Hi,
I'm testing the latest beta (7.0b17) with bproc and all tests (except
for the procname test) pass. Where I run into problems is when I try
running the mandelbrot example program (lam-7.0b17/examples/mandelbrot).
I am running the application using the following schema:
cat myapp
h /home/mmadore/master
C -s h /home/mmadore/slave
mpirun -v myapp
The master program executes on the head node:
master: allocating block (0, 0) - (19, 19) to process 1
master: allocating block (20, 0) - (39, 19) to process 2
master: allocating block (40, 0) - (59, 19) to process 3
master: allocating block (60, 0) - (79, 19) to process 4
master: allocating block (80, 0) - (99, 19) to process 1
....
However, the slave application does not seem to be running on the
compute nodes. The only process running on the compute nodes is lam-flatd:
ps ax | grep flatd
31890 pts/2 SW 0:00 [lam-flatd1]
31891 pts/2 SW 0:00 [lam-flatd1]
31892 pts/2 SW 0:00 [lam-flatd1]
31893 pts/2 SW 0:00 [lam-flatd1]
Does this look like a configuration problem or a bug?
Also, I notice that the head node does not get assigned any work, which
is probably desired in most cases. However (especially on smaller
clusters), it is sometimes desirable to use the head node for
computation also. Is this possible? I tried setting schedule=yes in my
hosts file, but it seems like the bproc code unconditionally sets the
NT_WASTE flag.
Thanks!
Mike
|
