Hi,
I get strange results if I use a tab instead of a space as a
delimiter in an appfile. Perhaps I've missed something but I
can't remember that I read that tabs are not allowed.
Tab between 2 and -host.
-np 2 -host tyr.informatik.hs-fulda.de rank_size
tyr small_prog 144 mpiexec -app app_ra
Hi,
the man page for "mpiexec" shows the following:
cat myrankfile
rank 0=aa slot=1:0-2
rank 1=bb slot=0:0,1
rank 2=cc slot=1-2
mpirun -H aa,bb,cc,dd -rf myrankfile ./a.out So that
Rank 0 runs on node aa, bound to socket 1, cores 0-2.
Ra
Are *all* the machines Sparc? Or just the 3rd one (rs0)?
On Sep 3, 2012, at 12:43 PM, Siegmar Gross
wrote:
> Hi,
>
> the man page for "mpiexec" shows the following:
>
> cat myrankfile
> rank 0=aa slot=1:0-2
> rank 1=bb slot=0:0,1
> rank 2=cc slot=1-2
>
Possible - yes. Likely to happen immediately - less so as most of us are quite
busy right now. I'll add it to the "requested feature" list, but can make no
promises on if/when it might happen. Certainly won't be included in anything
prior to the upcoming 1.7 series.
On Sep 3, 2012, at 12:42 PM
I have asked to my admin and he said that no log messages were present
in /var/log, apart my login on the compute node.
No killed processes, no full stack errors, the memory is ok, 1GB is
used and 2GB are free.
Actually I don't know what kind of problem coud be, does someone have
ideas? Or at least
Hi all,
I just compiled Open MPI 1.6.1 and before digging any deeper: does anyone else
notice, that the command:
$ mpiexec -n 4 -machinefile mymachines ./mpihello
will ignore the argument "-machinefile mymachines" and use the file
"openmpi-default-hostfile" instead all the time?
==
SGE issue
It looks to me like the network is losing connections - your error messages all
state "no route to host", which implies that the network interface dropped out.
On Sep 3, 2012, at 1:39 PM, Andrea Negri wrote:
> I have asked to my admin and he said that no log messages were present
> in /var/log,
On Sep 3, 2012, at 2:12 PM, Reuti wrote:
> Hi all,
>
> I just compiled Open MPI 1.6.1 and before digging any deeper: does anyone
> else notice, that the command:
>
> $ mpiexec -n 4 -machinefile mymachines ./mpihello
>
> will ignore the argument "-machinefile mymachines" and use the file
> "
Give the attached patch a try - this works for me, but I'd like it verified
before it goes into the next 1.6 release (singleton comm_spawn is so rarely
used that it can easily be overlooked for some time).
Thx
Ralph
singleton_comm_spawn.diff
Description: Binary data
On Aug 31, 2012, at 3:32
Hi Ralph,
Am 03.09.2012 um 23:34 schrieb Ralph Castain:
>
> On Sep 3, 2012, at 2:12 PM, Reuti wrote:
>
>> Hi all,
>>
>> I just compiled Open MPI 1.6.1 and before digging any deeper: does anyone
>> else notice, that the command:
>>
>> $ mpiexec -n 4 -machinefile mymachines ./mpihello
>>
>>
In which ways can I check the failure of the ethernet connections?
2012/9/3 :
> Send users mailing list submissions to
> us...@open-mpi.org
>
> To subscribe or unsubscribe via the World Wide Web, visit
> http://www.open-mpi.org/mailman/listinfo.cgi/users
> or, via email, send a me
On Sep 3, 2012, at 2:40 PM, Reuti wrote:
> Hi Ralph,
>
> Am 03.09.2012 um 23:34 schrieb Ralph Castain:
>
>>
>> On Sep 3, 2012, at 2:12 PM, Reuti wrote:
>>
>>> Hi all,
>>>
>>> I just compiled Open MPI 1.6.1 and before digging any deeper: does anyone
>>> else notice, that the command:
>>>
This is something you probably need to work on with your sys admin - it sounds
like there is something unreliable in your network, and that's usually a
somewhat hard thing to diagnose.
On Sep 3, 2012, at 2:49 PM, Andrea Negri wrote:
> In which ways can I check the failure of the ethernet conn
Am 04.09.2012 um 00:07 schrieb Ralph Castain:
> I'm leaning towards fixing it - it came due to discussions on how to handle
> hostfile when there is an allocation. For now, though, that should work.
Oh, did I miss this on the list? If there is a hostfile given as argument, it
should override th
On Sep 3, 2012, at 3:50 PM, Reuti wrote:
> Am 04.09.2012 um 00:07 schrieb Ralph Castain:
>
>> I'm leaning towards fixing it - it came due to discussions on how to handle
>> hostfile when there is an allocation. For now, though, that should work.
>
> Oh, did I miss this on the list? If there i
Great. I'll try applying this tomorrow and I'll let you know if it
works for me.
Brian
On Mon, Sep 3, 2012 at 2:36 PM, Ralph Castain wrote:
> Give the attached patch a try - this works for me, but I'd like it verified
> before it goes into the next 1.6 release (singleton comm_spawn is so rar
16 matches
Mail list logo
