Re: [Devel] [PATCH -mm 3/4] fork: charge threadinfo to memcg explicitly

2014-03-27 Thread Vladimir Davydov
On 03/27/2014 02:00 AM, Michal Hocko wrote: > On Wed 26-03-14 19:28:06, Vladimir Davydov wrote: >> We have only a few places where we actually want to charge kmem so >> instead of intruding into the general page allocation path with >> __GFP_KMEMCG it's better to explictly charge kmem there. All km

Re: [Devel] [PATCH -mm 3/4] fork: charge threadinfo to memcg explicitly

2014-03-26 Thread Michal Hocko
On Wed 26-03-14 19:28:06, Vladimir Davydov wrote: > We have only a few places where we actually want to charge kmem so > instead of intruding into the general page allocation path with > __GFP_KMEMCG it's better to explictly charge kmem there. All kmem > charges will be easier to follow that way. >

[Devel] [PATCH -mm 3/4] fork: charge threadinfo to memcg explicitly

2014-03-26 Thread Vladimir Davydov
We have only a few places where we actually want to charge kmem so instead of intruding into the general page allocation path with __GFP_KMEMCG it's better to explictly charge kmem there. All kmem charges will be easier to follow that way. This is a step toward removing __GFP_KMEMCG. It makes fork