Maybe it's possible to have a normal VM policy in cases where such a brain-dead
allocation is not requested and revert to something sub-sub-optimal in
case where the user decided to go for such windows-able hardware.
> Anything that requires more that 1 PAGE of physical memory at a time on
> running systems is a very bad thing in my opinion. The PAGE is the only
Given the time that can be spent in TLB reloading with some applications,
many Unixes on RISC machines nowadays try to lump virtually-contiguous
pages into physically-contiguous pages and then use bigger-pages for those
blocks (on architectures that allow a finer choice than the x86's 4KB or 4MB).
So it seems that some notion of blocks-of-pages might be useful.
Stefan
-
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/