lkml.org 
[lkml]   [1998]   [Dec]   [19]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: swap cache
Date
> 
> On Sat, 19 Dec 1998, Prasun Kapoor wrote:
>
> > > Linux VM, but we don't need that functionality: in Linux we have always
> > > swapped out ptes on a per-page-table basis, not on a per-physical-page
> > > basis. We *DO* swap processes out independently.
> >
> > I dont think I understand. The whole idea of doing it globally is
> > to do some kind of LRU on a global scale and swap out pages based
> > on that.
>
> This terribly fragments swap space -- you seem to be forgetting
> that we also need to swap things back _in_ and that is most
> efficient when the process' pages are contiguous on disk.
>
> LRU is just a good guess, the method Linux uses might be a bit
> worse on swap-out, but since we do less disk _seek_ I/O we come
> out slightly ahead of the normal way...
>
> For Linux 2.3 we are planning several major enhancements to
> this scheme though (much better I/O clustering and swap read-
> ahead/behind and several other goodies).

read ahead/behind i assume refers to clustering for I/O.

Also i was thinking about one of the other suggestions that was made regarding
the compression of a page(s) to a portion of the RAM, and uncompress it as part
of the swap back in. Although the compression/un-compression has to be measured
against the I/O cost. This will also involve looking at the available RAM. On a
small system with less RAM, this may not be a wise-thing to do.

It would be intersting to know if any1 has implemented such a thing and what's
the cost involved vis-a-vis available RAM, i/o etc.

thanks,
Rama.

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2005-03-22 13:46    [from the cache]
©2003-2011 Jasper Spaans. Advertise on this site