Re: [PATCH 1/6] mm, compaction: more robust check for scanners meeting

2015-06-19 Thread Mel Gorman
On Wed, Jun 10, 2015 at 11:32:29AM +0200, Vlastimil Babka wrote: > Compaction should finish when the migration and free scanner meet, i.e. they > reach the same pageblock. Currently however, the test in compact_finished() > simply just compares the exact pfns, which may yield a false negative when

Re: [PATCH 1/6] mm, compaction: more robust check for scanners meeting

2015-06-19 Thread Mel Gorman
On Wed, Jun 10, 2015 at 11:32:29AM +0200, Vlastimil Babka wrote: Compaction should finish when the migration and free scanner meet, i.e. they reach the same pageblock. Currently however, the test in compact_finished() simply just compares the exact pfns, which may yield a false negative when

Re: [PATCH 1/6] mm, compaction: more robust check for scanners meeting

2015-06-15 Thread Joonsoo Kim
On Wed, Jun 10, 2015 at 11:32:29AM +0200, Vlastimil Babka wrote: > Compaction should finish when the migration and free scanner meet, i.e. they > reach the same pageblock. Currently however, the test in compact_finished() > simply just compares the exact pfns, which may yield a false negative when

Re: [PATCH 1/6] mm, compaction: more robust check for scanners meeting

2015-06-15 Thread Joonsoo Kim
On Wed, Jun 10, 2015 at 11:32:29AM +0200, Vlastimil Babka wrote: Compaction should finish when the migration and free scanner meet, i.e. they reach the same pageblock. Currently however, the test in compact_finished() simply just compares the exact pfns, which may yield a false negative when

Re: [PATCH 1/6] mm, compaction: more robust check for scanners meeting

2015-06-12 Thread Michal Nazarewicz
On Wed, Jun 10 2015, Vlastimil Babka wrote: > Compaction should finish when the migration and free scanner meet, i.e. they > reach the same pageblock. Currently however, the test in compact_finished() > simply just compares the exact pfns, which may yield a false negative when the > free scanner

Re: [PATCH 1/6] mm, compaction: more robust check for scanners meeting

2015-06-12 Thread Michal Nazarewicz
On Wed, Jun 10 2015, Vlastimil Babka wrote: Compaction should finish when the migration and free scanner meet, i.e. they reach the same pageblock. Currently however, the test in compact_finished() simply just compares the exact pfns, which may yield a false negative when the free scanner

Re: [PATCH 1/6] mm, compaction: more robust check for scanners meeting

2015-06-10 Thread Rik van Riel
On 06/10/2015 05:32 AM, Vlastimil Babka wrote: > Compaction should finish when the migration and free scanner meet, i.e. they > reach the same pageblock. Currently however, the test in compact_finished() > simply just compares the exact pfns, which may yield a false negative when the > free

[PATCH 1/6] mm, compaction: more robust check for scanners meeting

2015-06-10 Thread Vlastimil Babka
Compaction should finish when the migration and free scanner meet, i.e. they reach the same pageblock. Currently however, the test in compact_finished() simply just compares the exact pfns, which may yield a false negative when the free scanner position is in the middle of a pageblock and the

[PATCH 1/6] mm, compaction: more robust check for scanners meeting

2015-06-10 Thread Vlastimil Babka
Compaction should finish when the migration and free scanner meet, i.e. they reach the same pageblock. Currently however, the test in compact_finished() simply just compares the exact pfns, which may yield a false negative when the free scanner position is in the middle of a pageblock and the

Re: [PATCH 1/6] mm, compaction: more robust check for scanners meeting

2015-06-10 Thread Rik van Riel
On 06/10/2015 05:32 AM, Vlastimil Babka wrote: Compaction should finish when the migration and free scanner meet, i.e. they reach the same pageblock. Currently however, the test in compact_finished() simply just compares the exact pfns, which may yield a false negative when the free scanner