problem with run

weit08@lzu_cn

New Member
Hi, everybody
I have a problem during run CCSM3. I have kept the model running for days(I just set "ndays" for stop_option and "5days" for stop_n to test),but it has not finished and there isn't any output. Could you help me? Thanks very much!

*************************env_mach:*************************
#! /bin/csh -f

# Documentation of following environment varibles is provided in env.readme

setenv CASE ex1
setenv CASESTR ex1
setenv COMP_ATM cam # [cam,latm,datm,xatm]
setenv COMP_LND clm # [clm,dlnd,xlnd]
setenv COMP_ICE csim # [csim,dice,xice]
setenv COMP_OCN pop # [pop,docn,xocn]
setenv COMP_CPL cpl # [cpl]
setenv CSIM_MODE prognostic # [prognostic,oceanmixed_ice]
setenv GRID T42_gx1v3 # [T42_gx1v3, T85_gx1v3, T31_gx3v5, T62_gx1v3, T62_gx3v5, 2x2.5_gx1v3]
setenv RUN_TYPE startup # [startup,hybrid,branch]
setenv RUN_STARTDATE 1990-01-01 # [yyyy-mm-dd]
setenv RUN_REFCASE case.std # [only applies to hybrid or branch runs]
setenv RUN_REFDATE 0001-01-01 # [only applies to hybrid or branch runs]
setenv IPCC_MODE OFF # [OFF, 1870_CONTROL, 1870_TO_PRESENT, RAMP_CO2_ONLY,
# FUTURE_A1, FUTURE_A2, FUTURE_B1, FUTURE_B2]
setenv RAMP_CO2_START_YMD 00000000 # Start date of CAM CO2 ramp in form YYYYMMDD
# This variable MUST be set if IPCC_MODE is RAMP_CO2_ONLY
# This variable is ignored if IPCC_MODE is not RAMP_CO2_ONLY

........

***********************env_mach.jazz************************
#! /bin/csh -f

# Documentation of following environment varibles is provided in env.readme

# -------------------------------------------------------------------------
# Tasks and Threads: Edit any time prior to invoking the configure command
# -------------------------------------------------------------------------

set COMPONENTS = ($COMP_CPL $COMP_ICE $COMP_LND $COMP_OCN $COMP_ATM)

set ntasks_atm = 1; set nthrds_atm = 1
set ntasks_lnd = 1; set nthrds_lnd = 1
set ntasks_ice = 1; set nthrds_ice = 1
set ntasks_ocn = 1; set nthrds_ocn = 1
set ntasks_cpl = 2; set nthrds_cpl = 1

if ($COMP_LND == xlnd) then
set ntasks_lnd = 2; set nthrds_lnd = 1
endif

if ($COMP_ICE == xice) then
set ntasks_ice = 4; set nthrds_ice = 1
endif

if ($COMP_ATM == cam) then
set ntasks_atm = 16; set nthrds_atm = 1
if ($GRID =~ T31* ) then
set ntasks_atm = 16; set nthrds_atm = 1
else if ($GRID =~ T42_gx1*) then
set ntasks_atm = 16; set nthrds_atm = 1
else if ($GRID =~ T85_gx1*) then
set ntasks_atm = 32; set nthrds_atm = 1
endif
endif

if ($COMP_LND == clm) then
set ntasks_lnd = 6; set nthrds_lnd = 1
if ($GRID =~ T31* ) then
set ntasks_lnd = 6; set nthrds_lnd = 1
else if ($GRID =~ T42_gx1*) then
set ntasks_lnd = 6; set nthrds_lnd = 1
else if ($GRID =~ T85_gx1*) then
set ntasks_lnd = 12; set nthrds_lnd = 1
endif
endif

if ($COMP_ICE == csim) then
set pic = prescribed_ice_clim
set pia = prescribed_ice_amip
set ntasks_ice = 8; set nthrds_ice = 1
if ($GRID =~ *gx3*) then
set ntasks_ice = 8; set nthrds_ice = 1
else if ($GRID =~ T42_gx1*) then
set ntasks_ice = 8; set nthrds_ice = 1
else if ($GRID =~ T85_gx1*) then
set ntasks_ice = 8; set nthrds_ice = 1
else if ($CSIM_MODE == $pic) then
set ntasks_ice = 8; set nthrds_ice = 1
else if ($CSIM_MODE == $pia) then
set ntasks_ice = 8; set nthrds_ice = 1
endif
endif

if ($COMP_OCN == pop) then
set ntasks_ocn = 24; set nthrds_ocn = 1
if ($GRID =~ *gx3*) then
set ntasks_ocn = 24; set nthrds_ocn = 1
else if ($GRID =~ T42_gx1*) then
set ntasks_ocn = 24; set nthrds_ocn = 1
else if ($GRID =~ T85_gx1*) then
set ntasks_ocn = 24; set nthrds_ocn = 1
endif
endif

setenv NTASKS_ATM 1
setenv NTHRDS_ATM 1
setenv NTASKS_LND 1
setenv NTHRDS_LND 1
setenv NTASKS_ICE 1
setenv NTHRDS_ICE 1
setenv NTASKS_OCN 1
setenv NTHRDS_OCN 1
setenv NTASKS_CPL 2
setenv NTHRDS_CPL 1

# -------------------------------------------------------------------------
# General machine specific environment variables - edit before the initial build
# -------------------------------------------------------------------------

setenv EXEROOT $HOME/weit/exe/$CASE
setenv RUNROOT $EXEROOT
setenv GMAKE_J 1

# -------------------------------------------------------------------------
# Environment variables for prestaging input data - edit anytime during run
# -------------------------------------------------------------------------

setenv DIN_LOC_ROOT /home/chen/weit/inputdata
setenv DIN_LOC_ROOT_USER /home/chen/weit/inputdata_user
setenv DIN_LOC_MSROOT /home/chen/weit/inputdata
setenv DIN_REM_MACH dataproc.ucar.edu
setenv DIN_REM_MSROOT /CCSM/inputdata
setenv DIN_REM_ROOT $HOME/inputdata

# -------------------------------------------------------------------------
# Environment variables for short term output storage - edit anytime during run
# -------------------------------------------------------------------------

setenv DOUT_S TRUE
setenv DOUT_S_ROOT $HOME/weit/archive/$CASE

# -------------------------------------------------------------------------
# Environment variables for longer term output storage - edit anytime during run
# -------------------------------------------------------------------------

setenv DOUT_L_RCP FALSE
setenv DOUT_L_RCP_ROOT mylogin@remotesite.edu:/ptmp/$LOGNAME/archive/$CASE
setenv DOUT_L_MS FALSE
setenv DOUT_L_MSNAME `echo $LOGNAME | tr '[a-z]' '[A-Z]'`
setenv DOUT_L_MSROOT /$DOUT_L_MSNAME/csm/$CASE
setenv DOUT_L_MSPWD $DOUT_L_MSNAME
setenv DOUT_L_MSRPD 3650
setenv DOUT_L_MSPRJ 00000000

# -------------------------------------------------------------------------
# Build and runtime environment variables - edit before the initial build
# -------------------------------------------------------------------------
......
 

weit08@lzu_cn

New Member
**********************************************************
************************env_run****************************
#! /bin/csh -f

# Documentation of following environment varibles is provided in env.readme

setenv RESUBMIT 0 # if RESUBMIT is > 0, then will resubmit

setenv CCSMROOT /home/chen/weit/ccsm3_0
setenv CASEROOT /home/chen/weit/ccsm3_0/scripts/ex1
setenv CONTINUE_RUN FALSE # [TRUE, FALSE]
setenv SETBLD TRUE # [AUTO, TRUE, FALSE]
setenv STOP_OPTION ndays # [ndays,nmonths,daily,monthly,yearly]
setenv STOP_N 5
setenv REST_OPTION $STOP_OPTION
setenv REST_N $STOP_N
setenv INFO_DBUG 1 # [0,1,2,3]
setenv DEBUG FALSE # [TRUE, FALSE]
set OCN_TRACER_MODULES = (iage) # [(iage), (iage cfc),(cfc),( )]

#=========================================================================
# DERIVED ENVIRONMENT VARIABLES (user may edit these)
#=========================================================================

# BUILD TYPE

if ($SETBLD =~ AUTO*) then
setenv BLDTYPE TRUE
if ($CONTINUE_RUN == 'TRUE') setenv BLDTYPE FALSE
else
setenv BLDTYPE $SETBLD
endif

# COUPLER HISTORY/DIAG NAMELIST SETTING

setenv HIST_OPTION never
setenv HIST_N -999 # unused
setenv HIST_64BIT .false. # use 32-bit (default behavior)
setenv AVHIST_OPTION never
setenv AVHIST_N -999 # unused
setenv DIAG_OPTION ndays
setenv DIAG_N 1 # current favorite value

setenv LOGDIR "/home/chen/weit/log" # save extra copy of log files here
.....

**********************************************************
*************************ex1.jazz.build***********************
I haven't change anything in this script, but after I have finished it successfully, I checked the log file and foundd that (eg. in atm.log.090315-081752) and I don't know is there something wrong.

Sun Mar 15 09:21:14 MST 2009 /home/chen/weit/exe/ex1/atm/atm.log.090315-081752
cp atm/cam2/ozone/pcmdio3.r8.64x1_L60_clim_c970515.nc to pcmdio3.r8.64x1_L60_clim_c970515.nc
cp: cannot stat `atm/cam2/ozone/pcmdio3.r8.64x1_L60_clim_c970515.nc': No such file or directory
cp /home/chen/weit/inputdata/atm/cam2/ozone/pcmdio3.r8.64x1_L60_clim_c970515.nc to pcmdio3.r8.64x1_L60_clim_c970515.nc
cp atm/cam2/rad/abs_ems_factors_fastvx.c030508.nc to abs_ems_factors_fastvx.c030508.nc
cp: cannot stat `atm/cam2/rad/abs_ems_factors_fastvx.c030508.nc': No such file or directory
cp /home/chen/weit/inputdata/atm/cam2/rad/abs_ems_factors_fastvx.c030508.nc to abs_ems_factors_fastvx.c030508.nc
cp atm/cam2/rad/AerosolOptics_c040105.nc to AerosolOptics_c040105.nc
cp: cannot stat `atm/cam2/rad/AerosolOptics_c040105.nc': No such file or directory
cp /home/chen/weit/inputdata/atm/cam2/rad/AerosolOptics_c040105.nc to AerosolOptics_c040105.nc
cp atm/cam2/rad/AerosolMass_V_64x128_clim_c031022.nc to AerosolMass_V_64x128_clim_c031022.nc
cp: cannot stat `atm/cam2/rad/AerosolMass_V_64x128_clim_c031022.nc': No such file or directory
cp /home/chen/weit/inputdata/atm/cam2/rad/AerosolMass_V_64x128_clim_c031022.nc to AerosolMass_V_64x128_clim_c031022.nc
cp atm/cam2/inic/gaus/cami_0000-09-01_64x128_L26_c030918.nc to cami_0000-09-01_64x128_L26_c030918.nc
cp: cannot stat `atm/cam2/inic/gaus/cami_0000-09-01_64x128_L26_c030918.nc': No such file or directory
cp /home/chen/weit/inputdata/atm/cam2/inic/gaus/cami_0000-09-01_64x128_L26_c030918.nc to cami_0000-09-01_64x128_L26_c030918.nc


*************************ex1.jazz.run***********************
#! /bin/csh -f
#===============================================================================
# This is a CCSM coupled model Load Leveler batch job script for jazz
#===============================================================================

#PBS -A CCSM2_1
#PBS -l nodes=6
#PBS -l walltime=2000:00:00
#PBS -N ccsm

#-----------------------------------------------------------------------
# Determine necessary environment variables
#-----------------------------------------------------------------------

cd /home/chen/weit/ccsm3_0/scripts/ex1
setenv MACH jazz

source env_conf || "problem sourcing env_conf" && exit -1
source env_run || "problem sourcing env_run" && exit -1
source env_mach.jazz || "problem sourcing env_mach.jazz" && exit -1

#-----------------------------------------------------------------------
# Resolved task/thread counts
# This is provider as user information only
# These are csh comments, DO NOT UNCOMMENT
#-----------------------------------------------------------------------
### COMPONENTS = ( cpl csim clm pop cam )
### NTASKS_CPL=2 NTHRDS_CPL=1
### NTASKS_ICE=1 NTHRDS_ICE=1
### NTASKS_LND=1 NTHRDS_LND=1
### NTASKS_OCN=1 NTHRDS_OCN=1
### NTASKS_ATM=1 NTHRDS_ATM=1

#-----------------------------------------------------------------------
# Determine time-stamp/file-ID string
#-----------------------------------------------------------------------

setenv LID "`date +%y%m%d-%H%M%S`"

# -------------------------------------------------------------------------
# Run machine dependent module commands
# -------------------------------------------------------------------------

if (-f modules.$MACH) then
echo sourcing modules.$MACH
source modules.$MACH || exit 1
endif

# -------------------------------------------------------------------------
# Build the models
# -------------------------------------------------------------------------

./${CASE}.${MACH}.build || exit 1

# -------------------------------------------------------------------------
# Create processor count input files
# -------------------------------------------------------------------------

cd $EXEROOT/all
@ PROC = 0 # counts total number of tasks
rm -rf mpirun.pgfile1 # create new pgfile
rm -rf mpirun.pgfile # create new pgfile
echo "0" >>! mpirun.pgfile1;
foreach n (1 2 3 4 5)
set comp = $COMPONENTS[$n]
set model = $MODELS[$n]
set nthrd = $NTHRDS[$n]
set ntask = $NTASKS[$n]
@ M = 0
while ( $M < $ntask )
if (($n == 1) && ($M == 0)) then
echo "skipping first model"
else
echo "1 $EXEROOT/all/$comp" >>! mpirun.pgfile1;
endif
@ M++
@ PROC++
end
ln -s $EXEROOT/$model/$comp $EXEROOT/all/. # link binaries into all dir
end

# -------------------------------------------------------------------------
# Run the model
# -------------------------------------------------------------------------
env | egrep '(MP_|LOADL|XLS|FPE|DSM|OMP|MPC)' # document env vars

cd $EXEROOT/all
#paste ${PBS_NODEFILE} mpirun.pgfile1 > mpirun.pgfile
echo "`date` -- CSM EXECUTION BEGINS HERE"
#mpirun -pg mpirun.pgfile ./$COMPONENTS[1]
/home/chen/mpich-1.2.7p1/bin/mpirun -v -prefix "[%g]" -d $EXEROOT/all/mpirun.pgfile1
-np $NTASKS[1] $COMPONENTS[1] :
-np $NTASKS[2] $COMPONENTS[2] :
-np $NTASKS[3] $COMPONENTS[3] :
-np $NTASKS[4] $COMPONENTS[4] :
-np $NTASKS[5] $COMPONENTS[5] &

wait
echo "`date` -- CSM EXECUTION HAS FINISHED"

# -------------------------------------------------------------------------
# Save model output stdout and stderr
# -------------------------------------------------------------------------

cd $EXEROOT/cpl
set CplLogFile = `ls -1t cpl.log* | head -1`
grep 'end of main program' $CplLogFile || echo "Model did not complete - see $CplLogFile" && exit -1

cd $EXEROOT
gzip */*.$LID

if ($LOGDIR != "") then
if (! -d $LOGDIR/bld) mkdir -p $LOGDIR/bld || echo " problem in creating $LOGDIR/bld" && exit -1
cp -p */*buildexe*$LID.* $LOGDIR/bld || echo "Error in copy of logs " && exit -1
cp -p */*log*$LID.* $LOGDIR || echo "Error in copy of logs " && exit -1
endif

# -------------------------------------------------------------------------
# Perform short term archiving of output
# -------------------------------------------------------------------------

if ($DOUT_S == 'TRUE') then
echo "Archiving ccsm output to $DOUT_S_ROOT"
echo "In $CASEROOT directory using the short term archiving script ccsm_s_archive.csh"
cd $CASEROOT; $UTILROOT/Tools/ccsm_s_archive.csh
endif

# -------------------------------------------------------------------------
# Submit longer term archiver if appropriate
# -------------------------------------------------------------------------

if ($DOUT_L_MS == 'TRUE' && $DOUT_S == 'TRUE') then
echo "Long term archiving ccsm output using the script $CASE.$MACH.l_archive"
qsub $CASE.$MACH.l_archive
endif

# -------------------------------------------------------------------------
# Resubmit another run script
# -------------------------------------------------------------------------

set echo
cd $CASEROOT
source env_run
if ($RESUBMIT > 0) then
echo RESUBMIT is $RESUBMIT
@ RESUBMIT = $RESUBMIT - 1
echo RESUBMIT is $RESUBMIT

sed '1,/^ *setenv *CONTINUE_RUN .*/s//setenv CONTINUE_RUN TRUE/'
env_run > env_run.tmp; mv env_run.tmp env_run
sed "s/^ *setenv *RESUBMIT .*/setenv RESUBMIT $RESUBMIT/;"
env_run > env_run.tmp; mv env_run.tmp env_run

qsub $CASE.$MACH.run
endif
endif


Thanks in advance for your help!
 
Back
Top