On Tue, 2002-10-22 at 18:45, Benjamin LaHaise wrote:
> On Tue, Oct 22, 2002 at 10:36:40AM -0700, Martin J. Bligh wrote:
> > Bear in mind that large pages are neither swap backed or file backed
> > (vetoed by Linus), for starters. There are other large app problem scenarios
> > apart from Oracle ;-)
>
> I think the fact that large page support doesn't support mmap for users
> that need it is utterly appauling; there are numerous places where it is
> needed. The requirement for root-only access makes it useless for most
> people, especially in HPC environments where it is most needed as such
> machines are usually shared and accounts are non-priveledged.
I was very suprised the large page crap went in, in the form it
currently exists. Merging pages makes sense, spotting and doing 4Mb page
allocations kernel side makes sense. The rest is very questionable
-
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/
This archive was generated by hypermail 2b29 : Wed Oct 23 2002 - 22:00:59 EST