Data Storage - disk bandwith decreasing?

This is Interesting: Free IT Magazines  
Home > Archive > Data Storage > June 2004 > disk bandwith decreasing?





You are viewing an archived Text-only version of the thread. To view this thread in it's original format and/or if you want to reply to this thread please [click here]

Author disk bandwith decreasing?
Stephane Guyetant

2004-06-08, 12:08 am

I read in a recent PhD dissertation: "Due to the higher complexity of
micro-actuation and track-tracing required during track and head
switches, increased disk storage density actually decreases the disk
bandwith."

Wow! My reference figure for that matter was that disk bandwith keeps
increasing at a 40% rate per year. But I've just checked last barracuda
drive: it has a sustained bandwidth of 58MB/s, not much more than last
year, huh?

Anyway I don't understand the argument about the complexity...
Paul Rubin

2004-06-08, 12:08 am

Stephane Guyetant <firstname.name@ir_nospam_isa.fr> writes:
> Anyway I don't understand the argument about the complexity...


I think the idea is that track density gets higher, you need more
complicated precision actuators to position the head on the track.
That means that track to track seek time increases. During seeks, no
data is getting transferred, so if you spend more time seeking,
bandwidth is lower.
VirtualSean

2004-06-09, 8:47 am

Stephane,

I am interested in reading the referenced paper, however, a Google search
produced this:

www.ece.northwestern.edu/~schiu/sd/OE.pdf

dead link.

Can you perhaps supply an active link to this paper?


Thanks.

--
VirtualSean

Stephane Guyetant <firstname.name@ir_nospam_isa.fr> wrote in message news:<ca1f0e$usf$1@amma.irisa.fr>...
> I read in a recent PhD dissertation: "Due to the higher complexity of
> micro-actuation and track-tracing required during track and head
> switches, increased disk storage density actually decreases the disk
> bandwith."
>
> Wow! My reference figure for that matter was that disk bandwith keeps
> increasing at a 40% rate per year. But I've just checked last barracuda
> drive: it has a sustained bandwidth of 58MB/s, not much more than last
> year, huh?
>
> Anyway I don't understand the argument about the complexity...

Stephane Guyetant

2004-06-09, 8:47 am

VirtualSean wrote:
> Stephane,
>
> I am interested in reading the referenced paper, however, a Google search
> produced this:
>
> www.ece.northwestern.edu/~schiu/sd/OE.pdf
>
> dead link.
>
> Can you perhaps supply an active link to this paper?


sure!

http://www.ece.northwestern.edu/~schiu/sd/nuphd.pdf

see p.14 for the quote.
[vbcol=seagreen]
>
> Thanks.
>
> --
> VirtualSean
>
> Stephane Guyetant <firstname.name@ir_nospam_isa.fr> wrote in message news:<ca1f0e$usf$1@amma.irisa.fr>...
>
VirtualSean

2004-06-09, 5:08 pm

Stephane,

Got it - thank you!


--
VirtualSean


Stephane Guyetant <firstname.name@ir_nospam_isa.fr> wrote in message news:<ca6f6h$7vq$1@amma.irisa.fr>...[vbcol=seagreen]
> VirtualSean wrote:
>
> sure!
>
> http://www.ece.northwestern.edu/~schiu/sd/nuphd.pdf
>
> see p.14 for the quote.
>
Sponsored Links






Free braindumps | Software forum | Database administration forum

Copyright 2003 - 2008 webservertalk.com