Re: Index Scans become Seq Scans after VACUUM ANALYSE

On Thu, 18 Apr 2002, mlw wrote:

> The days when "head movement" is relevant are long over. Not a single drive
> sold today, or in the last 5 years, is a simple spindle/head system. ....
> The assumption that sequentially reading a file from a modern disk drive means
> that the head will move less often is largely bogus.

Well, oddly enough, even with the head moving just as often, sequential
I/O has always been much faster than random I/O on every drive I've
owned in the past five years. So I guess I/O speed doesn't have a lot
to do with head movement or something.

Some of my drives have started to "chatter" quite noisily during random
I/O, too. I thought that this was due to the head movement, but I guess
not, since they're quite silent during sequential I/O.

BTW, what sort of benchmarking did you do to determine that the
head movement is similar during random and sequential I/O on drives
in the last five years or so?

cjs
-- 
Curt Sampson  <cjs@cynic.net>   +81 90 7737 2974   http://www.netbsd.org
    Don't you know, in this new Dark Age, we're all light.  --XTC