up vote 0 down vote favorite
share [g+] share [fb]

I'm having some trouble with a specific node. Until I resolve it, I don't want any jobs to run on ii. How can I temporarily take this node out of the nodes "pool"?

link|improve this question
58% accept rate
feedback

2 Answers

up vote 0 down vote

Without knowing your SGE version I cannot say for certain that this will achieve the desired outcome, however, qconf -de foo will delete the execution host foo. qconf -ae foo will then add the host foo back to the execution list.

link|improve this answer
This also doesn't seem to work. Jobs still get executed on th problematic node. – David B Dec 4 '10 at 12:17
@David B - After removing the host does qconf -s still show the host? – Tok Dec 6 '10 at 13:14
feedback
up vote 0 down vote

If you're running 6.1 or better, here's the best way. Create a new hostgroup called @disabled (qconf -ahgrp @disabled). Create a new resource quota set with "limit hosts @disabled to slots=0" (qconf -arqs). Now, to disable a host, just add it to the host group (qconf -aattr hostgroup hostlist MYHOST @disabled). To reenable the host, remove it from the host group (qconf -dattr hostgroup hostlist MYHOST @disabled). This process will stop new jobs from being scheduled to the machine and allow the currently running jobs to complete.

Daniel

link|improve this answer
This does not seem to work. Jobs still get executed on the problematic. What can go wrong here? I can see it was added to @disbaled (using qconf -mhgrp @disabled) and I have enabled the quota set. – David B Dec 4 '10 at 12:16
By the way, the resource quota set looks like this: { name disabled_hosts description created by me enabled TRUE limit hosts @disabled to slots=0 } – David B Dec 4 '10 at 12:19
By the way, this did work: { name disabled_hosts description created by me enabled TRUE limit hosts {my_bad_host} to slots=0 }, so I guess it has something to do with @disabled. – David B Dec 4 '10 at 12:30
feedback

Your Answer

 
or
required, but never shown
discard

Not the answer you're looking for? Browse other questions tagged or ask your own question.