USER = yinzping HOMEDIR = /home/yinzping JOB_ID = 4123 JOB_NAME = CaFPMfull QUEUE = wp10 NSLOTS = 36 NHOSTS = 8 SUB_HOST = rupc06 SUB_DIR = /mnt/wk05/yinzping/WIEN2k/DMFT/FeAs/CaFeAsF/P4nmm/U5J8/beta160/Full2/2444yinzping EXE_HOST = n152 NFS_HOST = caip02s EXE_DIR = /mnt/p06 OUT_DIR = /tmp TMP_DIR = /tmp/4123.1.wp10 INFO = Files larger than 100MB will be compressed to reduce the network load. INFO2 = Do NOT remove this file while job is running! PORT = 24123 rcp: /mnt/wk05/yinzping/WIEN2k/DMFT/FeAs/CaFeAsF/P4nmm/U5J8/beta160/Full2/2444yinzping/imp.0: not a plain file Failure to rcp files! Your job started at Mon Mar 21 22:35:02 EDT 2011 on host n152 in /mnt/p06/4123yinzping Submission directory is /mnt/wk05/yinzping/WIEN2k/DMFT/FeAs/CaFeAsF/P4nmm/U5J8/beta160/Full2/2444yinzping on host rupc06 ----------------------------------------------------------------------------------------- + echo -catch_rsh /opt/sge6/spool/n152/active_jobs/4123.1/pe_hostfile /opt/mpich2/intel/11.1/ -catch_rsh /opt/sge6/spool/n152/active_jobs/4123.1/pe_hostfile /opt/mpich2/intel/11.1/ + SLEEPTIME=5 + RETRIES=10 + catch_rsh=0 + catch_hostname=0 + '[' 3 -gt 0 ']' + case "$1" in + catch_rsh=1 + shift + '[' 2 -gt 0 ']' + case "$1" in + break ++ basename /opt/sge6/mpich2_smpd/startmpich2.sh + me=startmpich2.sh + '[' 2 -lt 2 ']' + pe_hostfile=/opt/sge6/spool/n152/active_jobs/4123.1/pe_hostfile + MPICH2_ROOT=/opt/mpich2/intel/11.1/ + export MPICH2_ROOT + '[' '!' -x /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 ']' + '[' '!' -x /opt/mpich2/intel/11.1//bin/smpd ']' + '[' '!' -r /opt/sge6/spool/n152/active_jobs/4123.1/pe_hostfile ']' + machines=/tmp/4123.1.wp10/machines + PeHostfile2MachineFile /opt/sge6/spool/n152/active_jobs/4123.1/pe_hostfile + cat /opt/sge6/spool/n152/active_jobs/4123.1/pe_hostfile + read line ++ echo n152 2 wp10@n152 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n152 ++ echo n152 2 wp10@n152 UNDEFINED ++ cut -f2 '-d ' + nslots=2 + i=1 + '[' 1 -le 2 ']' + echo n152 ++ expr 1 + 1 + i=2 + '[' 2 -le 2 ']' + echo n152 ++ expr 2 + 1 + i=3 + '[' 3 -le 2 ']' + read line ++ echo n161 1 wp10@n161 UNDEFINED ++ cut -f1 -d. ++ cut -f1 '-d ' + host=n161 ++ cut -f2 '-d ' ++ echo n161 1 wp10@n161 UNDEFINED + nslots=1 + i=1 + '[' 1 -le 1 ']' + echo n161 ++ expr 1 + 1 + i=2 + '[' 2 -le 1 ']' + read line ++ echo n155 4 wp10@n155 UNDEFINED ++ cut -f1 -d. ++ cut -f1 '-d ' + host=n155 ++ cut -f2 '-d ' ++ echo n155 4 wp10@n155 UNDEFINED + nslots=4 + i=1 + '[' 1 -le 4 ']' + echo n155 ++ expr 1 + 1 + i=2 + '[' 2 -le 4 ']' + echo n155 ++ expr 2 + 1 + i=3 + '[' 3 -le 4 ']' + echo n155 ++ expr 3 + 1 + i=4 + '[' 4 -le 4 ']' + echo n155 ++ expr 4 + 1 + i=5 + '[' 5 -le 4 ']' + read line ++ cut -f1 -d. ++ cut -f1 '-d ' ++ echo n146 1 wp10@n146 UNDEFINED + host=n146 ++ echo n146 1 wp10@n146 UNDEFINED ++ cut -f2 '-d ' + nslots=1 + i=1 + '[' 1 -le 1 ']' + echo n146 ++ expr 1 + 1 + i=2 + '[' 2 -le 1 ']' + read line ++ echo n149 4 wp10@n149 UNDEFINED ++ cut -f1 -d. ++ cut -f1 '-d ' + host=n149 ++ echo n149 4 wp10@n149 UNDEFINED ++ cut -f2 '-d ' + nslots=4 + i=1 + '[' 1 -le 4 ']' + echo n149 ++ expr 1 + 1 + i=2 + '[' 2 -le 4 ']' + echo n149 ++ expr 2 + 1 + i=3 + '[' 3 -le 4 ']' + echo n149 ++ expr 3 + 1 + i=4 + '[' 4 -le 4 ']' + echo n149 ++ expr 4 + 1 + i=5 + '[' 5 -le 4 ']' + read line ++ echo n143 11 wp10@n143 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n143 ++ cut -f2 '-d ' ++ echo n143 11 wp10@n143 UNDEFINED + nslots=11 + i=1 + '[' 1 -le 11 ']' + echo n143 ++ expr 1 + 1 + i=2 + '[' 2 -le 11 ']' + echo n143 ++ expr 2 + 1 + i=3 + '[' 3 -le 11 ']' + echo n143 ++ expr 3 + 1 + i=4 + '[' 4 -le 11 ']' + echo n143 ++ expr 4 + 1 + i=5 + '[' 5 -le 11 ']' + echo n143 ++ expr 5 + 1 + i=6 + '[' 6 -le 11 ']' + echo n143 ++ expr 6 + 1 + i=7 + '[' 7 -le 11 ']' + echo n143 ++ expr 7 + 1 + i=8 + '[' 8 -le 11 ']' + echo n143 ++ expr 8 + 1 + i=9 + '[' 9 -le 11 ']' + echo n143 ++ expr 9 + 1 + i=10 + '[' 10 -le 11 ']' + echo n143 ++ expr 10 + 1 + i=11 + '[' 11 -le 11 ']' + echo n143 ++ expr 11 + 1 + i=12 + '[' 12 -le 11 ']' + read line ++ echo n148 12 wp10@n148 UNDEFINED ++ cut -f1 -d. ++ cut -f1 '-d ' + host=n148 ++ echo n148 12 wp10@n148 UNDEFINED ++ cut -f2 '-d ' + nslots=12 + i=1 + '[' 1 -le 12 ']' + echo n148 ++ expr 1 + 1 + i=2 + '[' 2 -le 12 ']' + echo n148 ++ expr 2 + 1 + i=3 + '[' 3 -le 12 ']' + echo n148 ++ expr 3 + 1 + i=4 + '[' 4 -le 12 ']' + echo n148 ++ expr 4 + 1 + i=5 + '[' 5 -le 12 ']' + echo n148 ++ expr 5 + 1 + i=6 + '[' 6 -le 12 ']' + echo n148 ++ expr 6 + 1 + i=7 + '[' 7 -le 12 ']' + echo n148 ++ expr 7 + 1 + i=8 + '[' 8 -le 12 ']' + echo n148 ++ expr 8 + 1 + i=9 + '[' 9 -le 12 ']' + echo n148 ++ expr 9 + 1 + i=10 + '[' 10 -le 12 ']' + echo n148 ++ expr 10 + 1 + i=11 + '[' 11 -le 12 ']' + echo n148 ++ expr 11 + 1 + i=12 + '[' 12 -le 12 ']' + echo n148 ++ expr 12 + 1 + i=13 + '[' 13 -le 12 ']' + read line ++ echo n162 1 wp10@n162 UNDEFINED ++ cut -f1 -d. ++ cut -f1 '-d ' + host=n162 ++ echo n162 1 wp10@n162 UNDEFINED ++ cut -f2 '-d ' + nslots=1 + i=1 + '[' 1 -le 1 ']' + echo n162 ++ expr 1 + 1 + i=2 + '[' 2 -le 1 ']' + read line + cat /tmp/4123.1.wp10/machines n152 n152 n161 n155 n155 n155 n155 n146 n149 n149 n149 n149 n143 n143 n143 n143 n143 n143 n143 n143 n143 n143 n143 n148 n148 n148 n148 n148 n148 n148 n148 n148 n148 n148 n148 n162 + '[' 1 = 1 ']' + rsh_wrapper=/opt/sge6/mpich2_smpd/rsh + '[' '!' -x /opt/sge6/mpich2_smpd/rsh ']' + rshcmd=rsh + case "$ARC" in + ln -s /opt/sge6/mpich2_smpd/rsh /tmp/4123.1.wp10/rsh + hash -r + '[' 0 = 1 ']' + port=24123 ++ uniq ++ cat /tmp/4123.1.wp10/machines + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n152 /opt/mpich2/intel/11.1//bin/smpd 24123 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n161 /opt/mpich2/intel/11.1//bin/smpd 24123 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n155 /opt/mpich2/intel/11.1//bin/smpd 24123 rsh n152 /opt/mpich2/intel/11.1//bin/smpd -port 24123 -d 0 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n146 /opt/mpich2/intel/11.1//bin/smpd 24123 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n149 /opt/mpich2/intel/11.1//bin/smpd 24123 rsh n155 /opt/mpich2/intel/11.1//bin/smpd -port 24123 -d 0 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n143 /opt/mpich2/intel/11.1//bin/smpd 24123 rsh n146 /opt/mpich2/intel/11.1//bin/smpd -port 24123 -d 0 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n148 /opt/mpich2/intel/11.1//bin/smpd 24123 rsh n161 /opt/mpich2/intel/11.1//bin/smpd -port 24123 -d 0 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n162 /opt/mpich2/intel/11.1//bin/smpd 24123 rsh n143 /opt/mpich2/intel/11.1//bin/smpd -port 24123 -d 0 + actual_retry=1 + '[' 1 -le 10 ']' + echo 'startmpich2.sh: check for smpd daemons (1 of 10)' startmpich2.sh: check for smpd daemons (1 of 10) + numhosts=0 ++ cat /tmp/4123.1.wp10/machines ++ uniq + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 24123 -status n152 ++ head -n 1 ++ cut -f 1 -d ' ' rsh n149 /opt/mpich2/intel/11.1//bin/smpd -port 24123 -d 0 rsh n162 /opt/mpich2/intel/11.1//bin/smpd -port 24123 -d 0 + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n152' startmpich2.sh: found running smpd on n152 + for host in '`cat $machines | uniq`' ++ cut -f 1 -d ' ' ++ head -n 1 ++ /opt/mpich2/intel/11.1//bin/smpd -port 24123 -status n161 + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n161' startmpich2.sh: found running smpd on n161 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 24123 -status n155 ++ cut -f 1 -d ' ' ++ head -n 1 + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n155' startmpich2.sh: found running smpd on n155 + for host in '`cat $machines | uniq`' rsh n148 /opt/mpich2/intel/11.1//bin/smpd -port 24123 -d 0 ++ cut -f 1 -d ' ' ++ /opt/mpich2/intel/11.1//bin/smpd -port 24123 -status n146 ++ head -n 1 + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n146' startmpich2.sh: found running smpd on n146 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 24123 -status n149 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n149' startmpich2.sh: found running smpd on n149 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 24123 -status n143 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n143' startmpich2.sh: found running smpd on n143 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 24123 -status n148 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n148' startmpich2.sh: found running smpd on n148 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 24123 -status n162 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n162' startmpich2.sh: found running smpd on n162 + '[' 8 -eq 8 ']' + echo 'startmpich2.sh: got all 8 of 8 nodes' startmpich2.sh: got all 8 of 8 nodes + exit 0 rm: cannot remove `./*.broyd*': No such file or directory -catch_rsh /opt/mpich2/intel/11.1/ Your job finished at Mon Apr 4 16:51:08 EDT 2011