<div dir="ltr"><br><div class="gmail_extra"><br><div class="gmail_quote">On Wed, Jun 14, 2017 at 8:21 AM, Michael Bringmann <span dir="ltr"><<a href="mailto:mwb@linux.vnet.ibm.com" target="_blank">mwb@linux.vnet.ibm.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">On a related note, we are discussing the addition of 2 new device-tree properties<br>
with Pete Heyrman and his fellows that should simplify the determination of the<br>
set of required nodes.<br>
<br>
* One property would provide the total/max number of nodes needed by the kernel<br>
on the current hardware.<br></blockquote><div><br></div><div>Yes, that would be nice to have</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
* A second property would provide the total/max number of nodes that the kernel<br>
could use on any system to which it could be migrated.<br>
<br></blockquote><div><br></div><div>Not sure about this one, are you suggesting more memory can be added</div><div>depending on the migration target?</div><div><br></div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
These properties aren't available, yet, and it takes time to define new properties<br>
in the PAPR and have them implemented in pHyp and the kernel. As an intermediary<br>
step, the systems which are doing a lot of dynamic hot-add/hot-remove configuration<br>
could provide equivalent information to the PowerPC kernel with a command line<br>
parameter. The 'numa.c' code would then read this value and fill in the necessary<br>
entries in the 'node_possible_map'.<br>
<br>
Would you foresee any problems with using such a feature?<br></blockquote><div><br></div><div><br></div><div>Balbir Singh </div></div></div></div>