<div dir="ltr"><div dir="ltr"><br></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Fri, May 31, 2024 at 12:44 PM Luca Vizzarro <<a href="mailto:Luca.Vizzarro@arm.com">Luca.Vizzarro@arm.com</a>> wrote:</div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<br>
In my testing of Jeremy's patches which depend on this one ("Add second <br>
scatter test case"), I've discovered that the Intel E810-C NIC I am <br>
using to test does not automatically show "RX scattered packets: on". <br>
But I've noticed it does if the MTU is set to something big like 9000.<br>
<br>
I've tested a change of this by adding:<br>
<br>
self.set_port_mtu(0, 9000)<br>
> + rxq_info = self.send_command(command)<br>
self.set_port_mtu(1, 9000)<br>
<br>
And it seems to work alright. I've also tested this specific change with <br>
Mellanox NICs and it didn't seem to affect them at all. No errors or <br>
problems and they still showed "RX scattered packets: off" as expected.<br>
<br>
The `set_port_mtu` method comes from Jeremy's patch...<br><br>
<br></blockquote><div><br></div><div>Hi Jeremy,</div><div><br></div><div>Sounds like Luca's way ahead of me here, but I wanted to note that I did run from the capabilities patch + Jeremy's new Scatter patch, across these NICs:</div><div><br></div><div>Mellanox CX5</div><div>Broadcom 57414 25G</div><div>Broadcom P2100G </div><div>Intel XL710 40G </div><div><br></div><div>And in call cases scatter_mbuf_2048 skips, and scatter_mbuf_2048_with_offload runs. </div><div><br></div><div>The 2nd case passed in all cases, excluding the XL710 where it errors with "Test pmd failed to set fwd mode to mac." I can double check that to ensure there was no setup error on my part, but I think the more interesting part is the skip on the non-offload testcase, as I recall Jeremy saying that the XL710 was expected to natively support scatter and run the first testcase.<br></div><div><br></div><div>I can do a rerun, adding in the MTU modifier, and see if the same adjustment happens as with the E810 as Luca describes.</div></div></div>