Re: [Lse-tech] Re: [PATCH] [0/6] HUGETLB memory commitment

From: Suparna Bhattacharya
Date: Fri Mar 26 2004 - 06:46:13 EST

On Fri, Mar 26, 2004 at 02:39:09PM +1100, Keith Owens wrote:
> On Fri, 26 Mar 2004 14:28:26 +0530,
> Suparna Bhattacharya <suparna@xxxxxxxxxx> wrote:
> >On Thu, Mar 25, 2004 at 04:22:32PM -0800, Andrew Morton wrote:
> >> Keith Owens <kaos@xxxxxxx> wrote:
> >> >
> >> > FWIW, lkcd (crash dump) treats hugetlb pages as normal kernel pages and
> >> > dumps them, which is pointless and wastes a lot of time. To avoid
> >> > dumping these pages in lkcd, I had to add a PG_hugetlb flag. lkcd runs
> >
> >This should already be fixed in recent versions of lkcd. It uses a
> >little bit of trickery to avoid an extra page flag -- hugetlb pages are
> >detected as "in use" as well as reserved, unlike other reserved pages
> >which helps identify them.
> Are you sure that this works for hugetlb pages that have been
> preallocated but not yet mapped? AFAICT the hugetlb pages start off as
> reserved with a zero usecount.

I just realised that hugetlb pages are no longer marked as reserved in
the current trees, and since they are allocated as compound pages
they would show up as being in use and not LRU. So, we do have a problem,
without PG_hugetlb.


> -------------------------------------------------------
> This SF.Net email is sponsored by: IBM Linux Tutorials
> Free Linux tutorial presented by Daniel Robbins, President and CEO of
> GenToo technologies. Learn everything from fundamentals to system
> administration.
> _______________________________________________
> Lse-tech mailing list
> Lse-tech@xxxxxxxxxxxxxxxxxxxxx

Suparna Bhattacharya (suparna@xxxxxxxxxx)
Linux Technology Center
IBM Software Lab, India

To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at
Please read the FAQ at