HPE 9000 and HPE e3000 Servers
cancel
Showing results for 
Search instead for 
Did you mean: 

single point of failure for Superdome

 
Jimmy Tom_2
Frequent Advisor

single point of failure for Superdome

Can anyone tell me what are the single point of failure that will cause the entire Superdome to reboot or crash? From what I know is the system clock and the backplane. Are there anything else?

Thanks in Advance.
3 REPLIES 3
Thierry Poels_1
Honored Contributor

Re: single point of failure for Superdome

- a bomb
- a fire
- the sysadmin
- ...


Thierry
All unix flavours are exactly the same . . . . . . . . . . for end users anyway.
James Anker
Valued Contributor

Re: single point of failure for Superdome

Jimmy,

You are indeed correct with 2 x of them, official line is this:

"A single Superdome system contains single points of failure (SPOFs). The single points of failure are the
system clock, the system backplane and the power monitor
â ¢ To configure a cluster with no SPOF, the membership must extend beyond a single cabinet. The cluster must
be configured such that the failure of a single cabinet does not result in the failure of a majority of the nodes
in the cluster. The cluster lock device must be powered independently of the cabinets containing the cluster
nodes. "

Cheers

Ja
Jov
Honored Contributor

Re: single point of failure for Superdome

Hi,
Can anyone confirm the Core I/O in a partition will be the Single Point of Failure?

Going thru all the Superdome docos, it repeatly stated one active Core I/O per partition. Thus, I wonder if the active Core I/O fails, can it be configured to dynamically failover to a non-acitive one?

regards

Jov