On Wed, 24 Jan 2001, Chuck Cranor wrote:

> >possibily of readahead) methods the designer(s) found?
> 
> the advantage is that you can always do big cluster single i/o
> operation pageouts (provided the swap disk isn't too fragmented).   
> that makes recovery from heavy anon memory usage pretty fast (much
> faster than the old VM).
> 
> the disadvantage is that to do readahead pagein you will have
> to do multiple I/O operations since the data will not be contig
> on the disk.

That means big cluster pageout has the price of not always being able to
do contiguous swapin readahead.

I'm considering doing the same for Linux 2.5 swap scheme, though I'm not
sure how that will affect the system in practice. 

Thanks