Hi all,
We had an issue with one of our ESXi5.5 hosts in our HA Cluster this weekend.
Hardware: Dell Blade M620, Broadcom BCM57810 10Gb
It threw a PSOD complaining about PCPU no heart beat and showing broadcom errors (see pic attached).
Going through the vmkernel logs it seems that one of the HBAs failed
Extract from vmkernel.log
2014-12-05T23:13:58.377Z cpu8:10592052)WARNING: LinScsi: SCSILinuxAbortCommands:1837: Failed, Driver bnx2i, for vmhba36
...
2014-12-05T23:14:11.151Z cpu0:33497)<1>bnx2i::0x4109c61eab40: ####CID leaked bnx2i_tear_down_conn: sess 0x4109c75f4738 ep 0x4109dc859690 {0x5a, 0x1a}
...
2014-12-05T23:14:11.401Z cpu6:33497)bnx2i::0x4109c61eab40: bnx2i_conn_stop::vmnic3 - sess 0x4109c75f9948 conn 0x4109c75f9d20, icid 41, cmd stats={p=0,a=1,ts=1950037,tc=1950036}, ofld_conns 9
I will check whether there are new drivers available, but also including pic of current driver details....
Has anyone come across this before?
Am I right in assuming that the issue is with the physical nic?
What is strange is that in the vmkernel log file I cannot see any problems from the other 10Gb card (same model, I know it should be a different vendor) which should keep working an not failing the host (heartbeat).
Comments are appreciated.
