USER      =  jtomczak
HOMEDIR   =  /home/users/jtomczak
JOB_ID    =  4510
JOB_NAME  =  FS-b150-6
QUEUE     =  wp10
NSLOTS    =  15
NHOSTS    =  6

SUB_HOST  =  rupc06
SUB_DIR   =  /mnt/wk07/jtomczak/DATA/MATERIALS/FeSi/DMFT/QMC/U5.0/FAST/beta150/nf6

EXE_HOST  =  n165
NFS_HOST  =  caip02s
EXE_DIR   =  /mnt/p06
OUT_DIR   =  /tmp
TMP_DIR   =  /tmp/4510.1.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      =  24510
rcp: /mnt/wk07/jtomczak/DATA/MATERIALS/FeSi/DMFT/QMC/U5.0/FAST/beta150/nf6/imp.0: not a plain file
Failure to rcp files!

Your job started at Thu Mar 31 15:33:19 EDT 2011 on host n165 in /mnt/p06/4510jtomczak
Submission directory is /mnt/wk07/jtomczak/DATA/MATERIALS/FeSi/DMFT/QMC/U5.0/FAST/beta150/nf6 on host rupc06
-----------------------------------------------------------------------------------------
+ echo -catch_rsh /opt/sge6/spool/n165/active_jobs/4510.1/pe_hostfile /opt/mpich2/intel/11.1/
-catch_rsh /opt/sge6/spool/n165/active_jobs/4510.1/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/n165/active_jobs/4510.1/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/n165/active_jobs/4510.1/pe_hostfile ']'
+ machines=/tmp/4510.1.wp10/machines
+ PeHostfile2MachineFile /opt/sge6/spool/n165/active_jobs/4510.1/pe_hostfile
+ cat /opt/sge6/spool/n165/active_jobs/4510.1/pe_hostfile
+ read line
++ echo n165 4 wp10@n165 UNDEFINED
++ cut -f1 '-d '
++ cut -f1 -d.
+ host=n165
++ echo n165 4 wp10@n165 UNDEFINED
++ cut -f2 '-d '
+ nslots=4
+ i=1
+ '[' 1 -le 4 ']'
+ echo n165
++ expr 1 + 1
+ i=2
+ '[' 2 -le 4 ']'
+ echo n165
++ expr 2 + 1
+ i=3
+ '[' 3 -le 4 ']'
+ echo n165
++ expr 3 + 1
+ i=4
+ '[' 4 -le 4 ']'
+ echo n165
++ expr 4 + 1
+ i=5
+ '[' 5 -le 4 ']'
+ read line
++ echo n146 1 wp10@n146 UNDEFINED
++ cut -f1 '-d '
++ cut -f1 -d.
+ 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 n153 4 wp10@n153 UNDEFINED
++ cut -f1 '-d '
++ cut -f1 -d.
+ host=n153
++ echo n153 4 wp10@n153 UNDEFINED
++ cut -f2 '-d '
+ nslots=4
+ i=1
+ '[' 1 -le 4 ']'
+ echo n153
++ expr 1 + 1
+ i=2
+ '[' 2 -le 4 ']'
+ echo n153
++ expr 2 + 1
+ i=3
+ '[' 3 -le 4 ']'
+ echo n153
++ expr 3 + 1
+ i=4
+ '[' 4 -le 4 ']'
+ echo n153
++ expr 4 + 1
+ i=5
+ '[' 5 -le 4 ']'
+ read line
++ echo n163 2 wp10@n163 UNDEFINED
++ cut -f1 '-d '
++ cut -f1 -d.
+ host=n163
++ echo n163 2 wp10@n163 UNDEFINED
++ cut -f2 '-d '
+ nslots=2
+ i=1
+ '[' 1 -le 2 ']'
+ echo n163
++ expr 1 + 1
+ i=2
+ '[' 2 -le 2 ']'
+ echo n163
++ expr 2 + 1
+ i=3
+ '[' 3 -le 2 ']'
+ read line
++ echo n141 3 wp10@n141 UNDEFINED
++ cut -f1 '-d '
++ cut -f1 -d.
+ host=n141
++ echo n141 3 wp10@n141 UNDEFINED
++ cut -f2 '-d '
+ nslots=3
+ i=1
+ '[' 1 -le 3 ']'
+ echo n141
++ expr 1 + 1
+ i=2
+ '[' 2 -le 3 ']'
+ echo n141
++ expr 2 + 1
+ i=3
+ '[' 3 -le 3 ']'
+ echo n141
++ expr 3 + 1
+ i=4
+ '[' 4 -le 3 ']'
+ read line
++ echo n155 1 wp10@n155 UNDEFINED
++ cut -f1 '-d '
++ cut -f1 -d.
+ host=n155
++ echo n155 1 wp10@n155 UNDEFINED
++ cut -f2 '-d '
+ nslots=1
+ i=1
+ '[' 1 -le 1 ']'
+ echo n155
++ expr 1 + 1
+ i=2
+ '[' 2 -le 1 ']'
+ read line
+ cat /tmp/4510.1.wp10/machines
n165
n165
n165
n165
n146
n153
n153
n153
n153
n163
n163
n141
n141
n141
n155
+ '[' 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/4510.1.wp10/rsh
+ hash -r
+ '[' 0 = 1 ']'
+ port=24510
++ cat /tmp/4510.1.wp10/machines
++ uniq
+ for host in '`cat $machines | uniq`'
+ /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n165 /opt/mpich2/intel/11.1//bin/smpd 24510
+ for host in '`cat $machines | uniq`'
+ /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n146 /opt/mpich2/intel/11.1//bin/smpd 24510
+ for host in '`cat $machines | uniq`'
+ /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n153 /opt/mpich2/intel/11.1//bin/smpd 24510
+ for host in '`cat $machines | uniq`'
+ /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n163 /opt/mpich2/intel/11.1//bin/smpd 24510
rsh n146 /opt/mpich2/intel/11.1//bin/smpd -port 24510 -d 0
rsh n165 /opt/mpich2/intel/11.1//bin/smpd -port 24510 -d 0
+ for host in '`cat $machines | uniq`'
+ /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n141 /opt/mpich2/intel/11.1//bin/smpd 24510
rsh n163 /opt/mpich2/intel/11.1//bin/smpd -port 24510 -d 0
rsh n153 /opt/mpich2/intel/11.1//bin/smpd -port 24510 -d 0
+ for host in '`cat $machines | uniq`'
+ /opt/sge6/mpich2_smpd/bin/lx26-amd64/start_mpich2 -n n155 /opt/mpich2/intel/11.1//bin/smpd 24510
+ 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/4510.1.wp10/machines
++ uniq
+ for host in '`cat $machines | uniq`'
++ /opt/mpich2/intel/11.1//bin/smpd -port 24510 -status n165
++ head -n 1
++ cut -f 1 -d ' '
rsh n155 /opt/mpich2/intel/11.1//bin/smpd -port 24510 -d 0
rsh n141 /opt/mpich2/intel/11.1//bin/smpd -port 24510 -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 n165'
startmpich2.sh: missing smpd on n165
+ for host in '`cat $machines | uniq`'
++ /opt/mpich2/intel/11.1//bin/smpd -port 24510 -status n146
++ cut -f 1 -d ' '
++ head -n 1
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 24510 -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 24510 -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 24510 -status n141
++ head -n 1
++ cut -f 1 -d ' '
+ '[' smpd == smpd ']'
+ (( numhosts += 1 ))
+ echo 'startmpich2.sh: found running smpd on n141'
startmpich2.sh: found running smpd on n141
+ for host in '`cat $machines | uniq`'
++ /opt/mpich2/intel/11.1//bin/smpd -port 24510 -status n155
++ head -n 1
++ cut -f 1 -d ' '
+ '[' smpd == smpd ']'
+ (( numhosts += 1 ))
+ echo 'startmpich2.sh: found running smpd on n155'
startmpich2.sh: found running smpd on n155
+ '[' 6 -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/4510.1.wp10/machines
++ uniq
+ for host in '`cat $machines | uniq`'
++ /opt/mpich2/intel/11.1//bin/smpd -port 24510 -status n165
++ head -n 1
++ cut -f 1 -d ' '
+ '[' smpd == smpd ']'
+ (( numhosts += 1 ))
+ echo 'startmpich2.sh: found running smpd on n165'
startmpich2.sh: found running smpd on n165
+ for host in '`cat $machines | uniq`'
++ /opt/mpich2/intel/11.1//bin/smpd -port 24510 -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 24510 -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 24510 -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 24510 -status n141
++ head -n 1
++ cut -f 1 -d ' '
+ '[' smpd == smpd ']'
+ (( numhosts += 1 ))
+ echo 'startmpich2.sh: found running smpd on n141'
startmpich2.sh: found running smpd on n141
+ for host in '`cat $machines | uniq`'
++ /opt/mpich2/intel/11.1//bin/smpd -port 24510 -status n155
++ head -n 1
++ cut -f 1 -d ' '
+ '[' smpd == smpd ']'
+ (( numhosts += 1 ))
+ echo 'startmpich2.sh: found running smpd on n155'
startmpich2.sh: found running smpd on n155
+ '[' 6 -eq 6 ']'
+ echo 'startmpich2.sh: got all 6 of 6 nodes'
startmpich2.sh: got all 6 of 6 nodes
+ exit 0
START
END
Sat Apr  2 13:11:42 EDT 2011
-catch_rsh /opt/mpich2/intel/11.1/
Your job finished at Sat Apr 2 13:11:42 EDT 2011