Via a bsub, I’m doing:
MPICH_PORT_RANGE="46107:46140” mpiexec mpich/examples/cpi
When I ssh to the controlling node, I see it has spawned a set of blaunch processes with `--control-port node-12-3-2:46107` as expected, but:
ss -l -p -n | grep blaunch
tcp LISTEN 0 128 0.0.0.0:34361 0.0.0.0:* users:(("blaunch",pid=2823,fd=7))
tcp LISTEN 0 128 0.0.0.0:46107 0.0.0.0:* users:(("cpi",pid=2839,fd=5),("blaunch",pid=2837,fd=5),("blaunch",pid=2836,fd=5),("blaunch",pid=2835,fd=5),("blaunch",pid=2834,fd=5),("blaunch",pid=2833,fd=5),("blaunch",pid=2832,fd=5),("blaunch",pid=2831,fd=5),("blaunch",pid=2830,fd=5),("blaunch",pid=2829,fd=5),("blaunch",pid=2828,fd=5),("blaunch",pid=2827,fd=5),("blaunch",pid=2826,fd=5),("blaunch",pid=2825,fd=5),("blaunch",pid=2824,fd=5),("blaunch",pid=2823,fd=5),("hydra_pmi_proxy",pid=2822,fd=5),("mpiexec",pid=2821,fd=5))
tcp LISTEN 0 128 0.0.0.0:43741 0.0.0.0:* users:(("blaunch",pid=2825,fd=12))
tcp LISTEN 0 128 0.0.0.0:41983 0.0.0.0:* users:(("blaunch",pid=2830,fd=22))
tcp LISTEN 0 128 0.0.0.0:41215 0.0.0.0:* users:(("blaunch",pid=2832,fd=26))
tcp LISTEN 0 128 0.0.0.0:34433 0.0.0.0:* users:(("blaunch",pid=2831,fd=24))
tcp LISTEN 0 128 0.0.0.0:33219 0.0.0.0:* users:(("blaunch",pid=2827,fd=16))
tcp LISTEN 0 128 0.0.0.0:34405 0.0.0.0:* users:(("blaunch",pid=2837,fd=36))
tcp LISTEN 0 128 0.0.0.0:43465 0.0.0.0:* users:(("blaunch",pid=2836,fd=34))
tcp LISTEN 0 128 0.0.0.0:39755 0.0.0.0:* users:(("blaunch",pid=2833,fd=28))
tcp LISTEN 0 128 0.0.0.0:38095 0.0.0.0:* users:(("blaunch",pid=2829,fd=20))
tcp LISTEN 0 128 0.0.0.0:44625 0.0.0.0:* users:(("blaunch",pid=2834,fd=30))
tcp LISTEN 0 128 0.0.0.0:35345 0.0.0.0:* users:(("blaunch",pid=2835,fd=32))
tcp LISTEN 0 128 0.0.0.0:43827 0.0.0.0:* users:(("blaunch",pid=2826,fd=14))
tcp LISTEN 0 128 0.0.0.0:40915 0.0.0.0:* users:(("blaunch",pid=2828,fd=18))
tcp LISTEN 0 128 0.0.0.0:42549 0.0.0.0:* users:(("blaunch",pid=2824,fd=9))
Why are these all listening on ports outside my range? I’ve also tried setting MPIEXEC_PORT_RANGE and MPIR_CVAR_CH3_PORT_RANGE and still have the problem.
Is there any way to fully control the ports used?
Cheers,
Sendu.
--
The Wellcome Sanger Institute is operated by Genome Research
Limited, a charity registered in England with number 1021457 and a
company registered in England with number 2742969, whose registered
office is 215 Euston Road, London, NW1 2BE.