Re: New Feature Idea: Compress swap file
Ard van Breemen (ard@cstmel.hobby.nl)
Mon, 23 Feb 1998 10:08:13 +0100 (MET)
On Sun, 22 Feb 1998, Emil Briggs wrote:
> > This is an interesting concept, but I believe that a major factor in
> >swapping speed is hard drive seek times. I believe that the main delay in
> >writing data to disk is seek delay, and writing 1K instead of 4K won't affect
> >this.
> I don't know for certain but it sounds reasonable. Which brings to mind
> another question -- do the buffer flushing routines consider hard disk
> geometry when deciding which dirty buffers to write to disk and in what
> order to write them? (I'm not referring to swap specifically here).
What hard disk geometry is that? Hard disks are accessed using logical
block numbers. The so called heads,cylinders and sectors in bios setups
are just a patch on a patch on a patch on a very bad design. Modern
hard-disks usually have multiple zones in which the sectors/cylinder vary
to keep the recording density more or less the same. Furthermore bad
blocks or tracks are usually handled by the harddisk. If you want to count
in geometry, you first need a way to retrieve the information, and second
need a big (probably harddisk vendor specific) translation scheme...
And this all because modern harddisks usually do this for themselves
(provided you have > 32k buffer on the harddisk...).
--
dec1: 9:54am up 7 days, 14:30, 6 users, load average: 0.61, 0.37, 0.20
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu