[ofa-general] ibpanic

[Tziporet Koren]

Pawel Dziekonski wrote:
> Hi,
>
> today I got the following:
>
> kernel: ib_mthca 0000:06:00.0: SW2HW_MPT failed (-11)
> perfquery: ibpanic: [20876] madrpc_init: client_register for mgmt 1 failed: (Cannot allocate memory)
> kernel: ib_mthca 0000:06:00.0: SW2HW_MPT failed (-11)
> perfquery: ibpanic: [21040] madrpc_init: client_register for mgmt 1 failed: (Cannot allocate memory)
> kernel: ib_mthca 0000:06:00.0: SW2HW_MPT failed (-11)
> perfquery: ibpanic: [21050] madrpc_init: client_register for mgmt 1 failed: (Cannot allocate memory)
> kernel: ib_mthca 0000:06:00.0: SW2HW_MPT failed (-11)
> perfquery: ibpanic: [21137] madrpc_init: client_register for mgmt 1 failed: (Cannot allocate memory)
> kernel: ib_mthca 0000:06:00.0: SW2HW_MPT failed (-11)
> perfquery: ibpanic: [21246] madrpc_init: client_register for mgmt 1 failed: (Cannot allocate memory)
> kernel: ib_mthca 0000:06:00.0: SW2HW_MPT failed (-11)
> perfquery: ibpanic: [21256] madrpc_init: client_register for mgmt 1 failed: (Cannot allocate memory)
> kernel: ib_mthca 0000:06:00.0: SW2HW_MPT failed (-11)
> perfquery: ibpanic: [21343] madrpc_init: client_register for mgmt 1 failed: (Cannot allocate memory)
> kernel: ib_mthca 0000:06:00.0: SW2HW_MPT failed (-11)
> perfquery: ibpanic: [21431] madrpc_init: client_register for mgmt 1 failed: (Cannot allocate memory)
> kernel: ib_mthca 0000:06:00.0: SW2HW_MPT failed (-11)
> perfquery: ibpanic: [21441] madrpc_init: client_register for mgmt 1 failed: (Cannot allocate memory)
> kernel: ib_mthca 0000:06:00.0: SW2HW_MPT failed (-11)
> perfquery: ibpanic: [21528] madrpc_init: client_register for mgmt 1 failed: (Cannot allocate memory)
> kernel: NETDEV WATCHDOG: ib0: transmit timed out
> kernel: ib0: transmit timeout: latency 9037 msecs
> kernel: ib0: queue stopped 1, tx_head 35341, tx_tail 35213
> kernel: NETDEV WATCHDOG: ib0: transmit timed out
> kernel: ib0: transmit timeout: latency 10087 msecs
> kernel: ib0: queue stopped 1, tx_head 35341, tx_tail 35213
>
> Seems that IB connection is lost completely (lustre not working, can't ping
> remote IPoIB addresses etc.).
>
> Is it a hardware problem with IB iface or something else?
>
> regards, P
>
> # ibv_devinfo
> hca_id: mthca0
>         fw_ver:                 1.2.0
>         node_guid:                      0030:487e:0c06:0000
>         sys_image_guid:                 0030:487e:0c06:0003
>         vendor_id:                      0x02c9
>         vendor_part_id:                 25204
>         hw_ver:                 0xA0
>         board_id:               SM_0000000003
>         phys_port_cnt:                  1
>                 port:   1
>                   state:                        PORT_INIT (2)
>                   max_mtu:              2048 (4)
>                   active_mtu:           2048 (4)
>                   sm_lid:                       1
>                   port_lid:             448
>                   port_lmc:             0x00
>
>
>
>   
It seems HW issue but to ensure it can you see if it also happened with 
OFED 1.4?
If yes please approach Mellanox support  since you might need a FW update

Tziporet
>
>