Hi Tena
We setup the cluster nodes to run MPI programs
with stacksize unlimited,
memlock unlimited,
4096 max open files,
to avoid crashing on edge cases.
This is kind of typical for HPC, MPI, number crunching.
However, some are quite big codes,
and from what you said yours is not (or not yet).
Sounds about right. I'm not near a keyboard to check the reasons why pipe(2)
would fail.
Specifically, OMPI is failing when it is trying to setup stdin/stdout/stderr
forwarding for your job. Very strange.
Sent from my PDA. No type good.
On Feb 11, 2011, at 9:56 PM, "Tena Sakai" wrote:
> H
Hi Gus,
Thank you for your tips.
I didn't find any smoking gun or anything comes close.
Here's the upshot:
[tsakai@ip-10-114-239-188 ~]$ ulimit -a
core file size (blocks, -c) 0
data seg size (kbytes, -d) unlimited
scheduling priority (-e) 0
file size
Hi Tena
Please read one answer inline.
Tena Sakai wrote:
Hi Jeff,
Hi Gus,
Thanks for your replies.
I have pretty much ruled out PATH issues by setting tsakai's PATH
as identical to that of root. In that setting I reproduced the
same result as before: root can run mpirun correctly and tsakai
Hi Jeff,
Hi Gus,
Thanks for your replies.
I have pretty much ruled out PATH issues by setting tsakai's PATH
as identical to that of root. In that setting I reproduced the
same result as before: root can run mpirun correctly and tsakai
cannot.
I have also checked out permission on /tmp directory
It is concerning if the pipe system call fails - I can't think of why that
would happen. Thats not usually a permissions issue but rather a deeper
indication that something is either seriously wrong on your system or you are
running out of file descriptors. Are file descriptors limited on a per-
Hi Terry,
Someone else at the University builds the packages that I use, and we've been
experimenting for the last few days with different openmpi build options to see
what might be causing this.
Re the stack, I can always see the entire stack in the TV stack pane, and I can
always click on 'm
Hi Tena
Since root can but you can't,
is is a directory permission problem perhaps?
Check the execution directory permission (on both machines,
if this is not NFS mounted dir).
I am not sure, but IIRR OpenMPI also uses /tmp for
under-the-hood stuff, worth checking permissions there also.
Just a n
there is alltoall, scatter, gather, and many more. check out
https://computing.llnl.gov/tutorials/mpi/#Collective_Communication_Routines
On Fri, Feb 11, 2011 at 3:26 AM, Bibrak Qamar wrote:
> I want to know, if there is any other implementation of collective
> communication ( reduce and Bcast) a
Patrick -
Your program is erroneous, so the behavior of the MPI is not defined. The
default implementation of RMA with Open MPI uses active-message like semantics
to locally deliver the message, and does not do bounds checking, so the error
was not caught.
Brian
On Feb 11, 2011, at 5:41 AM,
yes setting LD_LIBRARY_PATH solved the problem
thanks for the help
On Fri, Feb 11, 2011 at 7:14 PM, Prentice Bisbal wrote:
> swagat mishra wrote:
> > hello everyone,
> > i have a network of systems connected over lan with each computer
> > running ubuntu. openmpi 1.4.x is installed on 1 machine
swagat mishra wrote:
> hello everyone,
> i have a network of systems connected over lan with each computer
> running ubuntu. openmpi 1.4.x is installed on 1 machine and the
> installation is mounted on other nodes through Networking File
> System(NFS). the source program and compiled file(a.out) ar
Hi all,
I am testing the one-sided message passing (MPI_Put, MPI_Get)
and it seems to me that the size parameter of MPI_Win_create()
is definitly not taken into account.
Then I can put/get messages using a window created with size=0
(or put/get after any others limits between 0 and the original bu
Sorry I have to ask this, did you build your lastest OMPI version, not
just the application, with the -g flag too.
IIRC, when I ran into this issue I was actually able to do stepi's and
eventually pop up the stack however that is really no way to debug a
program :-).
Unless OMPI is somehow t
I want to know, if there is any other implementation of collective
communication ( reduce and Bcast) available apart from what openMPI
provides.
Thanks
Bibrak Qamar
Undergraduate Student BIT-9
Member Center for High Performance Scientific Computing
NUST-School of Electrical Engineering and Compu
Excuse me. I forgot the attaching.
2011/2/11 Marcela Castro León
> Hello:
>
> I've the same version ob Ubuntu 10.04. The original version was Ubuntu
> Server 9.1 (64) and upgraded both of them to 10.04.
> Yesterday I've updated and upgraded to the same level again. But I've got
> the same error
Hello:
I've the same version ob Ubuntu 10.04. The original version was Ubuntu
Server 9.1 (64) and upgraded both of them to 10.04.
Yesterday I've updated and upgraded to the same level again. But I've got
the same error after that.
The machine are exactly the same, HP Compaq with inter Core I5.
An
Hi,
I have made a bit more progress. I think I can say ssh authenti-
cation problem is behind me now. I am still having a problem running
mpirun, but the latest discovery, which I can reproduce, is that
I can run mpirun as root. Here's the session log:
[tsakai@vixen ec2]$ 2ec2 ec2-184-73-104
18 matches
Mail list logo
