Mladen,
I agree you can measure how many IOs are being done and how many a disk sub-
system, such as those provided by EMC, can perform and still give good
performance. What I meant is that it is hard and some would say impossible to
estimate how many IOs per sec a new application will do. A
:Re: FW: Disk capacity planning
Mladen,
I agree you can measure how many IOs are being done and how many a disk sub-
system, such as those provided by EMC, can perform and still give good
performance. What I meant is that it is hard and some would say impossible to
estimate how many IOs per sec
PROTECTED]
Sent by: [EMAIL PROTECTED]
01/21/2004 01:34 AM
Please respond to ORACLE-L
To: Multiple recipients of list ORACLE-L
[EMAIL PROTECTED]
cc:
Subject:Re: FW: Disk capacity planning
Mladen,
I agree you can measure how many IOs are being done and how many a
disk
Cary,
Good answer. The problem is most people concentrate on bytes because it's
relatively easy and everyone understands it. IOs per sec is much harder to
calculate for a new system and hence it's not normally done.
Cheers,
Chris Dunscombe
Quoting Cary Millsap [EMAIL PROTECTED]:
I don't
Of [EMAIL PROTECTED]
Sent: 20 January 2004 09:19
To: Multiple recipients of list ORACLE-L
Subject: Re: FW: Disk capacity planning
Cary,
Good answer. The problem is most people concentrate on bytes
because it's
relatively easy and everyone understands it. IOs per sec is
much harder
Oh, but it is done, you only need to ask. EMC routinely measures how many I/Os
per second can they perform and they even have tools to measure it. Speaking of
monitoring I/O, there used to be an old OS, which is mostly dead today and it used
to have command monitor io/item=queue which would show
To: Multiple recipients of list ORACLE-L
Subject: Re: FW: Disk capacity planning
Cary,
Good answer. The problem is most people concentrate on bytes
because it's
relatively easy and everyone understands it. IOs per sec is
much harder to
calculate for a new system and hence it's
Chris,
Thanks.
When people do what you say, it's kind of like what would have happened
if NASA had used the following assumption throughout the Apollo project:
Assume adequate quantities of breathable air...
It would have made the planning phase much simpler, but it would have
been a touch more
I found myself working with some larger databases in the 500-800 GB range that also
spawn into multiple test databases.
I take a df -k or bdf and bring that into excel. Then I take a query on all
autoextend and break that out by disk.
then I put that all together and tell what's left on disks.
--- Niall Litchfield [EMAIL PROTECTED]
wrote:
Hi
The bad news is that I don't believe that
calculating IO/Sec *can* be done
for a *new* system. At least I'd like to see how it
is done. I'm willing to
bet that any formula for doing it will include (x%)
for 'overhead', which
actually means
I dont think this one made it
through on my first attempt.
Cary Millsap
Hotsos Enterprises, Ltd.
http://www.hotsos.com
Nullius in verba
Upcoming events:
- Performance
Diagnosis101: 1/27 Atlanta
- SQL Optimization101: 2/16 Dallas
- Hotsos Symposium 2004:
March 710 Dallas
- Visit
11 matches
Mail list logo