On Mon, Feb 02, 2015 at 09:51:01PM +0800, Zhang Yanfei wrote:
> Hello,
>
> At 2015/2/2 18:20, Vlastimil Babka wrote:
> > On 02/02/2015 08:15 AM, Joonsoo Kim wrote:
> >> Compaction has anti fragmentation algorithm. It is that freepage
> >> should be more than pageblock order to finish the
On 02/02/2015 02:51 PM, Zhang Yanfei wrote:
>> I've got another idea for small improvement. We should only test for
>> fallbacks
>> when migration scanner has scanned (and migrated) a whole pageblock. Should
>> be a
>> simple alignment test of cc->migrate_pfn.
>> Advantages:
>> - potentially
On 02/02/2015 02:23 PM, Joonsoo Kim wrote:
> 2015-02-02 19:20 GMT+09:00 Vlastimil Babka :
>> On 02/02/2015 08:15 AM, Joonsoo Kim wrote:
>>
>> So I've realized that this problaby won't always work as intended :/ Because
>> we
>> still differ from what page allocator does.
>> Consider we compact
Hello,
At 2015/2/2 18:20, Vlastimil Babka wrote:
> On 02/02/2015 08:15 AM, Joonsoo Kim wrote:
>> Compaction has anti fragmentation algorithm. It is that freepage
>> should be more than pageblock order to finish the compaction if we don't
>> find any freepage in requested migratetype buddy list.
2015-02-02 19:20 GMT+09:00 Vlastimil Babka :
> On 02/02/2015 08:15 AM, Joonsoo Kim wrote:
>> Compaction has anti fragmentation algorithm. It is that freepage
>> should be more than pageblock order to finish the compaction if we don't
>> find any freepage in requested migratetype buddy list. This
On 02/02/2015 08:15 AM, Joonsoo Kim wrote:
> Compaction has anti fragmentation algorithm. It is that freepage
> should be more than pageblock order to finish the compaction if we don't
> find any freepage in requested migratetype buddy list. This is for
> mitigating fragmentation, but, there is a
On 02/02/2015 02:51 PM, Zhang Yanfei wrote:
I've got another idea for small improvement. We should only test for
fallbacks
when migration scanner has scanned (and migrated) a whole pageblock. Should
be a
simple alignment test of cc-migrate_pfn.
Advantages:
- potentially less checking
2015-02-02 19:20 GMT+09:00 Vlastimil Babka vba...@suse.cz:
On 02/02/2015 08:15 AM, Joonsoo Kim wrote:
Compaction has anti fragmentation algorithm. It is that freepage
should be more than pageblock order to finish the compaction if we don't
find any freepage in requested migratetype buddy list.
Hello,
At 2015/2/2 18:20, Vlastimil Babka wrote:
On 02/02/2015 08:15 AM, Joonsoo Kim wrote:
Compaction has anti fragmentation algorithm. It is that freepage
should be more than pageblock order to finish the compaction if we don't
find any freepage in requested migratetype buddy list. This is
On 02/02/2015 02:23 PM, Joonsoo Kim wrote:
2015-02-02 19:20 GMT+09:00 Vlastimil Babka vba...@suse.cz:
On 02/02/2015 08:15 AM, Joonsoo Kim wrote:
So I've realized that this problaby won't always work as intended :/ Because
we
still differ from what page allocator does.
Consider we compact
On 02/02/2015 08:15 AM, Joonsoo Kim wrote:
Compaction has anti fragmentation algorithm. It is that freepage
should be more than pageblock order to finish the compaction if we don't
find any freepage in requested migratetype buddy list. This is for
mitigating fragmentation, but, there is a lack
On Mon, Feb 02, 2015 at 09:51:01PM +0800, Zhang Yanfei wrote:
Hello,
At 2015/2/2 18:20, Vlastimil Babka wrote:
On 02/02/2015 08:15 AM, Joonsoo Kim wrote:
Compaction has anti fragmentation algorithm. It is that freepage
should be more than pageblock order to finish the compaction if we
Compaction has anti fragmentation algorithm. It is that freepage
should be more than pageblock order to finish the compaction if we don't
find any freepage in requested migratetype buddy list. This is for
mitigating fragmentation, but, there is a lack of migratetype
consideration and it is too
Compaction has anti fragmentation algorithm. It is that freepage
should be more than pageblock order to finish the compaction if we don't
find any freepage in requested migratetype buddy list. This is for
mitigating fragmentation, but, there is a lack of migratetype
consideration and it is too
14 matches
Mail list logo