Les Mikesell wrote:
> All you have to do is look at the seek time on a disk drive
> compared to any other computer operation to see what the
> effect will be if a file that is normally read sequentially
> is broken into non-contiguous chunks.
This is one of my favourite hobby-horses, especially when I'm trying to
explain why we need multiple disk drives for performance...
But the manufacturer's quoted seek time is for random access. If two
file fragments are "suitably close" on a disk drive, then the seek time
between fragments will be significantly less.
My understanding is precisely that ext2 and ext3 locate files in such a
way on disk as to minimise the seek time.
Incidentally, my e-mails live in maildir mailboxes: one file per e-mail.
My Fedora List box gets rather large with time, and this makes it
somewhat slow to open (I keep all list e-mail, and archive it
eventually).
This is due to a very similar phenomenon: obviously, e-mails get written
to mailboxes as they arrive, and get located all around the hard disk.
So I have to wait for the hard drive to do a lot of seeks when I open
the mailbox. I find that copying a mailbox to a new location on the same
disk re-locates the e-mails so they are "suitably close". Seek time goes
right down, and the mail box opens a *lot* faster. I don't have any
figures to hand, but it feels like the mailbox opens in one fifth of the
time, maybe less.
Hope this helps,
James.
--
E-mail address: james | Q. "Why can't I print?"
@westexe.demon.co.uk | A. "Because you're not a printer."
| -- Stephen Judd
