Lustre discuss - Jul 2007 - Timeout value

In the FAQ secion:

"If Lustre is configured without shared storage for failover, and a server
node fails, then a client that tries to use that node will pause until the
failed server is returned to operation. After a short delay (a
configurable timeout value), applications waiting for those nodes can be
aborted with a signal (kill or Ctrl-C), similar to the NFS soft-mount
mode."

"a configurable timeout value" where do I find this in the
documentation?
I would like to decrease this value.

-- 
Jeremy Mann
jeremy@biochem.uthscsa.edu

University of Texas Health Science Center
Bioinformatics Core Facility
http://www.bioinformatics.uthscsa.edu
Phone: (210) 567-2672

On Jul 06, 2007  14:45 -0500, Jeremy Mann wrote:
> "If Lustre is configured without shared storage for failover, and a
server
> node fails, then a client that tries to use that node will pause until the
> failed server is returned to operation. After a short delay (a
> configurable timeout value), applications waiting for those nodes can be
> aborted with a signal (kill or Ctrl-C), similar to the NFS soft-mount
> mode."
> 
> "a configurable timeout value" where do I find this in the
documentation?
> I would like to decrease this value.
This is "obd_timeout", get/set via "sysctl [-w]
lustre.timeout[=value]"
at runtime, or via "--timeout=" in the lustre config.  The default is
100s,
but I''d caution against lowering it too much, as that can induce
failures
in other parts of the code, especially under heavy system load.

Cheers, Andreas
--
Andreas Dilger
Principal Software Engineer
Cluster File Systems, Inc.