Re: [PATCH 12/31] mm, vmscan: make shrink_node decisions more node-centric

2016-07-05 Thread Mel Gorman
On Tue, Jul 05, 2016 at 03:24:36PM +0900, Minchan Kim wrote: > > diff --git a/mm/vmscan.c b/mm/vmscan.c > > index 2f898ba2ee2e..b8e0f76b6e00 100644 > > --- a/mm/vmscan.c > > +++ b/mm/vmscan.c > > @@ -2226,10 +2226,11 @@ static inline void init_tlb_ubc(void) > > /* > > * This is a basic per-zone

Re: [PATCH 12/31] mm, vmscan: make shrink_node decisions more node-centric

2016-07-04 Thread Minchan Kim
On Fri, Jul 01, 2016 at 09:01:20PM +0100, Mel Gorman wrote: > Earlier patches focused on having direct reclaim and kswapd use data that > is node-centric for reclaiming but shrink_node() itself still uses too > much zone information. This patch removes unnecessary zone-based > information with the

[PATCH 12/31] mm, vmscan: make shrink_node decisions more node-centric

2016-07-01 Thread Mel Gorman
Earlier patches focused on having direct reclaim and kswapd use data that is node-centric for reclaiming but shrink_node() itself still uses too much zone information. This patch removes unnecessary zone-based information with the most important decision being whether to continue reclaim or not.

[PATCH 12/31] mm, vmscan: make shrink_node decisions more node-centric

2016-07-01 Thread Mel Gorman
Earlier patches focused on having direct reclaim and kswapd use data that is node-centric for reclaiming but shrink_node() itself still uses too much zone information. This patch removes unnecessary zone-based information with the most important decision being whether to continue reclaim or not.