[mpich-discuss] MPICH2 1.0.6p1 & Windows HPC Server 2008 (badperformance)

[Dorian Domenic Krause]

On Tue, 9 Dec 2008 11:11:16 +0800
  "Seifer Lin" <seiferlin at gmail.com> wrote:
> Hi:
> 
> After that I put all 4 nodes in the same domain 
>(originally they are in the
> same workgroup)
>For the MPI_Barrier(...) function, version 1.0.6p1 and 
>1.0.8 both return at
> once.
> But for another simple MPI program (Laplace equation 
>solver), both 1.0.6p1
> and 1.0.8 run very SLOW!!!!
> 
> I have noticed that if the command is like
> mpiexec -hosts 2 192.168.1.1 192.168.1.2
> \\192.168.1.1\shared\LaplaceSolver.exe<file://192.168.1.1/shared/LaplaceSolver.exe>
> It runs very SLOW!!! (the processes are located at 
>different machines)
> 
> Another command is like
> mpiexec -hosts 2 192.168.1.1 192.168.1.1
> \\192.168.1.1\shared\LaplaceSolver.exe<file://192.168.1.1/shared/LaplaceSolver.exe>
> It runs at normal fast speed! (the processes are located 
>at the SAME
> machine)
> 
> 
> I think this may due to the strict policies on network 
>transfer of Windows
> HPC Server 2008 (and Vista also)
> Do you have any solution to this? thank you!
> 

If you are working on HPC Server 2008 you should have MS 
MPI available ?! Do you experience the same behaviour? MS 
MPI is basically MPICH2 but with some enhancement related 
to Active Directory, Security, .... Maybe this can shed 
some light on the problem.

Dorian


> regards,
> 
> Seifer Lin
> 
> 2008/12/8 Jayesh Krishna <jayesh at mcs.anl.gov>
> 
>>  Hi,
>>  Can you try out the latest stable version (1.0.8) of 
>>MPICH2 (
>> http://www.mcs.anl.gov/research/projects/mpich2/downloads/index.php?s=downloads
>> )?
>>
>> Regards,
>> Jayesh
>>
>>  ------------------------------
>> *From:* mpich-discuss-bounces at mcs.anl.gov [mailto:
>> mpich-discuss-bounces at mcs.anl.gov] *On Behalf Of *Seifer 
>>Lin
>> *Sent:* Monday, December 08, 2008 12:47 AM
>> *To:* mpich-discuss at mcs.anl.gov
>> *Subject:* [mpich-discuss] MPICH2 1.0.6p1 & Windows HPC 
>>Server 2008
>> (badperformance)
>>
>>   Hi everyone:
>>
>> I have a cluster of 4 nodes, all of them are with 
>>Windows HPC server 2008
>> installed.
>> I make all of the 4 nodes in the same workgroup. I use 
>>MPICH2 1.0.6p1 from
>> Argonne Lab.
>> And then
>> 1. firewall of all 4 nodes are turned off
>> 2. UAC (User Account Control) of all 4 nodes are turned 
>>off
>> 3. I start smpd.exe (1.0.6p1 x64) in all the 4 nodes
>>
>> And I run a very simple MPI program (test_mpich2.exe)
>>
>> #include "mpi.h"
>> #include <iostream>
>> int main(int argc, char **argv)
>> {
>>     int cpuid, ncpu;
>>     MPI_Init(&argc, &argv);
>>     MPI_Comm_size(MPI_COMM_WORLD, &ncpu);
>>     MPI_Comm_rank(MPI_COMM_WORLD, &cpuid);
>>     printf("NCPU:%d, CPUID:%d\n", ncpu, cpuid);
>>     fflush(stdout);
>>     printf("start barrier\n"); fflush(stdout);
>>     MPI_Barrier(MPI_COMM_WORLD);
>>     printf("end barrier\n"); fflush(stdout);
>>     MPI_Finalize();
>>     return 0;
>> }
>>
>> The command is
>> mpiexec -hosts 2 192.168.1.1 192.168.1.2
>> \\192.168.1.1\shared\test_mpich2.exe
>>
>> And the MPI_Barrier(...) function costs 10 seconds to 
>>return !!!!!
>>
>> If the same code is running on a Windows XP cluster, 
>>MPI_Barrier(...)
>> returns at once!
>>
>>
>> Does anyone know how to solve this problem on Windows 
>>HPC Server 2008 ?
>> (Windows Vista has the same problem, too)
>>
>> regards,
>>
>> Seifer Lin
>>
>>
>>
>>
>>
>>
>>
>>
>>