Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1570427

Re: [RFC V2 00/12] Define coherent device memory node

Show all headers | View raw

On Tue, Jan 31, 2017 at 11:18:49AM +0530, Anshuman Khandual wrote:
> Hello Dave/Jerome/Mel,
> 
> Here is the overall layout of the functions I am trying to put together
> through this patch series.
> 
> (1) Define CDM from core VM and kernel perspective
> 
> (2) Isolation/Special consideration for HugeTLB allocations
> 
> (3) Isolation/Special consideration for buddy allocations
> 
> 	(a) Zonelist modification based isolation (proposed)
> 	(b) Cpuset modification based isolation	  (proposed)
> 	(c) Buddy modification based isolation	  (working)
> 
> (4) Define VMA containing CDM memory with a new flag VM_CDM
> 
> (5) Special consideration for VM_CDM marked VMAs
> 
> 	(a) Special consideration for auto NUMA
> 	(b) Special consideration for KSM

I believe (5) should not be done on per vma basis but on a page basis.
Thus rendering (4) pointless. A vma shouldn't be special because it has
some special kind of memory irespective of what the vma points to.


> Is there are any other area which needs to be taken care of before CDM
> node can be represented completely inside the kernel ?

Maybe thing like swap or suspend and resume (i know you are targetting big
computer and not laptop :)) but you can't presume what platform CDM might
be use latter on.

Also userspace might be confuse by looking a /proc/meminfo or any of the
sysfs file and see all this device memory without understanding that it
is special and might be unwise to be use for regular CPU only task.

I would probably want CDM memory be reported separatly from the rest of
memory. Which also most likely have repercution with memory cgroup.

My expectation is that you only want to use device memory in a process
if and only if that process also use the device to some extent. So
having new group hierarchy for this memory is probably a better path
forward.


Cheers,
Jérôme

Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread

Thread

[RFC V2 00/12] Define coherent device memory node Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-30 04:40 +0100
  [RFC V2 05/12] cpuset: Add cpuset_inc() inside cpuset_init() Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-30 04:40 +0100
    Re: [RFC V2 05/12] cpuset: Add cpuset_inc() inside cpuset_init() Dave Hansen <dave.hansen@intel.com> - 2017-01-30 19:20 +0100
    Re: [RFC V2 05/12] cpuset: Add cpuset_inc() inside cpuset_init() Mel Gorman <mgorman@suse.de> - 2017-01-30 21:50 +0100
      [RFC] cpuset: Enable changing of top_cpuset's mems_allowed nodemask Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-31 15:30 +0100
        Re: [RFC] cpuset: Enable changing of top_cpuset's mems_allowed  nodemask Mel Gorman <mgorman@suse.de> - 2017-01-31 17:10 +0100
          Re: [RFC] cpuset: Enable changing of top_cpuset's mems_allowed  nodemask Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-02-01 08:40 +0100
            Re: [RFC] cpuset: Enable changing of top_cpuset's mems_allowed  nodemask Michal Hocko <mhocko@kernel.org> - 2017-02-01 10:00 +0100
            Re: [RFC] cpuset: Enable changing of top_cpuset's mems_allowed  nodemask Mel Gorman <mgorman@suse.de> - 2017-02-01 10:20 +0100
      Re: [RFC V2 05/12] cpuset: Add cpuset_inc() inside cpuset_init() Vlastimil Babka <vbabka@suse.cz> - 2017-01-31 15:40 +0100
        Re: [RFC V2 05/12] cpuset: Add cpuset_inc() inside cpuset_init() Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-31 16:40 +0100
  [RFC V2 04/12] mm: Change mbind(MPOL_BIND) implementation for CDM nodes Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-30 04:40 +0100
  [DEBUG 16/21] mm: Enable CONFIG_MOVABLE_NODE on powerpc Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-30 04:50 +0100
  [DEBUG 18/21] mm: Add debugfs interface to dump each node's zonelist information Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-30 04:50 +0100
  [DEBUG 19/21] mm: Add migrate_virtual_range migration interface Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-30 04:50 +0100
  [DEBUG 17/21] mm: Export definition of 'zone_names' array through mmzone.h Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-30 04:50 +0100
  [DEBUG 15/21] powerpc/mm: Enable CONFIG_MOVABLE_NODE for PPC64 platform Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-30 04:50 +0100
  [DEBUG 21/21] selftests/powerpc: Add a script to perform random VMA migrations Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-30 04:50 +0100
  [DEBUG 14/21] powerpc/mm: Create numa nodes for hotplug memory Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-30 04:50 +0100
  [DEBUG 13/21] powerpc/mm: Identify coherent device memory nodes during platform init Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-30 04:50 +0100
  [DEBUG 20/21] drivers: Add two drivers for coherent device memory tests Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-30 04:50 +0100
  [RFC V2 09/12] mm: Exclude CDM marked VMAs from auto NUMA Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-30 07:10 +0100
  [RFC V2 12/12] mm: Tag VMA with VM_CDM flag explicitly during mbind(MPOL_BIND) Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-30 07:20 +0100
    Re: [RFC V2 12/12] mm: Tag VMA with VM_CDM flag explicitly during  mbind(MPOL_BIND) Dave Hansen <dave.hansen@intel.com> - 2017-01-30 19:00 +0100
      Re: [RFC V2 12/12] mm: Tag VMA with VM_CDM flag explicitly during  mbind(MPOL_BIND) Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-31 05:40 +0100
        Re: [RFC V2 12/12] mm: Tag VMA with VM_CDM flag explicitly during  mbind(MPOL_BIND) Dave Hansen <dave.hansen@intel.com> - 2017-02-07 19:10 +0100
          Re: [RFC V2 12/12] mm: Tag VMA with VM_CDM flag explicitly during  mbind(MPOL_BIND) Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-02-08 17:50 +0100
          Re: [RFC V2 12/12] mm: Tag VMA with VM_CDM flag explicitly during  mbind(MPOL_BIND) Jerome Glisse <jglisse@redhat.com> - 2017-02-08 19:40 +0100
  [RFC V2 10/12] mm: Ignore madvise(MADV_MERGEABLE) request for VM_CDM marked VMAs Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-30 10:30 +0100
  [RFC V2 11/12] mm: Tag VMA with VM_CDM flag during page fault Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-30 10:40 +0100
    Re: [RFC V2 11/12] mm: Tag VMA with VM_CDM flag during page fault Dave Hansen <dave.hansen@intel.com> - 2017-01-30 19:00 +0100
      Re: [RFC V2 11/12] mm: Tag VMA with VM_CDM flag during page fault Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-31 06:20 +0100
        Re: [RFC V2 11/12] mm: Tag VMA with VM_CDM flag during page fault Dave Hansen <dave.hansen@intel.com> - 2017-01-31 19:10 +0100
  Re: [RFC V2 00/12] Define coherent device memory node Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2017-01-31 06:50 +0100
    Re: [RFC V2 00/12] Define coherent device memory node Jerome Glisse <jglisse@redhat.com> - 2017-01-31 07:20 +0100

csiph-web