[gmx-users] MPICH hang

[Mehmet Suezen]

Hi All,

I have tried to compile with MPICH implementation of MPI and obtained
executable successfully.(called mdrun_mpi_d
Water sample simulation of gromacs works fine with single processor like

mpirun -np 1 -machinefile file_hosts mdrun_mpi_d -s water.tpr -o
water.trr -c water_out.gro -v -g water.log

where file_hosts is simply hosts.
But If I tried with -np 2 or more than it seems that program hanged
after MPI_init().I have noticed this in user guide of  
MPICH .I`m attaching echo of mpirun in case of -np 2.

Any suggestion .

Many Thanks

Mehmet
-------------- next part --------------
++ echo 'default_arch   = LINUX'
default_arch   = LINUX
++ echo 'default_device = ch_p4'
default_device = ch_p4
++ echo 'machine	     = ch_p4'
machine	     = ch_p4
++ '[' 1 -le 14 ']'
++ arg=-np
++ shift
++ np=2
+++ echo 2
+++ sed 's/^[0-9]*$//'
++ nodigits=
++ '[' '' '!=' '' -o 2 -lt 1 ']'
++ eval np0=2
+++ np0=2
++ NP=2
++ export NP
++ shift
++ '[' 1 -le 12 ']'
++ arg=-machinefile
++ shift
++ machineFile=file_hosts
++ eval machineFile0=file_hosts
+++ machineFile0=file_hosts
++ shift
++ '[' 1 -le 10 ']'
++ arg=mdrun_mpi_d
++ shift
++ '[' -x /users/suzen/mpich-1.2.2.1/bin/mpirun.ch_p4.args ']'
++ device_knows_arg=0
++ . /users/suzen/mpich-1.2.2.1/bin/mpirun.ch_p4.args
++ '[' 0 '!=' 0 ']'
+++ echo mdrun_mpi_d
+++ sed s/%a//g
++ proginstance=mdrun_mpi_d
++ '[' '' = '' -a '' = '' -a '!' -x mdrun_mpi_d ']'
++ '[' '' = '' -a -x mdrun_mpi_d ']'
++ progname=mdrun_mpi_d
++ '[' 1 -le 9 ']'
++ arg=-s
++ cmdLineArgsExecer= -arg="-s"
++ cmdLineArgs= "-s"
++ shift
++ '[' 1 -le 8 ']'
++ arg=water.tpr
++ cmdLineArgsExecer= -arg="-s" -arg="water.tpr"
++ cmdLineArgs= "-s" "water.tpr"
++ shift
++ '[' 1 -le 7 ']'
++ arg=-o
++ cmdLineArgsExecer= -arg="-s" -arg="water.tpr" -arg="-o"
++ cmdLineArgs= "-s" "water.tpr" "-o"
++ shift
++ '[' 1 -le 6 ']'
++ arg=water.trr
++ cmdLineArgsExecer= -arg="-s" -arg="water.tpr" -arg="-o" -arg="water.trr"
++ cmdLineArgs= "-s" "water.tpr" "-o" "water.trr"
++ shift
++ '[' 1 -le 5 ']'
++ arg=-c
++ cmdLineArgsExecer= -arg="-s" -arg="water.tpr" -arg="-o" -arg="water.trr" -arg="-c"
++ cmdLineArgs= "-s" "water.tpr" "-o" "water.trr" "-c"
++ shift
++ '[' 1 -le 4 ']'
++ arg=water_out.gro
++ cmdLineArgsExecer= -arg="-s" -arg="water.tpr" -arg="-o" -arg="water.trr" -arg="-c" -arg="water_out.gro"
++ cmdLineArgs= "-s" "water.tpr" "-o" "water.trr" "-c" "water_out.gro"
++ shift
++ '[' 1 -le 3 ']'
++ arg=-v
++ cmdLineArgsExecer= -arg="-s" -arg="water.tpr" -arg="-o" -arg="water.trr" -arg="-c" -arg="water_out.gro" -arg="-v"
++ cmdLineArgs= "-s" "water.tpr" "-o" "water.trr" "-c" "water_out.gro" "-v"
++ shift
++ '[' 1 -le 2 ']'
++ arg=-g
++ cmdLineArgsExecer= -arg="-s" -arg="water.tpr" -arg="-o" -arg="water.trr" -arg="-c" -arg="water_out.gro" -arg="-v" -arg="-g"
++ cmdLineArgs= "-s" "water.tpr" "-o" "water.trr" "-c" "water_out.gro" "-v" "-g"
++ shift
++ '[' 1 -le 1 ']'
++ arg=water.log
++ cmdLineArgsExecer= -arg="-s" -arg="water.tpr" -arg="-o" -arg="water.trr" -arg="-c" -arg="water_out.gro" -arg="-v" -arg="-g" -arg="water.log"
++ cmdLineArgs= "-s" "water.tpr" "-o" "water.trr" "-c" "water_out.gro" "-v" "-g" "water.log"
++ shift
++ '[' 1 -le 0 ']'
++ '[' 1 -le 0 ']'
++ '[' '' = '' -a mdrun_mpi_d = '' ']'
++ '[' -n '' -a -n mdrun_mpi_d ']'
++ larch=
++ '[' -z '' ']'
++ larch=LINUX
++ '[' -n 'sed -e s@/tmp_mnt/@/@g' ']'
+++ pwd
+++ sed -e s@/tmp_mnt/@/@g
++ PWDtest=/home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water
++ '[' '!' -d /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water ']'
++ '[' -n /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water ']'
+++ echo /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water
+++ sed -e s@/tmp_mnt/@/@g
++ PWDtest2=/home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water
++ /bin/rm -f /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/.mpirtmp30793 /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/.mpirtmp30793
+++ eval 'echo test > /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/.mpirtmp30793'
++ '[' '!' -s /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/.mpirtmp30793 ']'
++ PWD=/home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water
++ /bin/rm -f /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/.mpirtmp30793 /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/.mpirtmp30793
++ '[' -n /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water ']'
++ PWD_TRIAL=/home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water
+++ echo mdrun_mpi_d
+++ sed 's/\/.*//'
++ tail=mdrun_mpi_d
++ '[' mdrun_mpi_d = '' ']'
++ progname=/home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/mdrun_mpi_d
++ '[' '' = '' -a -x /users/suzen/mpich-1.2.2.1/bin/tarch ']'
+++ /users/suzen/mpich-1.2.2.1/bin/tarch
++ arch=LINUX
++ '[' LINUX = IRIX64 -a '(' LINUX = IRIX -o LINUX = IRIXN32 ')' ']'
++ archlist=LINUX
++ '[' ch_p4 = '' ']'
++ '[' ch_p4 = p4 -o ch_p4 = execer -o ch_p4 = sgi_mp -o ch_p4 = ch_p4 -o ch_p4 = ch_p4-2 -o ch_p4 = globus -o ch_p4 = globus ']'
++ '[' '' = '' ']'
++ MPI_HOST=
++ '[' LINUX = ipsc860 ']'
++ '[' '' = bproc ']'
+++ hostname
++ MPI_HOST=lx01
++ '[' lx01 = '' ']'
++ '[' /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water '!=' '' ']'
+++ pwd
+++ sed -e s%/tmp_mnt/%/%g
++ PWD_TRIAL=/home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water
++ '[' '!' -d /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water ']'
++ '[' 0 = 1 ']'
+ argsset=1
+ mpirun_version=
+ mpirun_version=/users/suzen/mpich-1.2.2.1/bin/mpirun.ch_p4
+ exitstat=1
+ '[' -n /users/suzen/mpich-1.2.2.1/bin/mpirun.ch_p4 ']'
+ '[' -x /users/suzen/mpich-1.2.2.1/bin/mpirun.ch_p4 ']'
+ . /users/suzen/mpich-1.2.2.1/bin/mpirun.ch_p4
++ exitstatus=1
++ move_pgfile_to_master=no
++ rcpcmd=rcp
++ '[' -z 1 ']'
++ '[' -n '' ']'
++ '[' -n '' ']'
++ '[' '' = shared ']'
++ MPI_MAX_CLUSTER_SIZE=1
++ . /users/suzen/mpich-1.2.2.1/bin/mpirun.pg
+++ external_allocate_cmd=
+++ '[' 1 = '' ']'
+++ '[' 0 = 0 ']'
+++ narch=1
+++ arch1=LINUX
+++ archlist1=LINUX
+++ archlocal=LINUX
+++ np1=2
+++ '[' 0 = 1 ']'
+++ procFound=1
+++ machinelist=
+++ archuselist=
+++ nprocuselist=
+++ curarch=1
+++ nolocalsave=0
+++ archlocal=LINUX
+++ '[' -n '' ']'
+++ '[' -n '' ']'
+++ '[' 1 -le 1 ']'
+++ eval 'arch=$arch1'
++++ arch=LINUX
+++ eval 'archlist=$archlist1'
++++ archlist=LINUX
+++ '[' -z LINUX ']'
+++ eval 'np=$np1'
++++ np=2
+++ '[' -z 2 ']'
+++ eval 'mFile=$machineFile1'
++++ mFile=
+++ '[' -n '' -a -r '' ']'
+++ '[' -z file_hosts ']'
+++ '[' -z file_hosts -o '!' -s file_hosts -o '!' -r file_hosts ']'
++++ expr lx01 : '\([^\.]*\).*'
+++ MPI_HOSTLeader=lx01
+++ '[' '' = yes ']'
++++ expr 2 + 0
+++ np=2
+++ '[' 0 = 0 -o 1 -gt 1 ']'
++++ cat file_hosts
++++ sed -e '/^#/d' -e 's/#.*^//g'
++++ head -2
++++ tr '\012' ' '
+++ machineavail=lx01:2 
+++ '[' -n '' ']'
+++ '[' -n '' ']'
+++ KeepHost=0
+++ loopcnt=0
+++ '[' -z 1 ']'
+++ '[' 0 = 0 -a 1 -gt 1 ']'
++++ expr 2 - 1
+++ nleft=1
+++ '[' 1 -lt 0 ']'
+++ '[' 1 -lt 2 ']'
+++ nfound=0
+++ nprocmachine=1
+++ '[' '' = 1 ']'
++++ expr lx01:2 : '.*:\([0-9]*\)'
+++ ntest=2
+++ '[' -n 2 -a 2 '!=' 0 ']'
+++ nprocmachine=2
+++ '[' -z 1 ']'
+++ '[' 1 -lt 2 ']'
+++ nprocmachine=1
++++ expr lx01:2 : '\(.*\):.*'
+++ machineName=lx01
++++ expr lx01 : '\([^\.]*\).*'
+++ machineNameLeader=lx01
+++ '[' 0 = 1 -o 0 = 1 -o '(' lx01 '!=' lx01 -a lx01 '!=' lx01 ')' ']'
+++ '[' 1 = 2 ']'
+++ '[' lx01 = lx01 ']'
+++ KeepHost=1
++++ expr 0 + 1
+++ loopcnt=1
+++ '[' 0 = 0 -a 1 -gt 1 ']'
+++ '[' 1 -lt 2 ']'
+++ nfound=0
+++ nprocmachine=1
+++ '[' '' = 1 ']'
++++ expr lx01:2 : '.*:\([0-9]*\)'
+++ ntest=2
+++ '[' -n 2 -a 2 '!=' 0 ']'
+++ nprocmachine=2
+++ '[' -z 1 ']'
+++ '[' 1 -lt 2 ']'
+++ nprocmachine=1
++++ expr lx01:2 : '\(.*\):.*'
+++ machineName=lx01
++++ expr lx01 : '\([^\.]*\).*'
+++ machineNameLeader=lx01
+++ '[' 0 = 1 -o 1 = 1 -o '(' lx01 '!=' lx01 -a lx01 '!=' lx01 ')' ']'
+++ '[' 1 -gt 1 ']'
+++ machinelist= lx01
+++ archuselist= LINUX
+++ nprocuselist= 1
++++ expr 1 + 1
+++ procFound=2
++++ expr 0 + 1
+++ nfound=1
++++ expr 1 - 1
+++ nleft=0
+++ '[' 2 = 2 ']'
+++ break
++++ expr 1 + 1
+++ loopcnt=2
+++ '[' 1 = 0 -a 2 -gt 1 ']'
+++ '[' 2 -lt 2 ']'
++++ expr 1 + 1
+++ curarch=2
+++ procFound=0
+++ nolocal=1
+++ machineFile=
+++ '[' 2 -le 1 ']'
+++ nolocal=0
+++ '[' 1 '!=' 1 ']'
+++ break
++ prognamemain=/home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/mdrun_mpi_d
++ '[' -z '' ']'
++ p4pgfile=/home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/PI30793
++ cat
++ '[' '!' -s /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/PI30793 ']'
++ /bin/rm -rf /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/PI30793
++ procNum=1
+++ echo 1
+++ cut '-d ' -f1
++ nprocval=1
++ '[' -z 1 ']'
+++ expr 1 - 1
++ nprocval=0
++ archval=LINUX
+++ echo /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/mdrun_mpi_d
+++ sed s/%a/LINUX/g
++ proginstance=/home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/mdrun_mpi_d
++ prognamemain=/home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/mdrun_mpi_d
++ '[' 0 = 1 ']'
++ '[' 0 = 0 ']'
++ '[' -z lx01 ']'
++ '[' -z '' ']'
++ nprocval=0
++ echo 'lx01 0 /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/mdrun_mpi_d'
++ cnt=1
++ '[' 1 = 2 ']'
+++ echo LINUX
+++ cut '-d ' -f1
++ archval=LINUX
+++ echo 1
+++ cut '-d ' -f1
++ nprocval=1
+++ expr 1 + 1
++ cnt=2
+++ echo /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/mdrun_mpi_d
+++ sed s/%a/LINUX/g
++ proginstance=/home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/mdrun_mpi_d
++ '[' 0 = 1 ']'
++ echo lx01 1 /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/mdrun_mpi_d
++ '[' 0 = 0 -a '!' -r /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/PI30793 ']'
++ '[' 0 = 0 -a 0 = 1 ']'
++ /bin/sync
++ '[' '' = '' ']'
++ p4workdir=/home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water
++ startpgm=/home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/mdrun_mpi_d  "-s" "water.tpr" "-o" "water.trr" "-c" "water_out.gro" "-v" "-g" "water.log" -p4pg /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/PI30793 -p4wd /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water
++ p4pgfile_master=/home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/PI30793
++ '[' 0 = 1 -a no = yes ']'
++ '[' '' '!=' '' ']'
++ MPIRUN_DEVICE=ch_p4
++ export MPIRUN_DEVICE
++ '[' 0 = 1 ']'
++ doitall=eval
++ '[' 0 = 1 ']'
++ '[' -n '' ']'
++ eval /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/mdrun_mpi_d '"-s"' '"water.tpr"' '"-o"' '"water.trr"' '"-c"' '"water_out.gro"' '"-v"' '"-g"' '"water.log"' -p4pg /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/PI30793 -p4wd /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water
+++ /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/mdrun_mpi_d -s water.tpr -o water.trr -c water_out.gro -v -g water.log -p4pg /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/PI30793 -p4wd /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water
++ exitstatus=1
++ '[' 0 '!=' 1 ']'
++ '[' 0 = 1 ']'
++ '[' 0 = 1 -a no = yes ']'
++ /bin/rm /home/suzen/MDcodes/gromacs-3.0.5/share/tutor/water/PI30793
++ '[' '' = yes ']'
++ exit 1