Tuning RMAN backup and recovery 2007-12-02 - By Mark Brinsmead
Back
Thank you, Ranko.
Of course, I was simplifying for the purpose of explanation.
As it happens, the platters all spin synchronously, and -- as you point out
yourself -- the heads all move synchronously. That there are multiples of
each is actually completely irrelevant with respect to understanding basic
disk drive physics, or the nature of "I/O contention". In terms of
"geometry", the disk effectively still *logically *has one head and one
platter. The actual number of heads and platters generally affects only one
thing: transfer rate. And transfer rate itself is almost meaningless in the
context of single-block random reads -- at least as long as
(average-seek-time + rotational-latency) exceeds single block transfer time
by orders of magnitude.
When I referred to disks with "multiple heads" no longer existing, I was
actually referring to "multiple heads *per platter*". Such things *used* to
exist (N independent heads per platter increases random I/Os per second by a
factor of *at least* N, and with a good scheduling algorithm, much better
than that) but I have not seen such a device in a very long time.
The references you have linked to do look quite good. I have not read them
in detail, but these do look like good resources for somebody who wants to
better understand how disk drives work. And a good basic understanding of
disk drive behaviour is very important indeed to a DBA trying to tune I/O
performance.
On Dec 2, 2007 7:03 AM, Ranko Mosic <ranko.mosic@(protected)> wrote:
> <It has a spinning platter, and a (one!) moving arm.>
> Disk has more than one platter.
> http://www.storagereview.com/guide2000/ref/hdd/op/index.html
> http://www.storagereview.com/guide2000/ref/hdd/op/act.html
> http://www.storagereview.com/guide2000/ref/hdd/op/over.html
> Each platter has two heads, one on the top of the platter and one on
> the bottom, so a hard disk with three platters (normally) has six
> surfaces and six total heads
>
> This means that when the actuator moves, all of the heads move
> together in a synchronized fashion. Heads cannot be individually sent
> to different track numbers
>
> On 11/28/07, Mark Brinsmead <pythianbrinsmead@(protected)> wrote:
> ...
> >
> > Don, to better understand the issue of I/O contention, remember how a
> > disk works. It has a spinning platter, and a (one!) moving arm. (Yes,
> > multi-actuator disk drives exist. But I haven't actually seen one for
> > decades; they are too costly to manufacture and most IT managers are so
> > fixated on metrics like $/GB that foolish matters like "throughput" and
> > response time are irrelevant. At least until well after the purchasing
> > decision has been made.)
> >
> > To read a given block of data, the disk drive need to move the arm to
> the
> > right track, and then wait for the required data to rotate beneath the
> head.
> > Sometimes it is a large movement ("seek"), and sometimes it is small.
> > Sometimes, the required data comes up right under the head, others you
> need
> > to wait for a full rotation.
> >
> > Simple first-year college math (which I confess to having mostly
> > forgotten nearly 20 years ago) shows pretty easily that for random I/Os,
> you
> > will need -- on average -- to move the arm half way across the disk, and
> > spin the platter for one half of a rotation. Once the required
> datablock is
> > beneath the read head, the data is read; usually in much less than a
> > millisecond.
> ... <http://www.pythian.com/blogs>
>
>
> --
> Regards,
> Ranko Mosic
> Consultant Senior Oracle DBA
> B. Eng, Oracle 10g, 9i Certified Database Professional
> Phone: 416-450-2785
> email: mosicr@(protected)
>
> http://ca.geocities.com/mosicr@(protected)
/ContractSeniorOracleDBARankoMosicMain.html
>
--
Cheers,
-- Mark Brinsmead
Senior DBA,
The Pythian Group
http://www.pythian.com/blogs
Thank you, Ranko.<br><br>Of course, I was simplifying for the purpose of
explanation.<br><br>As it happens, the platters all spin synchronously, and --
as you point out yourself -- the heads all move synchronously. That there
are multiples of each is actually completely irrelevant with respect to
understanding basic disk drive physics, or the nature of "I/O contention
". In terms of "geometry", the disk effectively still
<i>logically </i>has one head and one platter. The actual number of heads
and platters generally affects only one thing: transfer rate. And
transfer rate itself is almost meaningless in the context of single-block
random reads -- at least as long as (average-seek-time + rotational-latency)
exceeds single block transfer time by orders of magnitude.
<br><br>When I referred to disks with "multiple heads" no longer
existing, I was actually referring to "multiple heads <b>per platter</b>
". Such things <i>used</i> to exist (N independent heads per platter
increases random I/Os per second by a factor of
<i>at least</i> N, and with a good scheduling algorithm, much better than that)
but I have not seen such a device in a very long time.<br><br>The references
you have linked to do look quite good. I have not read them in detail,
but these do look like good resources for somebody who wants to better
understand how disk drives work. And a good basic understanding of disk
drive behaviour is very important indeed to a DBA trying to tune I/O
performance.
<br><br><div class="gmail_quote">On Dec 2, 2007 7:03 AM, Ranko Mosic <<a
href="mailto:ranko.mosic@(protected)">ranko.mosic@(protected)</a>> wrote:<br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204)
; margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div class="Ih2E3d"> <It has a spinning platter, and a (one!) moving
arm.><br></div>Disk has more than one platter.<br><a href="http://www
.storagereview.com/guide2000/ref/hdd/op/index.html" target="_blank">http://www
.storagereview.com/guide2000/ref/hdd/op/index.html
</a><br><a href="http://www.storagereview.com/guide2000/ref/hdd/op/act.html"
target="_blank">http://www.storagereview.com/guide2000/ref/hdd/op/act.html</a>
<br><a href="http://www.storagereview.com/guide2000/ref/hdd/op/over.html" target
="_blank">
http://www.storagereview.com/guide2000/ref/hdd/op/over.html</a><br> Each
platter has two heads, one on the top of the platter and one on<br>the bottom,
so a hard disk with three platters (normally) has six<br>surfaces and six total
heads
<br><br>This means that when the actuator moves, all of the heads move<br
>together in a synchronized fashion. Heads cannot be individually sent<br>to
different track numbers<br><div><div></div><div class="Wj3C7c"><br>On 11/28/07,
Mark Brinsmead <
<a href="mailto:pythianbrinsmead@(protected)">pythianbrinsmead@(protected)</a>>
wrote:<br>...<br>><br>> Don, to better understand the issue
of I/O contention, remember how a<br>> disk works. It has a spinning
platter, and a (one!) moving arm. (Yes,
<br>> multi-actuator disk drives exist. But I haven't actually
seen one for<br>> decades; they are too costly to manufacture and most IT
managers are so<br>> fixated on metrics like $/GB that foolish matters like
"throughput" and
<br>> response time are irrelevant. At least until well after the
purchasing<br>> decision has been made.)<br>><br>> To
read a given block of data, the disk drive need to move the arm to the<br>>
right track, and then wait for the required data to rotate beneath the head.
<br>> Sometimes it is a large movement ("seek"), and
sometimes it is small.<br>> Sometimes, the required data comes up right
under the head, others you need<br>> to wait for a full rotation.<br>><br
>
> Simple first-year college math (which I confess to having
mostly<br>> forgotten nearly 20 years ago) shows pretty easily that for
random I/Os, you<br>> will need -- on average -- to move the arm half way
across the disk, and
<br>> spin the platter for one half of a rotation. Once the required
datablock is<br>> beneath the read head, the data is read; usually in much
less than a<br>> millisecond.<br>...<a href="http://www.pythian.com/blogs"
target="_blank">
</a><br><br><br></div></div><font color="#888888">--<br>Regards,<br>Ranko Mosic
<br>Consultant Senior Oracle DBA<br>B. Eng, Oracle 10g, 9i Certified Database
Professional<br>Phone: 416-450-2785<br>email: <a href="mailto:mosicr@(protected)
">
mosicr@(protected)</a><br><a href="http://ca.geocities.com/mosicr@(protected)
/ContractSeniorOracleDBARankoMosicMain.html" target="_blank">http://ca.geocities
.com/mosicr@(protected)/ContractSeniorOracleDBARankoMosicMain.html</a>
<br></font></blockquote></div><br><br clear="all"><br>-- <br>Cheers,<br>-- Mark
Brinsmead<br> Senior DBA,<br> The Pythian Group<br> <a
href="http://www.pythian.com/blogs">http://www.pythian.com/blogs</a>
|
|
