Well what I am seeing seems to be an intermittent issue, though I am having no problem spawning 7 VFs which is my default environment.
My setup is just loading the PF driver, enabling SR-IOV, reloading the VF driver, and bringing up the PFs and VFs in separate namespaces. Sometimes it is working without any errors, but the majority of the time I am seeing the messages about "Device is still in reset" repeating and eventually scrolling of the screen. I'm not completely sure if my firmware is current. Output from "ethtool -i" is included below just in case this might be a firmware thing and I need to update: driver: i40e version: 1.5.1-k firmware-version: 4.26 0x8000152d 0.0.0 bus-info: 0000:02:00.0 supports-statistics: yes supports-test: yes supports-eeprom-access: yes supports-register-dump: yes supports-priv-flags: yes - Alex On Wed, Mar 16, 2016 at 11:12 AM, Bowers, AndrewX <andrewx.bow...@intel.com> wrote: > I'm not seeing the reset, but I get a permission denied error trying to echo > 4 to /sys/class/net/[device]/device/sriov_numvfs and an ls of the directory > shows no sriov_numvfs file present... I can do it with my ixgbe device, but > not my i40e device. I went back to a few different kernels from earlier this > week, last week, and the week before with the same results. Since I know it > WAS working earlier, I tried the stock kernel and get "no such file or > directory"... I'm thinking it's an issue with my card, although I wonder if > yours is related. I'll try a few things with mine and see if I get anywhere. > >> -----Original Message----- >> From: Intel-wired-lan [mailto:intel-wired-lan-boun...@lists.osuosl.org] On >> Behalf Of Alexander Duyck >> Sent: Wednesday, March 16, 2016 10:21 AM >> To: e1000-devel@lists.sourceforge.net; intel-wired-lan <intel-wired- >> l...@lists.osuosl.org> >> Subject: [Intel-wired-lan] Latest dev-queue pull has i40e VFs reporting >> "Device still in reset" >> >> So my system with the latest pull of the dev-queue branch is stuck reporting >> "Device is still in reset (-16), retrying" for one or more VFs after I >> reload the >> drivers. I've been trying to bisect the issue but haven't been having much >> luck. >> >> Just wanted to see if anyone in Intel was aware of the issue, otherwise I >> will >> probably re-run my bisection with a full system reset between patches as I >> suspect I may be having issues reproducing it due to stray data being left in >> from earlier driver loads. >> >> - Alex >> _______________________________________________ >> Intel-wired-lan mailing list >> intel-wired-...@lists.osuosl.org >> http://lists.osuosl.org/mailman/listinfo/intel-wired-lan ------------------------------------------------------------------------------ Transform Data into Opportunity. Accelerate data analysis in your applications with Intel Data Analytics Acceleration Library. Click to learn more. http://pubads.g.doubleclick.net/gampad/clk?id=278785231&iu=/4140 _______________________________________________ E1000-devel mailing list E1000-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/e1000-devel To learn more about Intel® Ethernet, visit http://communities.intel.com/community/wired
