USER = jtomczak HOMEDIR = /home/users/jtomczak JOB_ID = 8056 JOB_NAME = FS-b30-6 QUEUE = wp10 NSLOTS = 61 NHOSTS = 11 SUB_HOST = rupc06 SUB_DIR = /mnt/wk07/jtomczak/DATA/MATERIALS/FeSi/DMFT/QMC/U5.0/FAST/beta30/nf6/NEW EXE_HOST = n145 NFS_HOST = caip02s EXE_DIR = /mnt/p05 OUT_DIR = /tmp TMP_DIR = /tmp/8056.1.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 = 23056 rcp: /mnt/wk07/jtomczak/DATA/MATERIALS/FeSi/DMFT/QMC/U5.0/FAST/beta30/nf6/NEW/GO: not a plain file rcp: /mnt/wk07/jtomczak/DATA/MATERIALS/FeSi/DMFT/QMC/U5.0/FAST/beta30/nf6/NEW/GO-small: not a plain file rcp: /mnt/wk07/jtomczak/DATA/MATERIALS/FeSi/DMFT/QMC/U5.0/FAST/beta30/nf6/NEW/SPEC: not a plain file rcp: /mnt/wk07/jtomczak/DATA/MATERIALS/FeSi/DMFT/QMC/U5.0/FAST/beta30/nf6/NEW/ancont: not a plain file rcp: /mnt/wk07/jtomczak/DATA/MATERIALS/FeSi/DMFT/QMC/U5.0/FAST/beta30/nf6/NEW/ancont2: not a plain file rcp: /mnt/wk07/jtomczak/DATA/MATERIALS/FeSi/DMFT/QMC/U5.0/FAST/beta30/nf6/NEW/cdos: not a plain file rcp: /mnt/wk07/jtomczak/DATA/MATERIALS/FeSi/DMFT/QMC/U5.0/FAST/beta30/nf6/NEW/go.tmp: No such file or directory rcp: /mnt/wk07/jtomczak/DATA/MATERIALS/FeSi/DMFT/QMC/U5.0/FAST/beta30/nf6/NEW/imp.0: not a plain file Failure to rcp files! Your job started at Fri Jun 17 12:40:32 EDT 2011 on host n145 in /mnt/p05/8056jtomczak Submission directory is /mnt/wk07/jtomczak/DATA/MATERIALS/FeSi/DMFT/QMC/U5.0/FAST/beta30/nf6/NEW on host rupc06 ----------------------------------------------------------------------------------------- + echo -catch_rsh /opt/sge6/spool/n145/active_jobs/8056.1/pe_hostfile /opt/mpich2/intel/11.1/ -catch_rsh /opt/sge6/spool/n145/active_jobs/8056.1/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/n145/active_jobs/8056.1/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/n145/active_jobs/8056.1/pe_hostfile ']' + machines=/tmp/8056.1.wp10/machines + PeHostfile2MachineFile /opt/sge6/spool/n145/active_jobs/8056.1/pe_hostfile + cat /opt/sge6/spool/n145/active_jobs/8056.1/pe_hostfile + read line ++ echo n145 1 wp10@n145 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n145 ++ echo n145 1 wp10@n145 UNDEFINED ++ cut -f2 '-d ' + nslots=1 + i=1 + '[' 1 -le 1 ']' + echo n145 ++ expr 1 + 1 + i=2 + '[' 2 -le 1 ']' + read line ++ echo n143 8 wp10@n143 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n143 ++ echo n143 8 wp10@n143 UNDEFINED ++ cut -f2 '-d ' + nslots=8 + i=1 + '[' 1 -le 8 ']' + echo n143 ++ expr 1 + 1 + i=2 + '[' 2 -le 8 ']' + echo n143 ++ expr 2 + 1 + i=3 + '[' 3 -le 8 ']' + echo n143 ++ expr 3 + 1 + i=4 + '[' 4 -le 8 ']' + echo n143 ++ expr 4 + 1 + i=5 + '[' 5 -le 8 ']' + echo n143 ++ expr 5 + 1 + i=6 + '[' 6 -le 8 ']' + echo n143 ++ expr 6 + 1 + i=7 + '[' 7 -le 8 ']' + echo n143 ++ expr 7 + 1 + i=8 + '[' 8 -le 8 ']' + echo n143 ++ expr 8 + 1 + i=9 + '[' 9 -le 8 ']' + read line ++ echo n163 6 wp10@n163 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n163 ++ echo n163 6 wp10@n163 UNDEFINED ++ cut -f2 '-d ' + nslots=6 + i=1 + '[' 1 -le 6 ']' + echo n163 ++ expr 1 + 1 + i=2 + '[' 2 -le 6 ']' + echo n163 ++ expr 2 + 1 + i=3 + '[' 3 -le 6 ']' + echo n163 ++ expr 3 + 1 + i=4 + '[' 4 -le 6 ']' + echo n163 ++ expr 4 + 1 + i=5 + '[' 5 -le 6 ']' + echo n163 ++ expr 5 + 1 + i=6 + '[' 6 -le 6 ']' + echo n163 ++ expr 6 + 1 + i=7 + '[' 7 -le 6 ']' + read line ++ echo n158 12 wp10@n158 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n158 ++ echo n158 12 wp10@n158 UNDEFINED ++ cut -f2 '-d ' + nslots=12 + i=1 + '[' 1 -le 12 ']' + echo n158 ++ expr 1 + 1 + i=2 + '[' 2 -le 12 ']' + echo n158 ++ expr 2 + 1 + i=3 + '[' 3 -le 12 ']' + echo n158 ++ expr 3 + 1 + i=4 + '[' 4 -le 12 ']' + echo n158 ++ expr 4 + 1 + i=5 + '[' 5 -le 12 ']' + echo n158 ++ expr 5 + 1 + i=6 + '[' 6 -le 12 ']' + echo n158 ++ expr 6 + 1 + i=7 + '[' 7 -le 12 ']' + echo n158 ++ expr 7 + 1 + i=8 + '[' 8 -le 12 ']' + echo n158 ++ expr 8 + 1 + i=9 + '[' 9 -le 12 ']' + echo n158 ++ expr 9 + 1 + i=10 + '[' 10 -le 12 ']' + echo n158 ++ expr 10 + 1 + i=11 + '[' 11 -le 12 ']' + echo n158 ++ expr 11 + 1 + i=12 + '[' 12 -le 12 ']' + echo n158 ++ expr 12 + 1 + i=13 + '[' 13 -le 12 ']' + read line ++ echo n149 1 wp10@n149 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n149 ++ echo n149 1 wp10@n149 UNDEFINED ++ cut -f2 '-d ' + nslots=1 + i=1 + '[' 1 -le 1 ']' + echo n149 ++ expr 1 + 1 + i=2 + '[' 2 -le 1 ']' + read line ++ echo n160 3 wp10@n160 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n160 ++ echo n160 3 wp10@n160 UNDEFINED ++ cut -f2 '-d ' + nslots=3 + i=1 + '[' 1 -le 3 ']' + echo n160 ++ expr 1 + 1 + i=2 + '[' 2 -le 3 ']' + echo n160 ++ expr 2 + 1 + i=3 + '[' 3 -le 3 ']' + echo n160 ++ expr 3 + 1 + i=4 + '[' 4 -le 3 ']' + read line ++ echo n159 11 wp10@n159 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n159 ++ echo n159 11 wp10@n159 UNDEFINED ++ cut -f2 '-d ' + nslots=11 + i=1 + '[' 1 -le 11 ']' + echo n159 ++ expr 1 + 1 + i=2 + '[' 2 -le 11 ']' + echo n159 ++ expr 2 + 1 + i=3 + '[' 3 -le 11 ']' + echo n159 ++ expr 3 + 1 + i=4 + '[' 4 -le 11 ']' + echo n159 ++ expr 4 + 1 + i=5 + '[' 5 -le 11 ']' + echo n159 ++ expr 5 + 1 + i=6 + '[' 6 -le 11 ']' + echo n159 ++ expr 6 + 1 + i=7 + '[' 7 -le 11 ']' + echo n159 ++ expr 7 + 1 + i=8 + '[' 8 -le 11 ']' + echo n159 ++ expr 8 + 1 + i=9 + '[' 9 -le 11 ']' + echo n159 ++ expr 9 + 1 + i=10 + '[' 10 -le 11 ']' + echo n159 ++ expr 10 + 1 + i=11 + '[' 11 -le 11 ']' + echo n159 ++ expr 11 + 1 + i=12 + '[' 12 -le 11 ']' + read line ++ echo n161 3 wp10@n161 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n161 ++ echo n161 3 wp10@n161 UNDEFINED ++ cut -f2 '-d ' + nslots=3 + i=1 + '[' 1 -le 3 ']' + echo n161 ++ expr 1 + 1 + i=2 + '[' 2 -le 3 ']' + echo n161 ++ expr 2 + 1 + i=3 + '[' 3 -le 3 ']' + echo n161 ++ expr 3 + 1 + i=4 + '[' 4 -le 3 ']' + read line ++ echo n154 1 wp10@n154 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n154 ++ echo n154 1 wp10@n154 UNDEFINED ++ cut -f2 '-d ' + nslots=1 + i=1 + '[' 1 -le 1 ']' + echo n154 ++ expr 1 + 1 + i=2 + '[' 2 -le 1 ']' + 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 n150 6 wp10@n150 UNDEFINED ++ cut -f1 '-d ' ++ cut -f1 -d. + host=n150 ++ echo n150 6 wp10@n150 UNDEFINED ++ cut -f2 '-d ' + nslots=6 + i=1 + '[' 1 -le 6 ']' + echo n150 ++ expr 1 + 1 + i=2 + '[' 2 -le 6 ']' + echo n150 ++ expr 2 + 1 + i=3 + '[' 3 -le 6 ']' + echo n150 ++ expr 3 + 1 + i=4 + '[' 4 -le 6 ']' + echo n150 ++ expr 4 + 1 + i=5 + '[' 5 -le 6 ']' + echo n150 ++ expr 5 + 1 + i=6 + '[' 6 -le 6 ']' + echo n150 ++ expr 6 + 1 + i=7 + '[' 7 -le 6 ']' + read line + cat /tmp/8056.1.wp10/machines n145 n143 n143 n143 n143 n143 n143 n143 n143 n163 n163 n163 n163 n163 n163 n158 n158 n158 n158 n158 n158 n158 n158 n158 n158 n158 n158 n149 n160 n160 n160 n159 n159 n159 n159 n159 n159 n159 n159 n159 n159 n159 n161 n161 n161 n154 n151 n151 n151 n151 n151 n151 n151 n151 n151 n150 n150 n150 n150 n150 n150 + '[' 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/8056.1.wp10/rsh + hash -r + '[' 0 = 1 ']' + port=23056 ++ cat /tmp/8056.1.wp10/machines ++ uniq + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n145 /opt/mpich2/intel/11.1//bin/smpd 23056 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n143 /opt/mpich2/intel/11.1//bin/smpd 23056 rsh n145 /opt/mpich2/intel/11.1//bin/smpd -port 23056 -d 0 rsh n143 /opt/mpich2/intel/11.1//bin/smpd -port 23056 -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 23056 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n158 /opt/mpich2/intel/11.1//bin/smpd 23056 rsh n163 /opt/mpich2/intel/11.1//bin/smpd -port 23056 -d 0 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n149 /opt/mpich2/intel/11.1//bin/smpd 23056 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n160 /opt/mpich2/intel/11.1//bin/smpd 23056 rsh n149 /opt/mpich2/intel/11.1//bin/smpd -port 23056 -d 0 rsh n160 /opt/mpich2/intel/11.1//bin/smpd -port 23056 -d 0 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n159 /opt/mpich2/intel/11.1//bin/smpd 23056 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n161 /opt/mpich2/intel/11.1//bin/smpd 23056 rsh n159 /opt/mpich2/intel/11.1//bin/smpd -port 23056 -d 0 rsh n161 /opt/mpich2/intel/11.1//bin/smpd -port 23056 -d 0 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n154 /opt/mpich2/intel/11.1//bin/smpd 23056 rsh n154 /opt/mpich2/intel/11.1//bin/smpd -port 23056 -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 23056 + for host in '`cat $machines | uniq`' + /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n150 /opt/mpich2/intel/11.1//bin/smpd 23056 rsh n151 /opt/mpich2/intel/11.1//bin/smpd -port 23056 -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/8056.1.wp10/machines ++ uniq + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 23056 -status n145 ++ head -n 1 rsh n150 /opt/mpich2/intel/11.1//bin/smpd -port 23056 -d 0 ++ 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 23056 -status n143 ++ 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 n143' startmpich2.sh: missing smpd on n143 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 23056 -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 23056 -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 23056 -status n149 ++ 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 n149' startmpich2.sh: missing smpd on n149 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 23056 -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 23056 -status n159 ++ 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 n159' startmpich2.sh: missing smpd on n159 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 23056 -status n161 ++ head -n 1 ++ cut -f 1 -d ' ' rsh n158 /opt/mpich2/intel/11.1//bin/smpd -port 23056 -d 0 + '[' 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 23056 -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 23056 -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 23056 -status n150 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n150' startmpich2.sh: found running smpd on n150 + '[' 11 -eq 4 ']' + 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/8056.1.wp10/machines ++ uniq + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 23056 -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`' ++ head -n 1 ++ /opt/mpich2/intel/11.1//bin/smpd -port 23056 -status n143 ++ 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 23056 -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 23056 -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 23056 -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 23056 -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 23056 -status n159 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n159' startmpich2.sh: found running smpd on n159 + for host in '`cat $machines | uniq`' ++ /opt/mpich2/intel/11.1//bin/smpd -port 23056 -status n161 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' 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 23056 -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 23056 -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 23056 -status n150 ++ head -n 1 ++ cut -f 1 -d ' ' + '[' smpd == smpd ']' + (( numhosts += 1 )) + echo 'startmpich2.sh: found running smpd on n150' startmpich2.sh: found running smpd on n150 + '[' 11 -eq 11 ']' + echo 'startmpich2.sh: got all 11 of 11 nodes' startmpich2.sh: got all 11 of 11 nodes + exit 0 START END -catch_rsh /opt/mpich2/intel/11.1/ Your job finished at Sat Jun 18 07:41:43 EDT 2011