Re: [PATCH 2.6.14-rc2-mm2] core remove PageReserved

[Nick Piggin <nickpiggin@yahoo.com.au>]

Alan Cox wrote:
> On Maw, 2005-10-11 at 19:00 +1000, Nick Piggin wrote:
>
> > A last caveat: the ZERO_PAGE is now refcounted and managed with rmap
> > (and thus mapcounted and count towards shared rss).
>
>
> 32000 processes each with 2G mapped as zero pages appears to allow the
> refcount to overflow ?

That's right (though I count only 8192 required with 4K page size) -
close to impossible on 32-bit architectures, though not so the 64-bit
ones, which still use 32-bits for count and mapcount.

I was a bit worried about this too, but Hugh didn't think it was a
really big a deal - I guess because the real solution for the refcount
overflow on 64-bit is to expand the refcount type.

Note also that we can exclude ZERO_PAGE from being refcounted, which
may be desirable for a scalability perspective on big NUMA machines.

The aim with this patch is to provide a patch which is as simple as
possible in order to get the mechanism right. But you raise a valid
concern and we do need to discuss these peripheral issues and sort
them out before it gets merged upstream.

Thanks,
Nick

--
SUSE Labs, Novell Inc.

Send instant messages to your online friends http://au.messenger.yahoo.com 
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/