INFINIBAND: How To Test If Infiniband (IB) HCA Card Is Healthy?

Below command can be executed on the host which has IB HCA card to validated if Infiniband HCA Card is healthy.

/usr/bin/hca_self_test.ofed

Below is snippet of above command output. In below outputs you should see PASS result for "PCI Device Check", "Host Driver RPM Check", "Error Counter Check on HCA" and "Host Driver Initialization: fields.

---- Performing InfiniBand HCA Self Test ----
Number of HCAs Detected ................ 1
PCI Device Check ....................... PASS
Kernel Arch ............................ x86_64
Host Driver Version .................... OFED-IOV-1.5.5-1.0.0151: 1.5.5.151-2.6.32_400.34.1.el5uek
Host Driver RPM Check .................. PASS
HCA Firmware on HCA #0 ................. v2.11.2010
HCA Firmware Check for HCA #0 .......... NA
REASON: NO required fw version
Host Driver Initialization ............. PASS
Number of HCA Ports Active ............. 2
Port State of Port #1 on HCA #0 ........ UP 4X QDR
Port State of Port #2 on HCA #0 ........ UP 4X QDR
Error Counter Check on HCA #0 .......... PASS
Kernel Syslog Check .................... PASS
Node GUID on HCA #0 .................... 00:XX:XX:00:XX:28:XX:XX

Products to which Article Applies

All Hosts using Infiniband HCA cards.

Additional References

http://www.mellanox.com/related-docs/prod_software/Mellanox_OFED%20_Linux_Installation_Guide_1_5_2-2_1_0.pdf


 

tarun boyella