Re: hugetlb page migration vs. overcommit

2017-11-28 Thread Michal Hocko
On Tue 28-11-17 11:19:07, Michal Hocko wrote: > On Wed 22-11-17 16:28:32, Michal Hocko wrote: > > Hi, > > is there any reason why we enforce the overcommit limit during hugetlb > > pages migration? It's in alloc_huge_page_node->__alloc_buddy_huge_page > > path. I am wondering whether this is really

Re: hugetlb page migration vs. overcommit

2017-11-28 Thread Michal Hocko
On Wed 22-11-17 16:28:32, Michal Hocko wrote: > Hi, > is there any reason why we enforce the overcommit limit during hugetlb > pages migration? It's in alloc_huge_page_node->__alloc_buddy_huge_page > path. I am wondering whether this is really an intentional behavior. > The page migration allocates

Re: hugetlb page migration vs. overcommit

2017-11-26 Thread Naoya Horiguchi
On 11/23/2017 04:11 AM, Mike Kravetz wrote: > On 11/22/2017 07:28 AM, Michal Hocko wrote: >> Hi, >> is there any reason why we enforce the overcommit limit during hugetlb >> pages migration? It's in alloc_huge_page_node->__alloc_buddy_huge_page >> path. I am wondering whether this is really an inte

Re: hugetlb page migration vs. overcommit

2017-11-23 Thread Michal Hocko
On Wed 22-11-17 11:11:38, Mike Kravetz wrote: > On 11/22/2017 07:28 AM, Michal Hocko wrote: [...] > > Why don't we simply migrate as long as we are able to allocate the > > target hugetlb page? I have a half baked patch to remove this > > restriction, would there be an opposition to do something li

Re: hugetlb page migration vs. overcommit

2017-11-22 Thread Mike Kravetz
On 11/22/2017 07:28 AM, Michal Hocko wrote: > Hi, > is there any reason why we enforce the overcommit limit during hugetlb > pages migration? It's in alloc_huge_page_node->__alloc_buddy_huge_page > path. I am wondering whether this is really an intentional behavior. I do not think it was intention