On 01/20/2015 10:08 AM, Vlastimil Babka wrote:
> On 01/20/2015 06:52 AM, Aneesh Kumar K.V wrote:
>> Vlastimil Babka writes:
>>
>> is that check correct ? ie,
>>
>> if ((gfp & GFP_TRANSHUGE) == GFP_TRANSHUGE)
>>
>> may not always indicate transparent hugepage if defrag = 0 . With defrag
>>
On 01/20/2015 10:08 AM, Vlastimil Babka wrote:
On 01/20/2015 06:52 AM, Aneesh Kumar K.V wrote:
Vlastimil Babka vba...@suse.cz writes:
is that check correct ? ie,
if ((gfp GFP_TRANSHUGE) == GFP_TRANSHUGE)
may not always indicate transparent hugepage if defrag = 0 . With defrag
On 01/20/2015 06:52 AM, Aneesh Kumar K.V wrote:
> Vlastimil Babka writes:
>
>> On 01/17/2015 01:02 AM, Andrew Morton wrote:
>>> On Fri, 16 Jan 2015 12:56:36 +0530 "Aneesh Kumar K.V"
>>> wrote:
>>>
This make sure that we try to allocate hugepages from local node if
allowed by
On 01/20/2015 06:52 AM, Aneesh Kumar K.V wrote:
Vlastimil Babka vba...@suse.cz writes:
On 01/17/2015 01:02 AM, Andrew Morton wrote:
On Fri, 16 Jan 2015 12:56:36 +0530 Aneesh Kumar K.V
aneesh.ku...@linux.vnet.ibm.com wrote:
This make sure that we try to allocate hugepages from local node
Vlastimil Babka writes:
> On 01/17/2015 01:02 AM, Andrew Morton wrote:
>> On Fri, 16 Jan 2015 12:56:36 +0530 "Aneesh Kumar K.V"
>> wrote:
>>
>>> This make sure that we try to allocate hugepages from local node if
>>> allowed by mempolicy. If we can't, we fallback to small page allocation
>>>
On 01/17/2015 01:02 AM, Andrew Morton wrote:
> On Fri, 16 Jan 2015 12:56:36 +0530 "Aneesh Kumar K.V"
> wrote:
>
>> This make sure that we try to allocate hugepages from local node if
>> allowed by mempolicy. If we can't, we fallback to small page allocation
>> based on mempolicy. This is based
Vlastimil Babka vba...@suse.cz writes:
On 01/17/2015 01:02 AM, Andrew Morton wrote:
On Fri, 16 Jan 2015 12:56:36 +0530 Aneesh Kumar K.V
aneesh.ku...@linux.vnet.ibm.com wrote:
This make sure that we try to allocate hugepages from local node if
allowed by mempolicy. If we can't, we fallback
On 01/17/2015 01:02 AM, Andrew Morton wrote:
On Fri, 16 Jan 2015 12:56:36 +0530 Aneesh Kumar K.V
aneesh.ku...@linux.vnet.ibm.com wrote:
This make sure that we try to allocate hugepages from local node if
allowed by mempolicy. If we can't, we fallback to small page allocation
based on
Davidlohr Bueso writes:
> On Fri, 2015-01-16 at 16:02 -0800, Andrew Morton wrote:
>> On Fri, 16 Jan 2015 12:56:36 +0530 "Aneesh Kumar K.V"
>> wrote:
>>
>> > This make sure that we try to allocate hugepages from local node if
>> > allowed by mempolicy. If we can't, we fallback to small page
Andrew Morton writes:
> On Fri, 16 Jan 2015 12:56:36 +0530 "Aneesh Kumar K.V"
> wrote:
>
>> This make sure that we try to allocate hugepages from local node if
>> allowed by mempolicy. If we can't, we fallback to small page allocation
>> based on mempolicy. This is based on the observation
Andrew Morton a...@linux-foundation.org writes:
On Fri, 16 Jan 2015 12:56:36 +0530 Aneesh Kumar K.V
aneesh.ku...@linux.vnet.ibm.com wrote:
This make sure that we try to allocate hugepages from local node if
allowed by mempolicy. If we can't, we fallback to small page allocation
based on
Davidlohr Bueso d...@stgolabs.net writes:
On Fri, 2015-01-16 at 16:02 -0800, Andrew Morton wrote:
On Fri, 16 Jan 2015 12:56:36 +0530 Aneesh Kumar K.V
aneesh.ku...@linux.vnet.ibm.com wrote:
This make sure that we try to allocate hugepages from local node if
allowed by mempolicy. If we
On Fri, 2015-01-16 at 16:02 -0800, Andrew Morton wrote:
> On Fri, 16 Jan 2015 12:56:36 +0530 "Aneesh Kumar K.V"
> wrote:
>
> > This make sure that we try to allocate hugepages from local node if
> > allowed by mempolicy. If we can't, we fallback to small page allocation
> > based on mempolicy.
On Fri, 16 Jan 2015 12:56:36 +0530 "Aneesh Kumar K.V"
wrote:
> This make sure that we try to allocate hugepages from local node if
> allowed by mempolicy. If we can't, we fallback to small page allocation
> based on mempolicy. This is based on the observation that allocating pages
> on local
On 01/16/2015 08:26 AM, Aneesh Kumar K.V wrote:
> This make sure that we try to allocate hugepages from local node if
> allowed by mempolicy. If we can't, we fallback to small page allocation
> based on mempolicy. This is based on the observation that allocating pages
> on local node is more
On Fri, Jan 16, 2015 at 12:56:36PM +0530, Aneesh Kumar K.V wrote:
> This make sure that we try to allocate hugepages from local node if
> allowed by mempolicy. If we can't, we fallback to small page allocation
> based on mempolicy. This is based on the observation that allocating pages
> on local
On 01/16/2015 08:26 AM, Aneesh Kumar K.V wrote:
This make sure that we try to allocate hugepages from local node if
allowed by mempolicy. If we can't, we fallback to small page allocation
based on mempolicy. This is based on the observation that allocating pages
on local node is more
On Fri, 16 Jan 2015 12:56:36 +0530 Aneesh Kumar K.V
aneesh.ku...@linux.vnet.ibm.com wrote:
This make sure that we try to allocate hugepages from local node if
allowed by mempolicy. If we can't, we fallback to small page allocation
based on mempolicy. This is based on the observation that
On Fri, 2015-01-16 at 16:02 -0800, Andrew Morton wrote:
On Fri, 16 Jan 2015 12:56:36 +0530 Aneesh Kumar K.V
aneesh.ku...@linux.vnet.ibm.com wrote:
This make sure that we try to allocate hugepages from local node if
allowed by mempolicy. If we can't, we fallback to small page allocation
On Fri, Jan 16, 2015 at 12:56:36PM +0530, Aneesh Kumar K.V wrote:
This make sure that we try to allocate hugepages from local node if
allowed by mempolicy. If we can't, we fallback to small page allocation
based on mempolicy. This is based on the observation that allocating pages
on local node
This make sure that we try to allocate hugepages from local node if
allowed by mempolicy. If we can't, we fallback to small page allocation
based on mempolicy. This is based on the observation that allocating pages
on local node is more beneficial than allocating hugepages on remote node.
This make sure that we try to allocate hugepages from local node if
allowed by mempolicy. If we can't, we fallback to small page allocation
based on mempolicy. This is based on the observation that allocating pages
on local node is more beneficial than allocating hugepages on remote node.
22 matches
Mail list logo
