Re: [PATCH 12/27] mm, vmscan: Make shrink_node decisions more node-centric

2016-06-22 Thread Vlastimil Babka
On 06/21/2016 04:15 PM, 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 most important decision

Re: [PATCH 12/27] mm, vmscan: Make shrink_node decisions more node-centric

2016-06-22 Thread Michal Hocko
On Tue 21-06-16 15:15:51, 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 most important d

[PATCH 12/27] mm, vmscan: Make shrink_node decisions more node-centric

2016-06-21 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. So

Re: [PATCH 12/27] mm, vmscan: Make shrink_node decisions more node-centric

2016-06-16 Thread Mel Gorman
On Thu, Jun 16, 2016 at 03:35:15PM +0200, Vlastimil Babka wrote: > On 06/09/2016 08:04 PM, 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 re

Re: [PATCH 12/27] mm, vmscan: Make shrink_node decisions more node-centric

2016-06-16 Thread Vlastimil Babka
On 06/09/2016 08:04 PM, 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 most important decision

[PATCH 12/27] mm, vmscan: Make shrink_node decisions more node-centric

2016-06-09 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. So

[PATCH 12/27] mm, vmscan: Make shrink_node decisions more node-centric

2016-04-15 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. So

[PATCH 12/27] mm, vmscan: Make shrink_node decisions more node-centric

2016-04-06 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. So