Dear devs,
We are testing a concept where we are dynamically allocating a portion of our
compute nodes with oversubscribed interactive nodes for low-intensity use. To
make the use as simple as possible, we are testing redirecting user login
sessions directly to these nodes via SLURM.
We considered this option as well but the problem we saw with it is what
happens when a user tries to use screen? Many of our users login, start screen,
do some work and then disconnect. Whenever they reconnect they can pick up from
where they left off. If you are allocated to a compute node
Thank you. That fixed the problem. I don't understand why enabling accounting
limits would disable logging of that accounting information but it works now.
Thanks,
Carl
--
Carl Schmidtmann
Center for Integrated Research Computing
University of Rochester
On Mar 21, 2014, at 9:32 PM, Hongjia
Dear developers,
in the API, I can find a function slurm_pid2jobid, that's fine. For our
monitoring, we need the inverse function, which gives a list of process
IDs (+ nodes) for a given job. Is there already something like
slurm_jobid2pid ?
LSF has this function, and we have build our tools
I can foresee the screen issue as well. One could fairly simply add a check
when the user logs in to see if the the user has a node assigned to them
already and force the session to use that node. It could perhaps even prompt if
they want to do access this session or get a new one.
The
The closest thing available today is the scontrol listpids command
described on the scontrol man page.
Quoting Ulf Markwardt ulf.markwa...@tu-dresden.de:
Dear developers,
in the API, I can find a function slurm_pid2jobid, that's fine. For
our monitoring, we need the inverse function,
allocated but drained node will be shown mixed by sinfo.
From dd5772c1df235877edccef92d21645b4aa7a21c2 Mon Sep 17 00:00:00 2001
From: Hongjia Cao hj...@nudt.edu.cn
Date: Tue, 25 Mar 2014 09:12:45 +0800
Subject: [PATCH] fix select_nodeinfo_set_all() of select/linear
fix the problem that allocated
