On 12/19/22 10:55, David Hildenbrand wrote:
> 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 <mpriv...@redhat.com>
>>>> ---
>>>
>>> [...]
>>>
>>>> +#ifdef HAVE_NUMA_SET_PREFERRED_MANY
>
> That should be HAVE_NUMA_HAS_PREFERRED_MANY, right?
>
Oops, yes. Do you want me to send v3?
Michal
