On Thu, Jun 20, 2002 at 03:36:29PM +0200, Manuel Bouyer wrote:
> On Thu, Jun 20, 2002 at 08:35:50AM -0400, Aidan Cully wrote:
> > I'm starting to understand this a bit better...  Two things strike me
> > about this: 1) it's only a problem when the kernel allocates buffers
> > for its own internal use, during read()s and write()s, but not mmap().
> 
> mmap can probably trigger the problem as well. Anything that will create
> a large buffered write will.

If mmap can trigger the problem, can ordinary VM usage?  That is,
might it not also be a problem if an app needed to have a large set
paged out when loading another process?

--aidan