[GE users] mpich2 tight integration sge 6.2

reuti reuti at staff.uni-marburg.de
Thu Nov 18 11:37:09 GMT 2010


Am 18.11.2010 um 12:23 schrieb buudo:

> Dear all,
> i need mpich2 for a special application.

Which version of MPICH2 - I see 1.3 below? Starting with 1.3 (which I recommend, or even better the newer 1.3.1) is a Tight Integration into SGE setup by default. The documents are obsolete when the Hydra startup manager is used, therefore  Hydra is also not listed on the page.

The PE needs only /bin/true as start/stop_proc_args.

-- Reuti

PS: I'm not sure whether mpd is still compiled in in a proper way, as the official statement from the MPICH2 developers is to remove all other startup methods besides Hydra.


> Therefore Iinstalled straight forward and configured along reuti's http://gridengine.sunsource.net/howto/mpich2-integration/mpich2-integration.html
> with mpd startup method.
> Unfortunately, it gives me ayway the same error message in the outfile concernig a missing mpd.conf file. I created a .mpd.conf in $HOME ans also /etc/mpd.conf neither helps. If I start manually mpdboot and mpiexec -n 2 mpihello it looks okay. Has anyone an idea where this problem with the missing mpd.conf could come from ? 
> --------------------
> more 6348.out
> -catch_rsh /data/sge/default/spool/node025/active_jobs/6348.1/pe_hostfile /data/mpich2-1.3/mpd
> node025:1
> node027:1
> node028:1
> node030:1
> startmpich2.sh: check for local mpd daemon (1 of 10)
> /data/sge/bin/lx24-amd64/qrsh -inherit -V node025 /data/mpich2-1.3/mpd/bin/mpd
> unable to find mpd.conf file
> startmpich2.sh: check for local mpd daemon (2 of 10)
> startmpich2.sh: check for local mpd daemon (3 of 10)
> startmpich2.sh: check for local mpd daemon (4 of 10)
> startmpich2.sh: check for local mpd daemon (5 of 10)
> startmpich2.sh: check for local mpd daemon (6 of 10)
> startmpich2.sh: check for local mpd daemon (7 of 10)
> startmpich2.sh: check for local mpd daemon (8 of 10)
> startmpich2.sh: check for local mpd daemon (9 of 10)
> startmpich2.sh: check for local mpd daemon (10 of 10)
> startmpich2.sh: local mpd could not be started, aborting
> -catch_rsh /data/mpich2-1.3/mpd
> unable to find mpd.conf file
> -----------------------
> 
> Udo
> 
> ------------------------------------------------------
> http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=296618
> 
> To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].

------------------------------------------------------
http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=296623

To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].



More information about the gridengine-users mailing list