Re: [PATCH 0/1] memory offline issues with hugepage size > memory block size

2016-09-21 Thread Michal Hocko
On Wed 21-09-16 11:27:48, Dave Hansen wrote: > On 09/21/2016 11:20 AM, Michal Hocko wrote: > > I would even question the per page block offlining itself. Why would > > anybody want to offline few blocks rather than the whole node? What is > > the usecase here? > > The original reason was so that y

Re: [PATCH 0/1] memory offline issues with hugepage size > memory block size

2016-09-21 Thread Dave Hansen
On 09/21/2016 11:20 AM, Michal Hocko wrote: > I would even question the per page block offlining itself. Why would > anybody want to offline few blocks rather than the whole node? What is > the usecase here? The original reason was so that you could remove a DIMM or a riser card full of DIMMs, whi

Re: [PATCH 0/1] memory offline issues with hugepage size > memory block size

2016-09-21 Thread Michal Hocko
On Tue 20-09-16 10:37:04, Mike Kravetz wrote: > On 09/20/2016 08:53 AM, Gerald Schaefer wrote: > > dissolve_free_huge_pages() will either run into the VM_BUG_ON() or a > > list corruption and addressing exception when trying to set a memory > > block offline that is part (but not the first part) of

Re: [PATCH 0/1] memory offline issues with hugepage size > memory block size

2016-09-21 Thread Gerald Schaefer
On Tue, 20 Sep 2016 10:45:23 -0700 Dave Hansen wrote: > On 09/20/2016 10:37 AM, Mike Kravetz wrote: > > > > Their approach (I believe) would be to fail the offline operation in > > this case. However, I could argue that failing the operation, or > > dissolving the unused huge page containing th

Re: [PATCH 0/1] memory offline issues with hugepage size > memory block size

2016-09-21 Thread Gerald Schaefer
On Tue, 20 Sep 2016 10:37:04 -0700 Mike Kravetz wrote: > > Cc'ed Rui Teng and Dave Hansen as they were discussing the issue in > this thread: > https://lkml.org/lkml/2016/9/13/146 Ah, thanks, I didn't see that. > > Their approach (I believe) would be to fail the offline operation in > this ca

Re: [PATCH 0/1] memory offline issues with hugepage size > memory block size

2016-09-21 Thread Vlastimil Babka
On 09/20/2016 07:45 PM, Dave Hansen wrote: On 09/20/2016 10:37 AM, Mike Kravetz wrote: Their approach (I believe) would be to fail the offline operation in this case. However, I could argue that failing the operation, or dissolving the unused huge page containing the area to be offlined is the

Re: [PATCH 0/1] memory offline issues with hugepage size > memory block size

2016-09-20 Thread Dave Hansen
On 09/20/2016 10:37 AM, Mike Kravetz wrote: > > Their approach (I believe) would be to fail the offline operation in > this case. However, I could argue that failing the operation, or > dissolving the unused huge page containing the area to be offlined is > the right thing to do. I think the rig

Re: [PATCH 0/1] memory offline issues with hugepage size > memory block size

2016-09-20 Thread Mike Kravetz
On 09/20/2016 08:53 AM, Gerald Schaefer wrote: > dissolve_free_huge_pages() will either run into the VM_BUG_ON() or a > list corruption and addressing exception when trying to set a memory > block offline that is part (but not the first part) of a gigantic > hugetlb page with a size > memory block