Changeset 1201


Ignore:
Timestamp:
05/22/15 17:29:08 (9 years ago)
Author:
sdipsl
Message:
  • add jobWarningDelay in seconds to supervision messages see #253 (threshold for heartbeat)
  • add accountingProject to supervision messages see #255 (may ease gencmip6 data production tracking)
Location:
trunk/libIGCM
Files:
22 edited

Legend:

Unmodified
Added
Removed
  • trunk/libIGCM/AA_additionnal

    r1198 r1201  
    2626#-Q- ada # pour recevoir un mail en cas de depassement du temps Elapsed (ou autre pb.) 
    2727#-Q- ada # @ notification = error 
    28 #-Q- ada # @ environment  = $POST_DIR ; $SUBMIT_DIR ; $libIGCM ; $DEBUG_debug ; $BigBrother ; $R_INIT ; $R_BC ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $R_SAVE ; $config_UserChoices_JobName ; $config_UserChoices_TagName ; $YEARS ; $MASTER 
     28#-Q- ada # @ environment  = $POST_DIR ; $SUBMIT_DIR ; $libIGCM ; $DEBUG_debug ; $BigBrother ; $R_INIT ; $R_BC ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $R_SAVE ; $config_UserChoices_JobName ; $config_UserChoices_TagName ; $YEARS ; $MASTER ; wall_clock_limit=$(wall_clock_limit) 
    2929#-Q- ada # @ queue 
    3030#-Q- lxiv8 ###################### 
  • trunk/libIGCM/AA_atlas_LMDZ

    r1198 r1201  
    2626#-Q- ada # pour recevoir un mail en cas de depassement du temps Elapsed (ou autre pb.) 
    2727#-Q- ada # @ notification = error 
    28 #-Q- ada # @ environment  = $POST_DIR ; $Script_Post_Output ; $SUBMIT_DIR ; $libIGCM ; $DEBUG_debug ; $BigBrother ; $R_INIT ; $R_BC ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $RESOL_SBG ; $YEARS ; $DIR_OUT ; $MASTER ; $libIGCM_SX 
     28#-Q- ada # @ environment  = $POST_DIR ; $Script_Post_Output ; $SUBMIT_DIR ; $libIGCM ; $DEBUG_debug ; $BigBrother ; $R_INIT ; $R_BC ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $RESOL_SBG ; $YEARS ; $DIR_OUT ; $MASTER ; $libIGCM_SX ; wall_clock_limit=$(wall_clock_limit) 
    2929#-Q- ada # @ queue 
    3030#-Q- lxiv8 ###################### 
  • trunk/libIGCM/AA_atlas_ORCA_LIM

    r1198 r1201  
    2626#-Q- ada # pour recevoir un mail en cas de depassement du temps Elapsed (ou autre pb.) 
    2727#-Q- ada # @ notification = error 
    28 #-Q- ada # @ environment  = $POST_DIR ; $Script_Post_Output ; $SUBMIT_DIR ; $libIGCM ; $DEBUG_debug ; $BigBrother ; $R_INIT ; $R_BC ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $RESOL_SBG ; $YEARS ; $DIR_OUT ; $MASTER ; $libIGCM_SX 
     28#-Q- ada # @ environment  = $POST_DIR ; $Script_Post_Output ; $SUBMIT_DIR ; $libIGCM ; $DEBUG_debug ; $BigBrother ; $R_INIT ; $R_BC ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $RESOL_SBG ; $YEARS ; $DIR_OUT ; $MASTER ; $libIGCM_SX ; wall_clock_limit=$(wall_clock_limit) 
    2929#-Q- ada # @ queue 
    3030#-Q- lxiv8 ###################### 
  • trunk/libIGCM/AA_atlas_ORCHIDEE

    r1198 r1201  
    2626#-Q- ada # pour recevoir un mail en cas de depassement du temps Elapsed (ou autre pb.) 
    2727#-Q- ada # @ notification = error 
    28 #-Q- ada # @ environment  = $POST_DIR ; $Script_Post_Output ; $SUBMIT_DIR ; $libIGCM ; $DEBUG_debug ; $BigBrother ; $R_INIT ; $R_BC ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $RESOL_SBG ; $YEARS ; $DIR_OUT ; $MASTER ; $libIGCM_SX 
     28#-Q- ada # @ environment  = $POST_DIR ; $Script_Post_Output ; $SUBMIT_DIR ; $libIGCM ; $DEBUG_debug ; $BigBrother ; $R_INIT ; $R_BC ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $RESOL_SBG ; $YEARS ; $DIR_OUT ; $MASTER ; $libIGCM_SX ; wall_clock_limit=$(wall_clock_limit) 
    2929#-Q- ada # @ queue 
    3030#-Q- lxiv8 ###################### 
  • trunk/libIGCM/AA_atlas_PISCES

    r1198 r1201  
    2626#-Q- ada # pour recevoir un mail en cas de depassement du temps Elapsed (ou autre pb.) 
    2727#-Q- ada # @ notification = error 
    28 #-Q- ada # @ environment  = $POST_DIR ; $Script_Post_Output ; $SUBMIT_DIR ; $libIGCM ; $DEBUG_debug ; $BigBrother ; $R_INIT ; $R_BC ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $RESOL_SBG ; $YEARS ; $DIR_OUT ; $MASTER ; $libIGCM_SX 
     28#-Q- ada # @ environment  = $POST_DIR ; $Script_Post_Output ; $SUBMIT_DIR ; $libIGCM ; $DEBUG_debug ; $BigBrother ; $R_INIT ; $R_BC ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $RESOL_SBG ; $YEARS ; $DIR_OUT ; $MASTER ; $libIGCM_SX ; wall_clock_limit=$(wall_clock_limit) 
    2929#-Q- ada # @ queue 
    3030#-Q- lxiv8 ###################### 
  • trunk/libIGCM/AA_create_multi_se

    r1198 r1201  
    2626#-Q- ada # pour recevoir un mail en cas de depassement du temps Elapsed (ou autre pb.) 
    2727#-Q- ada # @ notification = error 
    28 #-Q- ada # @ environment  = $DEBUG_debug ; $BigBrother ; $MODIPSL ; $libIGCM ; $libIGCM_SX ; $SUBMIT_DIR ; $POST_DIR ; $Script_Post_Output ; $MASTER ; $DateBegin ; $PeriodDateEnd ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $RESOL_SBG 
     28#-Q- ada # @ environment  = $DEBUG_debug ; $BigBrother ; $MODIPSL ; $libIGCM ; $libIGCM_SX ; $SUBMIT_DIR ; $POST_DIR ; $Script_Post_Output ; $MASTER ; $DateBegin ; $PeriodDateEnd ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $RESOL_SBG ; wall_clock_limit=$(wall_clock_limit) 
    2929#-Q- ada # @ queue 
    3030#-Q- lxiv8 ###################### 
  • trunk/libIGCM/AA_create_se

    r1200 r1201  
    2626#-Q- ada # pour recevoir un mail en cas de depassement du temps Elapsed (ou autre pb.) 
    2727#-Q- ada # @ notification = error 
    28 #-Q- ada # @ environment  = $DEBUG_debug ; $BigBrother ; $MODIPSL ; $libIGCM ; $libIGCM_SX ; $SUBMIT_DIR ; $POST_DIR ; $Script_Post_Output ; $MASTER ; $DateBegin ; $PeriodDateEnd ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $RESOL_SBG 
     28#-Q- ada # @ environment  = $DEBUG_debug ; $BigBrother ; $MODIPSL ; $libIGCM ; $libIGCM_SX ; $SUBMIT_DIR ; $POST_DIR ; $Script_Post_Output ; $MASTER ; $DateBegin ; $PeriodDateEnd ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $RESOL_SBG ; wall_clock_limit=$(wall_clock_limit) 
    2929#-Q- ada # @ queue 
    3030#-Q- lxiv8 ###################### 
  • trunk/libIGCM/AA_create_ts

    r1198 r1201  
    2626#-Q- ada # pour recevoir un mail en cas de depassement du temps Elapsed (ou autre pb.) 
    2727#-Q- ada # @ notification = error 
    28 #-Q- ada # @ environment  = $DEBUG_debug ; $BigBrother ; $MODIPSL ; $libIGCM ; $libIGCM_SX ; $SUBMIT_DIR ; $POST_DIR ; $Script_Post_Output ; $MASTER ; $RebuildFrequency ; $DateBegin ; $PeriodDateEnd ; $StandAlone ; $CompletedFlag ; $TsTask ; $CompToRead ; $FlagToRead ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $RESOL_SBG 
     28#-Q- ada # @ environment  = $DEBUG_debug ; $BigBrother ; $MODIPSL ; $libIGCM ; $libIGCM_SX ; $SUBMIT_DIR ; $POST_DIR ; $Script_Post_Output ; $MASTER ; $RebuildFrequency ; $DateBegin ; $PeriodDateEnd ; $StandAlone ; $CompletedFlag ; $TsTask ; $CompToRead ; $FlagToRead ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $RESOL_SBG ; wall_clock_limit=$(wall_clock_limit) 
    2929#-Q- ada # @ queue 
    3030#-Q- lxiv8 ###################### 
  • trunk/libIGCM/AA_job

    r1189 r1201  
    3535#-Q- ada # Total number of tasks 
    3636#-Q- ada # @ total_tasks = ::JobNumProcTot:: 
    37 #-Q- ada # @ environment = "BATCH_NUM_PROC_TOT=::JobNumProcTot::" 
     37#-Q- ada # @ environment = "BATCH_NUM_PROC_TOT=::JobNumProcTot::" ; wall_clock_limit=$(wall_clock_limit) 
    3838#-Q- ada # Maximum CPU time per task hh:mm:ss 
    3939#-Q- ada # @ wall_clock_limit = 1:00:00 
  • trunk/libIGCM/AA_metrics_LMDZ

    r1198 r1201  
    2626#-Q- ada # pour recevoir un mail en cas de depassement du temps Elapsed (ou autre pb.) 
    2727#-Q- ada # @ notification = error 
    28 #-Q- ada # @ environment  = $POST_DIR ; $Script_Post_Output ; $SUBMIT_DIR ; $libIGCM ; $DEBUG_debug ; $BigBrother ; $R_INIT ; $R_BC ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $RESOL_SBG ; $YEARS ; $DIR_OUT ; $MASTER ; $libIGCM_SX 
     28#-Q- ada # @ environment  = $POST_DIR ; $Script_Post_Output ; $SUBMIT_DIR ; $libIGCM ; $DEBUG_debug ; $BigBrother ; $R_INIT ; $R_BC ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $RESOL_SBG ; $YEARS ; $DIR_OUT ; $MASTER ; $libIGCM_SX ; wall_clock_limit=$(wall_clock_limit) 
    2929#-Q- ada # @ queue 
    3030#-Q- lxiv8 ###################### 
  • trunk/libIGCM/AA_monitoring

    r1198 r1201  
    2626#-Q- ada # pour recevoir un mail en cas de depassement du temps Elapsed (ou autre pb.) 
    2727#-Q- ada # @ notification = error 
    28 #-Q- ada # @ environment  = $DEBUG_debug ; $BigBrother ; $POST_DIR ; $Script_Post_Output ; $SUBMIT_DIR ; $libIGCM ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF 
     28#-Q- ada # @ environment  = $DEBUG_debug ; $BigBrother ; $POST_DIR ; $Script_Post_Output ; $SUBMIT_DIR ; $libIGCM ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; wall_clock_limit=$(wall_clock_limit) 
    2929#-Q- ada # @ queue 
    3030#-Q- lxiv8 ###################### 
  • trunk/libIGCM/AA_pack_debug

    r1198 r1201  
    2626#-Q- ada # pour recevoir un mail en cas de depassement du temps Elapsed (ou autre pb.) 
    2727#-Q- ada # @ notification = error 
    28 #-Q- ada # @ environment  = $DEBUG_debug ; $BigBrother ; $MODIPSL ; $libIGCM ; $libIGCM_SX ; $POST_DIR ; $Script_Post_Output ; $SUBMIT_DIR ; $DateBegin ; $DateEnd ; $PeriodPack ; $StandAlone ; $MASTER 
     28#-Q- ada # @ environment  = $DEBUG_debug ; $BigBrother ; $MODIPSL ; $libIGCM ; $libIGCM_SX ; $POST_DIR ; $Script_Post_Output ; $SUBMIT_DIR ; $DateBegin ; $DateEnd ; $PeriodPack ; $StandAlone ; $MASTER ; wall_clock_limit=$(wall_clock_limit) 
    2929#-Q- ada # @ queue 
    3030#-Q- lxiv8 ###################### 
  • trunk/libIGCM/AA_pack_output

    r1198 r1201  
    2626#-Q- ada # pour recevoir un mail en cas de depassement du temps Elapsed (ou autre pb.) 
    2727#-Q- ada # @ notification = error 
    28 #-Q- ada # @ environment  = $DEBUG_debug ; $BigBrother ; $MODIPSL ; $libIGCM ; $libIGCM_SX ; $POST_DIR ; $Script_Post_Output ; $SUBMIT_DIR ; $DateBegin ; $DateEnd ; $PeriodPack ; $StandAlone ; $MASTER 
     28#-Q- ada # @ environment  = $DEBUG_debug ; $BigBrother ; $MODIPSL ; $libIGCM ; $libIGCM_SX ; $POST_DIR ; $Script_Post_Output ; $SUBMIT_DIR ; $DateBegin ; $DateEnd ; $PeriodPack ; $StandAlone ; $MASTER ; wall_clock_limit=$(wall_clock_limit) 
    2929#-Q- ada # @ queue 
    3030#-Q- lxiv8 ###################### 
  • trunk/libIGCM/AA_pack_restart

    r1198 r1201  
    2626#-Q- ada # pour recevoir un mail en cas de depassement du temps Elapsed (ou autre pb.) 
    2727#-Q- ada # @ notification = error 
    28 #-Q- ada # @ environment  = $DEBUG_debug ; $BigBrother ; $MODIPSL ; $libIGCM ; $libIGCM_SX ; $POST_DIR ; $Script_Post_Output ; $SUBMIT_DIR ; $DateBegin ; $DateEnd ; $PeriodPack ; $StandAlone ; $MASTER 
     28#-Q- ada # @ environment  = $DEBUG_debug ; $BigBrother ; $MODIPSL ; $libIGCM ; $libIGCM_SX ; $POST_DIR ; $Script_Post_Output ; $SUBMIT_DIR ; $DateBegin ; $DateEnd ; $PeriodPack ; $StandAlone ; $MASTER ; wall_clock_limit=$(wall_clock_limit) 
    2929#-Q- ada # @ queue 
    3030#-Q- lxiv8 ###################### 
  • trunk/libIGCM/AA_rebuild_fromWorkdir

    r1198 r1201  
    2929#-Q- ada # pour recevoir un mail en cas de depassement du temps Elapsed (ou autre pb.) 
    3030#-Q- ada # @ notification = error 
    31 #-Q- ada # @ environment  = $DEBUG_debug ; $BigBrother ; $MODIPSL ; $libIGCM ; $libIGCM_SX ; $SUBMIT_DIR ; $REBUILD_DIR ; $POST_DIR ; $Script_Post_Output ; $DateBegin ; $PeriodDateBegin ; $PeriodDateEnd ; $NbRebuildDir ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $RESOL_SBG ; $MASTER 
     31#-Q- ada # @ environment  = $DEBUG_debug ; $BigBrother ; $MODIPSL ; $libIGCM ; $libIGCM_SX ; $SUBMIT_DIR ; $REBUILD_DIR ; $POST_DIR ; $Script_Post_Output ; $DateBegin ; $PeriodDateBegin ; $PeriodDateEnd ; $NbRebuildDir ; $StandAlone ; $RESOL_ATM ; $RESOL_OCE ; $RESOL_ICE ; $RESOL_MBG ; $RESOL_SRF ; $RESOL_SBG ; $MASTER ; wall_clock_limit=$(wall_clock_limit) 
    3232#-Q- ada # @ queue 
    3333#-Q- lxiv8 ###################### 
  • trunk/libIGCM/libIGCM_debug/libIGCM_debug.ksh

    r1189 r1201  
    608608        genericSimulationID=$( echo "\"msgApplication\":\"monitoring\",\"msgProducer\":\"libigcm\",\"cumulPeriod\":\"${CumulPeriod}\",\"simuid\":\"${simuid}\",\"jobuid\":\"${jobuid}\"" ) 
    609609        # RabbitMQ message body with specific fields associated message codes treated here 
    610         Body=$( echo "{${genericSimulationID},\"msgCode\":\"${code}\",\"msgUID\":\"$(uuidgen)\",\"msgTimestamp\":\"$( date +"%Y-%m-%dT%H:%M:%S.%N%z" )\"}" ) 
     610        Body=$( echo "{${genericSimulationID},\"msgCode\":\"${code}\",\"accountingProject\":\"${PROJECT}\",\"jobWarningDelay\":\"${jobWarningDelay}\",\"msgUID\":\"$(uuidgen)\",\"msgTimestamp\":\"$( date +"%Y-%m-%dT%H:%M:%S.%N%z" )\"}" ) 
    611611        # Fill the rabbitMQ queue 
    612612        IGCM_debug_sendAMQP 
  • trunk/libIGCM/libIGCM_sys/libIGCM_sys_ada.ksh

    r1195 r1201  
    6969# $hostname of the MASTER job 
    7070typeset MASTER=ada 
     71# project name 
     72typeset PROJECT=$(echo ${LOADL_STEP_GROUP:=NONE}) 
     73# jobWarningDelay in seconds 
     74typeset jobWarningDelay=$( TZ=utc date -d '1970-01-01 '${wall_clock_time} +%s ) 
    7175 
    7276#D- 
  • trunk/libIGCM/libIGCM_sys/libIGCM_sys_ciclad.ksh

    r1188 r1201  
    6969# $hostname of the MASTER job 
    7070typeset MASTER=${MASTER:=$( hostname )} 
     71# project name 
     72typeset PROJECT=NONE 
     73# jobWarningDelay in seconds 
     74typeset jobWarningDelay=${PBS_WALLTIME} 
    7175 
    7276#D- 
  • trunk/libIGCM/libIGCM_sys/libIGCM_sys_curie.ksh

    r1196 r1201  
    6262 
    6363#===================================================== 
    64 # Host and user names 
     64# Host user names project maxCpuTime 
    6565# $hostname ou hostname 
    6666typeset HOST=${HOST:=$( hostname )} 
     
    7070typeset MASTER=curie 
    7171# add default project on curie 
    72 typeset DEFAULT_PROJECT=gen0826 
     72typeset PROJECT=$(echo ${BRIDGE_MSUB_PROJECT:=gen0826} | cut -d@ -f1 ) 
     73# jobWarningDelay in seconds 
     74typeset jobWarningDelay=${BRIDGE_MSUB_MAXTIME} 
    7375 
    7476#D- 
     
    424426  fi 
    425427  typeset options status 
    426   MY_PROJECT=$(echo ${BRIDGE_MSUB_PROJECT:=${DEFAULT_PROJECT}} | cut -d@ -f1 ) 
    427428 
    428429  # EASIER TO DO THIS INSTEAD OF DUPLICATING libIGCM_sys_curie.ksh 
    429430  case $( hostname -s ) in 
    430431  curie*) 
    431     options="-Q normal -A ${MY_PROJECT} -o ${POST_DIR}/${Script_Post_Output}.out -e ${POST_DIR}/${Script_Post_Output}.out";; 
     432    options="-Q normal -A ${PROJECT} -o ${POST_DIR}/${Script_Post_Output}.out -e ${POST_DIR}/${Script_Post_Output}.out";; 
    432433  airain*) 
    433434    options="-q ivybridge -A dsm -o ${POST_DIR}/${Script_Post_Output}.out -e ${POST_DIR}/${Script_Post_Output}.out" 
  • trunk/libIGCM/libIGCM_sys/libIGCM_sys_default.ksh

    r1186 r1201  
    6969# $hostname of the MASTER job 
    7070typeset MASTER=${MASTER:=$( hostname )} 
     71# project name 
     72typeset PROJECT=NONE 
     73# jobWarningDelay in seconds 
     74typeset jobWarningDelay=NONE 
    7175 
    7276#D- 
  • trunk/libIGCM/libIGCM_sys/libIGCM_sys_iitm.ksh

    r1186 r1201  
    6969# $hostname of the MASTER job 
    7070typeset MASTER=iitm01 
     71# project name 
     72typeset PROJECT=NONE 
     73# jobWarningDelay in seconds 
     74typeset jobWarningDelay=NONE 
    7175 
    7276#D- 
  • trunk/libIGCM/libIGCM_sys/libIGCM_sys_obelix.ksh

    r1186 r1201  
    6969# $hostname of the MASTER job 
    7070typeset MASTER=${MASTER:=$( hostname )} 
     71# project name 
     72typeset PROJECT=NONE 
     73# jobWarningDelay in seconds 
     74typeset jobWarningDelay=${PBS_WALLTIME} 
    7175 
    7276#D- 
Note: See TracChangeset for help on using the changeset viewer.