Re: [PATCH v2] hostmem: Honor multiple preferred nodes if possible

[David Hildenbrand <david@redhat.com>]

On 16.12.22 14:47, Michal Prívozník wrote:
> On 12/16/22 14:41, David Hildenbrand wrote:
>> On 15.12.22 10:55, Michal Privoznik wrote:
>>> If a memory-backend is configured with mode
>>> HOST_MEM_POLICY_PREFERRED then
>>> host_memory_backend_memory_complete() calls mbind() as:
>>>
>>>     mbind(..., MPOL_PREFERRED, nodemask, ...);
>>>
>>> Here, 'nodemask' is a bitmap of host NUMA nodes and corresponds
>>> to the .host-nodes attribute. Therefore, there can be multiple
>>> nodes specified. However, the documentation to MPOL_PREFERRED
>>> says:
>>>
>>>     MPOL_PREFERRED
>>>       This mode sets the preferred node for allocation. ...
>>>       If nodemask specifies more than one node ID, the first node
>>>       in the mask will be selected as the preferred node.
>>>
>>> Therefore, only the first node is honored and the rest is
>>> silently ignored. Well, with recent changes to the kernel and
>>> numactl we can do better.
>>>
>>> The Linux kernel added in v5.15 via commit cfcaa66f8032
>>> ("mm/hugetlb: add support for mempolicy MPOL_PREFERRED_MANY")
>>> support for MPOL_PREFERRED_MANY, which accepts multiple preferred
>>> NUMA nodes instead.
>>>
>>> Then, numa_has_preferred_many() API was introduced to numactl
>>> (v2.0.15~26) allowing applications to query kernel support.
>>>
>>> Wiring this all together, we can pass MPOL_PREFERRED_MANY to the
>>> mbind() call instead and stop ignoring multiple nodes, silently.
>>>
>>> Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
>>> ---
>>
>> [...]
>>
>>> +#ifdef HAVE_NUMA_SET_PREFERRED_MANY

That should be HAVE_NUMA_HAS_PREFERRED_MANY, right?

-- 
Thanks,

David / dhildenb