Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Problem with MPI methods #26

Open
Enoki-ru opened this issue Nov 5, 2023 · 0 comments
Open

Problem with MPI methods #26

Enoki-ru opened this issue Nov 5, 2023 · 0 comments

Comments

@Enoki-ru
Copy link

Enoki-ru commented Nov 5, 2023 •
edited
Loading

When im trying to start ImpactTexe-mpi with:

conda create -n impact
conda activate impact
conda install -c conda-forge impact-t
conda install -c conda-forge impact-t=*=mpi_openmpi*
conda install -c conda-forge impact-t=*=mpi_mpich*

cd IMPACT-T/src
cmake -S . -B build -DUSE_MPI=ON
cmake --build build
sudo cmake --build build --target install

cd ../examples/Sample1
mpirun -n 2 ImpactTexe-mpi

Impact sending me:

!-----------------------------------------------------------
 ! IMPACT-T Parallel Beam Dynamics Tracking Code: 2.1 beta version
 ! Copyright of The Regents of the University of California
 !-----------------------------------------------------------
 nblem:            5           5
 pass setting up lattice...
 check randomness:            0  0.30440529327431320     
 check randomness:            1  0.83543324059415791     
           0  0.35048827465642352     
           1  0.35525770737678408     
 check randomness:            2  0.66382677037082638     
 check randomness:            3  0.69219578710848950     
           2  0.39551813506767264     
           3  0.55451975303257017     
 pass generating initial distribution...
 i,t,<z>:            1   0.0000000000000000        0.0000000000000000     
 zmin,zmax:    0.0000000000000000       -1.7268989477123050E-009
 name: rfdata1rfdataxxrfdataxxx
 Ndata:          107
 Ndata:          107
 Ndata:          107
 Ndata:          107
 name: rfdata2rfdataxxrfdataxxx
 Ndata:           39
 Ndata:           39
 Ndata:           39
 Ndata:           39
 name: rfdata3rfdataxxrfdataxxx
 Ndata:           49
 Ndata:           49
 i,t,<z>:            2   9.9999999999999998E-013  -3.6672274150748500E-006
 Ndata:           49
 Ndata:           49
 zmin,zmax:    0.0000000000000000        6.2734199320243810E-007
--------------------------------------------------------------------------
Primary job  terminated normally, but 1 process returned
a non-zero exit code. Per user-direction, the job has been aborted.
--------------------------------------------------------------------------
--------------------------------------------------------------------------
mpirun noticed that process rank 1 with PID 0 on node n3 exited on signal 11 (Segmentation fault).
--------------------------------------------------------------------------

These errors appear simply if you start executing a simple sequence of commands, like in below, according to the description of Impact-T gihub page. With nano, I change no matter what, or raw to 2, or col to 2, always cause a problem
It turns out:
! col row
1 2

git clone https://github.com/impact-lbl/IMPACT-T.git

conda create -n impact
conda activate impact
conda install -c conda-forge impact-t
conda install -c conda-forge impact-t=*=mpi_openmpi*
conda install -c conda-forge impact-t=*=mpi_mpich*

cd IMPACT-T/src
cmake -S . -B build -DUSE_MPI=ON
cmake --build build
sudo cmake --build build --target install
cd ../examples/Sample1
nano ImpactT.in
mpirun -n 2 ImpactTexe-mpi

I realized that the error may also occur due to the fact that the local computer has its own openmpi, and somehow conda uses it on the machine, but I still can't figure out why. Deleting everything is also not an option, I tried.
I use Ubuntu of the latest stable version, so that there are no questions, I also tried using MPI methods on a Debian-based cluster, the same problems.

(base) enoki@lenovo-enoki:~/IMPACT-T/examples$ conda activate impact
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples$ cd Sample1
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ mpirun -X LD_LIBRARY_PATH-n 2 ImpactTexe-mpi
[mpiexec@lenovo-enoki] match_arg (lib/utils/args.c:166): unrecognized argument X
[mpiexec@lenovo-enoki] HYDU_parse_array (lib/utils/args.c:181): argument matching returned error
[mpiexec@lenovo-enoki] parse_args (mpiexec/get_parameters.c:315): error parsing input array
[mpiexec@lenovo-enoki] HYD_uii_mpx_get_parameters (mpiexec/get_parameters.c:47): unable to parse user arguments
[mpiexec@lenovo-enoki] main (mpiexec/mpiexec.c:54): error parsing parameters
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ mpirun -X LD_LIBRARY_PATH -n 2 ImpactTexe-mpi
[mpiexec@lenovo-enoki] match_arg (lib/utils/args.c:166): unrecognized argument X
[mpiexec@lenovo-enoki] HYDU_parse_array (lib/utils/args.c:181): argument matching returned error
[mpiexec@lenovo-enoki] parse_args (mpiexec/get_parameters.c:315): error parsing input array
[mpiexec@lenovo-enoki] HYD_uii_mpx_get_parameters (mpiexec/get_parameters.c:47): unable to parse user arguments
[mpiexec@lenovo-enoki] main (mpiexec/mpiexec.c:54): error parsing parameters
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ sudo strace ImpactTexe-mpi |& grep openmpi
[sudo] пароль для enoki: 
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ echo $LD_LIBRARY_PATH

(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ export LD_LIBRARY_PATH=$(~/.conda/)
bash: /home/enoki/.conda/: Это каталог
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ find ~/.conda -iname "*openmpi*"
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ find ~/ -iname "*openmpi*"
/home/enoki/miniconda3/pkgs/mpi-1.0-openmpi
/home/enoki/miniconda3/pkgs/openmpi-4.1.5-h414af15_101
/home/enoki/miniconda3/pkgs/openmpi-4.1.5-h414af15_101/include/openmpi
/home/enoki/miniconda3/pkgs/openmpi-4.1.5-h414af15_101/bin/.openmpi-post-link.sh
/home/enoki/miniconda3/pkgs/openmpi-4.1.5-h414af15_101/lib/openmpi
/home/enoki/miniconda3/pkgs/openmpi-4.1.5-h414af15_101/etc/openmpi-mca-params.conf
/home/enoki/miniconda3/pkgs/openmpi-4.1.5-h414af15_101/etc/openmpi-totalview.tcl
/home/enoki/miniconda3/pkgs/openmpi-4.1.5-h414af15_101/etc/openmpi-default-hostfile
/home/enoki/miniconda3/pkgs/openmpi-4.1.5-h414af15_101/share/man/man3/OpenMPI.3
/home/enoki/miniconda3/pkgs/openmpi-4.1.5-h414af15_101/share/openmpi
/home/enoki/miniconda3/pkgs/openmpi-4.1.5-h414af15_101/share/openmpi/openmpi-valgrind.supp
/home/enoki/miniconda3/pkgs/impact-t-2.2-mpi_openmpi_h36312d9_0.tar.bz2
/home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101
/home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/include/openmpi
/home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/bin/.openmpi-post-link.sh
/home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/lib/openmpi
/home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/etc/openmpi-mca-params.conf
/home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/etc/openmpi-totalview.tcl
/home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/etc/openmpi-default-hostfile
/home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/share/man/man3/OpenMPI.3
/home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/share/openmpi
/home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/share/openmpi/openmpi-valgrind.supp
/home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101.conda
/home/enoki/miniconda3/pkgs/mpi-1.0-openmpi.tar.bz2
/home/enoki/miniconda3/pkgs/impact-t-2.2-mpi_openmpi_h36312d9_0
/home/enoki/miniconda3/pkgs/openmpi-4.1.5-h414af15_101.conda
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ export LD_LIBRARY_PATH=$(~/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/lib/)
bash: /home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/lib/: Это каталог
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ export LD_LIBRARY_PATH=$(realpath ~/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/lib/)
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ ImpactTexe-mpi
Abort(943274508) on node 0 (rank 0 in comm 0): Fatal error in internal_Cart_create: Invalid argument, error stack:
internal_Cart_create(102): MPI_Cart_create(MPI_COMM_WORLD, ndims=2, dims=0x7ffc65ec4128, periods=0x7ffc65ec4138, reorder=1, comm_cart=0x55a48bc48a60) failed
MPIR_Cart_create_impl(41): Size of the communicator (1) is smaller than the size of the Cartesian topology (2)
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ mpirun -n 2 ImpactTexe-mpi
 !-----------------------------------------------------------
 ! IMPACT-T Parallel Beam Dynamics Tracking Code: 2.1 beta version
 ! Copyright of The Regents of the University of California
 !-----------------------------------------------------------
 nblem:            5           5
 pass setting up lattice...
 check randomness:            0  0.30440529327431320     
 check randomness:            1  0.83543324059415791     
           1  0.35525770737678408     
           0  0.35048827465642352     
 pass generating initial distribution...
 i,t,<z>:            1   0.0000000000000000        0.0000000000000000     
 zmin,zmax:    0.0000000000000000       -1.1640888804555367E-009
 name: rfdata1rfdataxxrfdataxxx
 Ndata:          107
 Ndata:          107
 name: rfdata2rfdataxxrfdataxxx
 Ndata:           39
 name: rfdata3rfdataxxrfdataxxx
 Ndata:           39
 Ndata:           49
 Ndata:           49
 i,t,<z>:            2   9.9999999999999998E-013  -3.6927341938133503E-006
 zmin,zmax:    0.0000000000000000        6.2790480215356623E-007

===================================================================================
=   BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES
=   PID 4951 RUNNING AT lenovo-enoki
=   EXIT CODE: 139
=   CLEANING UP REMAINING PROCESSES
=   YOU CAN IGNORE THE BELOW CLEANUP MESSAGES
===================================================================================
YOUR APPLICATION TERMINATED WITH THE EXIT STRING: Segmentation fault (signal 11)
This typically refers to a problem with your application.
Please see the FAQ page for debugging suggestions
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ sudo strace ImpactTexe-mpi |& grep openmpi
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ find ~/ -iname mca_vprotocol_pessimist.so
/home/enoki/miniconda3/pkgs/openmpi-4.1.5-h414af15_101/lib/openmpi/mca_vprotocol_pessimist.so
/home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/lib/openmpi/mca_vprotocol_pessimist.so
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ echo $LD_LIBRARY_PATH
/home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/lib
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ conda deactivate
(base) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ sudo apt remove openmpi
Чтение списков пакетов… Готово
Построение дерева зависимостей… Готово
Чтение информации о состоянии… Готово         
E: Невозможно найти пакет openmpi
(base) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ sudo apt remove libopenmpi-dev
Чтение списков пакетов… Готово
Построение дерева зависимостей… Готово
Чтение информации о состоянии… Готово         
Пакет «libopenmpi-dev» не установлен, поэтому не может быть удалён
Следующие пакеты устанавливались автоматически и больше не требуются:
  libevent-core-2.1-7 libevent-dev libevent-extra-2.1-7 libevent-openssl-2.1-7
  libevent-pthreads-2.1-7 libhwloc-dev libibverbs-dev libjs-jquery-ui
  libnl-3-dev libnl-route-3-dev libnuma-dev libpmix-dev libpmix2
  libpython2-stdlib libpython2.7-minimal libpython2.7-stdlib libucx0
  openmpi-common python-pkg-resources python-setuptools python2
  python2-minimal python2.7 python2.7-minimal
Для их удаления используйте «sudo apt autoremove».
Обновлено 0 пакетов, установлено 0 новых пакетов, для удаления отмечено 0 пакетов, и 37 пакетов не обновлено.
(base) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ find ~/ -iname mca_vprotocol_pessimist.so
/home/enoki/miniconda3/pkgs/openmpi-4.1.5-h414af15_101/lib/openmpi/mca_vprotocol_pessimist.so
/home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/lib/openmpi/mca_vprotocol_pessimist.so
(base) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ sudo apt remove libopenmpi
Чтение списков пакетов… Готово
Построение дерева зависимостей… Готово
Чтение информации о состоянии… Готово         
E: Невозможно найти пакет libopenmpi
(base) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ find ~/ -iname mca_vprotocol_pessimist.so
/home/enoki/miniconda3/pkgs/openmpi-4.1.5-h414af15_101/lib/openmpi/mca_vprotocol_pessimist.so
/home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/lib/openmpi/mca_vprotocol_pessimist.so
(base) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ conda activate impact
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ mpirun -n 2 ImpactTexe-mpi
 !-----------------------------------------------------------
 ! IMPACT-T Parallel Beam Dynamics Tracking Code: 2.1 beta version
 ! Copyright of The Regents of the University of California
 !-----------------------------------------------------------
 nblem:            5           5
 pass setting up lattice...
 check randomness:            0  0.30440529327431320     
 check randomness:            1  0.83543324059415791     
           0  0.35048827465642352     
           1  0.35525770737678408     
 pass generating initial distribution...
 i,t,<z>:            1   0.0000000000000000        0.0000000000000000     
 zmin,zmax:    0.0000000000000000       -1.1640888804555367E-009
 name: rfdata1rfdataxxrfdataxxx
 Ndata:          107
 name: rfdata2rfdataxxrfdataxxx
 Ndata:          107
 Ndata:           39
 Ndata:           39
 name: rfdata3rfdataxxrfdataxxx
 Ndata:           49
 Ndata:           49
 i,t,<z>:            2   9.9999999999999998E-013  -3.6927341938133503E-006
 zmin,zmax:    0.0000000000000000        6.2790480215356623E-007

===================================================================================
=   BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES
=   PID 5068 RUNNING AT lenovo-enoki
=   EXIT CODE: 139
=   CLEANING UP REMAINING PROCESSES
=   YOU CAN IGNORE THE BELOW CLEANUP MESSAGES
===================================================================================
YOUR APPLICATION TERMINATED WITH THE EXIT STRING: Segmentation fault (signal 11)
This typically refers to a problem with your application.
Please see the FAQ page for debugging suggestions
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ sudo strace ImpactTexe-mpi |& grep openmpi
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ sudo strace ImpactTexe-mpi
execve("/usr/local/bin/ImpactTexe-mpi", ["ImpactTexe-mpi"], 0x7ffdccd649a0 /* 17 vars */) = 0
brk(NULL)                               = 0x561797017000
arch_prctl(0x3001 /* ARCH_??? */, 0x7fff6d375530) = -1 EINVAL (Недопустимый аргумент)
mmap(NULL, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f8fd4958000
access("/etc/ld.so.preload", R_OK)      = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3
newfstatat(3, "", {st_mode=S_IFREG|0644, st_size=61135, ...}, AT_EMPTY_PATH) = 0
mmap(NULL, 61135, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f8fd4949000
close(3)                                = 0
openat(AT_FDCWD, "/lib/x86_64-linux-gnu/glibc-hwcaps/x86-64-v3/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/x86_64-linux-gnu/glibc-hwcaps/x86-64-v3", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/lib/x86_64-linux-gnu/glibc-hwcaps/x86-64-v2/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/x86_64-linux-gnu/glibc-hwcaps/x86-64-v2", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/lib/x86_64-linux-gnu/tls/x86_64/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/x86_64-linux-gnu/tls/x86_64/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/lib/x86_64-linux-gnu/tls/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/x86_64-linux-gnu/tls/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/lib/x86_64-linux-gnu/tls/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/x86_64-linux-gnu/tls/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/lib/x86_64-linux-gnu/tls/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/x86_64-linux-gnu/tls", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/lib/x86_64-linux-gnu/x86_64/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/x86_64-linux-gnu/x86_64/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/lib/x86_64-linux-gnu/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/x86_64-linux-gnu/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/lib/x86_64-linux-gnu/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/x86_64-linux-gnu/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/lib/x86_64-linux-gnu/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/x86_64-linux-gnu", {st_mode=S_IFDIR|0755, st_size=81920, ...}, 0) = 0
openat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/glibc-hwcaps/x86-64-v3/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/glibc-hwcaps/x86-64-v3", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/glibc-hwcaps/x86-64-v2/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/glibc-hwcaps/x86-64-v2", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/tls/x86_64/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/tls/x86_64/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/tls/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/tls/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/tls/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/tls/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/tls/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/tls", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/x86_64/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/x86_64/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/x86_64-linux-gnu", {st_mode=S_IFDIR|0755, st_size=81920, ...}, 0) = 0
openat(AT_FDCWD, "/lib/glibc-hwcaps/x86-64-v3/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/glibc-hwcaps/x86-64-v3", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/lib/glibc-hwcaps/x86-64-v2/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/glibc-hwcaps/x86-64-v2", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/lib/tls/x86_64/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/tls/x86_64/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/lib/tls/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/tls/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/lib/tls/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/tls/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/lib/tls/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/tls", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/lib/x86_64/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/x86_64/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/lib/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/lib/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/lib/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/lib", {st_mode=S_IFDIR|0755, st_size=4096, ...}, 0) = 0
openat(AT_FDCWD, "/usr/lib/glibc-hwcaps/x86-64-v3/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/glibc-hwcaps/x86-64-v3", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/usr/lib/glibc-hwcaps/x86-64-v2/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/glibc-hwcaps/x86-64-v2", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/usr/lib/tls/x86_64/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/tls/x86_64/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/usr/lib/tls/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/tls/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/usr/lib/tls/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/tls/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/usr/lib/tls/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/tls", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/usr/lib/x86_64/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/x86_64/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/usr/lib/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/usr/lib/x86_64/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib/x86_64", 0x7fff6d374750, 0) = -1 ENOENT (Нет такого файла или каталога)
openat(AT_FDCWD, "/usr/lib/libmpi_mpifh.so.40", O_RDONLY|O_CLOEXEC) = -1 ENOENT (Нет такого файла или каталога)
newfstatat(AT_FDCWD, "/usr/lib", {st_mode=S_IFDIR|0755, st_size=4096, ...}, 0) = 0
writev(2, [{iov_base="ImpactTexe-mpi", iov_len=14}, {iov_base=": ", iov_len=2}, {iov_base="error while loading shared libra"..., iov_len=36}, {iov_base=": ", iov_len=2}, {iov_base="libmpi_mpifh.so.40", iov_len=18}, {iov_base=": ", iov_len=2}, {iov_base="cannot open shared object file", iov_len=30}, {iov_base=": ", iov_len=2}, {iov_base="No such file or directory", iov_len=25}, {iov_base="\n", iov_len=1}], 10ImpactTexe-mpi: error while loading shared libraries: libmpi_mpifh.so.40: cannot open shared object file: No such file or directory
) = 132
exit_group(127)                         = ?
+++ exited with 127 +++
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ find ~/ -iname "*mfifh.so"
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ find ~/ -iname "*mpifh.so"
/home/enoki/miniconda3/pkgs/openmpi-4.1.5-h414af15_101/lib/libmpi_mpifh.so
/home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/lib/libmpi_mpifh.so
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ echo $LD_LIBRARY_PATH 
/home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/lib
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ ls $LD_LIBRARY_PATH
libmca_common_cuda.so                libmpi_usempif08.so.40.30.0
libmca_common_cuda.so.40             libmpi_usempi_ignore_tkr.so
libmca_common_cuda.so.40.30.0        libmpi_usempi_ignore_tkr.so.40
libmca_common_dstore.so              libmpi_usempi_ignore_tkr.so.40.30.0
libmca_common_dstore.so.1            libompitrace.so
libmca_common_dstore.so.1.0.2        libompitrace.so.40
libmca_common_monitoring.so          libompitrace.so.40.30.1
libmca_common_monitoring.so.50       libopen-pal.so
libmca_common_monitoring.so.50.20.0  libopen-pal.so.40
libmca_common_ompio.so               libopen-pal.so.40.30.3
libmca_common_ompio.so.41            libopen-rte.so
libmca_common_ompio.so.41.29.4       libopen-rte.so.40
libmca_common_sm.so                  libopen-rte.so.40.30.3
libmca_common_sm.so.40               liboshmem.so
libmca_common_sm.so.40.30.0          liboshmem.so.40
libmca_common_ucx.so                 liboshmem.so.40.30.3
libmca_common_ucx.so.40              mpi_ext.mod
libmca_common_ucx.so.40.30.2         mpi_f08_callbacks.mod
libmca_common_verbs.so               mpi_f08_ext.mod
libmca_common_verbs.so.40            mpi_f08_interfaces_callbacks.mod
libmca_common_verbs.so.40.30.0       mpi_f08_interfaces.mod
libmpi_mpifh.so                      mpi_f08.mod
libmpi_mpifh.so.40                   mpi_f08_types.mod
libmpi_mpifh.so.40.30.0              mpi.mod
libmpi.so                            ompi_monitoring_prof.so
libmpi.so.40                         openmpi
libmpi.so.40.30.6                    pkgconfig
libmpi_usempif08.so                  pmix
libmpi_usempif08.so.40               pmpi_f08_interfaces.mod
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ echo $LD_LIBRARY_PATH
/home/enoki/miniconda3/pkgs/openmpi-4.1.6-hc5af2df_101/lib
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ mpirun -X LD_LIBRARY_PATH -n 2 ImpactTexe-mpi
[mpiexec@lenovo-enoki] match_arg (lib/utils/args.c:166): unrecognized argument X
[mpiexec@lenovo-enoki] HYDU_parse_array (lib/utils/args.c:181): argument matching returned error
[mpiexec@lenovo-enoki] parse_args (mpiexec/get_parameters.c:315): error parsing input array
[mpiexec@lenovo-enoki] HYD_uii_mpx_get_parameters (mpiexec/get_parameters.c:47): unable to parse user arguments
[mpiexec@lenovo-enoki] main (mpiexec/mpiexec.c:54): error parsing parameters
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ mpirun --help

Usage: ./mpiexec [global opts] [local opts for exec1] [exec1] [exec1 args] : [local opts for exec2] [exec2] [exec2 args] : ...

Global options (passed to all executables):

  Global environment options:
    -genv {name} {value}             environment variable name and value
    -genvlist {env1,env2,...}        environment variable list to pass
    -genvnone                        do not pass any environment variables
    -genvall                         pass all environment variables not managed
                                          by the launcher (default)

  Other global options:
    -f {name}                        file containing the host names
    -hosts {host list}               comma separated host list
    -rankmap {rank map}              comma separated rank to node id list
    -wdir {dirname}                  working directory to use
    -configfile {name}               config file containing MPMD launch options


Local options (passed to individual executables):

  Local environment options:
    -env {name} {value}              environment variable name and value
    -envlist {env1,env2,...}         environment variable list to pass
    -envnone                         do not pass any environment variables
    -envall                          pass all environment variables (default)

  Other local options:
    -n/-np {value}                   number of processes
    {exec_name} {args}               executable name and arguments


Hydra specific options (treated as global):

  Launch options:
    -launcher                        launcher to use (ssh rsh fork slurm ll lsf sge manual persist)
    -launcher-exec                   executable to use to launch processes
    -enable-x/-disable-x             enable or disable X forwarding

  Resource management kernel options:
    -rmk                             resource management kernel to use (user slurm ll lsf sge pbs cobalt)

  Processor topology options:
    -topolib                         processor topology library (hwloc)
    -bind-to                         process binding
    -map-by                          process mapping
    -membind                         memory binding policy

  Demux engine options:
    -demux                           demux engine (poll select)

  Other Hydra options:
    -disable-auto-cleanup            dont cleanup processes on error
    -disable-hostname-propagation    let MPICH auto-detect the hostname
    -errfile-pattern                 direct stderr to file
    -gpus-per-proc                   number of GPUs per process (default: auto)
    -hybrid-hosts                    assume hosts do not share paths
    -iface                           network interface to use
    -info                            build information
    -localhost                       local hostname for the launching node
    -nameserver                      name server information (host:port format)
    -order-nodes                     order nodes as ascending/descending cores
    -outfile-pattern                 direct stdout to file
    -pmi-port                        use the PMI_PORT model
    -ppn                             processes per node
    -prepend-pattern                 prepend pattern to output
    -prepend-rank                    prepend rank to output
    -print-all-exitcodes             print exit codes of all processes
    -profile                         turn on internal profiling
    -skip-launch-node                do not run MPI processes on the launch node
    -usize                           universe size (SYSTEM, INFINITE, <value>)
    -verbose                         verbose mode

Please see the instructions provided at
http://wiki.mpich.org/mpich/index.php/Using_the_Hydra_Process_Manager
for further details

(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ mpirun -env LD_LIBRARY_PATH "$LD_LIBRARY_PATH" --host=localhost:2 -n 2 ImpactTexe-mpi
 !-----------------------------------------------------------
 ! IMPACT-T Parallel Beam Dynamics Tracking Code: 2.1 beta version
 ! Copyright of The Regents of the University of California
 !-----------------------------------------------------------
 nblem:            5           5
 pass setting up lattice...
 check randomness:            0  0.30440529327431320     
 check randomness:            1  0.83543324059415791     
           0  0.35048827465642352     
           1  0.35525770737678408     
 pass generating initial distribution...
 i,t,<z>:            1   0.0000000000000000        0.0000000000000000     
 zmin,zmax:    0.0000000000000000       -1.1640888804555367E-009
 name: rfdata1rfdataxxrfdataxxx
 Ndata:          107
 Ndata:          107
 name: rfdata2rfdataxxrfdataxxx
 Ndata:           39
 name: rfdata3rfdataxxrfdataxxx
 Ndata:           39
 Ndata:           49
 Ndata:           49
 i,t,<z>:            2   9.9999999999999998E-013  -3.6927341938133503E-006
 zmin,zmax:    0.0000000000000000        6.2790480215356623E-007

===================================================================================
=   BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES
=   PID 5097 RUNNING AT localhost
=   EXIT CODE: 139
=   CLEANING UP REMAINING PROCESSES
=   YOU CAN IGNORE THE BELOW CLEANUP MESSAGES
===================================================================================
YOUR APPLICATION TERMINATED WITH THE EXIT STRING: Segmentation fault (signal 11)
This typically refers to a problem with your application.
Please see the FAQ page for debugging suggestions
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ which ImpactTexe-mpi
/home/enoki/miniconda3/envs/impact/bin/ImpactTexe-mpi
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ ls /home/enoki/miniconda3/envs/impact/lib/
libatomic.so          libmpi.a              libmpl.so
libatomic.so.1        libmpichcxx.so        libopa.so
libatomic.so.1.2.0    libmpichf90.so        libquadmath.so
libfmpich.so          libmpich.so           libquadmath.so.0
libgcc_s.so           libmpicxx.a           libquadmath.so.0.0.0
libgcc_s.so.1         libmpicxx.so          libstdc++.so
libgfortran.so        libmpicxx.so.12       libstdc++.so.6
libgfortran.so.5      libmpicxx.so.12.3.1   libstdc++.so.6.0.32
libgfortran.so.5.0.0  libmpifort.a          libz.a
libgomp.so            libmpifort.so         libz.so
libgomp.so.1          libmpifort.so.12      libz.so.1
libgomp.so.1.0.0      libmpifort.so.12.3.1  libz.so.1.2.13
libitm.so             libmpi.so             pkgconfig
libitm.so.1           libmpi.so.12
libitm.so.1.0.0       libmpi.so.12.3.1
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ mpirun --host=localhost:2 -n 2 ImpactTexe-mpi
 !-----------------------------------------------------------
 ! IMPACT-T Parallel Beam Dynamics Tracking Code: 2.1 beta version
 ! Copyright of The Regents of the University of California
 !-----------------------------------------------------------
 nblem:            5           5
 pass setting up lattice...
 check randomness:            0  0.30440529327431320     
 check randomness:            1  0.83543324059415791     
           0  0.35048827465642352     
           1  0.35525770737678408     
 pass generating initial distribution...
 i,t,<z>:            1   0.0000000000000000        0.0000000000000000     
 zmin,zmax:    0.0000000000000000       -1.1640888804555367E-009
 name: rfdata1rfdataxxrfdataxxx
 Ndata:          107
 Ndata:          107
 name: rfdata2rfdataxxrfdataxxx
 Ndata:           39
 Ndata:           39
 name: rfdata3rfdataxxrfdataxxx
 Ndata:           49
 i,t,<z>:            2   9.9999999999999998E-013  -3.6927341938133503E-006
 Ndata:           49
 zmin,zmax:    0.0000000000000000        6.2790480215356623E-007

===================================================================================
=   BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES
=   PID 5110 RUNNING AT localhost
=   EXIT CODE: 139
=   CLEANING UP REMAINING PROCESSES
=   YOU CAN IGNORE THE BELOW CLEANUP MESSAGES
===================================================================================
YOUR APPLICATION TERMINATED WITH THE EXIT STRING: Segmentation fault (signal 11)
This typically refers to a problem with your application.
Please see the FAQ page for debugging suggestions
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ export LD_LIBRARY_PATH=/home/enoki/miniconda3/envs/impact/lib/
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ mpirun --host=localhost:2 -n 2 ImpactTexe-mpi
 !-----------------------------------------------------------
 ! IMPACT-T Parallel Beam Dynamics Tracking Code: 2.1 beta version
 ! Copyright of The Regents of the University of California
 !-----------------------------------------------------------
 nblem:            5           5
 pass setting up lattice...
 check randomness:            0  0.30440529327431320     
 check randomness:            1  0.83543324059415791     
           0  0.35048827465642352     
           1  0.35525770737678408     
 pass generating initial distribution...
 i,t,<z>:            1   0.0000000000000000        0.0000000000000000     
 zmin,zmax:    0.0000000000000000       -1.1640888804555367E-009
 name: rfdata1rfdataxxrfdataxxx
 Ndata:          107
 name: rfdata2rfdataxxrfdataxxx
 Ndata:          107
 Ndata:           39
 name: rfdata3rfdataxxrfdataxxx
 Ndata:           39
 Ndata:           49
 Ndata:           49
 i,t,<z>:            2   9.9999999999999998E-013  -3.6927341938133503E-006
 zmin,zmax:    0.0000000000000000        6.2790480215356623E-007

===================================================================================
=   BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES
=   PID 5119 RUNNING AT localhost
=   EXIT CODE: 139
=   CLEANING UP REMAINING PROCESSES
=   YOU CAN IGNORE THE BELOW CLEANUP MESSAGES
===================================================================================
YOUR APPLICATION TERMINATED WITH THE EXIT STRING: Segmentation fault (signal 11)
This typically refers to a problem with your application.
Please see the FAQ page for debugging suggestions
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$ less ~/.bash_history
(impact) enoki@lenovo-enoki:~/IMPACT-T/examples/Sample1$

I also tried using MPI mode without running `conda activate impact'. The program, by the way, began to think that progress was already being made (the MPI version, as I understood, differs on a PC with a cluster and the conda version), however, it gave lochigeski incorrect results. Either the particles fly away to infinity, or they start to be pulled randomly throughout the interval (it's scary even to show graphs)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@Enoki-ru