Attachments don't work here. You'll have to file a bug on sourceforge, or file an IPS for factory support (and tell me the number so it doesn't sit).
Todd Fujinaka Software Application Engineer Networking Division (ND) Intel Corporation todd.fujin...@intel.com (503) 712-4565 -----Original Message----- From: Ben Greear [mailto:gree...@candelatech.com] Sent: Tuesday, December 06, 2016 4:12 PM To: Rustad, Mark D <mark.d.rus...@intel.com> Cc: e1000-devel list <e1000-devel@lists.sourceforge.net> Subject: Re: [E1000-devel] ixgbe port missing, "PCI INT B: failed to register GSI" On 12/06/2016 04:03 PM, Rustad, Mark D wrote: > Ben Greear <gree...@candelatech.com> wrote: > >> [ 6.405914] ixgbe 0000:05:00.1: Intel(R) 10 Gigabit Network Connection >> [ 6.554373] ixgbe 0000:06:00.0: Multiqueue Enabled: Rx Queue count = 8, >> Tx Queue count = 8 >> [ 6.554501] ixgbe 0000:06:00.0: PCI Express bandwidth of 32GT/s available >> [ 6.554504] ixgbe 0000:06:00.0: (Speed:5.0GT/s, Width: x8, Encoding >> Loss:20%) >> [ 6.554588] ixgbe 0000:06:00.0: MAC: 2, PHY: 15, SFP+: 5, PBA No: >> FFFFFF-0FF >> [ 6.554590] ixgbe 0000:06:00.0: 00:e0:ed:79:06:56 >> [ 6.556994] ixgbe 0000:06:00.0: Intel(R) 10 Gigabit Network Connection >> [ 6.557160] ixgbe 0000:06:00.1: PCI INT B: failed to register GSI >> [ 6.557169] ixgbe: probe of 0000:06:00.1 failed with error -28 > > Comparing the successful initializations to the failing one, I can see > that all of the successful ones were able to use MSI-X interrupts, so > multiqueue was enabled. It appears that the failing one did not get > MSI-X and so tried to fail back to legacy interrupts and failed to get that > as well - or at least it failed to get the second IRQ that the driver would > use in that mode. If the platform only provides one legacy interrupt per > slot, it could fail like this. Still, the real problem is not getting MSI-X, > because these devices really only work well with MSI-X interrupts. > > Without any platform information, this could either be a hardware > limitation - not enough MSI-X vectors available - or a platform firmware > problem. Can you send information on your platform? The output from 'lspci > -vvv' and 'uname -a' might yield more clues. > > The full dmesg log would also be helpful because there should be a lot of > information in there on the interrupts available. Thanks for the quick response. lspci and dmesg are attached. We booted a 4.7.10+ kernel in this case, but same symptom. I forgot to mention earlier, we have 4 x 4-port NICs in here too, so likely we are pushing the IRQ resources. Any way to configure the NICs to use fewer IRQ resources and still perform at least moderately well? Thanks, Ben > > -- > Mark Rustad, Networking Division, Intel Corporation -- Ben Greear <gree...@candelatech.com> Candela Technologies Inc http://www.candelatech.com ------------------------------------------------------------------------------ Developer Access Program for Intel Xeon Phi Processors Access to Intel Xeon Phi processor-based developer platforms. With one year of Intel Parallel Studio XE. Training and support from Colfax. Order your platform today.http://sdm.link/xeonphi _______________________________________________ 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
