RE: IOPS's calculations

[Brian Desmond]

Your SAN should be able to produce these numbers.

Thanks,
Brian Desmond
br...@briandesmond.com

w - 312.625.1438 | c   - 312.731.3132

From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
Sent: Monday, February 06, 2012 2:56 PM
To: NT System Admin Issues
Subject: IOPS's calculations

Hi folks,

Thanks for all your help in the past.

Looking at setting up a SAN. From my research, I think one thing to be aware of 
is current IOPS (disk). There are a number of sites that will help you 
determine IOPS based on what hard drives (and RAID configuration). My question 
is: Many of my current servers are light use. The IOPS that these servers are 
capable of is much greater than what is actually being used.

So, in order to more properly size the SAN, is there a way to determine working 
IOPS? That is, what is actually being used? I assume Perfmon would help, and 
will need to log over a period of time (I think a week would be about right, to 
catch most scenarios). But what counters, and how to analyze those counters?

Servers are Windows 2003.

Thanks.


Mark Reimer, A+, MCSA
Servers & Networking Admin
Prairie Bible Institute
Box 4000
Three Hills, AB  T0M-2N0
Canada
Tel: 403-443-5511, Ext. 3476
Fax: 403-443-5540
Email: mark.rei...@prairie.edu
www.prairie.edu



~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~   ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to 
listmana...@lyris.sunbeltsoftware.com
with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~   ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to listmana...@lyris.sunbeltsoftware.com
with the body: unsubscribe ntsysadmin

RE: IOPS's calculations

[Michael B. Smith]

Disk Reads per second
Disk Writes per second
Average Disk Queue Length

I'd track both logical disk and physical disk.

Regards,

Michael B. Smith
Consultant and Exchange MVP
http://TheEssentialExchange.com

From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
Sent: Monday, February 06, 2012 3:56 PM
To: NT System Admin Issues
Subject: IOPS's calculations

Hi folks,

Thanks for all your help in the past.

Looking at setting up a SAN. From my research, I think one thing to be aware of 
is current IOPS (disk). There are a number of sites that will help you 
determine IOPS based on what hard drives (and RAID configuration). My question 
is: Many of my current servers are light use. The IOPS that these servers are 
capable of is much greater than what is actually being used.

So, in order to more properly size the SAN, is there a way to determine working 
IOPS? That is, what is actually being used? I assume Perfmon would help, and 
will need to log over a period of time (I think a week would be about right, to 
catch most scenarios). But what counters, and how to analyze those counters?

Servers are Windows 2003.

Thanks.


Mark Reimer, A+, MCSA
Servers & Networking Admin
Prairie Bible Institute
Box 4000
Three Hills, AB  T0M-2N0
Canada
Tel: 403-443-5511, Ext. 3476
Fax: 403-443-5540
Email: mark.rei...@prairie.edu
www.prairie.edu



~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~   ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to 
listmana...@lyris.sunbeltsoftware.com
with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~   ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to listmana...@lyris.sunbeltsoftware.com
with the body: unsubscribe ntsysadmin

RE: IOPS's calculations

[Reimer, Mark]

The question is: I want to know what my different servers (no san, each with 
their own direct attached disks storage) is using (not what they are capable 
of, but what they are actually using/doing).

Sorry if I was unclear to begin with.

Mark

From: Brian Desmond [mailto:br...@briandesmond.com]
Sent: Monday, February 06, 2012 2:55 PM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Your SAN should be able to produce these numbers.

Thanks,
Brian Desmond
br...@briandesmond.com<mailto:br...@briandesmond.com>

w - 312.625.1438 | c   - 312.731.3132

From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
Sent: Monday, February 06, 2012 2:56 PM
To: NT System Admin Issues
Subject: IOPS's calculations

Hi folks,

Thanks for all your help in the past.

Looking at setting up a SAN. From my research, I think one thing to be aware of 
is current IOPS (disk). There are a number of sites that will help you 
determine IOPS based on what hard drives (and RAID configuration). My question 
is: Many of my current servers are light use. The IOPS that these servers are 
capable of is much greater than what is actually being used.

So, in order to more properly size the SAN, is there a way to determine working 
IOPS? That is, what is actually being used? I assume Perfmon would help, and 
will need to log over a period of time (I think a week would be about right, to 
catch most scenarios). But what counters, and how to analyze those counters?

Servers are Windows 2003.

Thanks.


Mark Reimer, A+, MCSA
Servers & Networking Admin
Prairie Bible Institute
Box 4000
Three Hills, AB  T0M-2N0
Canada
Tel: 403-443-5511, Ext. 3476
Fax: 403-443-5540
Email: mark.rei...@prairie.edu<mailto:mark.rei...@prairie.edu>
www.prairie.edu<http://www.prairie.edu/>



~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to 
listmana...@lyris.sunbeltsoftware.com<mailto:listmana...@lyris.sunbeltsoftware.com>
with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to 
listmana...@lyris.sunbeltsoftware.com<mailto:listmana...@lyris.sunbeltsoftware.com>
with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to listmana...@lyris.sunbeltsoftware.com
with the body: unsubscribe ntsysadmin

RE: IOPS's calculations

[Jacob]

Look at dell dpack

 

From: Reimer, Mark [mailto:mark.rei...@prairie.edu] 
Sent: Monday, February 06, 2012 2:56 PM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

 

The question is: I want to know what my different servers (no san, each with
their own direct attached disks storage) is using (not what they are capable
of, but what they are actually using/doing). 

 

Sorry if I was unclear to begin with.


Mark

 

From: Brian Desmond [mailto:br...@briandesmond.com] 
Sent: Monday, February 06, 2012 2:55 PM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

 

Your SAN should be able to produce these numbers. 

 

Thanks,

Brian Desmond

br...@briandesmond.com

 

w - 312.625.1438 | c   - 312.731.3132

 

From: Reimer, Mark [mailto:mark.rei...@prairie.edu] 
Sent: Monday, February 06, 2012 2:56 PM
To: NT System Admin Issues
Subject: IOPS's calculations

 

Hi folks,

 

Thanks for all your help in the past.

 

Looking at setting up a SAN. From my research, I think one thing to be aware
of is current IOPS (disk). There are a number of sites that will help you
determine IOPS based on what hard drives (and RAID configuration). My
question is: Many of my current servers are light use. The IOPS that these
servers are capable of is much greater than what is actually being used.

 

So, in order to more properly size the SAN, is there a way to determine
working IOPS? That is, what is actually being used? I assume Perfmon would
help, and will need to log over a period of time (I think a week would be
about right, to catch most scenarios). But what counters, and how to analyze
those counters?

 

Servers are Windows 2003.

 

Thanks.

 

 

Mark Reimer, A+, MCSA

Servers & Networking Admin

Prairie Bible Institute

Box 4000

Three Hills, AB  T0M-2N0

Canada

Tel: 403-443-5511, Ext. 3476

Fax: 403-443-5540

Email: mark.rei...@prairie.edu

www.prairie.edu <http://www.prairie.edu/> 

 

 

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here:
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to listmana...@lyris.sunbeltsoftware.com
with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here:
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to listmana...@lyris.sunbeltsoftware.com
with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here:
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to listmana...@lyris.sunbeltsoftware.com
with the body: unsubscribe ntsysadmin


~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to listmana...@lyris.sunbeltsoftware.com
with the body: unsubscribe ntsysadmin

RE: IOPS's calculations

[Brian Desmond]

Those perf counters can be a bit misleading when you're looking at a SAN on the 
backend, though.

Thanks,
Brian Desmond
br...@briandesmond.com

w - 312.625.1438 | c   - 312.731.3132

From: Michael B. Smith [mailto:mich...@smithcons.com]
Sent: Monday, February 06, 2012 3:32 PM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Disk Reads per second
Disk Writes per second
Average Disk Queue Length

I'd track both logical disk and physical disk.

Regards,

Michael B. Smith
Consultant and Exchange MVP
http://TheEssentialExchange.com

From: Reimer, Mark 
[mailto:mark.rei...@prairie.edu]<mailto:[mailto:mark.rei...@prairie.edu]>
Sent: Monday, February 06, 2012 3:56 PM
To: NT System Admin Issues
Subject: IOPS's calculations

Hi folks,

Thanks for all your help in the past.

Looking at setting up a SAN. From my research, I think one thing to be aware of 
is current IOPS (disk). There are a number of sites that will help you 
determine IOPS based on what hard drives (and RAID configuration). My question 
is: Many of my current servers are light use. The IOPS that these servers are 
capable of is much greater than what is actually being used.

So, in order to more properly size the SAN, is there a way to determine working 
IOPS? That is, what is actually being used? I assume Perfmon would help, and 
will need to log over a period of time (I think a week would be about right, to 
catch most scenarios). But what counters, and how to analyze those counters?

Servers are Windows 2003.

Thanks.


Mark Reimer, A+, MCSA
Servers & Networking Admin
Prairie Bible Institute
Box 4000
Three Hills, AB  T0M-2N0
Canada
Tel: 403-443-5511, Ext. 3476
Fax: 403-443-5540
Email: mark.rei...@prairie.edu<mailto:mark.rei...@prairie.edu>
www.prairie.edu<http://www.prairie.edu/>



~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to 
listmana...@lyris.sunbeltsoftware.com<mailto:listmana...@lyris.sunbeltsoftware.com>
with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to 
listmana...@lyris.sunbeltsoftware.com<mailto:listmana...@lyris.sunbeltsoftware.com>
with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to listmana...@lyris.sunbeltsoftware.com
with the body: unsubscribe ntsysadmin

RE: IOPS's calculations

[Brian Desmond]

Accept-Language: en-US
Content-Language: en-US
X-MS-Has-Attach:
X-MS-TNEF-Correlator:
x-originating-ip: [10.42.111.27]
Content-Type: multipart/alternative;
boundary="_000_040311EACB6A5641B59395C8639A36CF1CB6637DCH1PRD0106MB172_"
MIME-Version: 1.0
Return-Path: br...@briandesmond.com
X-OriginatorOrg: briandesmond.com

--_000_040311EACB6A5641B59395C8639A36CF1CB6637DCH1PRD0106MB172_
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

OK and now that I read Mark's reply to me, never mind.

Thanks,
Brian Desmond
br...@briandesmond.com

w - 312.625.1438 | c   - 312.731.3132

From: Brian Desmond
Sent: Monday, February 06, 2012 10:33 PM
To: 'NT System Admin Issues'
Subject: RE: IOPS's calculations

Those perf counters can be a bit misleading when you're looking at a SAN on=
 the backend, though.

Thanks,
Brian Desmond
br...@briandesmond.com<mailto:br...@briandesmond.com>

w - 312.625.1438 | c   - 312.731.3132

From: Michael B. Smith [mailto:mich...@smithcons.com]<mailto:[mailto:michae=
l...@smithcons.com]>
Sent: Monday, February 06, 2012 3:32 PM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Disk Reads per second
Disk Writes per second
Average Disk Queue Length

I'd track both logical disk and physical disk.

Regards,

Michael B. Smith
Consultant and Exchange MVP
http://TheEssentialExchange.com

From: Reimer, Mark [mailto:mark.rei...@prairie.edu]<mailto:[mailto:mark.rei=
m...@prairie.edu]>
Sent: Monday, February 06, 2012 3:56 PM
To: NT System Admin Issues
Subject: IOPS's calculations

Hi folks,

Thanks for all your help in the past.

Looking at setting up a SAN. From my research, I think one thing to be awar=
e of is current IOPS (disk). There are a number of sites that will help you=
 determine IOPS based on what hard drives (and RAID configuration). My ques=
tion is: Many of my current servers are light use. The IOPS that these serv=
ers are capable of is much greater than what is actually being used.

So, in order to more properly size the SAN, is there a way to determine wor=
king IOPS? That is, what is actually being used? I assume Perfmon would hel=
p, and will need to log over a period of time (I think a week would be abou=
t right, to catch most scenarios). But what counters, and how to analyze th=
ose counters?

Servers are Windows 2003.

Thanks.


Mark Reimer, A+, MCSA
Servers & Networking Admin
Prairie Bible Institute
Box 4000
Three Hills, AB  T0M-2N0
Canada
Tel: 403-443-5511, Ext. 3476
Fax: 403-443-5540
Email: mark.rei...@prairie.edu<mailto:mark.rei...@prairie.edu>
www.prairie.edu<http://www.prairie.edu/>



~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: http://lyris.sunbelt-software.com/read/=
my_forums/
or send an email to listmana...@lyris.sunbeltsoftware.com<mailto:listmanage=
r...@lyris.sunbeltsoftware.com>
with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: http://lyris.sunbelt-software.com/read/=
my_forums/
or send an email to listmana...@lyris.sunbeltsoftware.com<mailto:listmanage=
r...@lyris.sunbeltsoftware.com>
with the body: unsubscribe ntsysadmin

--_000_040311EACB6A5641B59395C8639A36CF1CB6637DCH1PRD0106MB172_
Content-Type: text/html; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

http://schemas.microsoft.com/office/2004/12/omml"; xmlns=3D"http:=
//www.w3.org/TR/REC-html40">



<!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:Tahoma;
panose-1:2 11 6 4 3 5 4 4 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
margin-bottom:.0001pt;
font-size:11.0pt;
font-family:"Calibri","sans-serif";}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:blue;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:purple;
text-decoration:underline;}
p
{mso-style-priority:99;
mso-margin-top-alt:auto;
margin-right:0in;
mso-margin-bottom-alt:auto;
margin-left:0in;
font-size:12.0pt;
font-family:"Times New Roman","serif";}
p.MsoAcetate, li.MsoAcetate, div.MsoAcetate
{mso-style-priority:99;
mso-style-link:"Balloon Text Char";
margin:0in;
margin-bottom:.0001pt;
font-size:8.0pt;
font-family:"Tahoma&qu

Re: IOPS's calculations

[Sean Martin]

Mark,

Are you sure that's the data you're after? The difficult data to obtain is
typically what the system is capable of and not what they're actually
doing. DAS storage typically presents an IO ceiling the applications simply
cannot exceed. The actual capabilities of disks can be argued, but I've
always done well by using the following statistics for IO capabilities by
drive: 7.2k RPM = 75-100 IOPS, 10K RPM = 100-150 IOPS, 15K RPM = 150-200
IOPS. This doesn't take into account the other pros/cons between drive
types (Fiber Channel, ATA, SAS, etc.) but works for simple math.

Michael gave you some good perfmon counters to monitor. The two I would add
is Avg Disk Sec/Read and Avg Disk Sec/Write. This, along with avg queue
length, will help you identify what kind of bottleneck your systems may be
encountering. Typical thresholds for read/write latencies are avg below
10/20ms and spikes below 50/60ms. Some applications may be more or less
sensitive to certain latency but those are decent numbers to work with. Avg
queue length is tough to gauge because there seems to be two camps on the
subject. There are those that strive for avg queue lengths below 1 and
others that feel and avg queue length of N or below (where N = the number
of disks serving IO) is a good place to be. As far as total IO, you simply
add the avg disk reads/writes per second or max disk reads/writes per
second. That depends on if you're spec'ing your SAN to support your
sustained IO or your peak IO.

Whatever data you're able to collect in terms of IO, I would multiply that
by a certain factor if  you're looking to increase performance. This
practice will help you account for applications that may have been IO
constrained by DAS that could end up on high-end storage and consume all of
the IO you're able to provide. Now, to use the data to help spec your SAN
solution, we would need to know what solutions you're currently
entertaining. There are a number of different solutions that all leverage
very unique technologies that have changed the game from previous raw
storage solutions.

Just to share my recent experience, I have migrated approximately 30
servers from an EMC CX700 array to two Compellent Arrays over the last few
weeks. We didn't have very in-depth tools to gauge IO requirements but we
did our best with the tools at our disposal. One SQL server we migrated had
DBs residing on a LUN served by a 7 Disk RAID 5 RAID Group backed by
146GB/10K Fiber Channel disks. This RAID group also served LUNs for 4-5
other SQL servers so disk contention was evident. This SQL server, over
a 12 week period, was identified as never exceeding 300 IOPS. After
migrating this server to one of our Compellent Arrays backed by 12 SSDs, 36
15K SAS and 24 7.2K NL SAS drives, we saw peak IOPS exceed 5500. This
certainly wasn't a common experience during our migrations but we had a few
servers that really started to open up after migration.

- Sean



On Mon, Feb 6, 2012 at 1:56 PM, Reimer, Mark wrote:

> The question is: I want to know what my different servers (no san, each
> with their own direct attached disks storage) is using (not what they are
> capable of, but what they are actually using/doing). 
>
> ** **
>
> Sorry if I was unclear to begin with.
>
>
> Mark
>
> ** **
>
> *From:* Brian Desmond [mailto:br...@briandesmond.com]
> *Sent:* Monday, February 06, 2012 2:55 PM
>
> *To:* NT System Admin Issues
> *Subject:* RE: IOPS's calculations
>
> ** **
>
> *Your SAN should be able to produce these numbers. ***
>
> * *
>
> *Thanks,*
>
> *Brian Desmond*
>
> *br...@briandesmond.com*
>
> * *
>
> *w – 312.625.1438 | c   – 312.731.3132*
>
> * *
>
> *From:* Reimer, Mark [mailto:mark.rei...@prairie.edu]
> *Sent:* Monday, February 06, 2012 2:56 PM
> *To:* NT System Admin Issues
> *Subject:* IOPS's calculations
>
> ** **
>
> Hi folks,
>
> ** **
>
> Thanks for all your help in the past.
>
> ** **
>
> Looking at setting up a SAN. From my research, I think one thing to be
> aware of is current IOPS (disk). There are a number of sites that will help
> you determine IOPS based on what hard drives (and RAID configuration). My
> question is: Many of my current servers are light use. The IOPS that these
> servers are capable of is much greater than what is actually being used.**
> **
>
> ** **
>
> So, in order to more properly size the SAN, is there a way to determine
> working IOPS? That is, what is actually being used? I assume Perfmon would
> help, and will need to log over a period of time (I think a week would be
> about right, to catch most scenarios). But what counters, and how to
> analyze those counters?
>
> ** **
>
> Servers are Windows 2003.
>

Re: IOPS's calculations

[Kurt Buff]

So, to which counters should I be paying attention in such a
situation, or what should be the difference in interpretation?

I've got a file server that's being extremely slow to back up, though
daily performance is adequate.

I'm seeing disk queue length hit as high as 37, with 5 LUNS for the machine.

Kurt

On Mon, Feb 6, 2012 at 21:32, Brian Desmond  wrote:
> Those perf counters can be a bit misleading when you’re looking at a SAN on
> the backend, though.
>
>
>
> Thanks,
>
> Brian Desmond
>
> br...@briandesmond.com
>
>
>
> w – 312.625.1438 | c   – 312.731.3132
>
>
>
> From: Michael B. Smith [mailto:mich...@smithcons.com]
> Sent: Monday, February 06, 2012 3:32 PM
> To: NT System Admin Issues
> Subject: RE: IOPS's calculations
>
>
>
> Disk Reads per second
>
> Disk Writes per second
>
> Average Disk Queue Length
>
>
>
> I’d track both logical disk and physical disk.
>
>
>
> Regards,
>
>
>
> Michael B. Smith
>
> Consultant and Exchange MVP
>
> http://TheEssentialExchange.com
>
>
>
> From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
> Sent: Monday, February 06, 2012 3:56 PM
> To: NT System Admin Issues
> Subject: IOPS's calculations
>
>
>
> Hi folks,
>
>
>
> Thanks for all your help in the past.
>
>
>
> Looking at setting up a SAN. From my research, I think one thing to be aware
> of is current IOPS (disk). There are a number of sites that will help you
> determine IOPS based on what hard drives (and RAID configuration). My
> question is: Many of my current servers are light use. The IOPS that these
> servers are capable of is much greater than what is actually being used.
>
>
>
> So, in order to more properly size the SAN, is there a way to determine
> working IOPS? That is, what is actually being used? I assume Perfmon would
> help, and will need to log over a period of time (I think a week would be
> about right, to catch most scenarios). But what counters, and how to analyze
> those counters?
>
>
>
> Servers are Windows 2003.
>
>
>
> Thanks.
>
>
>
>
>
> Mark Reimer, A+, MCSA
>
> Servers & Networking Admin
>
> Prairie Bible Institute
>
> Box 4000
>
> Three Hills, AB  T0M-2N0
>
> Canada
>
> Tel: 403-443-5511, Ext. 3476
>
> Fax: 403-443-5540
>
> Email: mark.rei...@prairie.edu
>
> www.prairie.edu
>
>
>
>
>
> ~ Finally, powerful endpoint security that ISN'T a resource hog! ~
> ~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~
>
> ---
> To manage subscriptions click here:
> http://lyris.sunbelt-software.com/read/my_forums/
> or send an email to listmana...@lyris.sunbeltsoftware.com
> with the body: unsubscribe ntsysadmin
>
> ~ Finally, powerful endpoint security that ISN'T a resource hog! ~
> ~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~
>
> ---
> To manage subscriptions click here:
> http://lyris.sunbelt-software.com/read/my_forums/
> or send an email to listmana...@lyris.sunbeltsoftware.com
> with the body: unsubscribe ntsysadmin
>
> ~ Finally, powerful endpoint security that ISN'T a resource hog! ~
> ~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~
>
> ---
> To manage subscriptions click here:
> http://lyris.sunbelt-software.com/read/my_forums/
> or send an email to listmana...@lyris.sunbeltsoftware.com
> with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to listmana...@lyris.sunbeltsoftware.com
with the body: unsubscribe ntsysadmin

RE: IOPS's calculations

[Paul Hutchings]

As a rule of thumb queue length shouldn't exceed the physical number of disks 
in the array that the LUN is on x 2.

-Original Message-
From: Kurt Buff [mailto:kurt.b...@gmail.com] 
Sent: 07 February 2012 13:50
To: NT System Admin Issues
Subject: Re: IOPS's calculations

So, to which counters should I be paying attention in such a situation, or what 
should be the difference in interpretation?

I've got a file server that's being extremely slow to back up, though daily 
performance is adequate.

I'm seeing disk queue length hit as high as 37, with 5 LUNS for the machine.

Kurt

On Mon, Feb 6, 2012 at 21:32, Brian Desmond  wrote:
> Those perf counters can be a bit misleading when you’re looking at a 
> SAN on the backend, though.
>
>
>
> Thanks,
>
> Brian Desmond
>
> br...@briandesmond.com
>
>
>
> w – 312.625.1438 | c   – 312.731.3132
>
>
>
> From: Michael B. Smith [mailto:mich...@smithcons.com]
> Sent: Monday, February 06, 2012 3:32 PM
> To: NT System Admin Issues
> Subject: RE: IOPS's calculations
>
>
>
> Disk Reads per second
>
> Disk Writes per second
>
> Average Disk Queue Length
>
>
>
> I’d track both logical disk and physical disk.
>
>
>
> Regards,
>
>
>
> Michael B. Smith
>
> Consultant and Exchange MVP
>
> http://TheEssentialExchange.com
>
>
>
> From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
> Sent: Monday, February 06, 2012 3:56 PM
> To: NT System Admin Issues
> Subject: IOPS's calculations
>
>
>
> Hi folks,
>
>
>
> Thanks for all your help in the past.
>
>
>
> Looking at setting up a SAN. From my research, I think one thing to be 
> aware of is current IOPS (disk). There are a number of sites that will 
> help you determine IOPS based on what hard drives (and RAID 
> configuration). My question is: Many of my current servers are light 
> use. The IOPS that these servers are capable of is much greater than what is 
> actually being used.
>
>
>
> So, in order to more properly size the SAN, is there a way to 
> determine working IOPS? That is, what is actually being used? I assume 
> Perfmon would help, and will need to log over a period of time (I 
> think a week would be about right, to catch most scenarios). But what 
> counters, and how to analyze those counters?
>
>
>
> Servers are Windows 2003.
>
>
>
> Thanks.
>
>
>
>
>
> Mark Reimer, A+, MCSA
>
> Servers & Networking Admin
>
> Prairie Bible Institute
>
> Box 4000
>
> Three Hills, AB  T0M-2N0
>
> Canada
>
> Tel: 403-443-5511, Ext. 3476
>
> Fax: 403-443-5540
>
> Email: mark.rei...@prairie.edu
>
> www.prairie.edu
>
>
>
>
>
> ~ Finally, powerful endpoint security that ISN'T a resource hog! ~ ~ 
> <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~
>
> ---
> To manage subscriptions click here:
> http://lyris.sunbelt-software.com/read/my_forums/
> or send an email to listmana...@lyris.sunbeltsoftware.com
> with the body: unsubscribe ntsysadmin
>
> ~ Finally, powerful endpoint security that ISN'T a resource hog! ~ ~ 
> <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~
>
> ---
> To manage subscriptions click here:
> http://lyris.sunbelt-software.com/read/my_forums/
> or send an email to listmana...@lyris.sunbeltsoftware.com
> with the body: unsubscribe ntsysadmin
>
> ~ Finally, powerful endpoint security that ISN'T a resource hog! ~ ~ 
> <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~
>
> ---
> To manage subscriptions click here:
> http://lyris.sunbelt-software.com/read/my_forums/
> or send an email to listmana...@lyris.sunbeltsoftware.com
> with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~ ~ 
<http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to listmana...@lyris.sunbeltsoftware.com
with the body: unsubscribe ntsysadmin


--
MIRA Ltd

Watling Street, Nuneaton, Warwickshire, CV10 0TU, England
Registered in England and Wales No. 402570
VAT Registration  GB 100 1464 84

The contents of this e-mail are confidential and are solely for the use of the 
intended recipient.  If you receive this e-mail in error, please delete it and 
notify us either by e-mail, telephone or fax.  You should not copy, forward or 
otherwise disclose the content of the e-mail as this is prohibited.

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to listmana...@lyris.sunbeltsoftware.com
with the body: unsubscribe ntsysadmin

RE: IOPS's calculations

[Miller Bonnie L .]

When we were planning for our SAN and VM conversion/migration, the Microsoft 
engineer we worked with had us collect information on our servers about usage 
using the MAPs tool.  Looks like it's still around-not sure if it would do what 
you need:

http://www.microsoft.com/download/en/details.aspx?id=7826

http://technet.microsoft.com/en-us/library/bb977556.aspx

If you are a Dell shop, their new dpack tool is nice too, but was still in beta 
when we used it a few weeks ago-not sure if they've released yet.  If not, 
you'll have to work with your Dell engineer to get the reports generated that 
you would need.

-Bonnie


From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
Sent: Monday, February 06, 2012 2:56 PM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

The question is: I want to know what my different servers (no san, each with 
their own direct attached disks storage) is using (not what they are capable 
of, but what they are actually using/doing).

Sorry if I was unclear to begin with.

Mark

From: Brian Desmond [mailto:br...@briandesmond.com]
Sent: Monday, February 06, 2012 2:55 PM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Your SAN should be able to produce these numbers.

Thanks,
Brian Desmond
br...@briandesmond.com<mailto:br...@briandesmond.com>

w - 312.625.1438 | c   - 312.731.3132

From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
Sent: Monday, February 06, 2012 2:56 PM
To: NT System Admin Issues
Subject: IOPS's calculations

Hi folks,

Thanks for all your help in the past.

Looking at setting up a SAN. From my research, I think one thing to be aware of 
is current IOPS (disk). There are a number of sites that will help you 
determine IOPS based on what hard drives (and RAID configuration). My question 
is: Many of my current servers are light use. The IOPS that these servers are 
capable of is much greater than what is actually being used.

So, in order to more properly size the SAN, is there a way to determine working 
IOPS? That is, what is actually being used? I assume Perfmon would help, and 
will need to log over a period of time (I think a week would be about right, to 
catch most scenarios). But what counters, and how to analyze those counters?

Servers are Windows 2003.

Thanks.


Mark Reimer, A+, MCSA
Servers & Networking Admin
Prairie Bible Institute
Box 4000
Three Hills, AB  T0M-2N0
Canada
Tel: 403-443-5511, Ext. 3476
Fax: 403-443-5540
Email: mark.rei...@prairie.edu<mailto:mark.rei...@prairie.edu>
www.prairie.edu<http://www.prairie.edu/>



~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to 
listmana...@lyris.sunbeltsoftware.com<mailto:listmana...@lyris.sunbeltsoftware.com>
with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to 
listmana...@lyris.sunbeltsoftware.com<mailto:listmana...@lyris.sunbeltsoftware.com>
with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to 
listmana...@lyris.sunbeltsoftware.com<mailto:listmana...@lyris.sunbeltsoftware.com>
with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to listmana...@lyris.sunbeltsoftware.com
with the body: unsubscribe ntsysadmin

RE: IOPS's calculations

[Michael B. Smith]

Where do you get "x 2" ? I was with you - until that.

Regards,

Michael B. Smith
Consultant and Exchange MVP
http://TheEssentialExchange.com


-Original Message-
From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk] 
Sent: Tuesday, February 07, 2012 8:56 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

As a rule of thumb queue length shouldn't exceed the physical number of disks 
in the array that the LUN is on x 2.

-Original Message-
From: Kurt Buff [mailto:kurt.b...@gmail.com] 
Sent: 07 February 2012 13:50
To: NT System Admin Issues
Subject: Re: IOPS's calculations

So, to which counters should I be paying attention in such a situation, or what 
should be the difference in interpretation?

I've got a file server that's being extremely slow to back up, though daily 
performance is adequate.

I'm seeing disk queue length hit as high as 37, with 5 LUNS for the machine.

Kurt

On Mon, Feb 6, 2012 at 21:32, Brian Desmond  wrote:
> Those perf counters can be a bit misleading when you’re looking at a 
> SAN on the backend, though.
>
>
>
> Thanks,
>
> Brian Desmond
>
> br...@briandesmond.com
>
>
>
> w – 312.625.1438 | c   – 312.731.3132
>
>
>
> From: Michael B. Smith [mailto:mich...@smithcons.com]
> Sent: Monday, February 06, 2012 3:32 PM
> To: NT System Admin Issues
> Subject: RE: IOPS's calculations
>
>
>
> Disk Reads per second
>
> Disk Writes per second
>
> Average Disk Queue Length
>
>
>
> I’d track both logical disk and physical disk.
>
>
>
> Regards,
>
>
>
> Michael B. Smith
>
> Consultant and Exchange MVP
>
> http://TheEssentialExchange.com
>
>
>
> From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
> Sent: Monday, February 06, 2012 3:56 PM
> To: NT System Admin Issues
> Subject: IOPS's calculations
>
>
>
> Hi folks,
>
>
>
> Thanks for all your help in the past.
>
>
>
> Looking at setting up a SAN. From my research, I think one thing to be 
> aware of is current IOPS (disk). There are a number of sites that will 
> help you determine IOPS based on what hard drives (and RAID 
> configuration). My question is: Many of my current servers are light 
> use. The IOPS that these servers are capable of is much greater than what is 
> actually being used.
>
>
>
> So, in order to more properly size the SAN, is there a way to 
> determine working IOPS? That is, what is actually being used? I assume 
> Perfmon would help, and will need to log over a period of time (I 
> think a week would be about right, to catch most scenarios). But what 
> counters, and how to analyze those counters?
>
>
>
> Servers are Windows 2003.
>
>
>
> Thanks.
>
>
>
>
>
> Mark Reimer, A+, MCSA
>
> Servers & Networking Admin
>
> Prairie Bible Institute
>
> Box 4000
>
> Three Hills, AB  T0M-2N0
>
> Canada
>
> Tel: 403-443-5511, Ext. 3476
>
> Fax: 403-443-5540
>
> Email: mark.rei...@prairie.edu
>
> www.prairie.edu
>
>
>
>
>
> ~ Finally, powerful endpoint security that ISN'T a resource hog! ~ ~ 
> <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~
>
> ---
> To manage subscriptions click here:
> http://lyris.sunbelt-software.com/read/my_forums/
> or send an email to listmana...@lyris.sunbeltsoftware.com
> with the body: unsubscribe ntsysadmin
>
> ~ Finally, powerful endpoint security that ISN'T a resource hog! ~ ~ 
> <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~
>
> ---
> To manage subscriptions click here:
> http://lyris.sunbelt-software.com/read/my_forums/
> or send an email to listmana...@lyris.sunbeltsoftware.com
> with the body: unsubscribe ntsysadmin
>
> ~ Finally, powerful endpoint security that ISN'T a resource hog! ~ ~ 
> <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~
>
> ---
> To manage subscriptions click here:
> http://lyris.sunbelt-software.com/read/my_forums/
> or send an email to listmana...@lyris.sunbeltsoftware.com
> with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~ ~ 
<http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to listmana...@lyris.sunbeltsoftware.com
with the body: unsubscribe ntsysadmin


--
MIRA Ltd

Watling Street, Nuneaton, Warwickshire, CV10 0TU, England
Registered in England and Wales No. 402570
VAT Registration  GB 100 1464 84

The contents of this e-mail are confidential and are solely for the use of the 
intended recipient.  If you receive this 

RE: IOPS's calculations

[Paul Hutchings]

Most guides I've read suggest if the LUN has 10 physical disks, you don't want 
the queue to exceed around 20, or if you have 5 disks a queue of 10 and so on.

-Original Message-
From: Michael B. Smith [mailto:mich...@smithcons.com] 
Sent: 07 February 2012 15:06
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Where do you get "x 2" ? I was with you - until that.

Regards,

Michael B. Smith
Consultant and Exchange MVP
http://TheEssentialExchange.com


-Original Message-
From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk]
Sent: Tuesday, February 07, 2012 8:56 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

As a rule of thumb queue length shouldn't exceed the physical number of disks 
in the array that the LUN is on x 2.

-Original Message-
From: Kurt Buff [mailto:kurt.b...@gmail.com]
Sent: 07 February 2012 13:50
To: NT System Admin Issues
Subject: Re: IOPS's calculations

So, to which counters should I be paying attention in such a situation, or what 
should be the difference in interpretation?

I've got a file server that's being extremely slow to back up, though daily 
performance is adequate.

I'm seeing disk queue length hit as high as 37, with 5 LUNS for the machine.

Kurt

On Mon, Feb 6, 2012 at 21:32, Brian Desmond  wrote:
> Those perf counters can be a bit misleading when you’re looking at a 
> SAN on the backend, though.
>
>
>
> Thanks,
>
> Brian Desmond
>
> br...@briandesmond.com
>
>
>
> w – 312.625.1438 | c   – 312.731.3132
>
>
>
> From: Michael B. Smith [mailto:mich...@smithcons.com]
> Sent: Monday, February 06, 2012 3:32 PM
> To: NT System Admin Issues
> Subject: RE: IOPS's calculations
>
>
>
> Disk Reads per second
>
> Disk Writes per second
>
> Average Disk Queue Length
>
>
>
> I’d track both logical disk and physical disk.
>
>
>
> Regards,
>
>
>
> Michael B. Smith
>
> Consultant and Exchange MVP
>
> http://TheEssentialExchange.com
>
>
>
> From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
> Sent: Monday, February 06, 2012 3:56 PM
> To: NT System Admin Issues
> Subject: IOPS's calculations
>
>
>
> Hi folks,
>
>
>
> Thanks for all your help in the past.
>
>
>
> Looking at setting up a SAN. From my research, I think one thing to be 
> aware of is current IOPS (disk). There are a number of sites that will 
> help you determine IOPS based on what hard drives (and RAID 
> configuration). My question is: Many of my current servers are light 
> use. The IOPS that these servers are capable of is much greater than what is 
> actually being used.
>
>
>
> So, in order to more properly size the SAN, is there a way to 
> determine working IOPS? That is, what is actually being used? I assume 
> Perfmon would help, and will need to log over a period of time (I 
> think a week would be about right, to catch most scenarios). But what 
> counters, and how to analyze those counters?
>
>
>
> Servers are Windows 2003.
>
>
>
> Thanks.
>
>
>
>
>
> Mark Reimer, A+, MCSA
>
> Servers & Networking Admin
>
> Prairie Bible Institute
>
> Box 4000
>
> Three Hills, AB  T0M-2N0
>
> Canada
>
> Tel: 403-443-5511, Ext. 3476
>
> Fax: 403-443-5540
>
> Email: mark.rei...@prairie.edu
>
> www.prairie.edu
>
>
>
>
>
> ~ Finally, powerful endpoint security that ISN'T a resource hog! ~ ~ 
> <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~
>
> ---
> To manage subscriptions click here:
> http://lyris.sunbelt-software.com/read/my_forums/
> or send an email to listmana...@lyris.sunbeltsoftware.com
> with the body: unsubscribe ntsysadmin
>
> ~ Finally, powerful endpoint security that ISN'T a resource hog! ~ ~ 
> <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~
>
> ---
> To manage subscriptions click here:
> http://lyris.sunbelt-software.com/read/my_forums/
> or send an email to listmana...@lyris.sunbeltsoftware.com
> with the body: unsubscribe ntsysadmin
>
> ~ Finally, powerful endpoint security that ISN'T a resource hog! ~ ~ 
> <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~
>
> ---
> To manage subscriptions click here:
> http://lyris.sunbelt-software.com/read/my_forums/
> or send an email to listmana...@lyris.sunbeltsoftware.com
> with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~ ~ 
<http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to 

RE: IOPS's calculations

[Michael B. Smith]

I'm not a SAN expert. But for typical RAID subsystems, I don't want the 
physical queue to exceed the number of disks in the array. If it does, then 
I've got excessive queuing and degraded performance.

I don't see how it would be different for a SAN, but I dunno.

Regards,

Michael B. Smith
Consultant and Exchange MVP
http://TheEssentialExchange.com


-Original Message-
From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk] 
Sent: Tuesday, February 07, 2012 10:40 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Most guides I've read suggest if the LUN has 10 physical disks, you don't want 
the queue to exceed around 20, or if you have 5 disks a queue of 10 and so on.

-Original Message-
From: Michael B. Smith [mailto:mich...@smithcons.com] 
Sent: 07 February 2012 15:06
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Where do you get "x 2" ? I was with you - until that.

Regards,

Michael B. Smith
Consultant and Exchange MVP
http://TheEssentialExchange.com


-Original Message-
From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk]
Sent: Tuesday, February 07, 2012 8:56 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

As a rule of thumb queue length shouldn't exceed the physical number of disks 
in the array that the LUN is on x 2.

-Original Message-
From: Kurt Buff [mailto:kurt.b...@gmail.com]
Sent: 07 February 2012 13:50
To: NT System Admin Issues
Subject: Re: IOPS's calculations

So, to which counters should I be paying attention in such a situation, or what 
should be the difference in interpretation?

I've got a file server that's being extremely slow to back up, though daily 
performance is adequate.

I'm seeing disk queue length hit as high as 37, with 5 LUNS for the machine.

Kurt

On Mon, Feb 6, 2012 at 21:32, Brian Desmond  wrote:
> Those perf counters can be a bit misleading when you’re looking at a 
> SAN on the backend, though.
>
>
>
> Thanks,
>
> Brian Desmond
>
> br...@briandesmond.com
>
>
>
> w – 312.625.1438 | c   – 312.731.3132
>
>
>
> From: Michael B. Smith [mailto:mich...@smithcons.com]
> Sent: Monday, February 06, 2012 3:32 PM
> To: NT System Admin Issues
> Subject: RE: IOPS's calculations
>
>
>
> Disk Reads per second
>
> Disk Writes per second
>
> Average Disk Queue Length
>
>
>
> I’d track both logical disk and physical disk.
>
>
>
> Regards,
>
>
>
> Michael B. Smith
>
> Consultant and Exchange MVP
>
> http://TheEssentialExchange.com
>
>
>
> From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
> Sent: Monday, February 06, 2012 3:56 PM
> To: NT System Admin Issues
> Subject: IOPS's calculations
>
>
>
> Hi folks,
>
>
>
> Thanks for all your help in the past.
>
>
>
> Looking at setting up a SAN. From my research, I think one thing to be 
> aware of is current IOPS (disk). There are a number of sites that will 
> help you determine IOPS based on what hard drives (and RAID 
> configuration). My question is: Many of my current servers are light 
> use. The IOPS that these servers are capable of is much greater than what is 
> actually being used.
>
>
>
> So, in order to more properly size the SAN, is there a way to 
> determine working IOPS? That is, what is actually being used? I assume 
> Perfmon would help, and will need to log over a period of time (I 
> think a week would be about right, to catch most scenarios). But what 
> counters, and how to analyze those counters?
>
>
>
> Servers are Windows 2003.
>
>
>
> Thanks.
>
>
>
>
>
> Mark Reimer, A+, MCSA
>
> Servers & Networking Admin
>
> Prairie Bible Institute
>
> Box 4000
>
> Three Hills, AB  T0M-2N0
>
> Canada
>
> Tel: 403-443-5511, Ext. 3476
>
> Fax: 403-443-5540
>
> Email: mark.rei...@prairie.edu
>
> www.prairie.edu
>
>
>
>
>
> ~ Finally, powerful endpoint security that ISN'T a resource hog! ~ ~ 
> <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~
>
> ---
> To manage subscriptions click here:
> http://lyris.sunbelt-software.com/read/my_forums/
> or send an email to listmana...@lyris.sunbeltsoftware.com
> with the body: unsubscribe ntsysadmin
>
> ~ Finally, powerful endpoint security that ISN'T a resource hog! ~ ~ 
> <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~
>
> ---
> To manage subscriptions click here:
> http://lyris.sunbelt-software.com/read/my_forums/
> or send an email to listmana...@lyris.sunbeltsoftware.com
> with the body: unsubscribe ntsysadmin
>
> ~ Finally, powerful endpoint security that ISN'T a reso

RE: IOPS's calculations

[Brian Desmond]

I've always used the *2 rule of thumb cited below also...

Thanks,
Brian Desmond
br...@briandesmond.com

w – 312.625.1438 | c   – 312.731.3132


-Original Message-
From: Michael B. Smith [mailto:mich...@smithcons.com] 
Sent: Tuesday, February 07, 2012 9:26 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

I'm not a SAN expert. But for typical RAID subsystems, I don't want the 
physical queue to exceed the number of disks in the array. If it does, then 
I've got excessive queuing and degraded performance.

I don't see how it would be different for a SAN, but I dunno.

Regards,

Michael B. Smith
Consultant and Exchange MVP
http://TheEssentialExchange.com


-Original Message-
From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk]
Sent: Tuesday, February 07, 2012 10:40 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Most guides I've read suggest if the LUN has 10 physical disks, you don't want 
the queue to exceed around 20, or if you have 5 disks a queue of 10 and so on.

-Original Message-
From: Michael B. Smith [mailto:mich...@smithcons.com]
Sent: 07 February 2012 15:06
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Where do you get "x 2" ? I was with you - until that.

Regards,

Michael B. Smith
Consultant and Exchange MVP
http://TheEssentialExchange.com


-Original Message-
From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk]
Sent: Tuesday, February 07, 2012 8:56 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

As a rule of thumb queue length shouldn't exceed the physical number of disks 
in the array that the LUN is on x 2.

-Original Message-
From: Kurt Buff [mailto:kurt.b...@gmail.com]
Sent: 07 February 2012 13:50
To: NT System Admin Issues
Subject: Re: IOPS's calculations

So, to which counters should I be paying attention in such a situation, or what 
should be the difference in interpretation?

I've got a file server that's being extremely slow to back up, though daily 
performance is adequate.

I'm seeing disk queue length hit as high as 37, with 5 LUNS for the machine.

Kurt

On Mon, Feb 6, 2012 at 21:32, Brian Desmond  wrote:
> Those perf counters can be a bit misleading when you’re looking at a 
> SAN on the backend, though.
>
>
>
> Thanks,
>
> Brian Desmond
>
> br...@briandesmond.com
>
>
>
> w – 312.625.1438 | c   – 312.731.3132
>
>
>
> From: Michael B. Smith [mailto:mich...@smithcons.com]
> Sent: Monday, February 06, 2012 3:32 PM
> To: NT System Admin Issues
> Subject: RE: IOPS's calculations
>
>
>
> Disk Reads per second
>
> Disk Writes per second
>
> Average Disk Queue Length
>
>
>
> I’d track both logical disk and physical disk.
>
>
>
> Regards,
>
>
>
> Michael B. Smith
>
> Consultant and Exchange MVP
>
> http://TheEssentialExchange.com
>
>
>
> From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
> Sent: Monday, February 06, 2012 3:56 PM
> To: NT System Admin Issues
> Subject: IOPS's calculations
>
>
>
> Hi folks,
>
>
>
> Thanks for all your help in the past.
>
>
>
> Looking at setting up a SAN. From my research, I think one thing to be 
> aware of is current IOPS (disk). There are a number of sites that will 
> help you determine IOPS based on what hard drives (and RAID 
> configuration). My question is: Many of my current servers are light 
> use. The IOPS that these servers are capable of is much greater than what is 
> actually being used.
>
>
>
> So, in order to more properly size the SAN, is there a way to 
> determine working IOPS? That is, what is actually being used? I assume 
> Perfmon would help, and will need to log over a period of time (I 
> think a week would be about right, to catch most scenarios). But what 
> counters, and how to analyze those counters?
>
>
>
> Servers are Windows 2003.
>
>
>
> Thanks.
>
>
>
>
>
> Mark Reimer, A+, MCSA
>
> Servers & Networking Admin
>
> Prairie Bible Institute
>
> Box 4000
>
> Three Hills, AB  T0M-2N0
>
> Canada
>
> Tel: 403-443-5511, Ext. 3476
>
> Fax: 403-443-5540
>
> Email: mark.rei...@prairie.edu
>
> www.prairie.edu
>
>
>
>
>
> ~ Finally, powerful endpoint security that ISN'T a resource hog! ~ ~ 
> <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~
>
> ---
> To manage subscriptions click here:
> http://lyris.sunbelt-software.com/read/my_forums/
> or send an email to listmana...@lyris.sunbeltsoftware.com
> with the body: unsubscribe ntsysadmin
>
> ~ Finally, powerful endpoint security that ISN'T a resource hog! ~ ~ 
> <http://www.

RE: IOPS's calculations

[Paul Hutchings]

I don't think SAN vs. DAS/NAS should matter tbh, just the spindles in the array 
- no expert either I just muddle by.

This is what I was going from - 
http://technet.microsoft.com/en-us/library/cc938625.aspx

From: Michael B. Smith [mich...@smithcons.com]
Sent: 07 February 2012 4:25 PM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

I'm not a SAN expert. But for typical RAID subsystems, I don't want the 
physical queue to exceed the number of disks in the array. If it does, then 
I've got excessive queuing and degraded performance.

I don't see how it would be different for a SAN, but I dunno.

Regards,

Michael B. Smith
Consultant and Exchange MVP
http://TheEssentialExchange.com


-Original Message-
From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk]
Sent: Tuesday, February 07, 2012 10:40 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Most guides I've read suggest if the LUN has 10 physical disks, you don't want 
the queue to exceed around 20, or if you have 5 disks a queue of 10 and so on.

-Original Message-
From: Michael B. Smith [mailto:mich...@smithcons.com]
Sent: 07 February 2012 15:06
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Where do you get "x 2" ? I was with you - until that.

Regards,

Michael B. Smith
Consultant and Exchange MVP
http://TheEssentialExchange.com


-Original Message-
From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk]
Sent: Tuesday, February 07, 2012 8:56 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

As a rule of thumb queue length shouldn't exceed the physical number of disks 
in the array that the LUN is on x 2.

-Original Message-
From: Kurt Buff [mailto:kurt.b...@gmail.com]
Sent: 07 February 2012 13:50
To: NT System Admin Issues
Subject: Re: IOPS's calculations

So, to which counters should I be paying attention in such a situation, or what 
should be the difference in interpretation?

I've got a file server that's being extremely slow to back up, though daily 
performance is adequate.

I'm seeing disk queue length hit as high as 37, with 5 LUNS for the machine.

Kurt

On Mon, Feb 6, 2012 at 21:32, Brian Desmond  wrote:
> Those perf counters can be a bit misleading when you’re looking at a
> SAN on the backend, though.
>
>
>
> Thanks,
>
> Brian Desmond
>
> br...@briandesmond.com
>
>
>
> w – 312.625.1438 | c   – 312.731.3132
>
>
>
> From: Michael B. Smith [mailto:mich...@smithcons.com]
> Sent: Monday, February 06, 2012 3:32 PM
> To: NT System Admin Issues
> Subject: RE: IOPS's calculations
>
>
>
> Disk Reads per second
>
> Disk Writes per second
>
> Average Disk Queue Length
>
>
>
> I’d track both logical disk and physical disk.
>
>
>
> Regards,
>
>
>
> Michael B. Smith
>
> Consultant and Exchange MVP
>
> http://TheEssentialExchange.com
>
>
>
> From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
> Sent: Monday, February 06, 2012 3:56 PM
> To: NT System Admin Issues
> Subject: IOPS's calculations
>
>
>
> Hi folks,
>
>
>
> Thanks for all your help in the past.
>
>
>
> Looking at setting up a SAN. From my research, I think one thing to be
> aware of is current IOPS (disk). There are a number of sites that will
> help you determine IOPS based on what hard drives (and RAID
> configuration). My question is: Many of my current servers are light
> use. The IOPS that these servers are capable of is much greater than what is 
> actually being used.
>
>
>
> So, in order to more properly size the SAN, is there a way to
> determine working IOPS? That is, what is actually being used? I assume
> Perfmon would help, and will need to log over a period of time (I
> think a week would be about right, to catch most scenarios). But what
> counters, and how to analyze those counters?
>
>
>
> Servers are Windows 2003.
>
>
>
> Thanks.
>
>
>
>
>
> Mark Reimer, A+, MCSA
>
> Servers & Networking Admin
>
> Prairie Bible Institute
>
> Box 4000
>
> Three Hills, AB  T0M-2N0
>
> Canada
>
> Tel: 403-443-5511, Ext. 3476
>
> Fax: 403-443-5540
>
> Email: mark.rei...@prairie.edu
>
> www.prairie.edu
>
>
>
>
>
> ~ Finally, powerful endpoint security that ISN'T a resource hog! ~ ~
> <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~
>
> ---
> To manage subscriptions click here:
> http://lyris.sunbelt-software.com/read/my_forums/
> or send an email to listmana...@lyris.sunbeltsoftware.com
> with the body: unsubscribe ntsysadmin
>
> ~ Finally, powerful endpoint securi

RE: IOPS's calculations

[Brian Desmond]

Gets more interesting with SAN though when you have something like a Netapp 
FlashCache or something in the mix

Thanks,
Brian Desmond
br...@briandesmond.com

w - 312.625.1438 | c   - 312.731.3132


-Original Message-
From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk] 
Sent: Tuesday, February 07, 2012 10:36 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

I don't think SAN vs. DAS/NAS should matter tbh, just the spindles in the array 
- no expert either I just muddle by.

This is what I was going from - 
http://technet.microsoft.com/en-us/library/cc938625.aspx

From: Michael B. Smith [mich...@smithcons.com]
Sent: 07 February 2012 4:25 PM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

I'm not a SAN expert. But for typical RAID subsystems, I don't want the 
physical queue to exceed the number of disks in the array. If it does, then 
I've got excessive queuing and degraded performance.

I don't see how it would be different for a SAN, but I dunno.

Regards,

Michael B. Smith
Consultant and Exchange MVP
http://TheEssentialExchange.com


-Original Message-
From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk]
Sent: Tuesday, February 07, 2012 10:40 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Most guides I've read suggest if the LUN has 10 physical disks, you don't want 
the queue to exceed around 20, or if you have 5 disks a queue of 10 and so on.

-Original Message-
From: Michael B. Smith [mailto:mich...@smithcons.com]
Sent: 07 February 2012 15:06
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Where do you get "x 2" ? I was with you - until that.

Regards,

Michael B. Smith
Consultant and Exchange MVP
http://TheEssentialExchange.com


-Original Message-
From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk]
Sent: Tuesday, February 07, 2012 8:56 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

As a rule of thumb queue length shouldn't exceed the physical number of disks 
in the array that the LUN is on x 2.

-Original Message-
From: Kurt Buff [mailto:kurt.b...@gmail.com]
Sent: 07 February 2012 13:50
To: NT System Admin Issues
Subject: Re: IOPS's calculations

So, to which counters should I be paying attention in such a situation, or what 
should be the difference in interpretation?

I've got a file server that's being extremely slow to back up, though daily 
performance is adequate.

I'm seeing disk queue length hit as high as 37, with 5 LUNS for the machine.

Kurt

On Mon, Feb 6, 2012 at 21:32, Brian Desmond  wrote:
> Those perf counters can be a bit misleading when you're looking at a 
> SAN on the backend, though.
>
>
>
> Thanks,
>
> Brian Desmond
>
> br...@briandesmond.com
>
>
>
> w - 312.625.1438 | c   - 312.731.3132
>
>
>
> From: Michael B. Smith [mailto:mich...@smithcons.com]
> Sent: Monday, February 06, 2012 3:32 PM
> To: NT System Admin Issues
> Subject: RE: IOPS's calculations
>
>
>
> Disk Reads per second
>
> Disk Writes per second
>
> Average Disk Queue Length
>
>
>
> I'd track both logical disk and physical disk.
>
>
>
> Regards,
>
>
>
> Michael B. Smith
>
> Consultant and Exchange MVP
>
> http://TheEssentialExchange.com
>
>
>
> From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
> Sent: Monday, February 06, 2012 3:56 PM
> To: NT System Admin Issues
> Subject: IOPS's calculations
>
>
>
> Hi folks,
>
>
>
> Thanks for all your help in the past.
>
>
>
> Looking at setting up a SAN. From my research, I think one thing to be 
> aware of is current IOPS (disk). There are a number of sites that will 
> help you determine IOPS based on what hard drives (and RAID 
> configuration). My question is: Many of my current servers are light 
> use. The IOPS that these servers are capable of is much greater than what is 
> actually being used.
>
>
>
> So, in order to more properly size the SAN, is there a way to 
> determine working IOPS? That is, what is actually being used? I assume 
> Perfmon would help, and will need to log over a period of time (I 
> think a week would be about right, to catch most scenarios). But what 
> counters, and how to analyze those counters?
>
>
>
> Servers are Windows 2003.
>
>
>
> Thanks.
>
>
>
>
>
> Mark Reimer, A+, MCSA
>
> Servers & Networking Admin
>
> Prairie Bible Institute
>
> Box 4000
>
> Three Hills, AB  T0M-2N0
>
> Canada
>
> Tel: 403-443-5511, Ext. 3476
>
> Fax: 403-443-5540
>
> Email: mark.rei...@prairie.edu
>
> www.prairie.edu
>
>
>
>
>
> ~ 

RE: IOPS's calculations

[Paul Hutchings]

I think even DAS is getting smarter these days.  I've just had a new Dell 
arrive and whilst we aren't using the feature, it seems the PERC can use an SSD 
drive as cache, which I thought was pretty cool for such an entry level box of 
tricks (relatively speaking).

From: Brian Desmond [br...@briandesmond.com]
Sent: 07 February 2012 5:58 PM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Gets more interesting with SAN though when you have something like a Netapp 
FlashCache or something in the mix

Thanks,
Brian Desmond
br...@briandesmond.com

w - 312.625.1438 | c   - 312.731.3132


-Original Message-
From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk]
Sent: Tuesday, February 07, 2012 10:36 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

I don't think SAN vs. DAS/NAS should matter tbh, just the spindles in the array 
- no expert either I just muddle by.

This is what I was going from - 
http://technet.microsoft.com/en-us/library/cc938625.aspx

From: Michael B. Smith [mich...@smithcons.com]
Sent: 07 February 2012 4:25 PM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

I'm not a SAN expert. But for typical RAID subsystems, I don't want the 
physical queue to exceed the number of disks in the array. If it does, then 
I've got excessive queuing and degraded performance.

I don't see how it would be different for a SAN, but I dunno.

Regards,

Michael B. Smith
Consultant and Exchange MVP
http://TheEssentialExchange.com


-Original Message-
From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk]
Sent: Tuesday, February 07, 2012 10:40 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Most guides I've read suggest if the LUN has 10 physical disks, you don't want 
the queue to exceed around 20, or if you have 5 disks a queue of 10 and so on.

-Original Message-
From: Michael B. Smith [mailto:mich...@smithcons.com]
Sent: 07 February 2012 15:06
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Where do you get "x 2" ? I was with you - until that.

Regards,

Michael B. Smith
Consultant and Exchange MVP
http://TheEssentialExchange.com


-Original Message-
From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk]
Sent: Tuesday, February 07, 2012 8:56 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

As a rule of thumb queue length shouldn't exceed the physical number of disks 
in the array that the LUN is on x 2.

-Original Message-
From: Kurt Buff [mailto:kurt.b...@gmail.com]
Sent: 07 February 2012 13:50
To: NT System Admin Issues
Subject: Re: IOPS's calculations

So, to which counters should I be paying attention in such a situation, or what 
should be the difference in interpretation?

I've got a file server that's being extremely slow to back up, though daily 
performance is adequate.

I'm seeing disk queue length hit as high as 37, with 5 LUNS for the machine.

Kurt

On Mon, Feb 6, 2012 at 21:32, Brian Desmond  wrote:
> Those perf counters can be a bit misleading when you're looking at a
> SAN on the backend, though.
>
>
>
> Thanks,
>
> Brian Desmond
>
> br...@briandesmond.com
>
>
>
> w - 312.625.1438 | c   - 312.731.3132
>
>
>
> From: Michael B. Smith [mailto:mich...@smithcons.com]
> Sent: Monday, February 06, 2012 3:32 PM
> To: NT System Admin Issues
> Subject: RE: IOPS's calculations
>
>
>
> Disk Reads per second
>
> Disk Writes per second
>
> Average Disk Queue Length
>
>
>
> I'd track both logical disk and physical disk.
>
>
>
> Regards,
>
>
>
> Michael B. Smith
>
> Consultant and Exchange MVP
>
> http://TheEssentialExchange.com
>
>
>
> From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
> Sent: Monday, February 06, 2012 3:56 PM
> To: NT System Admin Issues
> Subject: IOPS's calculations
>
>
>
> Hi folks,
>
>
>
> Thanks for all your help in the past.
>
>
>
> Looking at setting up a SAN. From my research, I think one thing to be
> aware of is current IOPS (disk). There are a number of sites that will
> help you determine IOPS based on what hard drives (and RAID
> configuration). My question is: Many of my current servers are light
> use. The IOPS that these servers are capable of is much greater than what is 
> actually being used.
>
>
>
> So, in order to more properly size the SAN, is there a way to
> determine working IOPS? That is, what is actually being used? I assume
> Perfmon would help, and will need to log over a period of time (I
> think a week would be about right, to catch most scenarios). But what
> counters, and how to analyze those counters?

Re: IOPS's calculations

[Sean Martin]

Very true. Large global cache, automated tiering, etc. are all
technologies that change the way performance and bottlenecks are
measured. There are situations introduced in SAN environment (forced
flushing of cache), that can occur in a DAS scenario, are much more
prevelant in a SAN and have much wider impact. Looking at solutions
like Compellent or 3Par that have virtualized storage add another
level complexity. Your data could be striped across hundreds of
drives. I wouldn't consider a queue depth at an equal number
acceptable for a single volume.

- Sean

On 2/7/12, Brian Desmond  wrote:
> Gets more interesting with SAN though when you have something like a Netapp
> FlashCache or something in the mix
>
> Thanks,
> Brian Desmond
> br...@briandesmond.com
>
> w - 312.625.1438 | c   - 312.731.3132
>
>
> -Original Message-
> From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk]
> Sent: Tuesday, February 07, 2012 10:36 AM
> To: NT System Admin Issues
> Subject: RE: IOPS's calculations
>
> I don't think SAN vs. DAS/NAS should matter tbh, just the spindles in the
> array - no expert either I just muddle by.
>
> This is what I was going from -
> http://technet.microsoft.com/en-us/library/cc938625.aspx
> 
> From: Michael B. Smith [mich...@smithcons.com]
> Sent: 07 February 2012 4:25 PM
> To: NT System Admin Issues
> Subject: RE: IOPS's calculations
>
> I'm not a SAN expert. But for typical RAID subsystems, I don't want the
> physical queue to exceed the number of disks in the array. If it does, then
> I've got excessive queuing and degraded performance.
>
> I don't see how it would be different for a SAN, but I dunno.
>
> Regards,
>
> Michael B. Smith
> Consultant and Exchange MVP
> http://TheEssentialExchange.com
>
>
> -Original Message-
> From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk]
> Sent: Tuesday, February 07, 2012 10:40 AM
> To: NT System Admin Issues
> Subject: RE: IOPS's calculations
>
> Most guides I've read suggest if the LUN has 10 physical disks, you don't
> want the queue to exceed around 20, or if you have 5 disks a queue of 10 and
> so on.
>
> -Original Message-
> From: Michael B. Smith [mailto:mich...@smithcons.com]
> Sent: 07 February 2012 15:06
> To: NT System Admin Issues
> Subject: RE: IOPS's calculations
>
> Where do you get "x 2" ? I was with you - until that.
>
> Regards,
>
> Michael B. Smith
> Consultant and Exchange MVP
> http://TheEssentialExchange.com
>
>
> -Original Message-
> From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk]
> Sent: Tuesday, February 07, 2012 8:56 AM
> To: NT System Admin Issues
> Subject: RE: IOPS's calculations
>
> As a rule of thumb queue length shouldn't exceed the physical number of
> disks in the array that the LUN is on x 2.
>
> -Original Message-
> From: Kurt Buff [mailto:kurt.b...@gmail.com]
> Sent: 07 February 2012 13:50
> To: NT System Admin Issues
> Subject: Re: IOPS's calculations
>
> So, to which counters should I be paying attention in such a situation, or
> what should be the difference in interpretation?
>
> I've got a file server that's being extremely slow to back up, though daily
> performance is adequate.
>
> I'm seeing disk queue length hit as high as 37, with 5 LUNS for the machine.
>
> Kurt
>
> On Mon, Feb 6, 2012 at 21:32, Brian Desmond  wrote:
>> Those perf counters can be a bit misleading when you're looking at a
>> SAN on the backend, though.
>>
>>
>>
>> Thanks,
>>
>> Brian Desmond
>>
>> br...@briandesmond.com
>>
>>
>>
>> w - 312.625.1438 | c   - 312.731.3132
>>
>>
>>
>> From: Michael B. Smith [mailto:mich...@smithcons.com]
>> Sent: Monday, February 06, 2012 3:32 PM
>> To: NT System Admin Issues
>> Subject: RE: IOPS's calculations
>>
>>
>>
>> Disk Reads per second
>>
>> Disk Writes per second
>>
>> Average Disk Queue Length
>>
>>
>>
>> I'd track both logical disk and physical disk.
>>
>>
>>
>> Regards,
>>
>>
>>
>> Michael B. Smith
>>
>> Consultant and Exchange MVP
>>
>> http://TheEssentialExchange.com
>>
>>
>>
>> From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
>> Sent: Monday, February 06, 2012 3:56 PM
>> To: NT System Admin Issues
>> Subject: IOPS's calculations
>>
>>
>>
>> Hi folks,
>>
>>
>>
>> Th

RE: IOPS's calculations

[David Lum]

You mean a disk queue length of 5 on  two-spindle RAID1 for more than 5 minutes 
is bad? LOL. I have a client that is constantly HDD-bound (I've seen queue 
lengths of 15 for over 10 mins at a time - and they're not out or RAM either), 
running SBS2K3 on dual SATA RAID1 volumes (the OS, Exchange and SQL are on the 
same volume though - long story)...17 users, most of them use a SQL, all of 
course use Exchange. As a general rule, I don't tell people that they'll see 
_significant_ performance improvements regardless of what kind of upgrade they 
are getting be it GB switches, SSD drives, etc. 

This client I _have_ told them they would see significant increase on their 
SQL-based app when they get a new server since it'll be 15K SAS drives and the 
SQL will be on a separate volume than Exchange.

Dave

-Original Message-
From: Michael B. Smith [mailto:mich...@smithcons.com] 
Sent: Tuesday, February 07, 2012 8:26 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

I'm not a SAN expert. But for typical RAID subsystems, I don't want the 
physical queue to exceed the number of disks in the array. If it does, then 
I've got excessive queuing and degraded performance.

I don't see how it would be different for a SAN, but I dunno.

Regards,

Michael B. Smith
Consultant and Exchange MVP
http://TheEssentialExchange.com


-Original Message-
From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk]
Sent: Tuesday, February 07, 2012 10:40 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Most guides I've read suggest if the LUN has 10 physical disks, you don't want 
the queue to exceed around 20, or if you have 5 disks a queue of 10 and so on.

-Original Message-
From: Michael B. Smith [mailto:mich...@smithcons.com]
Sent: 07 February 2012 15:06
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Where do you get "x 2" ? I was with you - until that.

Regards,

Michael B. Smith
Consultant and Exchange MVP
http://TheEssentialExchange.com


-Original Message-
From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk]
Sent: Tuesday, February 07, 2012 8:56 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

As a rule of thumb queue length shouldn't exceed the physical number of disks 
in the array that the LUN is on x 2.

-Original Message-
From: Kurt Buff [mailto:kurt.b...@gmail.com]
Sent: 07 February 2012 13:50
To: NT System Admin Issues
Subject: Re: IOPS's calculations

So, to which counters should I be paying attention in such a situation, or what 
should be the difference in interpretation?

I've got a file server that's being extremely slow to back up, though daily 
performance is adequate.

I'm seeing disk queue length hit as high as 37, with 5 LUNS for the machine.

Kurt

On Mon, Feb 6, 2012 at 21:32, Brian Desmond  wrote:
> Those perf counters can be a bit misleading when you’re looking at a 
> SAN on the backend, though.
>
>
>
> Thanks,
>
> Brian Desmond
>
> br...@briandesmond.com
>
>
>
> w – 312.625.1438 | c   – 312.731.3132
>
>
>
> From: Michael B. Smith [mailto:mich...@smithcons.com]
> Sent: Monday, February 06, 2012 3:32 PM
> To: NT System Admin Issues
> Subject: RE: IOPS's calculations
>
>
>
> Disk Reads per second
>
> Disk Writes per second
>
> Average Disk Queue Length
>
>
>
> I’d track both logical disk and physical disk.
>
>
>
> Regards,
>
>
>
> Michael B. Smith
>
> Consultant and Exchange MVP
>
> http://TheEssentialExchange.com
>
>
>
> From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
> Sent: Monday, February 06, 2012 3:56 PM
> To: NT System Admin Issues
> Subject: IOPS's calculations
>
>
>
> Hi folks,
>
>
>
> Thanks for all your help in the past.
>
>
>
> Looking at setting up a SAN. From my research, I think one thing to be 
> aware of is current IOPS (disk). There are a number of sites that will 
> help you determine IOPS based on what hard drives (and RAID 
> configuration). My question is: Many of my current servers are light 
> use. The IOPS that these servers are capable of is much greater than what is 
> actually being used.
>
>
>
> So, in order to more properly size the SAN, is there a way to 
> determine working IOPS? That is, what is actually being used? I assume 
> Perfmon would help, and will need to log over a period of time (I 
> think a week would be about right, to catch most scenarios). But what 
> counters, and how to analyze those counters?
>
>
>
> Servers are Windows 2003.
>
>
>
> Thanks.
>
>
>
>
>
> Mark Reimer, A+, MCSA
>
> Servers & Networking Admin
>
> Prairie Bible Institute
>
> Box 4000
&

Re: IOPS's calculations

[Webster]

One of my first Exchange migrations was for an accounting firm whose
Exchange 2000 server had an average DQL of * (Do you remember that one
MBS?).  I was able to convince them to get all new servers and upgrade
their AD and Exchange.  Of course, the fact it took hours for e-mail to be
sent and received helped the financing of the upgrades.


Carl Webster
Consultant and Citrix Technology Professional
http://www.CarlWebster.com <http://www.carlwebster.com/>






On 2/7/12 9:19 AM, "David Lum"  wrote:

>You mean a disk queue length of 5 on  two-spindle RAID1 for more than 5
>minutes is bad? LOL. I have a client that is constantly HDD-bound (I've
>seen queue lengths of 15 for over 10 mins at a time - and they're not out
>or RAM either), running SBS2K3 on dual SATA RAID1 volumes (the OS,
>Exchange and SQL are on the same volume though - long story)...17 users,
>most of them use a SQL, all of course use Exchange. As a general rule, I
>don't tell people that they'll see _significant_ performance improvements
>regardless of what kind of upgrade they are getting be it GB switches,
>SSD drives, etc. 
>
>This client I _have_ told them they would see significant increase on
>their SQL-based app when they get a new server since it'll be 15K SAS
>drives and the SQL will be on a separate volume than Exchange.
>
>Dave
>
>-Original Message-
>From: Michael B. Smith [mailto:mich...@smithcons.com]
>Sent: Tuesday, February 07, 2012 8:26 AM
>To: NT System Admin Issues
>Subject: RE: IOPS's calculations
>
>I'm not a SAN expert. But for typical RAID subsystems, I don't want the
>physical queue to exceed the number of disks in the array. If it does,
>then I've got excessive queuing and degraded performance.
>
>I don't see how it would be different for a SAN, but I dunno.
>
>Regards,
>
>Michael B. Smith
>Consultant and Exchange MVP
>http://TheEssentialExchange.com
>
>
>-----Original Message-
>From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk]
>Sent: Tuesday, February 07, 2012 10:40 AM
>To: NT System Admin Issues
>Subject: RE: IOPS's calculations
>
>Most guides I've read suggest if the LUN has 10 physical disks, you don't
>want the queue to exceed around 20, or if you have 5 disks a queue of 10
>and so on.
>
>-Original Message-
>From: Michael B. Smith [mailto:mich...@smithcons.com]
>Sent: 07 February 2012 15:06
>To: NT System Admin Issues
>Subject: RE: IOPS's calculations
>
>Where do you get "x 2" ? I was with you - until that.
>
>Regards,
>
>Michael B. Smith
>Consultant and Exchange MVP
>http://TheEssentialExchange.com
>
>
>-Original Message-
>From: Paul Hutchings [mailto:paul.hutchi...@mira.co.uk]
>Sent: Tuesday, February 07, 2012 8:56 AM
>To: NT System Admin Issues
>Subject: RE: IOPS's calculations
>
>As a rule of thumb queue length shouldn't exceed the physical number of
>disks in the array that the LUN is on x 2.
>
>-Original Message-
>From: Kurt Buff [mailto:kurt.b...@gmail.com]
>Sent: 07 February 2012 13:50
>To: NT System Admin Issues
>Subject: Re: IOPS's calculations
>
>So, to which counters should I be paying attention in such a situation,
>or what should be the difference in interpretation?
>
>I've got a file server that's being extremely slow to back up, though
>daily performance is adequate.
>
>I'm seeing disk queue length hit as high as 37, with 5 LUNS for the
>machine.
>
>Kurt
>
>On Mon, Feb 6, 2012 at 21:32, Brian Desmond 
>wrote:
>> Those perf counters can be a bit misleading when you¹re looking at a
>> SAN on the backend, though.
>>
>>
>>
>> Thanks,
>>
>> Brian Desmond
>>
>> br...@briandesmond.com
>>
>>
>>
>> w ­ 312.625.1438 | c   ­ 312.731.3132
>>
>>
>>
>> From: Michael B. Smith [mailto:mich...@smithcons.com]
>> Sent: Monday, February 06, 2012 3:32 PM
>> To: NT System Admin Issues
>> Subject: RE: IOPS's calculations
>>
>>
>>
>> Disk Reads per second
>>
>> Disk Writes per second
>>
>> Average Disk Queue Length
>>
>>
>>
>> I¹d track both logical disk and physical disk.
>>
>>
>>
>> Regards,
>>
>>
>>
>> Michael B. Smith
>>
>> Consultant and Exchange MVP
>>
>> http://TheEssentialExchange.com
>>
>>
>>
>> From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
>> Sent: Monday, February 06, 2012 3:56 PM
>> To: NT System Admin Issues
>> Subject: IOPS's calculations
>>
>>

RE: IOPS's calculations

[Reimer, Mark]

Thanks for all the ideas, helps, etc.

Mark

From: Miller Bonnie L. [mailto:mille...@mukilteo.wednet.edu]
Sent: Tuesday, February 07, 2012 7:00 AM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

When we were planning for our SAN and VM conversion/migration, the Microsoft 
engineer we worked with had us collect information on our servers about usage 
using the MAPs tool.  Looks like it's still around-not sure if it would do what 
you need:

http://www.microsoft.com/download/en/details.aspx?id=7826

http://technet.microsoft.com/en-us/library/bb977556.aspx

If you are a Dell shop, their new dpack tool is nice too, but was still in beta 
when we used it a few weeks ago-not sure if they've released yet.  If not, 
you'll have to work with your Dell engineer to get the reports generated that 
you would need.

-Bonnie


From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
Sent: Monday, February 06, 2012 2:56 PM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

The question is: I want to know what my different servers (no san, each with 
their own direct attached disks storage) is using (not what they are capable 
of, but what they are actually using/doing).

Sorry if I was unclear to begin with.

Mark

From: Brian Desmond [mailto:br...@briandesmond.com]
Sent: Monday, February 06, 2012 2:55 PM
To: NT System Admin Issues
Subject: RE: IOPS's calculations

Your SAN should be able to produce these numbers.

Thanks,
Brian Desmond
br...@briandesmond.com<mailto:br...@briandesmond.com>

w - 312.625.1438 | c   - 312.731.3132

From: Reimer, Mark [mailto:mark.rei...@prairie.edu]
Sent: Monday, February 06, 2012 2:56 PM
To: NT System Admin Issues
Subject: IOPS's calculations

Hi folks,

Thanks for all your help in the past.

Looking at setting up a SAN. From my research, I think one thing to be aware of 
is current IOPS (disk). There are a number of sites that will help you 
determine IOPS based on what hard drives (and RAID configuration). My question 
is: Many of my current servers are light use. The IOPS that these servers are 
capable of is much greater than what is actually being used.

So, in order to more properly size the SAN, is there a way to determine working 
IOPS? That is, what is actually being used? I assume Perfmon would help, and 
will need to log over a period of time (I think a week would be about right, to 
catch most scenarios). But what counters, and how to analyze those counters?

Servers are Windows 2003.

Thanks.


Mark Reimer, A+, MCSA
Servers & Networking Admin
Prairie Bible Institute
Box 4000
Three Hills, AB  T0M-2N0
Canada
Tel: 403-443-5511, Ext. 3476
Fax: 403-443-5540
Email: mark.rei...@prairie.edu<mailto:mark.rei...@prairie.edu>
www.prairie.edu<http://www.prairie.edu/>



~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to 
listmana...@lyris.sunbeltsoftware.com<mailto:listmana...@lyris.sunbeltsoftware.com>
with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to 
listmana...@lyris.sunbeltsoftware.com<mailto:listmana...@lyris.sunbeltsoftware.com>
with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to 
listmana...@lyris.sunbeltsoftware.com<mailto:listmana...@lyris.sunbeltsoftware.com>
with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to 
listmana...@lyris.sunbeltsoftware.com<mailto:listmana...@lyris.sunbeltsoftware.com>
with the body: unsubscribe ntsysadmin

~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/>  ~

---
To manage subscriptions click here: 
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to listmana...@lyris.sunbeltsoftware.com
with the body: unsubscribe ntsysadmin