RE: [myrinet] GM_BOGUS_SEND_INTERRUPT

Patrick

Thanks for replying.

I am using gm-1.5pre4 and mpich-1.2..8
OS is vanilla Red Hat linux 7.1
Hardware is a dozen Pentium III, Dual Processor 1Gig
GM is configured with the following options
--enable-new-features
--enable-linux-modversions
--enable-linux-smp
--enable-linux-directcopy

I am using the Lanai 7 card.

MPICH over GM is configured using the options suggested from the README with
the addition of those required for SMP to work correctly (I am not sure what
they were or I would write them down!!)

Just recently upgraded from an older version.

I have done some more testing and have come up with the following additional
results.

Large data volums all work fine running across one machine (multiple mpi
processes).

For small data volumes (round about 12Kb), running across 
multiple machines the code works fine.
Anything over that yeilds the send could not complete error
and the bogus intterrupt (see previous emails).

I am using threads but all thread creation is done BEFORE MPI_Init() is
called and only one thread ever accesses the mpi routines. Condition
variable and mutexs are used throughout though.

I was wondering if perhaps the threads were causing EINTR or 
other interrupts that GM does not handle?????? I thought that mayby small
data volumes would complete in a small enough time 
frame as to not be interrupted, where as the large ones take too long and
get premepted????

This is only a guess and I hope that I am wrong because I have to re-write a
mountain of code to de-thread it all :(

If I have to re-write is there any reason why forked processes communicating
over shared memory would not work???? (So long as all forking was done
before MPI_Init()) 

Thanks

Harvey Davis