[MPICH] choosing hosts for spawn

[David Ashton]

Let's say you have 26 machines available: a-z

Let's say you have two machine files:

mf1 contains:

a

b

c

d

mf2 contains:

m

n

o

Let's say you have an application that uses MPI_Comm_spawn to spawn another
5 process job.

 

What hosts would you expect to be used for the spawned processes given the
following commands?:

 

A)      mpiexec -n 1 spawner

B)      mpiexec -machinefile mf1 -n 3 spawner

C)      mpiexec -machinefile mf1 -n 2 spawner : -machinefile mf2 -n 1
spawner

D)     mpiexec -host a -n 1 spawner : -host b -n 1 spawner

 

A)

In the first example I would expect the hosts to come from the main pool
like this:

1 process on host a, five spawned processes on b,c,d,e,f.  The order of the
hosts is irrelevant but they would all come from the big pool.

 

B)

In the second example I would expect one of two possibilities:

The first 3 processes must come from the machinefile, a,b,c and the 5
spawned processes would either come from the main pool, d,e,f,g,h, or from
the machinefile, d,a,b,c,d.

 

If a machinefile is specified would you expect spawned processes to come
from the machinefile or the global pool?

 

What if the global pool was unknown but a machinefile was specified?  So in
that case the global pool would be the local machine and you could get the
following:

3 processes on a,b,c and 5 spawned processes on a

Or

3 processes on a,b,c and 5 spawned processes on d,a,b,c,d

 

C)

The first three processes must be on a,b,m and the 5 spawned processes could
come from the main pool.  If the spawned processes came from the machine
files which one would be used? mf1? mf2? mf1+mf2?

 

D)

The first two processes must be on a and b.  The spawned processes could
come from the pool, c,d,e,f,g.  But if the pool was unknown would you expect
all the spawned processes to be on the local host a?  Or would you expect
the processes to be placed on both a and b?

 

I know you could just run each of the examples and see what happens but I'm
interested in what you think should happen, not what the current
implementation actually does.

 

-David Ashton

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20050927/fa966eb1/attachment.htm>