On Tue, May 10, 2011 at 1:21 PM, Mel Gorman [off-list ref] wrote:

It goes on. A number of filesystem and network paths are being hit
with high-order allocs. i915 was a red herring, it's present but not
in massive numbers. The filesystem, network and mempool allocations
are likely to be kicking kswapd awake frequently and hurting overall
system performance as a result.

I really would like to hear if the fix makes a big difference or
if we need to consider forcing SLUB high-order allocations bailing
at the first sign of trouble (e.g. by masking out __GFP_WAIT in
allocate_slab). Even with the fix applied, kswapd might be waking up
less but processes will still be getting stalled in direct compaction
and direct reclaim so it would still be jittery.

Yes, sounds reasonable to me.

                         Pekka

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>