PATCH fix distribution of bootmem huge pages
Against: 2.6.31-rc3
For stable, applicable back through 2.6.27
[A version of this patch has been added to the -mm tree. That patch
won't apply cleanly to mainline nor stable trees because of function
renaming. This one should.]
I noticed that alloc_bootmem_huge_page() will only advance to the
next node on failure to allocate a huge page. I asked about this
on linux-mm and linux-numa, cc'ing the usual huge page suspects.
Mel Gorman responded:
I strongly suspect that the same node being used until allocation
failure instead of round-robin is an oversight and not deliberate
at all. It appears to be a side-effect of a fix made way back in
commit 63b4613c3f0d4b724ba259dc6c201bb68b884e1a ["hugetlb: fix
hugepage allocation with memoryless nodes"]. Prior to that patch
it looked like allocations would always round-robin even when
allocation was successful.
Andy Whitcroft countered that the existing behavior looked like Andi
Kleen's original implementation and suggested that we ask him. We
did and Andy replied that his intention was to interleave the
allocations. So, ...
This patch moves the advance of the hstate next node from which to
allocate up before the test for success of the attempted allocation.
This will unconditionally advance the next node from which to alloc,
interleaving successful allocations over the nodes with sufficient
contiguous memory, and skipping over nodes that fail the huge page
allocation attempt.
Note that alloc_bootmem_huge_page() will only be called for huge pages
of order > MAX_ORDER.
Signed-off-by: Lee Schermerhorn <[email protected]>
mm/hugetlb.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
Index: linux-2.6.31-rc3-mmotm-090715-2057/mm/hugetlb.c
===================================================================
--- linux-2.6.31-rc3-mmotm-090715-2057.orig/mm/hugetlb.c 2009-07-17 11:30:20.000000000 -0400
+++ linux-2.6.31-rc3-mmotm-090715-2057/mm/hugetlb.c 2009-07-17 11:37:30.000000000 -0400
@@ -1010,6 +1010,7 @@ int __weak alloc_bootmem_huge_page(struc
NODE_DATA(h->hugetlb_next_nid),
huge_page_size(h), huge_page_size(h), 0);
+ hstate_next_node(h);
if (addr) {
/*
* Use the beginning of the huge page to store the
@@ -1019,7 +1020,6 @@ int __weak alloc_bootmem_huge_page(struc
m = addr;
goto found;
}
- hstate_next_node(h);
nr_nodes--;
}
return 0;
> Signed-off-by: Lee Schermerhorn <[email protected]>
Reviewed-by: Andi Kleen <[email protected]>
-Andi
--
[email protected] -- Speaking for myself only.
On Fri, Jul 17, 2009 at 03:49:14PM -0400, Lee Schermerhorn wrote:
> PATCH fix distribution of bootmem huge pages
>
> Against: 2.6.31-rc3
>
> For stable, applicable back through 2.6.27
>
> [A version of this patch has been added to the -mm tree. That patch
> won't apply cleanly to mainline nor stable trees because of function
> renaming. This one should.]
What is the git commit id of this patch that is in Linus's tree?
thanks,
greg k-h
On Thu, Sep 03, 2009 at 01:33:39PM -0700, Greg KH wrote:
> On Fri, Jul 17, 2009 at 03:49:14PM -0400, Lee Schermerhorn wrote:
> > PATCH fix distribution of bootmem huge pages
> >
> > Against: 2.6.31-rc3
> >
> > For stable, applicable back through 2.6.27
> >
> > [A version of this patch has been added to the -mm tree. That patch
> > won't apply cleanly to mainline nor stable trees because of function
> > renaming. This one should.]
>
> What is the git commit id of this patch that is in Linus's tree?
>
I can only find it in mmotm. It doesn't appear to have been merged to
mainline at all. Lee, what happened with this? Did it get held off until
post-2.6.31 for merging to mainline?
--
Mel Gorman
Part-time Phd Student Linux Technology Center
University of Limerick IBM Dublin Software Lab
On Tue, 2009-09-08 at 11:32 +0100, Mel Gorman wrote:
> On Thu, Sep 03, 2009 at 01:33:39PM -0700, Greg KH wrote:
> > On Fri, Jul 17, 2009 at 03:49:14PM -0400, Lee Schermerhorn wrote:
> > > PATCH fix distribution of bootmem huge pages
> > >
> > > Against: 2.6.31-rc3
> > >
> > > For stable, applicable back through 2.6.27
> > >
> > > [A version of this patch has been added to the -mm tree. That patch
> > > won't apply cleanly to mainline nor stable trees because of function
> > > renaming. This one should.]
> >
> > What is the git commit id of this patch that is in Linus's tree?
> >
>
> I can only find it in mmotm. It doesn't appear to have been merged to
> mainline at all. Lee, what happened with this? Did it get held off until
> post-2.6.31 for merging to mainline?
Mel:
This patch, along with the interleaving of freeing persistent huge pages
are still in mmotm, awaiting the merge window. I had sent out another
version suitable for mainline and stable--same patch with conflicts
resolved--but, apparently it didn't make mainline yet.
Lee
On Tue, 08 Sep 2009 10:13:35 -0400
Lee Schermerhorn <[email protected]> wrote:
> On Tue, 2009-09-08 at 11:32 +0100, Mel Gorman wrote:
> > On Thu, Sep 03, 2009 at 01:33:39PM -0700, Greg KH wrote:
> > > On Fri, Jul 17, 2009 at 03:49:14PM -0400, Lee Schermerhorn wrote:
> > > > PATCH fix distribution of bootmem huge pages
> > > >
> > > > Against: 2.6.31-rc3
> > > >
> > > > For stable, applicable back through 2.6.27
> > > >
> > > > [A version of this patch has been added to the -mm tree. That patch
> > > > won't apply cleanly to mainline nor stable trees because of function
> > > > renaming. This one should.]
> > >
> > > What is the git commit id of this patch that is in Linus's tree?
> > >
> >
> > I can only find it in mmotm. It doesn't appear to have been merged to
> > mainline at all. Lee, what happened with this? Did it get held off until
> > post-2.6.31 for merging to mainline?
>
> Mel:
>
> This patch, along with the interleaving of freeing persistent huge pages
> are still in mmotm, awaiting the merge window. I had sent out another
> version suitable for mainline and stable--same patch with conflicts
> resolved--but, apparently it didn't make mainline yet.
>
I queued the original patch for 2.6.31 and -stable.
For 2.6.32 I queued a patch which reverts this same patch to make way
for all the new stuff.
It would have been better had the 2.6.31 minipatch come out first!