[openib-general] Question

[Ronald G. Minnich]

On Mon, 28 Feb 2005, Hal Rosenstock wrote:

> The opensm log preferably in verbose (-V) mode.

It's a long log :-)

Here is the point at which it goes to pieces.


[1109360115:000609200][40BFF970] -> osm_pkey_rcv_process: Got 
GetResp(PKey) block:1 port_num 1 with GUID = 0x2c90108d192e0 for parent 
node GUID = 0x2c90108d192e0, TID = 0x6a39.
[1109360115:000609563][40BFF970] -> Received a SMP on a 10 hop path:
                                Initial path = 
[0][1][3][5][5][7][3][1][3][1][2]
                                Return path  = 
[0][4][4][2][6][7][6][1][2][1][1]
[1109360115:000609574][40BFF970] -> __osm_ni_rcv_process_new: Discovered 
new Channel Adapter node,
                                GUID = 0x2c90108666d50, TID = 0x6a3a.
[1109360115:000609724][40BFF970] -> osm_pkey_rcv_process: Got 
GetResp(PKey) block:0 port_num 2 with GUID = 0x2c90108d192e0 for parent 
node GUID = 0x2c90108d192e0, TID = 0x6a3b.
[1109360115:000609887][40BFF970] -> osm_pkey_rcv_process: Got 
GetResp(PKey) block:1 port_num 2 with GUID = 0x2c90108d192e0 for parent 
node GUID = 0x2c90108d192e0, TID = 0x6a3c.
[1109360115:000610061][40BFF970] -> __osm_ni_rcv_process_existing: 
Rediscovered Switch node 0x2c90108e9c1e8
                                TID = 0x6a3d, discovered 6 times already.
[1109360115:000610226][40BFF970] -> osm_pkey_rcv_process: Got 
GetResp(PKey) block:0 port_num 3 with GUID = 0x2c90108d192e0 for parent 
node GUID = 0x2c90108d192e0, TID = 0x6a3e.
[1109360115:000610391][40BFF970] -> osm_pkey_rcv_process: Got 
GetResp(PKey) block:1 port_num 3 with GUID = 0x2c90108d192e0 for parent 
node GUID = 0x2c90108d192e0, TID = 0x6a3f.
[1109360115:000710603][411FF970] -> umad_receiver: send completed with 
error(method=1 attr=11) -- dropping.


Form then on, that's all I see:
[1109360115:000710603][411FF970] -> umad_receiver: send completed with 
error(method=1 attr=11) -- dropping.

But to this point it's found a lot: I've got about 16710 messages in there 
with 'GUID = ' in them. 

I do get a bunch of these:
 Bad LinearFDBTop value = 0xC000 on switch 0x2c90108d19820.


ron