On Thu, Jan 25, 2001 at 04:22:13AM +0000, Charles M. Hannum wrote:

 > Looking more closely at the way we handle MADV_SEQUENTIAL and
 > MADV_DONTNEED, it seems to me that this is actually *wrong*.  The
 > current implementation works by explicitly deactivating the pages.
 > While this gives a slight paging disadvantage to those pages, it also
 > actively penalizes other processes using the same data.

Using the patch I posted, uvm_pagedeactivate() does not require or
imply any penalty.  If another process is using the data, then the
referenced bit will get set, and it will get reactivated.

 > It seems to me that it should actually:
 > 
 > * Rather than deactivating the pages, remove them from the pmap
 >   instead, thus lowering their reference counts.

What reference count?  On the page?  Pages don't have a reference
count.

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