See this FAQ:

http://icl.cs.utk.edu/open-mpi/faq/?category=running#oversubscribing

OMPI by default assumes that each process has its own cpu, thus aggressively looks for data to receive. I think there is a way to yield the processor if you want, but I think what your seeing is behavior you want. If your application is spending allot of time waiting to receive data it might be unbalanced, check out opt (http://www.allinea.com/ index.php?page=74) works with OMPI, lets you see what your process are doing, I think Tau (http://www.cs.uoregon.edu/research/tau/users/ samrai.php) would be a free alternative but i do not know if it works with OMPI.

Brock Palen
Center for Advanced Computing
bro...@umich.edu
(734)936-1985


On Jan 22, 2008, at 12:54 AM, Terry Frankcombe wrote:

Well, I have noticed that when a process is waiting for communication
from another process the reported CPU usage remains around 100%.  Is
that what you mean? I haven't explored whether these processes give way
to other active processes under the linux scheduler, nor whether I
should expect anything different.  This has been with 1.2.3 and 1.2.4.



On Tue, 2008-01-22 at 16:48 +1100, Graham Jenkins wrote:
We've observed an excessive use of CPU system resources with OpenMPI
1.2.4 using TCP connections only on our SL5 x86_64 Cluster. Typically,
for a simple Canonical Ring Program, we're seeing between 30 and 70%
system usage.

Has anybody else noticed this sort of behaviour?
And does anybody have some suggestions for resolving the issue?

Present values we have are:
--
ompi_info --param btl tcp |grep MCA
MCA btl: parameter "btl_base_debug" (current value: "0")
                 MCA btl: parameter "btl" (current value: <none>)
MCA btl: parameter "btl_base_verbose" (current value: "0") MCA btl: parameter "btl_tcp_if_include" (current value:
"eth0")
MCA btl: parameter "btl_tcp_if_exclude" (current value:
"lo")
                 MCA btl: parameter "btl_tcp_free_list_num" (current
value: "8")
                 MCA btl: parameter "btl_tcp_free_list_max" (current
value: "-1")
                 MCA btl: parameter "btl_tcp_free_list_inc" (current
value: "32")
                 MCA btl: parameter "btl_tcp_sndbuf" (current value:
"131072")
                 MCA btl: parameter "btl_tcp_rcvbuf" (current value:
"131072")
                 MCA btl: parameter "btl_tcp_endpoint_cache" (current
value: "30720")
                 MCA btl: parameter "btl_tcp_exclusivity" (current
value: "0")
                 MCA btl: parameter "btl_tcp_eager_limit" (current
value: "65536")
                 MCA btl: parameter "btl_tcp_min_send_size" (current
value: "65536")
                 MCA btl: parameter "btl_tcp_max_send_size" (current
value: "131072")
                 MCA btl: parameter "btl_tcp_min_rdma_size" (current
value: "131072")
                 MCA btl: parameter "btl_tcp_max_rdma_size" (current
value: "2147483647")
MCA btl: parameter "btl_tcp_flags" (current value: "122") MCA btl: parameter "btl_tcp_priority" (current value: "0")
                 MCA btl: parameter "btl_base_warn_component_unused"
(current value: "1")


_______________________________________________
users mailing list
us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users



Reply via email to