USER      =  jtomczak
HOMEDIR   =  /home/users/jtomczak
JOB_ID    =  7885
JOB_NAME  =  FS-LOW
QUEUE     =  wp10
NSLOTS    =  24
NHOSTS    =  5

SUB_HOST  =  rupc04
SUB_DIR   =  /mnt/wk07/jtomczak/DATA/MATERIALS/FeSi/DMFT/QMC/U5.0/FAST/beta250

EXE_HOST  =  n150
NFS_HOST  =  caip02s
EXE_DIR   =  /mnt/p06
OUT_DIR   =  /tmp
TMP_DIR   =  /tmp/7885.1.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      =  22885
rcp: /mnt/wk07/jtomczak/DATA/MATERIALS/FeSi/DMFT/QMC/U5.0/FAST/beta250/imp.0: not a plain file
Failure to rcp files!

Your job started at Tue Jun 14 10:33:57 EDT 2011 on host n150 in /mnt/p06/7885jtomczak
Submission directory is /mnt/wk07/jtomczak/DATA/MATERIALS/FeSi/DMFT/QMC/U5.0/FAST/beta250 on host rupc04
-----------------------------------------------------------------------------------------
+ echo -catch_rsh /opt/sge6/spool/n150/active_jobs/7885.1/pe_hostfile /opt/mpich2/intel/11.1/
-catch_rsh /opt/sge6/spool/n150/active_jobs/7885.1/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/n150/active_jobs/7885.1/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/n150/active_jobs/7885.1/pe_hostfile ']'
+ machines=/tmp/7885.1.wp10/machines
+ PeHostfile2MachineFile /opt/sge6/spool/n150/active_jobs/7885.1/pe_hostfile
+ cat /opt/sge6/spool/n150/active_jobs/7885.1/pe_hostfile
+ read line
++ echo n150 11 wp10@n150 UNDEFINED
++ cut -f1 '-d '
++ cut -f1 -d.
+ host=n150
++ echo n150 11 wp10@n150 UNDEFINED
++ cut -f2 '-d '
+ nslots=11
+ i=1
+ '[' 1 -le 11 ']'
+ echo n150
++ expr 1 + 1
+ i=2
+ '[' 2 -le 11 ']'
+ echo n150
++ expr 2 + 1
+ i=3
+ '[' 3 -le 11 ']'
+ echo n150
++ expr 3 + 1
+ i=4
+ '[' 4 -le 11 ']'
+ echo n150
++ expr 4 + 1
+ i=5
+ '[' 5 -le 11 ']'
+ echo n150
++ expr 5 + 1
+ i=6
+ '[' 6 -le 11 ']'
+ echo n150
++ expr 6 + 1
+ i=7
+ '[' 7 -le 11 ']'
+ echo n150
++ expr 7 + 1
+ i=8
+ '[' 8 -le 11 ']'
+ echo n150
++ expr 8 + 1
+ i=9
+ '[' 9 -le 11 ']'
+ echo n150
++ expr 9 + 1
+ i=10
+ '[' 10 -le 11 ']'
+ echo n150
++ expr 10 + 1
+ i=11
+ '[' 11 -le 11 ']'
+ echo n150
++ expr 11 + 1
+ i=12
+ '[' 12 -le 11 ']'
+ 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 n159 7 wp10@n159 UNDEFINED
++ cut -f1 '-d '
++ cut -f1 -d.
+ host=n159
++ echo n159 7 wp10@n159 UNDEFINED
++ cut -f2 '-d '
+ nslots=7
+ i=1
+ '[' 1 -le 7 ']'
+ echo n159
++ expr 1 + 1
+ i=2
+ '[' 2 -le 7 ']'
+ echo n159
++ expr 2 + 1
+ i=3
+ '[' 3 -le 7 ']'
+ echo n159
++ expr 3 + 1
+ i=4
+ '[' 4 -le 7 ']'
+ echo n159
++ expr 4 + 1
+ i=5
+ '[' 5 -le 7 ']'
+ echo n159
++ expr 5 + 1
+ i=6
+ '[' 6 -le 7 ']'
+ echo n159
++ expr 6 + 1
+ i=7
+ '[' 7 -le 7 ']'
+ echo n159
++ expr 7 + 1
+ i=8
+ '[' 8 -le 7 ']'
+ read line
++ echo n164 3 wp10@n164 UNDEFINED
++ cut -f1 '-d '
++ cut -f1 -d.
+ host=n164
++ echo n164 3 wp10@n164 UNDEFINED
++ cut -f2 '-d '
+ nslots=3
+ i=1
+ '[' 1 -le 3 ']'
+ echo n164
++ expr 1 + 1
+ i=2
+ '[' 2 -le 3 ']'
+ echo n164
++ expr 2 + 1
+ i=3
+ '[' 3 -le 3 ']'
+ echo n164
++ expr 3 + 1
+ i=4
+ '[' 4 -le 3 ']'
+ read line
++ echo n154 2 wp10@n154 UNDEFINED
++ cut -f1 '-d '
++ cut -f1 -d.
+ host=n154
++ echo n154 2 wp10@n154 UNDEFINED
++ cut -f2 '-d '
+ nslots=2
+ i=1
+ '[' 1 -le 2 ']'
+ echo n154
++ expr 1 + 1
+ i=2
+ '[' 2 -le 2 ']'
+ echo n154
++ expr 2 + 1
+ i=3
+ '[' 3 -le 2 ']'
+ read line
+ cat /tmp/7885.1.wp10/machines
n150
n150
n150
n150
n150
n150
n150
n150
n150
n150
n150
n145
n159
n159
n159
n159
n159
n159
n159
n164
n164
n164
n154
n154
+ '[' 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/7885.1.wp10/rsh
+ hash -r
+ '[' 0 = 1 ']'
+ port=22885
++ cat /tmp/7885.1.wp10/machines
++ uniq
+ for host in '`cat $machines | uniq`'
+ /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n150 /opt/mpich2/intel/11.1//bin/smpd 22885
+ for host in '`cat $machines | uniq`'
+ /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n145 /opt/mpich2/intel/11.1//bin/smpd 22885
+ for host in '`cat $machines | uniq`'
+ /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n159 /opt/mpich2/intel/11.1//bin/smpd 22885
+ for host in '`cat $machines | uniq`'
+ /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n164 /opt/mpich2/intel/11.1//bin/smpd 22885
+ for host in '`cat $machines | uniq`'
+ /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n154 /opt/mpich2/intel/11.1//bin/smpd 22885
+ 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/7885.1.wp10/machines
++ uniq
rsh n150 /opt/mpich2/intel/11.1//bin/smpd -port 22885 -d 0
rsh n159 /opt/mpich2/intel/11.1//bin/smpd -port 22885 -d 0
rsh n145 /opt/mpich2/intel/11.1//bin/smpd -port 22885 -d 0
+ for host in '`cat $machines | uniq`'
++ /opt/mpich2/intel/11.1//bin/smpd -port 22885 -status n150
++ cut -f 1 -d ' '
rsh n164 /opt/mpich2/intel/11.1//bin/smpd -port 22885 -d 0
++ head -n 1
rsh n154 /opt/mpich2/intel/11.1//bin/smpd -port 22885 -d 0
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 n150'
startmpich2.sh: missing smpd on n150
+ for host in '`cat $machines | uniq`'
++ /opt/mpich2/intel/11.1//bin/smpd -port 22885 -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 22885 -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 22885 -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 22885 -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
+ '[' 5 -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/7885.1.wp10/machines
++ uniq
+ for host in '`cat $machines | uniq`'
++ /opt/mpich2/intel/11.1//bin/smpd -port 22885 -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
+ for host in '`cat $machines | uniq`'
++ /opt/mpich2/intel/11.1//bin/smpd -port 22885 -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 22885 -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 22885 -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 22885 -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
+ '[' 5 -eq 5 ']'
+ echo 'startmpich2.sh: got all 5 of 5 nodes'
startmpich2.sh: got all 5 of 5 nodes
+ exit 0
rm: cannot remove `dmft?.error*': No such file or directory
rm: cannot remove `*.outputdmf?.*': No such file or directory
START
-catch_rsh /opt/mpich2/intel/11.1/
Your job finished at Wed Jun 15 11:25:29 EDT 2011