Am 04.04.2012 um 12:45 schrieb Ursula Winkler:

> Reuti wrote:
>> This is also some kind of personal taste. Some prefer classic spooling as 
>> you can check all the information of a job as they are just stored as text 
>> files. And it even handles a large number of nodes before it gets 
>> performance problems. Maybe Chris can make a statement about it as he runs 
>> large clusters with classic spooling IIRC.
>>  
> Hmm, but it has obviously nothing to do with my spooling problem I guess. I 
> asked another university. They use the same Berkeley DB as I do and they have 
> not that problem. You have much experience with the SGE. Do you think I 
> should compile and install another version?
>> You tried a file in / and it's working then, e.g. copy "/bin/true" to 
>> "/true"?
>>  
> Yes, with /true it works then. But not with "startmpi.sh" --> /stamp. There I 
> get "got wrong number of arguments". Probably because it does see only the 
> first 6 characters and not "-catch_rsh $pe_hostfile".

Yes, it expects exactly one argument: $pe_hostfile (besides any number of 
options prefixed by a dash).

So the complete string specified for start_proc_args is limited this number of 
characters.

To be honest: I have no clue for the cause of this issue, it never happened to 
me anywhere before.

-- Reuti
_______________________________________________
users mailing list
[email protected]
https://gridengine.org/mailman/listinfo/users

Reply via email to