Uploaded image for project: 'RHEL'
  1. RHEL
  2. RHEL-6084

[RHEL9.3] various number of cores files detected when running fabtests over CXGB4 iWARP device

    • Icon: Bug Bug
    • Resolution: Done
    • Icon: Undefined Undefined
    • None
    • rhel-9.3.0
    • fabtests
    • None
    • None
    • sst_network_drivers
    • ssg_networking
    • None
    • False
    • Hide

      None

      Show
      None
    • None
    • None
    • None
    • None
    • If docs needed, set a value
    • None

      Description of problem:

      Various number of core files generated while testing "fabtests" on CXGB4 iWARP device. One time it generated cores from almost all fi_xxxxx test modules.
      However, when ran all by itself, it generated 2 cores from "/usr/bin/fi_multi_ep" as shown below.

      Version-Release number of selected component (if applicable):

      Clients: rdma-dev-13
      Servers: rdma-dev-12

      DISTRO=RHEL-9.3.0-20230603.0

      + [23-06-03 21:02:07] cat /etc/redhat-release
      Red Hat Enterprise Linux release 9.3 Beta (Plow)

      + [23-06-03 21:02:07] uname -a
      Linux rdma-dev-13.rdma.lab.eng.rdu2.redhat.com 5.14.0-319.el9.x86_64 #1 SMP PREEMPT_DYNAMIC Fri May 26 17:01:24 EDT 2023 x86_64 x86_64 x86_64 GNU/Linux

      + [23-06-03 21:02:07] cat /proc/cmdline
      BOOT_IMAGE=(hd0,msdos1)/vmlinuz-5.14.0-319.el9.x86_64 root=UUID=ecc06464-c7cf-4df9-a3f6-5fd58052088c ro intel_idle.max_cstate=0 intremap=no_x2apic_optout processor.max_cstate=0 console=tty0 rd_NO_PLYMOUTH crashkernel=1G-4G:192M,4G-64G:256M,64G-:512M resume=UUID=47223275-b449-4a4b-aafe-ce865e8572e1 console=ttyS1,115200n81

      + [23-06-03 21:02:07] rpm -q rdma-core linux-firmware
      rdma-core-46.0-1.el9.x86_64
      linux-firmware-20230404-134.el9.noarch

      + [23-06-03 21:02:07] tail /sys/class/infiniband/cxgb4_0/fw_ver
      1.27.1.0

      + [23-06-03 21:02:07] lspci
      + [23-06-03 21:02:07] grep -i -e ethernet -e infiniband -e omni -e ConnectX
      03:00.0 Ethernet controller: Broadcom Inc. and subsidiaries NetXtreme BCM5717 Gigabit Ethernet PCIe (rev 10)
      03:00.1 Ethernet controller: Broadcom Inc. and subsidiaries NetXtreme BCM5717 Gigabit Ethernet PCIe (rev 10)
      05:00.0 Ethernet controller: Chelsio Communications Inc T62100-LP-CR Unified Wire Ethernet Controller
      05:00.1 Ethernet controller: Chelsio Communications Inc T62100-LP-CR Unified Wire Ethernet Controller
      05:00.2 Ethernet controller: Chelsio Communications Inc T62100-LP-CR Unified Wire Ethernet Controller
      05:00.3 Ethernet controller: Chelsio Communications Inc T62100-LP-CR Unified Wire Ethernet Controller
      05:00.4 Ethernet controller: Chelsio Communications Inc T62100-LP-CR Unified Wire Ethernet Controller

      How reproducible:

      Steps to Reproduce:
      1./usr/bin/runfabtests.sh -T 20 -vvv -t all '"net"' 172.31.50.112 172.31.50.113
      2.
      3.

      Actual results:

      Running python As root:
      TIME PID UID GID SIG COREFILE EXE SIZE
      Sat 2023-06-03 21:57:03 EDT 122782 0 0 SIGABRT present /usr/bin/fi_multi_ep 613.2K
      Sun 2023-06-04 01:36:24 EDT 215447 0 0 SIGABRT present /usr/bin/fi_multi_ep 609.1K
      total 1236
      rw-r----. 1 root root 627993 Jun 3 21:57 core.fi_multi_ep.0.79b0c3468edb44bba50875b07d02ae25.122782.1685843821000000.zst
      rw-r----. 1 root root 623766 Jun 4 01:36 core.fi_multi_ep.0.79b0c3468edb44bba50875b07d02ae25.215447.1685856982000000.zst
      Red Hat Enterprise Linux release 9.3 Beta (Plow)

      Expected results:

      No core files generated

      Additional info:

            mschmidt@redhat.com Michal Schmidt
            bchae Brian Chae
            RH Bugzilla Integration RH Bugzilla Integration
            infiniband-qe infiniband-qe infiniband-qe infiniband-qe
            Votes:
            0 Vote for this issue
            Watchers:
            1 Start watching this issue

              Created:
              Updated:
              Resolved: