Re: [PATCH 0/7] improve robustness on handling migratetype

2014-02-03 Thread Vlastimil Babka
On 02/03/2014 08:45 AM, Joonsoo Kim wrote: On Wed, Jan 29, 2014 at 05:52:41PM +0100, Vlastimil Babka wrote: On 01/10/2014 09:48 AM, Joonsoo Kim wrote: On Thu, Jan 09, 2014 at 09:27:20AM +, Mel Gorman wrote: On Thu, Jan 09, 2014 at 04:04:40PM +0900, Joonsoo Kim wrote: Hello, I found some

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-02-03 Thread Vlastimil Babka
On 02/03/2014 08:45 AM, Joonsoo Kim wrote: On Wed, Jan 29, 2014 at 05:52:41PM +0100, Vlastimil Babka wrote: On 01/10/2014 09:48 AM, Joonsoo Kim wrote: On Thu, Jan 09, 2014 at 09:27:20AM +, Mel Gorman wrote: On Thu, Jan 09, 2014 at 04:04:40PM +0900, Joonsoo Kim wrote: Hello, I found some

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-02-02 Thread Joonsoo Kim
On Wed, Jan 29, 2014 at 05:52:41PM +0100, Vlastimil Babka wrote: > On 01/10/2014 09:48 AM, Joonsoo Kim wrote: > >On Thu, Jan 09, 2014 at 09:27:20AM +, Mel Gorman wrote: > >>On Thu, Jan 09, 2014 at 04:04:40PM +0900, Joonsoo Kim wrote: > >>>Hello, > >>> > >>>I found some weaknesses on handling

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-02-02 Thread Joonsoo Kim
On Wed, Jan 29, 2014 at 05:52:41PM +0100, Vlastimil Babka wrote: On 01/10/2014 09:48 AM, Joonsoo Kim wrote: On Thu, Jan 09, 2014 at 09:27:20AM +, Mel Gorman wrote: On Thu, Jan 09, 2014 at 04:04:40PM +0900, Joonsoo Kim wrote: Hello, I found some weaknesses on handling migratetype during

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-01-31 Thread Mel Gorman
On Wed, Jan 29, 2014 at 05:52:41PM +0100, Vlastimil Babka wrote: > On 01/10/2014 09:48 AM, Joonsoo Kim wrote: > >On Thu, Jan 09, 2014 at 09:27:20AM +, Mel Gorman wrote: > >>On Thu, Jan 09, 2014 at 04:04:40PM +0900, Joonsoo Kim wrote: > >>>Hello, > >>> > >>>I found some weaknesses on handling

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-01-31 Thread Mel Gorman
On Wed, Jan 29, 2014 at 05:52:41PM +0100, Vlastimil Babka wrote: On 01/10/2014 09:48 AM, Joonsoo Kim wrote: On Thu, Jan 09, 2014 at 09:27:20AM +, Mel Gorman wrote: On Thu, Jan 09, 2014 at 04:04:40PM +0900, Joonsoo Kim wrote: Hello, I found some weaknesses on handling migratetype during

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-01-29 Thread Vlastimil Babka
On 01/10/2014 09:48 AM, Joonsoo Kim wrote: On Thu, Jan 09, 2014 at 09:27:20AM +, Mel Gorman wrote: On Thu, Jan 09, 2014 at 04:04:40PM +0900, Joonsoo Kim wrote: Hello, I found some weaknesses on handling migratetype during code review and testing CMA. First, we don't have any

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-01-29 Thread Vlastimil Babka
On 01/10/2014 09:48 AM, Joonsoo Kim wrote: On Thu, Jan 09, 2014 at 09:27:20AM +, Mel Gorman wrote: On Thu, Jan 09, 2014 at 04:04:40PM +0900, Joonsoo Kim wrote: Hello, I found some weaknesses on handling migratetype during code review and testing CMA. First, we don't have any

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-01-12 Thread Joonsoo Kim
On Fri, Jan 10, 2014 at 09:48:34AM +, Mel Gorman wrote: > On Fri, Jan 10, 2014 at 05:48:55PM +0900, Joonsoo Kim wrote: > > On Thu, Jan 09, 2014 at 09:27:20AM +, Mel Gorman wrote: > > > On Thu, Jan 09, 2014 at 04:04:40PM +0900, Joonsoo Kim wrote: > > > > Hello, > > > > > > > > I found some

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-01-12 Thread Joonsoo Kim
On Fri, Jan 10, 2014 at 09:48:34AM +, Mel Gorman wrote: On Fri, Jan 10, 2014 at 05:48:55PM +0900, Joonsoo Kim wrote: On Thu, Jan 09, 2014 at 09:27:20AM +, Mel Gorman wrote: On Thu, Jan 09, 2014 at 04:04:40PM +0900, Joonsoo Kim wrote: Hello, I found some weaknesses on

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-01-10 Thread Mel Gorman
On Fri, Jan 10, 2014 at 05:48:55PM +0900, Joonsoo Kim wrote: > On Thu, Jan 09, 2014 at 09:27:20AM +, Mel Gorman wrote: > > On Thu, Jan 09, 2014 at 04:04:40PM +0900, Joonsoo Kim wrote: > > > Hello, > > > > > > I found some weaknesses on handling migratetype during code review and > > > testing

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-01-10 Thread Joonsoo Kim
On Thu, Jan 09, 2014 at 09:27:20AM +, Mel Gorman wrote: > On Thu, Jan 09, 2014 at 04:04:40PM +0900, Joonsoo Kim wrote: > > Hello, > > > > I found some weaknesses on handling migratetype during code review and > > testing CMA. > > > > First, we don't have any synchronization method on get/set

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-01-10 Thread Joonsoo Kim
On Thu, Jan 09, 2014 at 09:27:20AM +, Mel Gorman wrote: On Thu, Jan 09, 2014 at 04:04:40PM +0900, Joonsoo Kim wrote: Hello, I found some weaknesses on handling migratetype during code review and testing CMA. First, we don't have any synchronization method on get/set pageblock

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-01-10 Thread Mel Gorman
On Fri, Jan 10, 2014 at 05:48:55PM +0900, Joonsoo Kim wrote: On Thu, Jan 09, 2014 at 09:27:20AM +, Mel Gorman wrote: On Thu, Jan 09, 2014 at 04:04:40PM +0900, Joonsoo Kim wrote: Hello, I found some weaknesses on handling migratetype during code review and testing CMA.

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-01-09 Thread Joonsoo Kim
2014/1/9 Michal Nazarewicz : > On Thu, Jan 09 2014, Joonsoo Kim wrote: >> Third, there is the problem on buddy allocator. It doesn't consider >> migratetype when merging buddy, so pages from cma or isolate region can >> be moved to other migratetype freelist. It makes CMA failed over and over. >>

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-01-09 Thread Mel Gorman
On Thu, Jan 09, 2014 at 04:04:40PM +0900, Joonsoo Kim wrote: > Hello, > > I found some weaknesses on handling migratetype during code review and > testing CMA. > > First, we don't have any synchronization method on get/set pageblock > migratetype. When we change migratetype, we hold the zone

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-01-09 Thread Michal Nazarewicz
On Thu, Jan 09 2014, Joonsoo Kim wrote: > Third, there is the problem on buddy allocator. It doesn't consider > migratetype when merging buddy, so pages from cma or isolate region can > be moved to other migratetype freelist. It makes CMA failed over and over. > To prevent it, the buddy allocator

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-01-09 Thread Michal Nazarewicz
On Thu, Jan 09 2014, Joonsoo Kim iamjoonsoo@lge.com wrote: Third, there is the problem on buddy allocator. It doesn't consider migratetype when merging buddy, so pages from cma or isolate region can be moved to other migratetype freelist. It makes CMA failed over and over. To prevent it,

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-01-09 Thread Mel Gorman
On Thu, Jan 09, 2014 at 04:04:40PM +0900, Joonsoo Kim wrote: Hello, I found some weaknesses on handling migratetype during code review and testing CMA. First, we don't have any synchronization method on get/set pageblock migratetype. When we change migratetype, we hold the zone lock. So

Re: [PATCH 0/7] improve robustness on handling migratetype

2014-01-09 Thread Joonsoo Kim
2014/1/9 Michal Nazarewicz min...@mina86.com: On Thu, Jan 09 2014, Joonsoo Kim iamjoonsoo@lge.com wrote: Third, there is the problem on buddy allocator. It doesn't consider migratetype when merging buddy, so pages from cma or isolate region can be moved to other migratetype freelist. It