HI Jeff,
by adding PATH and LD_LIBRARY_PATH, I don't see orted not found issue.
[root@vcn03 pasokan]# mpirun --allow-run-as-root -np 4 -host
vcn03,vcn03,vcn04,vcn04 /mnt/lustre_client/pasokan/a.out
--------------------------------------------------------------------------
WARNING: No preset parameters were found for the device that Open MPI
detected:
Local host: vcn03
Device name: mlx5_0
Device vendor ID: 0x02c9
Device vendor part ID: 4114
Default device parameters will be used, which may result in lower
performance. You can edit any of the files specified by the
btl_openib_device_param_files MCA parameter to set values for your
device.
NOTE: You can turn off this warning by setting the MCA parameter
btl_openib_warn_no_device_params_found to 0.
--------------------------------------------------------------------------
[vcn04][[33859,1],2][connect/btl_openib_connect_udcm.c:1235:udcm_rc_qp_to_rtr]
error modifing QP to RTR errno says Invalid argument
[vcn03][[33859,1],0][connect/btl_openib_connect_udcm.c:1235:udcm_rc_qp_to_rtr]
error modifing QP to RTR errno says Invalid argument
[vcn03][[33859,1],1][connect/btl_openib_connect_udcm.c:1235:udcm_rc_qp_to_rtr]
error modifing QP to RTR errno says Invalid argument
[vcn04][[33859,1],3][connect/btl_openib_connect_udcm.c:1235:udcm_rc_qp_to_rtr]
error modifing QP to RTR errno says Invalid argument
Hello world from processor vcn03, rank 0 out of 4 processors
Hello world from processor vcn03, rank 1 out of 4 processors
Hello world from processor vcn04, rank 2 out of 4 processors
Hello world from processor vcn04, rank 3 out of 4 processors
[vcn03:05070] 3 more processes have sent help message help-mpi-btl-openib.txt /
no device params found
[vcn03:05070] Set MCA parameter "orte_base_help_aggregate" to 0 to see all help
/ error messages
[root@vcn03 pasokan]#
but still IOR isn't running while compiled using OpenMPI, throwing segmentation
fault, which used to be very straight forward in Baremetal but not in KVM +
SR-IOV
________________________________________
From: Pharthiphan Asokan
Sent: Tuesday, March 13, 2018 8:42 PM
To: Open MPI Developers
Subject: RE: [OMPI devel] How to Build OpenMPI to support FDR over SR-IOV
Thanks Jeff,
OpenMPI is installed here
[root@vcn03 C]# cd /mnt/lustre_client/pasokan/openmpi-3.0.0/openmpi-3.0.0/
bin/ etc/ include/ lib/ share/
[root@vcn03 C]#
why exporting these variables not taking effect
export PATH=/mnt/lustre_client/pasokan/openmpi-3.0.0/openmpi-3.0.0/bin:$PATH
export
LD_LIBRARY_PATH=/mnt/lustre_client/pasokan/openmpi-3.0.0/openmpi-3.0.0/lib:$LD_LIBRARY_PATH
export
INCLUDE=/mnt/lustre_client/pasokan/openmpi-3.0.0/openmpi-3.0.0/include:$INCLUDE
but as said by providing --prefix
/mnt/lustre_client/pasokan/openmpi-3.0.0/openmpi-3.0.0/ is working
[root@vcn03 C]# mpirun --prefix
/mnt/lustre_client/pasokan/openmpi-3.0.0/openmpi-3.0.0/ --allow-run-as-root -np
2 -host vcn03,vcn04 hostname
vcn04
vcn03
[root@vcn03 C]#
though my issue is IOR isn't running while compile with OpenMPI on SR-IOV
envirorment
[root@vcn03 C]# pwd
/mnt/lustre_client/pasokan/IOR-July12/src/C
[root@vcn03 C]#
[root@vcn03 C]# export
PATH=/mnt/lustre_client/pasokan/openmpi-3.0.0/openmpi-3.0.0/bin:$PATH
[root@vcn03 C]# export
LD_LIBRARY_PATH=/mnt/lustre_client/pasokan/openmpi-3.0.0/openmpi-3.0.0/lib:$LD_LIBRARY_PATH
[root@vcn03 C]# export
INCLUDE=/mnt/lustre_client/pasokan/openmpi-3.0.0/openmpi-3.0.0/include:$INCLUDE
[root@vcn03 C]#
[root@vcn03 C]# gmake posix mpiio
mpicc -o IOR IOR.o utilities.o parse_options.o \
aiori-POSIX.o aiori-noMPIIO.o aiori-noHDF5.o aiori-noNCMPI.o \
-lm
mpicc -o IOR IOR.o utilities.o parse_options.o \
aiori-POSIX.o aiori-MPIIO.o aiori-noHDF5.o aiori-noNCMPI.o \
-lm
[root@vcn03 C]# ./IOR
--------------------------------------------------------------------------
WARNING: No preset parameters were found for the device that Open MPI
detected:
Local host: vcn03
Device name: mlx5_0
Device vendor ID: 0x02c9
Device vendor part ID: 4114
Default device parameters will be used, which may result in lower
performance. You can edit any of the files specified by the
btl_openib_device_param_files MCA parameter to set values for your
device.
NOTE: You can turn off this warning by setting the MCA parameter
btl_openib_warn_no_device_params_found to 0.
--------------------------------------------------------------------------
[vcn03][[34068,1],0][connect/btl_openib_connect_udcm.c:1235:udcm_rc_qp_to_rtr]
error modifing QP to RTR errno says Invalid argument
Segmentation fault
[root@vcn03 C]#
Please help !
________________________________________
From: devel [devel-boun...@lists.open-mpi.org] on behalf of Jeff Squyres
(jsquyres) [jsquy...@cisco.com]
Sent: Tuesday, March 13, 2018 8:20 PM
To: Open MPI Developers List
Subject: Re: [OMPI devel] How to Build OpenMPI to support FDR over SR-IOV
On Mar 13, 2018, at 2:08 AM, Pharthiphan Asokan <paso...@ddn.com> wrote:
>
> [root@vcn03 C]# mpirun --allow-run-as-root -np 2 -host vcn03,vcn04 hostname
> bash: orted: command not found
This is the key ^^
These FAQ items may help:
* https://www.open-mpi.org/faq/?category=running#run-prereqs.
* https://www.open-mpi.org/faq/?category=running#adding-ompi-to-path
* https://www.open-mpi.org/faq/?category=running#mpirun-prefix
--
Jeff Squyres
jsquy...@cisco.com
_______________________________________________
devel mailing list
devel@lists.open-mpi.org
https://lists.open-mpi.org/mailman/listinfo/devel
_______________________________________________
devel mailing list
devel@lists.open-mpi.org
https://lists.open-mpi.org/mailman/listinfo/devel
