> Also I am not sure which API should be used:
I'd go for madvise() -- it's more widespread than disclaim(),
even if details may differ slightly between implementations.
Neither are in the SUS v2 spec, although I don't know about v3.
> (1) madvise is known on many systems, but they do not agree about the
> meaning of MADV_DONTNEED. Most of them only use it as hint to page
> this area out. Perhaps a flag MADV_FREE or MADV_DISCLAIM would be
> better.
Why is this a problem? Whether the pages ares freed immediately
or merely marked to be freed at a later time should be of no
relevance to the application, only to the OS. Or are you relying
on the zero-fill-on-demand behaviour? What do you do on other
OSes that don't support this (e.g., Solaris)?
Tet
-- You have moved the mouse. NT must be restarted for the changes to take effect. -------------------------+-------------+-------------------------------------- tethys@it.newsint.co.uk | Micro$oft | Linux; the choice of a GNU generation tet@astradyne.co.uk | Just say no | See http://www.linux.org for details.- 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/