RE: [PATCH 1/2] mm: Export split_page()

2013-03-18 Thread KY Srinivasan
; a...@firstfloor.org; a...@linux-foundation.org; linux...@kvack.org; > kamezawa.hiroy...@gmail.com; han...@cmpxchg.org; ying...@google.com > Subject: Re: [PATCH 1/2] mm: Export split_page() > > On Sat 16-03-13 14:42:04, K. Y. Srinivasan wrote: > > The split_page() function will be very us

Re: [PATCH 1/2] mm: Export split_page()

2013-03-18 Thread Michal Hocko
On Sat 16-03-13 14:42:04, K. Y. Srinivasan wrote: > The split_page() function will be very useful for balloon drivers. On Hyper-V, > it will be very efficient to use 2M allocations in the guest as this (a) makes > the ballooning protocol with the host that much more efficient and (b) moving >

Re: [PATCH 1/2] mm: Export split_page()

2013-03-18 Thread Michal Hocko
On Sat 16-03-13 14:42:04, K. Y. Srinivasan wrote: The split_page() function will be very useful for balloon drivers. On Hyper-V, it will be very efficient to use 2M allocations in the guest as this (a) makes the ballooning protocol with the host that much more efficient and (b) moving memory

RE: [PATCH 1/2] mm: Export split_page()

2013-03-18 Thread KY Srinivasan
-foundation.org; linux...@kvack.org; kamezawa.hiroy...@gmail.com; han...@cmpxchg.org; ying...@google.com Subject: Re: [PATCH 1/2] mm: Export split_page() On Sat 16-03-13 14:42:04, K. Y. Srinivasan wrote: The split_page() function will be very useful for balloon drivers. On Hyper-V

[PATCH 1/2] mm: Export split_page()

2013-03-16 Thread K. Y. Srinivasan
The split_page() function will be very useful for balloon drivers. On Hyper-V, it will be very efficient to use 2M allocations in the guest as this (a) makes the ballooning protocol with the host that much more efficient and (b) moving memory in 2M chunks minimizes fragmentation in the host.

[PATCH 1/2] mm: Export split_page()

2013-03-16 Thread K. Y. Srinivasan
The split_page() function will be very useful for balloon drivers. On Hyper-V, it will be very efficient to use 2M allocations in the guest as this (a) makes the ballooning protocol with the host that much more efficient and (b) moving memory in 2M chunks minimizes fragmentation in the host.