On Wed, Jul 13, 2022 at 05:50:43PM +0200, Olivier Matz wrote: > The dev->device.numa_node field is set by the bus driver for each device > it manages to indicate on which NUMA node this device lies. > > When this information is unknown, the assigned value is not consistent > across the bus drivers. In v22.11, the value will be set to -1 in > this case. > > Link: > https://patches.dpdk.org/project/dpdk/patch/20211026090610.10823-1-houssem.bouh...@6wind.com/ > > Signed-off-by: Olivier Matz <olivier.m...@6wind.com> > --- > doc/guides/rel_notes/deprecation.rst | 6 ++++++ > 1 file changed, 6 insertions(+) > > diff --git a/doc/guides/rel_notes/deprecation.rst > b/doc/guides/rel_notes/deprecation.rst > index 4e5b23c53d..5f269bf527 100644 > --- a/doc/guides/rel_notes/deprecation.rst > +++ b/doc/guides/rel_notes/deprecation.rst > @@ -125,3 +125,9 @@ Deprecation Notices > applications should be updated to use the ``dmadev`` library instead, > with the underlying HW-functionality being provided by the ``ioat`` or > ``idxd`` dma drivers > + > +* bus: The ``dev->device.numa_node`` field is set by the bus driver for > + each device it manages to indicate on which NUMA node this device > + lies. When this information is unknown, the assigned value is not > + consistent across the bus drivers. In v22.11, the value will be set > + to -1 in this case.
Acked-by: Bruce Richardson <bruce.richard...@intel.com> Couple of minor rewording suggestions: * "the bus driver" seems wrong in the first line as we haven't referred to one in particular. How about "...set by each bus driver for every device..." * "the assigned value is not consistent across the bus drivers" - this reads a little strange to me and I find it unclear. Not sure how to reword it, maybe something like: "each bus driver selects its own value to set. To resolve this inconsistency, in v22.11, the device numa_node value will be set to -1 by all bus drivers when the actual NUMA information is unavailable." > -- > 2.30.2 >
