SGE execute daemon

If the queue instances for a running slave node are shown as having state "u" or "au" in the output of qstat -f, or the load_avg ("load average") field is shown as "-NA-", it is likely that the SGE execute daemon on that node has crashed. To find out if the daemon is running, look for a process called sge_execd in the output of ps aux. If this process is not running, it can be restarted by executing the following command as root:

/etc/init.d/sgeexecd start

-- DanBretherton - 17 Jul 2009

Topic revision: r1 - 17 Jul 2009 - 17:19:52 - DanBretherton
 
This site is powered by the TWiki collaboration platformCopyright &© by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding TWiki? Send feedback