Hi All,
I want to start by saying I am not a member of the
LAM development team and that the utility described
herein is not endorsed by the LAM team or by anybody
else, I am simply making it available as a possibly
useful tool. I hope this is not considered abuse of
this list.
I wrote a little cluster inspection/noodling utility
that folks here are finding useful.
Probably the most interesting thing it does is allow
long running tasks to be run on many nodes in parallel,
while collecting all of the stdout/stderr/syslog output
into a single file. We have used it for running
badblocks across a cluster, and it made the job much
less painful.
It currently uses rsh, because that's what we use
internally on our cluster, but there is some inline
documentation for modifying it to use ssh.
The script requires that the Tcl interpreter tclsh
be in the path of the user running the script.
The script is here:
http://inferno.slug.org/cgi-bin/wiki?ScanCluster
The output of the script is optimised for manual
inspection using 'more'. I am working on an optional
more 'grep friendly' output mode.
--
Phil Ehrens <pehrens_at_[hidden]>| Fun stuff:
The LIGO Laboratory, MS 18-34 | http://www.ralphmag.org
California Institute of Technology | http://www.yellow5.com
1200 East California Blvd. | http://www.total.net/~fishnet/
Pasadena, CA 91125 USA | http://slashdot.org
Phone:(626)395-8518 Fax:(626)793-9744 | http://kame56.homepage.com
|
