Hi, Jeff and all:
I could boot lam universe using rsh by ¡°lamboot ¨Cv nodes¡±, but got the
same error while booting within a PBS job.
Thanks
_____
·¢¼þÈË: lam-bounces_at_[hidden] [mailto:lam-bounces_at_[hidden]] ´ú±í
Guangyu Wu
·¢ËÍʱ¼ä: 2005Äê11ÔÂ12ÈÕ 11:45
ÊÕ¼þÈË: 'General LAM/MPI mailing list'
Ö÷Ìâ: LAM: Uable to boot lam within PBS job
Hi,Jeff and all:
Thanks for your reply! Now it seems I have compiled lam with TM enabled.
But I got an "The lamboot agent timed out while waiting for the newly-booted
process "error while booting lam within a PBS job.
The followingmessage in the .e36 file indicates that lam was trying to boot
via tm.
n0<16809> ssi:boot:tm: successfully launched on n2 (linux3)
Attached please find the job script and error output file.
I didn¡¯t configure any rsh or ssh between the 3 nodes.
Please could you have a look inside the file and give me some suggestions?
I need to get cpu time information of the MPP jobs over LAM.
Thanks for your kindly help all the time!
Best regards!
Guangyu Wu.
-----ÓʼþÔ¼þ-----
·¢¼þÈË: lam-bounces_at_[hidden] [mailto:lam-bounces_at_[hidden]] ´ú±í Jeff
Squyres
·¢ËÍʱ¼ä: 2005Äê11ÔÂ10ÈÕ 20:49
ÊÕ¼þÈË: General LAM/MPI mailing list
Ö÷Ìâ: Re: LAM: configure: error: *** Cannot find working libgm.
On Nov 11, 2005, at 4:44 AM, Guangyu Wu wrote:
> Hi,Jeff and all:
> I am back to this problem again now; actually it has been pending and
> unsolved for a long time. I am eager to go through it this time, since
> I have to take benefit from the integration of PBS with LAM.
> 1/Error information I got are:
> [root_at_linux1 lam-7.0.3]# ./configure --with-tm=/usr/pbs>>look2
> configure: error: Cannot continue
> configure: error: Cannot continue
> configure: error: cannot continue
> configure: error: cannot continue
> configure: error: *** Cannot find working libgm.
Looking at only the stderr is looking at these messages out of context.
You really need to look at both the stdout and stderr in a combined,
ordered fashion.
It is quite normal for some of LAM's sub-configure scripts to fail.
For example, if you do not have Myrinet, then it's not going to be able
to find libgm, and therefore the gm RPI sub-configure script will fail.
This is normal and expected behavior; the top-level configure script
will complete normally. Looking at the stdout and stderr together
should show this.
> 2/I could not find anything in the ¡°results¡± files that shows that
> configure completed normally and is ready to run "make"( although I
> could run make all install). Attachments please find the results file
> and config.log created.
> I noticed that there is a line at the end of config.log:
> configure: exit 0
> But from a successful case, it seems it should be configure: exit 1.
> How could I make sure that configure is successful?
If it creates all the Makefiles at the end and exits with status 0,
then everything should be fine.
--
{+} Jeff Squyres
{+} The Open MPI Project
{+} http://www.open-mpi.org/
_______________________________________________
This list is archived at http://www.lam-mpi.org/MailArchives/lam/
|
