Following perfquery command can be executed on Compute node to check the Symbol Errors and Other details of Compute Nodes Ports.
perfquery <Baselid> <Port>
We can get Base lid and Port details from "ibstat" command of the Compute Node. Below is example snippet of "ibstat" command.
CA 'mlx4_0'
CA type: MT26428
Number of ports: 2
Firmware version: 2.11.2010
Hardware version: b0
Node GUID: XXXXXXXXXXXXX
System image GUID: XXXXXXXXXXXXX
Port 1:
State: Active
Physical state: LinkUp
Rate: 40
Base lid: 7
LMC: 0
SM lid: 41
Capability mask: 0x02510868
Port GUID: XXXXXXXXXXXXX
Link layer: IB
Port 2:
State: Active
Physical state: LinkUp
Rate: 40
Base lid: 9
LMC: 0
]SM lid: 41
Capability mask: 0x02510868
Port GUID: XXXXXXXXXXXXX
Link layer: IB
From above output we can see Base lid for Ports 1 and 2 of Compute Nodes. Now if we want to run perfquery on Port 1 on lid 7 command will look as follows:
perfquery 7 1
Below is example snippet of above command. If we notice Symbol Errors increasing in above command output, then it indicates that there is an issue with Compute node IB Port (bad cable, loose cable or other issues).
# Port counters: Lid 7 port 1 (CapMask: 0x1400)
PortSelect:......................1
CounterSelect:...................0x0000
SymbolErrorCounter:..............0
LinkErrorRecoveryCounter:........0
LinkDownedCounter:...............0
PortRcvErrors:...................0
PortRcvRemotePhysicalErrors:.....0
PortRcvSwitchRelayErrors:........0
PortXmitDiscards:................2
PortXmitConstraintErrors:........0
PortRcvConstraintErrors:.........0
CounterSelect2:..................0x00
LocalLinkIntegrityErrors:........0
ExcessiveBufferOverrunErrors:....0
VL15Dropped:.....................0
PortXmitData:....................4294967295
PortRcvData:.....................4294967295
PortXmitPkts:....................4294967295
PortRcvPkts:.....................1088593887
PortXmitWait:....................65418428
Products to which Article Applies
Exalogic racks using Infiniband Switches
Article Author: Tarun Boyella
