Re: [gridengine users] Enabling an execd host after a particular job has run

2017-11-06 Thread Simon Matthews
The node startup or node build cannot include all the steps because the purpose of the grid is regression testing of new builds of a software tool. The execd node needs to locally install the new build. I could perhaps use a single network location that all execd hosts use for their installation,

Re: [gridengine users] Enabling an execd host after a particular job has run

2017-11-06 Thread Reuti
> Am 06.11.2017 um 23:54 schrieb Reuti : > > >> Am 06.11.2017 um 22:29 schrieb Simon Matthews : >> >> I need to run a job on every execd host that must be run before the >> main batch of jobs are run. >> >> I could submit a "setup" job

Re: [gridengine users] Enabling an execd host after a particular job has run

2017-11-06 Thread MacMullan IV, Hugh
You could put that code in the exec startup script, above the line that starts execd, and error out if that part doesn’t complete successfully. Seems weird, though. Shouldn’t the node build include all necessary bits to set up your execd nodes to ‘run jobs’? Are these on your Cygwin cluster?

Re: [gridengine users] Enabling an execd host after a particular job has run

2017-11-06 Thread Reuti
> Am 06.11.2017 um 22:29 schrieb Simon Matthews : > > I need to run a job on every execd host that must be run before the > main batch of jobs are run. > > I could submit a "setup" job on each specific execd host and make all > the subsequent jobs dependent on the

[gridengine users] Enabling an execd host after a particular job has run

2017-11-06 Thread Simon Matthews
I need to run a job on every execd host that must be run before the main batch of jobs are run. I could submit a "setup" job on each specific execd host and make all the subsequent jobs dependent on the list of "setup" jobs, but, if one setup job gets hung up, all the subsequent jobs will wait,

Re: [gridengine users] cluster OS survey

2017-11-06 Thread Benjamin LIPERE
>From expérience ISV like your entreprise use Redhat. For me 6 is the easy way, but it is a lost cause. So Redhat 7 is your horse. Now Redhat is not CentOS, there is tiny differencies. Le 6 nov. 2017 16:56, a écrit : > Our cluster is used in academic research on medical

[gridengine users] cluster OS survey

2017-11-06 Thread bergman
Our cluster is used in academic research on medical imaging. Our research group writes and distributes software for use on clusters & desktops. As part of determining what OSs (and for Linux distributions, GLIBC release levels) to target in our software, I would highly appreciate your feedback