On Monday 04 May 2009, David Rientjes wrote:
> On Mon, 4 May 2009, Rafael J. Wysocki wrote:
>
> > > > Index: linux-2.6/mm/page_alloc.c
> > > > ===================================================================
> > > > --- linux-2.6.orig/mm/page_alloc.c
> > > > +++ linux-2.6/mm/page_alloc.c
> > > > @@ -1620,7 +1620,8 @@ nofail_alloc:
> > > > }
> > > >
> > > > /* The OOM killer will not help higher order allocs so fail */
> > > > - if (order > PAGE_ALLOC_COSTLY_ORDER) {
> > > > + if (order > PAGE_ALLOC_COSTLY_ORDER ||
> > > > + (gfp_mask & __GFP_NO_OOM_KILL)) {
> > > > clear_zonelist_oom(zonelist, gfp_mask);
> > > > goto nopage;
> > > > }
> > >
> > > This is inconsistent because __GFP_NO_OOM_KILL now implies __GFP_NORETRY
> > > (the "goto nopage" above), but only for allocations with __GFP_FS set and
> > > __GFP_NORETRY clear.
> >
> > Well, what would you suggest?
> >
>
> A couple things:
>
> - rebase this on mmotm so that it doesn't conflict with Mel Gorman's page
> allocator speedup changes, and
I'm going to rebase the patchset on top of linux-next eventually.
> - avoid the final call to get_page_from_freelist() for
> !(gfp_mask & __GFP_NO_OOM_KILL) by adding a check for it alongside
> (gfp_mask & __GFP_FS) and !(gfp_mask & __GFP_NORETRY) because it should
> really only catch parallel oom killings which won't happen in your
> suspend case since it uses ALLOC_WMARK_HIGH.
>
> The latter is important to avoid unnecessary dependencies among low-level
> __GFP_* flags (although all __GFP_NO_OOM_KILL allocations should really
> all be passing __GFP_NORETRY too to avoid relying too heavily on direct
> reclaim).
OK, thanks.
Something like this?
---
include/linux/gfp.h | 3 ++-
mm/page_alloc.c | 3 ++-
2 files changed, 4 insertions(+), 2 deletions(-)
Index: linux-2.6/mm/page_alloc.c
===================================================================
--- linux-2.6.orig/mm/page_alloc.c
+++ linux-2.6/mm/page_alloc.c
@@ -1599,7 +1599,8 @@ nofail_alloc:
zonelist, high_zoneidx, alloc_flags);
if (page)
goto got_pg;
- } else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
+ } else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)
+ && !(gfp_mask & __GFP_NO_OOM_KILL)) {
if (!try_set_zone_oom(zonelist, gfp_mask)) {
schedule_timeout_uninterruptible(1);
goto restart;
Index: linux-2.6/include/linux/gfp.h
===================================================================
--- linux-2.6.orig/include/linux/gfp.h
+++ linux-2.6/include/linux/gfp.h
@@ -51,8 +51,9 @@ struct vm_area_struct;
#define __GFP_THISNODE ((__force gfp_t)0x40000u)/* No fallback, no policies */
#define __GFP_RECLAIMABLE ((__force gfp_t)0x80000u) /* Page is reclaimable */
#define __GFP_MOVABLE ((__force gfp_t)0x100000u) /* Page is movable */
+#define __GFP_NO_OOM_KILL ((__force gfp_t)0x200000u) /* Don't invoke out_of_memory() */
-#define __GFP_BITS_SHIFT 21 /* Room for 21 __GFP_FOO bits */
+#define __GFP_BITS_SHIFT 22 /* Number of __GFP_FOO bits */
#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
/* This equals 0, but use constants in case they ever change */
--
To unsubscribe from this list: send the line "unsubscribe kernel-testers" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
