Re: [RFC] mm: bail out in shrin_inactive_list

2016-08-01 Thread Minchan Kim
On Fri, Jul 29, 2016 at 10:11:30AM -0400, Johannes Weiner wrote: > On Mon, Jul 25, 2016 at 04:51:59PM +0900, Minchan Kim wrote: > > With node-lru, if there are enough reclaimable pages in highmem > > but nothing in lowmem, VM can try to shrink inactive list although > > the requested zone is

Re: [RFC] mm: bail out in shrin_inactive_list

2016-08-01 Thread Minchan Kim
On Fri, Jul 29, 2016 at 10:11:30AM -0400, Johannes Weiner wrote: > On Mon, Jul 25, 2016 at 04:51:59PM +0900, Minchan Kim wrote: > > With node-lru, if there are enough reclaimable pages in highmem > > but nothing in lowmem, VM can try to shrink inactive list although > > the requested zone is

Re: [RFC] mm: bail out in shrin_inactive_list

2016-07-29 Thread Johannes Weiner
On Mon, Jul 25, 2016 at 04:51:59PM +0900, Minchan Kim wrote: > With node-lru, if there are enough reclaimable pages in highmem > but nothing in lowmem, VM can try to shrink inactive list although > the requested zone is lowmem. > > The problem is direct reclaimer scans inactive list is fulled

Re: [RFC] mm: bail out in shrin_inactive_list

2016-07-29 Thread Johannes Weiner
On Mon, Jul 25, 2016 at 04:51:59PM +0900, Minchan Kim wrote: > With node-lru, if there are enough reclaimable pages in highmem > but nothing in lowmem, VM can try to shrink inactive list although > the requested zone is lowmem. > > The problem is direct reclaimer scans inactive list is fulled

Re: [RFC] mm: bail out in shrin_inactive_list

2016-07-26 Thread Minchan Kim
On Tue, Jul 26, 2016 at 08:46:50AM +0100, Mel Gorman wrote: > On Tue, Jul 26, 2016 at 10:21:57AM +0900, Minchan Kim wrote: > > > > I believe proper fix is to modify get_scan_count. IOW, I think > > > > we should introduce lruvec_reclaimable_lru_size with proper > > > > classzone_idx but I don't

Re: [RFC] mm: bail out in shrin_inactive_list

2016-07-26 Thread Minchan Kim
On Tue, Jul 26, 2016 at 08:46:50AM +0100, Mel Gorman wrote: > On Tue, Jul 26, 2016 at 10:21:57AM +0900, Minchan Kim wrote: > > > > I believe proper fix is to modify get_scan_count. IOW, I think > > > > we should introduce lruvec_reclaimable_lru_size with proper > > > > classzone_idx but I don't

Re: [RFC] mm: bail out in shrin_inactive_list

2016-07-26 Thread Mel Gorman
On Tue, Jul 26, 2016 at 10:21:57AM +0900, Minchan Kim wrote: > > > I believe proper fix is to modify get_scan_count. IOW, I think > > > we should introduce lruvec_reclaimable_lru_size with proper > > > classzone_idx but I don't know how we can fix it with memcg > > > which doesn't have zone stat

Re: [RFC] mm: bail out in shrin_inactive_list

2016-07-26 Thread Mel Gorman
On Tue, Jul 26, 2016 at 10:21:57AM +0900, Minchan Kim wrote: > > > I believe proper fix is to modify get_scan_count. IOW, I think > > > we should introduce lruvec_reclaimable_lru_size with proper > > > classzone_idx but I don't know how we can fix it with memcg > > > which doesn't have zone stat

Re: [RFC] mm: bail out in shrin_inactive_list

2016-07-25 Thread Minchan Kim
On Mon, Jul 25, 2016 at 10:29:09AM +0100, Mel Gorman wrote: > There is a typo in the subject line. > > On Mon, Jul 25, 2016 at 04:51:59PM +0900, Minchan Kim wrote: > > With node-lru, if there are enough reclaimable pages in highmem > > but nothing in lowmem, VM can try to shrink inactive list

Re: [RFC] mm: bail out in shrin_inactive_list

2016-07-25 Thread Minchan Kim
On Mon, Jul 25, 2016 at 10:29:09AM +0100, Mel Gorman wrote: > There is a typo in the subject line. > > On Mon, Jul 25, 2016 at 04:51:59PM +0900, Minchan Kim wrote: > > With node-lru, if there are enough reclaimable pages in highmem > > but nothing in lowmem, VM can try to shrink inactive list

Re: [RFC] mm: bail out in shrin_inactive_list

2016-07-25 Thread Mel Gorman
There is a typo in the subject line. On Mon, Jul 25, 2016 at 04:51:59PM +0900, Minchan Kim wrote: > With node-lru, if there are enough reclaimable pages in highmem > but nothing in lowmem, VM can try to shrink inactive list although > the requested zone is lowmem. > > The problem is direct

Re: [RFC] mm: bail out in shrin_inactive_list

2016-07-25 Thread Mel Gorman
There is a typo in the subject line. On Mon, Jul 25, 2016 at 04:51:59PM +0900, Minchan Kim wrote: > With node-lru, if there are enough reclaimable pages in highmem > but nothing in lowmem, VM can try to shrink inactive list although > the requested zone is lowmem. > > The problem is direct

[RFC] mm: bail out in shrin_inactive_list

2016-07-25 Thread Minchan Kim
With node-lru, if there are enough reclaimable pages in highmem but nothing in lowmem, VM can try to shrink inactive list although the requested zone is lowmem. The problem is direct reclaimer scans inactive list is fulled with highmem pages to find a victim page at a reqested zone or lower zones

[RFC] mm: bail out in shrin_inactive_list

2016-07-25 Thread Minchan Kim
With node-lru, if there are enough reclaimable pages in highmem but nothing in lowmem, VM can try to shrink inactive list although the requested zone is lowmem. The problem is direct reclaimer scans inactive list is fulled with highmem pages to find a victim page at a reqested zone or lower zones