[Beowulf] Supercomputers face growing resilience problems
john.hearns at mclaren.com
Fri Nov 23 01:22:49 PST 2012
On 22/11/12 21:39, Hearns, John wrote:
> How often have you run a parallel shell to grep through logs on a
> buch of nodes to look for a certain string or a certain event?
That's what remote syslog is for. :-)
But of course.
The SGI ICE clusters I manage use remote syslog on the nodes to log all events to the rack leaders.
It is a nice architecture.
So yes, I don't spawn off parallel shells that often - I grep through the rack leader's logs.
The contents of this email are confidential and for the exclusive use of the intended recipient. If you receive this email in error you should not copy it, retransmit it, use it or disclose its contents but should return it to the sender immediately and delete your copy.
More information about the Beowulf