On Thu, Jan 25, 2001 at 05:49:57PM -0000, eeh@netbsd.org wrote:

 > 	In these cases, it appears that the data to be written backs up very
 > 	badly and causes process (e.g. the X server and my Emacs) to lose
 > 	pages.  Some sort of flow control is badly needed to repair this.
 > 
 > We should be able to fix that by puting UBC pages directly on to the
 > inactive list as soon as current UBC operation is complete.  As far
 > as I'm concerned there's no reason UBC pages should ever be `active'
 > unless they are mmapp()ed into some process' address space.

I agree completely.  And without unmapping the pages before they're
deactivated, this isn't even a very expensive thing to do.

However, still is the case that pages could be not cleaned quickly enough.
Maybe we need to have more aggressive cleaning of pages recently involved
in a UBC write operation?

-- 
        -- Jason R. Thorpe <thorpej@zembu.com>