3 Replies Latest reply on Jul 25, 2018 3:22 AM by karen

    mst start fails with ConnectX-4 on ppc64le

    vaibhavs

      Hi,

       

      I'm trying to setup VFs using SRIOV on a ppc64le machine

       

      $ lsb_release -a

      No LSB modules are available.

      Distributor ID: Ubuntu

      Description:    Ubuntu 16.04.4 LTS

      Release:        16.04

      Codename:       xenial


      $ uname -a

       

      Linux p006n03 4.10.0-35-generic #39~16.04.1-Ubuntu SMP Wed Sep 13 08:59:44 UTC 2017 ppc64le ppc64le ppc64le GNU/Linux

       

      $ lspci | grep Mellanox

      0000:01:00.0 Ethernet controller: Mellanox Technologies MT27700 Family [ConnectX-4]

      0040:01:00.0 Ethernet controller: Mellanox Technologies MT27700 Family [ConnectX-4]

       

      First i installed MLNX_OFED driver as per steps: https://community.mellanox.com/docs/DOC-2688

      Then i installed latest MFT (4.10.0) for ppc64le from here: http://www.mellanox.com/page/management_tools

       

      Running "mst start" subsequently fails however

       

      $ sudo mst start

      Starting MST (Mellanox Software Tools) driver set

      Loading MST PCI module - Success

      Loading MST PCI configuration module - Success

      Create devices

      /usr/bin/mst: line 382: 13070 Segmentation fault      (core dumped) ${mbindir}/minit $fullname ${busdevfn} 88 92

      cat: /dev/mst/mt4115_pci_cr0: No such file or directory

      /usr/bin/mst: line 382: 13132 Segmentation fault      (core dumped) ${mbindir}/minit $fullname ${busdevfn} 88 92

      cat: /dev/mst/mt4115_pci_cr1: No such file or directory

      Unloading MST PCI module (unused) - Success

       

      Unloading MST PCI configuration module (unused) - Success

       

      What could be the reason for this error?

       

      I ultimately want to enable VFs on the CX4 as per steps here: https://community.mellanox.com/docs/DOC-2386 but cannot proceed due to this error

        • Re: mst start fails with ConnectX-4 on ppc64le
          karen

          Hi Sood,

           

          Do you have Advance Toolchain Runtime installed on the machine?

          If yes please not for the following known issue and workaround at page 16 :

          http://www.mellanox.com/related-docs/MFT/MFT_4_10_0_Release_Notes.pdf

           

          Regards,

          Karen.

            • Re: mst start fails with ConnectX-4 on ppc64le
              vaibhavs

              Hi Karen,

               

              Thanks for your response. I do have the Advanced Toolchain Runtime installed.

               

              $ sudo apt list --installed | grep advance-toolchain

              WARNING: apt does not have a stable CLI interface. Use with caution in scripts.

              advance-toolchain-at10.0-devel/now 10.0-3 ppc64el [installed,local]

              advance-toolchain-at10.0-mcore-libs/now 10.0-3 ppc64el [installed,local]

              advance-toolchain-at10.0-perf/now 10.0-3 ppc64el [installed,local]

              advance-toolchain-at10.0-runtime/now 10.0-3 ppc64el [installed,local]

              advance-toolchain-at7.1-devel/trusty,now 7.1-5 ppc64el [installed]

              advance-toolchain-at7.1-mcore-libs/trusty,now 7.1-5 ppc64el [installed]

              advance-toolchain-at7.1-perf/trusty,now 7.1-5 ppc64el [installed]

              advance-toolchain-at7.1-runtime/trusty,now 7.1-5 ppc64el [installed]

               

              I did the export as mentioned(libc.so.6 exists on my system) but still see the error

               

              $ echo $LD_PRELOAD

              /lib/powerpc64le-linux-gnu/libc.so.6

               

              I still see the error however.

               

              ${mbindir}/minit from /usr/bin/mst gives a segmentation fault for some reason (as seen in the logs from my previous message), not sure why that happens