[Users] opensm messages

[Hal Rosenstock]

Hi Viswa,

Since Hop Ptr is 0, it's the local IB device that's timing out. There is no
LID or GUID as direct route SMPs are being used.

Is this from OpenSM running on a SIF CA port ?

-- Hal

On Sat, Sep 3, 2016 at 7:04 PM, Viswa Nath <viswa.nath at oracle.com> wrote:

> Hi All,
>
> The following are some logs from opensm.
> Is there any way to know which link or path in the ib network is timing
> out ?   Is there anything in these messages which will help us know that ?
>  Does TID or ERR codes such as 3113 or 5411 help to know what is timing out
> and why ?
>
> Aug 29 07:31:46 086122 [B5EF1B90] 0x01 -> umad_receiver: ERR 5411: DR SMP
> Send completed with error -- dropping
>             Method 0x1, Attr 0x15, TID 0xc0a03345c, Hop Ptr: 0x0
> Aug 29 07:31:46 086122 [B5EF1B90] 0x01 -> __osm_sm_mad_ctrl_send_err_cb:
> ERR 3113: SubnGet(PortInfo) completed in error (IB_TIMEOUT): attr_mod 0x0,
> TID 0xa03345c
> Aug 29 07:31:46 086122 [B5EF1B90] 0x01 -> umad_receiver: ERR 5411: DR SMP
> Send completed with error -- dropping
>             Method 0x1, Attr 0x15, TID 0xc0a033460, Hop Ptr: 0x0
> Aug 29 07:31:46 086122 [B5EF1B90] 0x01 -> __osm_sm_mad_ctrl_send_err_cb:
> ERR 3113: SubnGet(PortInfo) completed in error (IB_TIMEOUT): attr_mod 0x0,
> TID 0xa033460
>
> It would have been ideal if these messages contain the LIDs/GUIDs and/or
> port numbers in the DR MAD that timed out or dropped.
>
> Thanks.
> Viswa
>
>
>
> _______________________________________________
> Users mailing list
> Users at lists.openfabrics.org
> http://lists.openfabrics.org/mailman/listinfo/users
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openfabrics.org/pipermail/users/attachments/20160906/af95af19/attachment.html>