3 6.9 5.7 20.0 22.9 3
58B0 52344 86.6 16.7 22.5 14.4 2.2 24.9 7.1
0<<<<<<<<<
58B0 52344 86.6 16.2 24.1 13.6 2.5 27.5 5.8 0
58B0 52344 86.6 20.1 26.4 17.2 2.8 29.9 5.3 0
58B0 52344 86.6 28.6 19.5 17.4 11.2 29.1 4.6 0
433C 127892 78.5 24.1 11.3 7.5 16.6 24.9 5.1 3
433C 127892 78.5 11.9 14.3 5.9 5.9 22.0 6.5 2
433C 127892 78.5 17.1 17.6 7.9 9.2 24.3 11.8 3
433C 127892 78.5 10.3 22.6 6.9 3.4 26.0 15.5 2
433C 127892 78.5 12.3 17.1 5.3 6.9 24.1 11.6 2
433C 127892 78.5 11.5 19.0 6.8 4.6 26.4 8.3 3
433C 127892 78.5 15.8 14.0 6.4 9.4 25.4 6.2 2
433C 127892 78.5 16.8 19.3 5.7 11.1 27.2 15.2 2
433C 127892 78.5 13.0 15.9 6.7 6.3 23.7 7.5 3
...
...
...
Rob Berendt
--
IBM Certified System Administrator - IBM i 6.1 Group Dekko Dept 1600 Mail
to: 2505 Dekko Drive
Garrett, IN 46738
Ship to: Dock 108
6928N 400E
Kendallville, IN 46755
http://www.dekko.com
From: Jeff Crosby <jlcrosby@xxxxxxxxxxxxxxxx>
To: Midrange Systems Technical Discussion <midrange-l@xxxxxxxxxxxx>
Date: 03/20/2014 12:39 PM
Subject: Re: RAID 6 rebuild time - can I slash it?
Sent by: midrange-l-bounces@xxxxxxxxxxxx
I write really efficient code. :)
On Thu, Mar 20, 2014 at 12:35 PM, DrFranken <midrange@xxxxxxxxxxxx>
wrote:
With those I/O numbers yes 0% is correct!Pro*
Take drive 1 with only 3.4 average requests per second averaging 7K it's
seriously loafing.
With numbers like these RAID-6 will likely have little effect. As you
say though the 5 hour time means these numbers are averaged to mush. The
10 minute slice is better. Your idea to do this during billing is also
a good one. You might actually find a time slice where a minor slowdown
could occur. :-)
- Larry "DrFranken" Bolhuis
www.frankeni.com
www.iDevCloud.com
www.iInTheCloud.com
On 3/20/2014 12:27 PM, Jeff Crosby wrote:
*This message was transferred with a trial version of CommuniGate(r)
WriteWell, here's an up-to-date WRKDSKSTS. Note it's over 5 hrs worth.
Work with Disk Status
DILGARD
03/20/14
12:09:59
Elapsed time: 05:22:55
Size % I/O Request Read Write Read
blank%
Unit Type (M) Used Rqs Size (K) Rqs Rqs (K) (K)
Busy
1 4326 35165 48.2 3.4 7.5 .9 2.5 11.4 6.0
0
2 4326 26373 48.2 2.2 8.9 1.0 1.2 10.8 7.3
0
3 4326 26373 48.2 2.3 8.0 .8 1.4 11.6 6.0
0
4 4326 26373 48.2 3.6 7.2 1.1 2.4 10.4 5.7
0
5 4326 26373 48.2 2.9 7.9 .9 2.0 11.9 6.1
0
6 4326 35165 48.2 3.6 8.2 1.2 2.4 12.6 6.0
0
7 4326 35165 48.2 5.2 7.5 1.5 3.7 11.9 5.7
0
8 4326 35165 48.2 3.5 8.6 1.3 2.2 11.9 6.6
0
9 4326 30769 48.2 3.3 8.5 1.3 1.9 11.6 6.5
0
10 4326 30769 48.2 3.2 8.2 1.1 2.0 11.8 6.1
0
11 4326 30769 48.2 3.4 7.9 1.1 2.2 11.3 6.1
0
12 4326 30769 48.2 2.9 7.7 .9 2.0 11.7 5.9
0
13 4326 30769 48.2 3.6 7.5 1.1 2.5 11.6 5.7
0
14 4326 30769 48.2 3.1 8.1 1.1 1.9 11.1 6.4
0
15 4326 30769 48.2 2.8 7.8 .9 1.9 11.4 6.0
0
16 4326 30769 48.2 3.9 8.9 1.5 2.4 10.7 7.8
0
0% Busy for every drive? The help for % Busy says "This field is
ifdisplay?
the performance characteristics of the
disk unit are not available." Is zero the same as blank on this
beI wouldn't think so, but really don't know.see
I then did F13 to restart statistics. Let it run for 10 minutes. All
drives still show 0% with comparable numbers to the above in the other
columns.
I think I will look at it later today while the billing is running and
if I get at least a 1% somewhere.wrote:
On Thu, Mar 20, 2014 at 12:08 PM, DrFranken <midrange@xxxxxxxxxxxx>
It Depends. :-)
Seriously it really does.
If (which is impossible) you had 100% reads then your I.O times will
beingapproximately 12.5% slower (1 of 8) because of the hot spare not
thanavailable to 'contribute'.
If (also impossible) you had 100% writes then you should see more
plus50% longer response times as there are two additional ops required
penaltythe hot spare not contributing and don't forget the RAID card will be
more busy tracking two RAID sets.
But of course you do a mix of reads and writes, more reads less
tomore writes more penalty.
And then there is queuing theory to deal with. If your disks are
currently 3 to 5% busy you're not going to care much if they go to 5
wouldtrouble8% busy. But if they are already 35 to 40% busy and jump to 50 to 60%
busy that's gonna hurt.
From everything you've said I really don't think you will be in
Pro*here, just better protected!
- Larry "DrFranken" Bolhuis
www.frankeni.com
www.iDevCloud.com
www.iInTheCloud.com
On 3/20/2014 12:01 PM, Jeff Crosby wrote:
*This message was transferred with a trial version of CommuniGate(r)
But, Jeff, if your run time went from 38 seconds to 5 minutes,
factorthey
complain?
Is that what's going to happen? Everything will be slower by a
sayingof 7
or 8 *times* (38 seconds to 300 seconds)? Seriously, or are you
Asaboutit
for effect?
On Thu, Mar 20, 2014 at 11:44 AM, <rob@xxxxxxxxx> wrote:
Everything is relative. Many of us on this list will go on and on
how much of a performance dog a 3 drive raid set is on scsi disks.
theyknowyearsrecently stated: PA-THE-TIC! However one poster put on here (some
ago) that these people were coming from a S/36 and wouldn't really
how fast the machine could go. They would be impressed with what
wouldgot.
But, Jeff, if your run time went from 38 seconds to 5 minutes,
goingmidrange-l@xxxxxxxxxxxx>they
complain?
Rob Berendt
--
IBM Certified System Administrator - IBM i 6.1
Group Dekko
Dept 1600
Mail to: 2505 Dekko Drive
Garrett, IN 46738
Ship to: Dock 108
6928N 400E
Kendallville, IN 46755
http://www.dekko.com
From: Jeff Crosby <jlcrosby@xxxxxxxxxxxxxxxx>
To: Midrange Systems Technical Discussion <
Date: 03/20/2014 11:03 AM
Subject: Re: RAID 6 rebuild time - can I slash it?
Sent by: midrange-l-bounces@xxxxxxxxxxxx
In various discussions regarding disk and performance and RAID 6
6.back
many months, posters keep hammering away on the performance of RAID
whatsoever.The
most important thing to us is protection.
Last October, Dr Franken posted this:
http://archive.midrange.com/midrange-l/201310/msg00754.html
I assume that's still true.
Regarding our performance, we have no performance issues,
Ia
mean none. No one *ever* complains about response time or how long
bebatch
job takes on the System i. Ever.
As an example, we're a food distribution warehouse. The orders to
indelivered today were staged yesterday and then are run all-at-once
everybatch. The operator took the option at @4:35pm. This processed
invoices,order against inventory, generated all picking labels, the
andsome
timeall documentation needed by the night crew to load the trucks. This
entire
process took 38 seconds. This is very typical. The actual *print*
done.for those labels and invoices was obviously longer, but the job was
This is followed by running a ton of reports (some hardcopy and
andPDF)
in a follow up batch job. This takes less than 2 minutes.
The above is our most complex and important business hours task,
wipedit's
less than 3 minutes total. Should I be worried about performance?
On Thu, Mar 20, 2014 at 10:39 AM, Wilson Jonathan
<piercing_male@xxxxxxxxxxx
wrote:
On Thu, 2014-03-20 at 08:33 -0400, rob@xxxxxxxxx wrote:
Sue,
Raid 6 would mean you'd have to lose at least two drives to be
running,drives,out.
Raid 6 with hot spare means you'd have to lose at least three
right?
Raid 6 means you can loose 2 working disks, but can continue
you'rebut if 1 more working disk failed during a re-building spare
you'redead
in the water, unless it was the rebuilding spare in which case
bethinkstill running.
Kind of like, which is better:
Raid 5 with a hot spare, or
Raid 6 with no hot spare
Either way, you'd have to lose two drives to be fried. I would
that
Raid 6 would be better if there was a risk the second drive would
outlost
rebuilding.while the hot spare for raid 5 was becoming active and still
With Raid 5 you lose the space of one drive to striping (spread
apposedacross
all drives). How much do you lose to Raid 6?
You loose 2 drives worth of space to the redundancy, no matter the
layout or number of raid6 disks.
Ideally the parity should be spread across all the disks as
toof
concerned...specific parity drives, at least as far as linux mdadm is
itsit may be different for IBM i cards/systems but in the linux world
preventsmuch faster to have the parity interleaved with the data as it
fromcontention on what would become a parity disk(s).drives
Is there a performance degradation from removing one of your disk
of a 8 drive SCSI raid set to become hot spare?
I would think there would be two performance hits. One, dropping
there8
performancedrives supporting the raid stripe down to only 4. The other
hit would be one less disk arm assisting while it's just sitting
mailingwaiting to be hot spare.
Rob Berendt
--
IBM Certified System Administrator - IBM i 6.1
Group Dekko
Dept 1600
Mail to: 2505 Dekko Drive
Garrett, IN 46738
Ship to: Dock 108
6928N 400E
Kendallville, IN 46755
http://www.dekko.com
From: Sue Baker <sue.baker@xxxxxxxxxx>
To: midrange-l@xxxxxxxxxxxx
Date: 03/19/2014 06:34 PM
Subject: Re: RAID 6 rebuild time - can I slash it?
Sent by: midrange-l-bounces@xxxxxxxxxxxx
Jeff Crosby <jlcrosby@xxxxxxxxxxxxxxxx> wrote on Wed, 19 Mar
2014 16:29:52 GMT:
On a Saturday of my choosing, our HW service provider is going
to take our System i 520 from 2 8-drive RAID 5 sets to 2
8-drive RAID 6 sets w/hot spare.
Wow! This is quite a change in data protection.
You realize that in order to have your data at risk, you need to
lose 2 drives in the RAID6 array?
Generally, I recommend to customers to do RAID5 + hot spare or
RAID6. I see it as more importante to have as many disk units
as possible for RAID6 versus adding the tiny bit of reduced
delay time for rebuild to begin on a single failed drive that is
provided by hot spare.
Time to create the RAID6 arrays is mostly dependent on the size
of the drives. Other factors are whether there is data on them
or not (% full is irrelevent) and the type of disk controller.
--
This is the Midrange Systems Technical Discussion (MIDRANGE-L)
mailinglist
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)
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.
--
Jeff Crosby
VP Information Systems
UniPro FoodService/Dilgard
P.O. Box 13369
Ft. Wayne, IN 46868-3369
260-422-7531
www.dilgardfoods.com
The opinions expressed are my own and not necessarily the opinion
mymailing
company. Unless I say so.
--
This is the Midrange Systems Technical Discussion (MIDRANGE-L)
mailinglist
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)
mailinglist
--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)
listlist
--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
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.
--
Jeff Crosby
VP Information Systems
UniPro FoodService/Dilgard
P.O. Box 13369
Ft. Wayne, IN 46868-3369
260-422-7531
www.dilgardfoods.com
The opinions expressed are my own and not necessarily the opinion of my
company. Unless I say so.
--
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.
--
Jeff Crosby
VP Information Systems
UniPro FoodService/Dilgard
P.O. Box 13369
Ft. Wayne, IN 46868-3369
260-422-7531
www.dilgardfoods.com
The opinions expressed are my own and not necessarily the opinion of my
company. Unless I say so.
As an Amazon Associate we earn from qualifying purchases.
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.