USER      =  yinzping
HOMEDIR   =  /home/yinzping
JOB_ID    =  371136
JOB_NAME  =  KDOS-100
QUEUE     =  wsp64_hp
NSLOTS    =  8
NHOSTS    =  2

SUB_HOST  =  rupc04
SUB_DIR   =  /mnt/wk18/yinzping/WIEN2k/DMFT/FeAs/K122/I4mmm/U5J8/beta160/Full2/d5.5/beta100/U5J8/115355yinzping/K122/123694yinzping/K122/dos

EXE_HOST  =  sub04n07
EXE_DIR   =  /mnt/sub04n07
OUT_DIR   =  /scr
TMP_DIR   =  /tmp/371136.1.wsp64_hp

INFO      =  Files larger than 100MB will be compressed to reduce the network load.
INFO2     =  Do NOT remove this file while job is running!

PORT      =  21136

Your job started at Wed Dec 10 23:04:48 EST 2014 on host sub04n07 in /mnt/sub04n07/371136yinzping
Submission directory is /mnt/wk18/yinzping/WIEN2k/DMFT/FeAs/K122/I4mmm/U5J8/beta160/Full2/d5.5/beta100/U5J8/115355yinzping/K122/123694yinzping/K122/dos on host rupc04
-----------------------------------------------------------------------------------------

+ echo -catch_rsh /opt/SGE/spool/sub04n07/active_jobs/371136.1/pe_hostfile /opt/mpich2/intel/14.0/
-catch_rsh /opt/SGE/spool/sub04n07/active_jobs/371136.1/pe_hostfile /opt/mpich2/intel/14.0/
+ SLEEPTIME=5
+ RETRIES=10
+ catch_rsh=0
+ catch_hostname=0
+ '[' 3 -gt 0 ']'
+ case "$1" in
+ catch_rsh=1
+ shift
+ '[' 2 -gt 0 ']'
+ case "$1" in
+ break
++ basename /opt/sge6/mpich2_smpd/startmpich2.sh
+ me=startmpich2.sh
+ '[' 2 -lt 2 ']'
+ pe_hostfile=/opt/SGE/spool/sub04n07/active_jobs/371136.1/pe_hostfile
+ MPICH2_ROOT=/opt/mpich2/intel/14.0/
+ export MPICH2_ROOT
+ '[' '!' -x /opt/SGE/mpich2_smpd/bin/lx24-amd64/start_mpich2 ']'
+ '[' '!' -x /opt/mpich2/intel/14.0//bin/smpd ']'
+ '[' '!' -r /opt/SGE/spool/sub04n07/active_jobs/371136.1/pe_hostfile ']'
+ machines=/tmp/371136.1.wsp64_hp/machines
+ PeHostfile2MachineFile /opt/SGE/spool/sub04n07/active_jobs/371136.1/pe_hostfile
+ cat /opt/SGE/spool/sub04n07/active_jobs/371136.1/pe_hostfile
+ read line
++ echo sub04n07 4 wsp64_hp@sub04n07 '<NULL>'
++ cut -f1 '-d '
++ cut -f1 -d.
+ host=sub04n07
++ echo sub04n07 4 wsp64_hp@sub04n07 '<NULL>'
++ cut -f2 '-d '
+ nslots=4
+ i=1
+ '[' 1 -le 4 ']'
+ echo sub04n07
++ expr 1 + 1
+ i=2
+ '[' 2 -le 4 ']'
+ echo sub04n07
++ expr 2 + 1
+ i=3
+ '[' 3 -le 4 ']'
+ echo sub04n07
++ expr 3 + 1
+ i=4
+ '[' 4 -le 4 ']'
+ echo sub04n07
++ expr 4 + 1
+ i=5
+ '[' 5 -le 4 ']'
+ read line
++ echo sub04n08 4 wsp64_hp@sub04n08 '<NULL>'
++ cut -f1 '-d '
++ cut -f1 -d.
+ host=sub04n08
++ echo sub04n08 4 wsp64_hp@sub04n08 '<NULL>'
++ cut -f2 '-d '
+ nslots=4
+ i=1
+ '[' 1 -le 4 ']'
+ echo sub04n08
++ expr 1 + 1
+ i=2
+ '[' 2 -le 4 ']'
+ echo sub04n08
++ expr 2 + 1
+ i=3
+ '[' 3 -le 4 ']'
+ echo sub04n08
++ expr 3 + 1
+ i=4
+ '[' 4 -le 4 ']'
+ echo sub04n08
++ expr 4 + 1
+ i=5
+ '[' 5 -le 4 ']'
+ read line
+ cat /tmp/371136.1.wsp64_hp/machines
sub04n07
sub04n07
sub04n07
sub04n07
sub04n08
sub04n08
sub04n08
sub04n08
+ '[' 1 = 1 ']'
+ rsh_wrapper=/opt/SGE/mpich2_smpd/rsh
+ '[' '!' -x /opt/SGE/mpich2_smpd/rsh ']'
+ rshcmd=rsh
+ case "$ARC" in
+ ln -s /opt/SGE/mpich2_smpd/rsh /tmp/371136.1.wsp64_hp/rsh
+ hash -r
+ '[' 0 = 1 ']'
+ port=21136
++ cat /tmp/371136.1.wsp64_hp/machines
++ uniq
+ for host in '`cat $machines | uniq`'
+ /opt/SGE/mpich2_smpd/bin/lx24-amd64/start_mpich2 -n sub04n07 /opt/mpich2/intel/14.0//bin/smpd 21136
+ for host in '`cat $machines | uniq`'
+ /opt/SGE/mpich2_smpd/bin/lx24-amd64/start_mpich2 -n sub04n08 /opt/mpich2/intel/14.0//bin/smpd 21136
+ 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/371136.1.wsp64_hp/machines
++ uniq
+ for host in '`cat $machines | uniq`'
++ /opt/mpich2/intel/14.0//bin/smpd -port 21136 -status sub04n07
++ head -n 1
++ cut -f 1 -d ' '
rsh sub04n07 /opt/mpich2/intel/14.0//bin/smpd -port 21136 -d 0
rsh sub04n08 /opt/mpich2/intel/14.0//bin/smpd -port 21136 -d 0
+ '[' no == smpd ']'
+ echo 'startmpich2.sh: missing smpd on sub04n07'
startmpich2.sh: missing smpd on sub04n07
+ for host in '`cat $machines | uniq`'
++ /opt/mpich2/intel/14.0//bin/smpd -port 21136 -status sub04n08
++ head -n 1
++ cut -f 1 -d ' '
+ '[' no == smpd ']'
+ echo 'startmpich2.sh: missing smpd on sub04n08'
startmpich2.sh: missing smpd on sub04n08
+ '[' 2 -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/371136.1.wsp64_hp/machines
++ uniq
+ for host in '`cat $machines | uniq`'
++ /opt/mpich2/intel/14.0//bin/smpd -port 21136 -status sub04n07
++ head -n 1
++ cut -f 1 -d ' '
+ '[' smpd == smpd ']'
+ (( numhosts += 1 ))
+ echo 'startmpich2.sh: found running smpd on sub04n07'
startmpich2.sh: found running smpd on sub04n07
+ for host in '`cat $machines | uniq`'
++ /opt/mpich2/intel/14.0//bin/smpd -port 21136 -status sub04n08
++ head -n 1
++ cut -f 1 -d ' '
+ '[' smpd == smpd ']'
+ (( numhosts += 1 ))
+ echo 'startmpich2.sh: found running smpd on sub04n08'
startmpich2.sh: found running smpd on sub04n08
+ '[' 2 -eq 2 ']'
+ echo 'startmpich2.sh: got all 2 of 2 nodes'
startmpich2.sh: got all 2 of 2 nodes
+ exit 0
-catch_rsh /opt/mpich2/intel/14.0/
Your job finished at Wed Dec 10 23:12:24 EST 2014