Re: [OMPI users] mca_pml_ob1_send blocks

[Shaun Jackman]

I neglected to include some pertinent information:
I'm using Open MPI 1.3.2. Here's a backtrace:

#0  0x0000002a95e6890c in epoll_wait () from /lib64/tls/libc.so.6
#1  0x0000002a9623a39c in epoll_dispatch ()
   from /home/sjackman/arch/xhost/lib/libopen-pal.so.0
#2  0x0000002a96238f10 in opal_event_base_loop ()
   from /home/sjackman/arch/xhost/lib/libopen-pal.so.0
#3  0x0000002a9622dfb0 in opal_progress ()
   from /home/sjackman/arch/xhost/lib/libopen-pal.so.0
#4  0x0000002a989502c5 in mca_pml_ob1_send ()
   from /home/sjackman/arch/xhost/lib/openmpi/mca_pml_ob1.so
#5  0x0000002a956c56f1 in PMPI_Send ()
   from /home/sjackman/arch/xhost/lib/libmpi.so.0

Frames #0-#3 do return and loop. Frame #4 never returns.

Cheers,
Shaun

Shaun Jackman wrote:

Hi,

I'm seeing MPI_Send block in mca_pml_ob1_send. The packet is shorter than the eager transmit limit for shared memory (3300 bytes < 4096 bytes). I'm trying to determine if MPI_Send is blocking due to a deadlock. Will MPI_Send block even when sending a packet eagerly?

Thanks,
Shaun