On 10/28/2024 11:49 PM, Stephen Hemminger wrote:
On Mon, 28 Oct 2024 11:18:22 +0200
"Minggang Li(Gavin)" <gav...@nvidia.com> wrote:
+* **Updated NVIDIA mlx5 driver.**
+
+ Optimized port probe in large scale.
+ In previous release, it would take long time to probe one VF/SF if
+ hundreds of VF/SF were created in the system. With this newly introduced
+ feature optimization, the time to probe a VF/SF will be reduced greatly in
+ large scale, eg hundreds of VF/SFs. This feature is controlled through the
+ ``probe_opt_en`` device argument. Setting it to a non-zero value indicates
+ the application will enable this functionality when probing a device. This
+ feature relies on a feature of RDMA driver to be release in incoming
+ upstream kernel 6.13 or the equivalent in OFED 24.10, ie. RDMA monitor.
+ For further information on the devargs limitation, see
+ "doc/guides/nics/mlx5.rst".
Too wordy. Many filler words and phrases.
And no clear description of when to use and when not to use.
ACK
