USER = yinzping HOMEDIR = /home/yinzping JOB_ID = 71152 JOB_NAME = LFAPM QUEUE = wp10 NSLOTS = 116 NHOSTS = 13 SUB_HOST = rupc03 SUB_DIR = /mnt/wk05/yinzping/WIEN2k/DMFT/FeAs/LiFeAs/P4nmm/U5J8/beta160/Full2/2208yinzping/10606yinzping/13406yinzping/69739yinzping EXE_HOST = n143 NFS_HOST = caip02s EXE_DIR = /mnt/p05 OUT_DIR = /tmp TMP_DIR = /tmp/71152.1.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 = 21152 rcp: /mnt/wk05/yinzping/WIEN2k/DMFT/FeAs/LiFeAs/P4nmm/U5J8/beta160/Full2/2208yinzping/10606yinzping/13406yinzping/69739yinzping/Vertex: not a plain file rcp: /mnt/wk05/yinzping/WIEN2k/DMFT/FeAs/LiFeAs/P4nmm/U5J8/beta160/Full2/2208yinzping/10606yinzping/13406yinzping/69739yinzping/imp.0: not a plain file Failure to rcp files! Your job started at Sun Feb 23 01:47:17 EST 2014 on host n143 in /mnt/p05/71152yinzping Submission directory is /mnt/wk05/yinzping/WIEN2k/DMFT/FeAs/LiFeAs/P4nmm/U5J8/beta160/Full2/2208yinzping/10606yinzping/13406yinzping/69739yinzping on host rupc03 ----------------------------------------------------------------------------------------- + echo -catch_rsh /opt/sge6/spool/n143/active_jobs/71152.1/pe_hostfile /opt/mpich2/intel/11.1/ -catch_rsh /opt/sge6/spool/n143/active_jobs/71152.1/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/n143/active_jobs/71152.1/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/n143/active_jobs/71152.1/pe_hostfile ']' + machines=/tmp/71152.1.wp10/machines + PeHostfile2MachineFile /opt/sge6/spool/n143/active_jobs/71152.1/pe_hostfile + cat /opt/sge6/spool/n143/active_jobs/71152.1/pe_hostfile + read line ++ echo n143 7 wp10@n143 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n143 ++ echo n143 7 wp10@n143 UNDEFINED ++ cut -f2 '-d ' + nslots=7 + i=1 + '[' 1 -le 7 ']' + echo n143 ++ expr 1 + 1 + i=2 + '[' 2 -le 7 ']' + echo n143 ++ expr 2 + 1 + i=3 + '[' 3 -le 7 ']' + echo n143 ++ expr 3 + 1 + i=4 + '[' 4 -le 7 ']' + echo n143 ++ expr 4 + 1 + i=5 + '[' 5 -le 7 ']' + echo n143 ++ expr 5 + 1 + i=6 + '[' 6 -le 7 ']' + echo n143 ++ expr 6 + 1 + i=7 + '[' 7 -le 7 ']' + echo n143 ++ expr 7 + 1 + i=8 + '[' 8 -le 7 ']' + read line ++ echo n162 12 wp10@n162 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n162 ++ echo n162 12 wp10@n162 UNDEFINED ++ cut -f2 '-d ' + nslots=12 + i=1 + '[' 1 -le 12 ']' + echo n162 ++ expr 1 + 1 + i=2 + '[' 2 -le 12 ']' + echo n162 ++ expr 2 + 1 + i=3 + '[' 3 -le 12 ']' + echo n162 ++ expr 3 + 1 + i=4 + '[' 4 -le 12 ']' + echo n162 ++ expr 4 + 1 + i=5 + '[' 5 -le 12 ']' + echo n162 ++ expr 5 + 1 + i=6 + '[' 6 -le 12 ']' + echo n162 ++ expr 6 + 1 + i=7 + '[' 7 -le 12 ']' + echo n162 ++ expr 7 + 1 + i=8 + '[' 8 -le 12 ']' + echo n162 ++ expr 8 + 1 + i=9 + '[' 9 -le 12 ']' + echo n162 ++ expr 9 + 1 + i=10 + '[' 10 -le 12 ']' + echo n162 ++ expr 10 + 1 + i=11 + '[' 11 -le 12 ']' + echo n162 ++ expr 11 + 1 + i=12 + '[' 12 -le 12 ']' + echo n162 ++ expr 12 + 1 + i=13 + '[' 13 -le 12 ']' + read line ++ echo n154 12 wp10@n154 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n154 ++ echo n154 12 wp10@n154 UNDEFINED ++ cut -f2 '-d ' + nslots=12 + i=1 + '[' 1 -le 12 ']' + echo n154 ++ expr 1 + 1 + i=2 + '[' 2 -le 12 ']' + echo n154 ++ expr 2 + 1 + i=3 + '[' 3 -le 12 ']' + echo n154 ++ expr 3 + 1 + i=4 + '[' 4 -le 12 ']' + echo n154 ++ expr 4 + 1 + i=5 + '[' 5 -le 12 ']' + echo n154 ++ expr 5 + 1 + i=6 + '[' 6 -le 12 ']' + echo n154 ++ expr 6 + 1 + i=7 + '[' 7 -le 12 ']' + echo n154 ++ expr 7 + 1 + i=8 + '[' 8 -le 12 ']' + echo n154 ++ expr 8 + 1 + i=9 + '[' 9 -le 12 ']' + echo n154 ++ expr 9 + 1 + i=10 + '[' 10 -le 12 ']' + echo n154 ++ expr 10 + 1 + i=11 + '[' 11 -le 12 ']' + echo n154 ++ expr 11 + 1 + i=12 + '[' 12 -le 12 ']' + echo n154 ++ expr 12 + 1 + i=13 + '[' 13 -le 12 ']' + read line ++ echo n144 9 wp10@n144 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n144 ++ echo n144 9 wp10@n144 UNDEFINED ++ cut -f2 '-d ' + nslots=9 + i=1 + '[' 1 -le 9 ']' + echo n144 ++ expr 1 + 1 + i=2 + '[' 2 -le 9 ']' + echo n144 ++ expr 2 + 1 + i=3 + '[' 3 -le 9 ']' + echo n144 ++ expr 3 + 1 + i=4 + '[' 4 -le 9 ']' + echo n144 ++ expr 4 + 1 + i=5 + '[' 5 -le 9 ']' + echo n144 ++ expr 5 + 1 + i=6 + '[' 6 -le 9 ']' + echo n144 ++ expr 6 + 1 + i=7 + '[' 7 -le 9 ']' + echo n144 ++ expr 7 + 1 + i=8 + '[' 8 -le 9 ']' + echo n144 ++ expr 8 + 1 + i=9 + '[' 9 -le 9 ']' + echo n144 ++ expr 9 + 1 + i=10 + '[' 10 -le 9 ']' + read line ++ echo n160 12 wp10@n160 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n160 ++ echo n160 12 wp10@n160 UNDEFINED ++ cut -f2 '-d ' + nslots=12 + i=1 + '[' 1 -le 12 ']' + echo n160 ++ expr 1 + 1 + i=2 + '[' 2 -le 12 ']' + echo n160 ++ expr 2 + 1 + i=3 + '[' 3 -le 12 ']' + echo n160 ++ expr 3 + 1 + i=4 + '[' 4 -le 12 ']' + echo n160 ++ expr 4 + 1 + i=5 + '[' 5 -le 12 ']' + echo n160 ++ expr 5 + 1 + i=6 + '[' 6 -le 12 ']' + echo n160 ++ expr 6 + 1 + i=7 + '[' 7 -le 12 ']' + echo n160 ++ expr 7 + 1 + i=8 + '[' 8 -le 12 ']' + echo n160 ++ expr 8 + 1 + i=9 + '[' 9 -le 12 ']' + echo n160 ++ expr 9 + 1 + i=10 + '[' 10 -le 12 ']' + echo n160 ++ expr 10 + 1 + i=11 + '[' 11 -le 12 ']' + echo n160 ++ expr 11 + 1 + i=12 + '[' 12 -le 12 ']' + echo n160 ++ expr 12 + 1 + i=13 + '[' 13 -le 12 ']' + read line ++ echo n163 10 wp10@n163 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n163 ++ echo n163 10 wp10@n163 UNDEFINED ++ cut -f2 '-d ' + nslots=10 + i=1 + '[' 1 -le 10 ']' + echo n163 ++ expr 1 + 1 + i=2 + '[' 2 -le 10 ']' + echo n163 ++ expr 2 + 1 + i=3 + '[' 3 -le 10 ']' + echo n163 ++ expr 3 + 1 + i=4 + '[' 4 -le 10 ']' + echo n163 ++ expr 4 + 1 + i=5 + '[' 5 -le 10 ']' + echo n163 ++ expr 5 + 1 + i=6 + '[' 6 -le 10 ']' + echo n163 ++ expr 6 + 1 + i=7 + '[' 7 -le 10 ']' + echo n163 ++ expr 7 + 1 + i=8 + '[' 8 -le 10 ']' + echo n163 ++ expr 8 + 1 + i=9 + '[' 9 -le 10 ']' + echo n163 ++ expr 9 + 1 + i=10 + '[' 10 -le 10 ']' + echo n163 ++ expr 10 + 1 + i=11 + '[' 11 -le 10 ']' + read line ++ echo n158 5 wp10@n158 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n158 ++ echo n158 5 wp10@n158 UNDEFINED ++ cut -f2 '-d ' + nslots=5 + i=1 + '[' 1 -le 5 ']' + echo n158 ++ expr 1 + 1 + i=2 + '[' 2 -le 5 ']' + echo n158 ++ expr 2 + 1 + i=3 + '[' 3 -le 5 ']' + echo n158 ++ expr 3 + 1 + i=4 + '[' 4 -le 5 ']' + echo n158 ++ expr 4 + 1 + i=5 + '[' 5 -le 5 ']' + echo n158 ++ expr 5 + 1 + i=6 + '[' 6 -le 5 ']' + read line ++ echo n145 12 wp10@n145 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n145 ++ echo n145 12 wp10@n145 UNDEFINED ++ cut -f2 '-d ' + nslots=12 + i=1 + '[' 1 -le 12 ']' + echo n145 ++ expr 1 + 1 + i=2 + '[' 2 -le 12 ']' + echo n145 ++ expr 2 + 1 + i=3 + '[' 3 -le 12 ']' + echo n145 ++ expr 3 + 1 + i=4 + '[' 4 -le 12 ']' + echo n145 ++ expr 4 + 1 + i=5 + '[' 5 -le 12 ']' + echo n145 ++ expr 5 + 1 + i=6 + '[' 6 -le 12 ']' + echo n145 ++ expr 6 + 1 + i=7 + '[' 7 -le 12 ']' + echo n145 ++ expr 7 + 1 + i=8 + '[' 8 -le 12 ']' + echo n145 ++ expr 8 + 1 + i=9 + '[' 9 -le 12 ']' + echo n145 ++ expr 9 + 1 + i=10 + '[' 10 -le 12 ']' + echo n145 ++ expr 10 + 1 + i=11 + '[' 11 -le 12 ']' + echo n145 ++ expr 11 + 1 + i=12 + '[' 12 -le 12 ']' + echo n145 ++ expr 12 + 1 + i=13 + '[' 13 -le 12 ']' + read line ++ echo n164 10 wp10@n164 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n164 ++ echo n164 10 wp10@n164 UNDEFINED ++ cut -f2 '-d ' + nslots=10 + i=1 + '[' 1 -le 10 ']' + echo n164 ++ expr 1 + 1 + i=2 + '[' 2 -le 10 ']' + echo n164 ++ expr 2 + 1 + i=3 + '[' 3 -le 10 ']' + echo n164 ++ expr 3 + 1 + i=4 + '[' 4 -le 10 ']' + echo n164 ++ expr 4 + 1 + i=5 + '[' 5 -le 10 ']' + echo n164 ++ expr 5 + 1 + i=6 + '[' 6 -le 10 ']' + echo n164 ++ expr 6 + 1 + i=7 + '[' 7 -le 10 ']' + echo n164 ++ expr 7 + 1 + i=8 + '[' 8 -le 10 ']' + echo n164 ++ expr 8 + 1 + i=9 + '[' 9 -le 10 ']' + echo n164 ++ expr 9 + 1 + i=10 + '[' 10 -le 10 ']' + echo n164 ++ expr 10 + 1 + i=11 + '[' 11 -le 10 ']' + read line ++ echo n153 2 wp10@n153 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n153 ++ echo n153 2 wp10@n153 UNDEFINED ++ cut -f2 '-d ' + nslots=2 + i=1 + '[' 1 -le 2 ']' + echo n153 ++ expr 1 + 1 + i=2 + '[' 2 -le 2 ']' + echo n153 ++ expr 2 + 1 + i=3 + '[' 3 -le 2 ']' + read line ++ echo n151 9 wp10@n151 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n151 ++ echo n151 9 wp10@n151 UNDEFINED ++ cut -f2 '-d ' + nslots=9 + i=1 + '[' 1 -le 9 ']' + echo n151 ++ expr 1 + 1 + i=2 + '[' 2 -le 9 ']' + echo n151 ++ expr 2 + 1 + i=3 + '[' 3 -le 9 ']' + echo n151 ++ expr 3 + 1 + i=4 + '[' 4 -le 9 ']' + echo n151 ++ expr 4 + 1 + i=5 + '[' 5 -le 9 ']' + echo n151 ++ expr 5 + 1 + i=6 + '[' 6 -le 9 ']' + echo n151 ++ expr 6 + 1 + i=7 + '[' 7 -le 9 ']' + echo n151 ++ expr 7 + 1 + i=8 + '[' 8 -le 9 ']' + echo n151 ++ expr 8 + 1 + i=9 + '[' 9 -le 9 ']' + echo n151 ++ expr 9 + 1 + i=10 + '[' 10 -le 9 ']' + read line ++ echo n146 4 wp10@n146 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n146 ++ echo n146 4 wp10@n146 UNDEFINED ++ cut -f2 '-d ' + nslots=4 + i=1 + '[' 1 -le 4 ']' + echo n146 ++ expr 1 + 1 + i=2 + '[' 2 -le 4 ']' + echo n146 ++ expr 2 + 1 + i=3 + '[' 3 -le 4 ']' + echo n146 ++ expr 3 + 1 + i=4 + '[' 4 -le 4 ']' + echo n146 ++ expr 4 + 1 + i=5 + '[' 5 -le 4 ']' + read line ++ echo n147 12 wp10@n147 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n147 ++ echo n147 12 wp10@n147 UNDEFINED ++ cut -f2 '-d ' + nslots=12 + i=1 + '[' 1 -le 12 ']' + echo n147 ++ expr 1 + 1 + i=2 + '[' 2 -le 12 ']' + echo n147 ++ expr 2 + 1 + i=3 + '[' 3 -le 12 ']' + echo n147 ++ expr 3 + 1 + i=4 + '[' 4 -le 12 ']' + echo n147 ++ expr 4 + 1 + i=5 + '[' 5 -le 12 ']' + echo n147 ++ expr 5 + 1 + i=6 + '[' 6 -le 12 ']' + echo n147 ++ expr 6 + 1 + i=7 + '[' 7 -le 12 ']' + echo n147 ++ expr 7 + 1 + i=8 + '[' 8 -le 12 ']' + echo n147 ++ expr 8 + 1 + i=9 + '[' 9 -le 12 ']' + echo n147 ++ expr 9 + 1 + i=10 + '[' 10 -le 12 ']' + echo n147 ++ expr 10 + 1 + i=11 + '[' 11 -le 12 ']' + echo n147 ++ expr 11 + 1 + i=12 + '[' 12 -le 12 ']' + echo n147 ++ expr 12 + 1 + i=13 + '[' 13 -le 12 ']' + read line + cat /tmp/71152.1.wp10/machines n143 n143 n143 n143 n143 n143 n143 n162 n162 n162 n162 n162 n162 n162 n162 n162 n162 n162 n162 n154 n154 n154 n154 n154 n154 n154 n154 n154 n154 n154 n154 n144 n144 n144 n144 n144 n144 n144 n144 n144 n160 n160 n160 n160 n160 n160 n160 n160 n160 n160 n160 n160 n163 n163 n163 n163 n163 n163 n163 n163 n163 n163 n158 n158 n158 n158 n158 n145 n145 n145 n145 n145 n145 n145 n145 n145 n145 n145 n145 n164 n164 n164 n164 n164 n164 n164 n164 n164 n164 n153 n153 n151 n151 n151 n151 n151 n151 n151 n151 n151 n146 n146 n146 n146 n147 n147 n147 n147 n147 n147 n147 n147 n147 n147 n147 n147 + '[' 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/71152.1.wp10/rsh + hash -r + '[' 0 = 1 ']' + port=21152 ++ cat /tmp/71152.1.wp10/machines ++ uniq + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n143 /opt/mpich2/intel/11.1//bin/smpd 21152 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n162 /opt/mpich2/intel/11.1//bin/smpd 21152 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n154 /opt/mpich2/intel/11.1//bin/smpd 21152 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n144 /opt/mpich2/intel/11.1//bin/smpd 21152 rsh n143 /opt/mpich2/intel/11.1//bin/smpd -port 21152 -d 0 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n160 /opt/mpich2/intel/11.1//bin/smpd 21152 rsh n162 /opt/mpich2/intel/11.1//bin/smpd -port 21152 -d 0 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n163 /opt/mpich2/intel/11.1//bin/smpd 21152 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n158 /opt/mpich2/intel/11.1//bin/smpd 21152 rsh n144 /opt/mpich2/intel/11.1//bin/smpd -port 21152 -d 0 rsh n160 /opt/mpich2/intel/11.1//bin/smpd -port 21152 -d 0 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n145 /opt/mpich2/intel/11.1//bin/smpd 21152 rsh n154 /opt/mpich2/intel/11.1//bin/smpd -port 21152 -d 0 rsh n163 /opt/mpich2/intel/11.1//bin/smpd -port 21152 -d 0 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n164 /opt/mpich2/intel/11.1//bin/smpd 21152 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n153 /opt/mpich2/intel/11.1//bin/smpd 21152 rsh n158 /opt/mpich2/intel/11.1//bin/smpd -port 21152 -d 0 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n151 /opt/mpich2/intel/11.1//bin/smpd 21152 rsh n164 /opt/mpich2/intel/11.1//bin/smpd -port 21152 -d 0 rsh n145 /opt/mpich2/intel/11.1//bin/smpd -port 21152 -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 21152 rsh n153 /opt/mpich2/intel/11.1//bin/smpd -port 21152 -d 0 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n147 /opt/mpich2/intel/11.1//bin/smpd 21152 + 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/71152.1.wp10/machines rsh n151 /opt/mpich2/intel/11.1//bin/smpd -port 21152 -d 0 ++ uniq + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n143 rsh n146 /opt/mpich2/intel/11.1//bin/smpd -port 21152 -d 0 ++ head -n 1 ++ cut -f 1 -d ' ' Assertion failed in file smpd_sock_wait.i at line 337: pollinfo->state == SMPDU_SOCKI_STATE_DISCONNECTED && pollfd->fd == -1 internal ABORT - process 0 rsh n147 /opt/mpich2/intel/11.1//bin/smpd -port 21152 -d 0 + '[' '' == smpd ']' + echo 'startmpich2.sh: missing smpd on n143' startmpich2.sh: missing smpd on n143 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n162 ++ head -n 1 ++ cut -f 1 -d ' ' Assertion failed in file smpd_sock_wait.i at line 337: pollinfo->state == SMPDU_SOCKI_STATE_DISCONNECTED && pollfd->fd == -1 internal ABORT - process 0 + '[' '' == smpd ']' + echo 'startmpich2.sh: missing smpd on n162' startmpich2.sh: missing smpd on n162 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n154 ++ head -n 1 ++ cut -f 1 -d ' ' Assertion failed in file smpd_sock_wait.i at line 337: pollinfo->state == SMPDU_SOCKI_STATE_DISCONNECTED && pollfd->fd == -1 internal ABORT - process 0 + '[' '' == smpd ']' + echo 'startmpich2.sh: missing smpd on n154' startmpich2.sh: missing smpd on n154 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n144 ++ head -n 1 ++ cut -f 1 -d ' ' Assertion failed in file smpd_sock_wait.i at line 337: pollinfo->state == SMPDU_SOCKI_STATE_DISCONNECTED && pollfd->fd == -1 internal ABORT - process 0 + '[' '' == smpd ']' + echo 'startmpich2.sh: missing smpd on n144' startmpich2.sh: missing smpd on n144 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n160 ++ head -n 1 ++ cut -f 1 -d ' ' Assertion failed in file smpd_sock_wait.i at line 337: pollinfo->state == SMPDU_SOCKI_STATE_DISCONNECTED && pollfd->fd == -1 internal ABORT - process 0 + '[' '' == smpd ']' + echo 'startmpich2.sh: missing smpd on n160' startmpich2.sh: missing smpd on n160 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n163 ++ head -n 1 ++ cut -f 1 -d ' ' Assertion failed in file smpd_sock_wait.i at line 337: pollinfo->state == SMPDU_SOCKI_STATE_DISCONNECTED && pollfd->fd == -1 internal ABORT - process 0 + '[' '' == smpd ']' + echo 'startmpich2.sh: missing smpd on n163' startmpich2.sh: missing smpd on n163 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n158 ++ head -n 1 ++ cut -f 1 -d ' ' Assertion failed in file smpd_sock_wait.i at line 337: pollinfo->state == SMPDU_SOCKI_STATE_DISCONNECTED && pollfd->fd == -1 internal ABORT - process 0 + '[' '' == smpd ']' + echo 'startmpich2.sh: missing smpd on n158' startmpich2.sh: missing smpd on n158 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n145 ++ head -n 1 ++ cut -f 1 -d ' ' Assertion failed in file smpd_sock_wait.i at line 337: pollinfo->state == SMPDU_SOCKI_STATE_DISCONNECTED && pollfd->fd == -1 internal ABORT - process 0 + '[' '' == smpd ']' + echo 'startmpich2.sh: missing smpd on n145' startmpich2.sh: missing smpd on n145 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n164 ++ head -n 1 ++ cut -f 1 -d ' ' Assertion failed in file smpd_sock_wait.i at line 337: pollinfo->state == SMPDU_SOCKI_STATE_DISCONNECTED && pollfd->fd == -1 internal ABORT - process 0 + '[' '' == smpd ']' + echo 'startmpich2.sh: missing smpd on n164' startmpich2.sh: missing smpd on n164 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n153 ++ head -n 1 ++ cut -f 1 -d ' ' Assertion failed in file smpd_sock_wait.i at line 337: pollinfo->state == SMPDU_SOCKI_STATE_DISCONNECTED && pollfd->fd == -1 internal ABORT - process 0 + '[' '' == smpd ']' + echo 'startmpich2.sh: missing smpd on n153' startmpich2.sh: missing smpd on n153 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n151 ++ head -n 1 ++ cut -f 1 -d ' ' Assertion failed in file smpd_sock_wait.i at line 337: pollinfo->state == SMPDU_SOCKI_STATE_DISCONNECTED && pollfd->fd == -1 internal ABORT - process 0 + '[' '' == smpd ']' + echo 'startmpich2.sh: missing smpd on n151' startmpich2.sh: missing smpd on n151 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n146 ++ head -n 1 ++ cut -f 1 -d ' ' Assertion failed in file smpd_sock_wait.i at line 337: pollinfo->state == SMPDU_SOCKI_STATE_DISCONNECTED && pollfd->fd == -1 internal ABORT - process 0 + '[' '' == smpd ']' + echo 'startmpich2.sh: missing smpd on n146' startmpich2.sh: missing smpd on n146 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n147 ++ head -n 1 ++ cut -f 1 -d ' ' Assertion failed in file smpd_sock_wait.i at line 337: pollinfo->state == SMPDU_SOCKI_STATE_DISCONNECTED && pollfd->fd == -1 internal ABORT - process 0 + '[' '' == smpd ']' + echo 'startmpich2.sh: missing smpd on n147' startmpich2.sh: missing smpd on n147 + '[' 13 -eq 0 ']' + sleep 5 + (( actual_retry += 1 )) + '[' 2 -le 10 ']' + echo 'startmpich2.sh: check for smpd daemons (2 of 10)' startmpich2.sh: check for smpd daemons (2 of 10) + numhosts=0 ++ cat /tmp/71152.1.wp10/machines ++ uniq + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n143 ++ cut -f 1 -d ' ' ++ head -n 1 + '[' 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 21152 -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 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n154 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n154' startmpich2.sh: found running smpd on n154 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n144 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n144' startmpich2.sh: found running smpd on n144 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n160 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n160' startmpich2.sh: found running smpd on n160 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n163 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n163' startmpich2.sh: found running smpd on n163 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n158 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n158' startmpich2.sh: found running smpd on n158 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n145 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n145' startmpich2.sh: found running smpd on n145 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n164 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n164' startmpich2.sh: found running smpd on n164 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n153 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n153' startmpich2.sh: found running smpd on n153 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n151 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n151' startmpich2.sh: found running smpd on n151 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 21152 -status n146 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' 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 21152 -status n147 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n147' startmpich2.sh: found running smpd on n147 + '[' 13 -eq 13 ']' + echo 'startmpich2.sh: got all 13 of 13 nodes' startmpich2.sh: got all 13 of 13 nodes + exit 0 rm: cannot remove `./*.broyd*': No such file or directory -catch_rsh /opt/mpich2/intel/11.1/ Your job finished at Sat Mar 29 09:20:28 EDT 2014