|
|
|
@1013
|
10 years |
sdipsl |
first try to furgely support ergon. not fully tested
should find regular …
|
|
|
|
@1012
|
10 years |
sdipsl |
just replacing gaya by ergon
will work when submitting a new simulation …
|
|
|
|
@1011
|
10 years |
mafoipsl |
On ada revert [1005] to keep reference to netcdf4. Switch to netcdf4par is …
|
|
|
|
@1010
|
10 years |
aclsce |
Use of "typeset -x" instead of "typeset" in order to keep the SUBMIT_DIR …
|
|
|
|
@1005
|
10 years |
mafoipsl |
On ada delete reference to a specific netcdf4 library. Fix #191
|
|
|
|
@1004
|
10 years |
mafoipsl |
On ada fix to reduce memory usage. required since 2014/04/22.
|
|
|
|
@1003
|
10 years |
jgipsl |
Updated adress to documentation
|
|
|
|
@1002
|
10 years |
jgipsl |
Add print of script_exec file as already done on curie.
|
|
|
|
@1000
|
10 years |
aclsce |
Added treatment of MPMD mode with MPI-OpenMP hybrid parallelization for …
|
|
|
|
@996
|
10 years |
sdipsl |
- put back comments for user
- BigBrother? settings
|
|
|
|
@993
|
10 years |
sdipsl |
- Use a netCDF4 compatible AddNoise? binary
- Waiting for a rabbitMQ use an …
|
|
|
|
@992
|
10 years |
mafoipsl |
For curie, add AddNoise PATH to AddNoise compiled with predefined netcdf …
|
|
|
|
@991
|
10 years |
mafoipsl |
For ada : add PATH for AddNoise, add also standard atlas environment even …
|
|
|
|
@989
|
10 years |
sdipsl |
some adjustment
|
|
|
|
@984
|
10 years |
mafoipsl |
On curie use netcdf4 library and add comments to run with netcdf/3.6.3 …
|
|
|
|
@983
|
10 years |
sdipsl |
bypass firewalling difficulties. use mailing system to send AMQP message …
|
|
|
|
@981
|
10 years |
aclsce |
Modified to use OASIS-MCT as coupler (now it is a library, no executable …
|
|
|
|
@979
|
10 years |
jgipsl |
Changed path to english platform documentation.
|
|
|
|
@978
|
10 years |
jgipsl |
- Added login in suffix for /tmp/out_command file to make the file unique. …
|
|
|
|
@977
|
10 years |
aclsce |
Changed rebuild binary used : now we always use rebuild compiled with …
|
|
|
|
@968
|
11 years |
jgipsl |
Removed readonly option for SUBMIT_DIR. RunChecker? and create_ts can not …
|
|
|
|
@964
|
11 years |
jgipsl |
At obelix, the sceduler does the cleaning.
|
|
|
|
@960
|
11 years |
labetoulle |
Bugfix for RunChecker? on Ada :
Skip the first and the last two lines of …
|
|
|
|
@959
|
11 years |
mafoipsl |
On ada, add export MP_STDOUTMODE=combined to combine multiple standard …
|
|
|
|
@958
|
11 years |
labetoulle |
RunChecker? : add JobID to output (#169).
|
|
|
|
@955
|
11 years |
labetoulle |
RunChecker? :
- Introduction of getopts to process command line options
- …
|
|
|
|
@949
|
11 years |
sdipsl |
obelix case. see #125
|
|
|
|
@948
|
11 years |
sdipsl |
catch JobID to be able to connect computing trees and post-processing …
|
|
|
|
@946
|
11 years |
mafoipsl |
Bug fixed in #945.
|
|
|
|
@945
|
11 years |
mafoipsl |
On ada, consolidation of IGCM_sys_check_quota. Exemple with : 15.69% used.
|
|
|
|
@944
|
11 years |
sdipsl |
we want it quiet : atlas_env_ada_bash
it will disturb debug mode …
|
|
|
|
@938
|
11 years |
sdipsl |
cleanup.
replace out_rsync by /tmp/out_command.$$
|
|
|
|
@936
|
11 years |
sdipsl |
bugfix again with instrumentation. Should be fine now...
syntax error in …
|
|
|
|
@933
|
11 years |
sdipsl |
properly remove RUN_DIR_PATH used by AA_job on curie. see #141
but add …
|
|
|
|
@926
|
11 years |
sdipsl |
Add instrumentation for IGCM_sys_ncrcat IGCM_sys_ncecat IGCM_sys_ncra …
|
|
|
|
@923
|
11 years |
sdipsl |
cleanup
|
|
|
|
@922
|
11 years |
sdipsl |
Once per simulation send email containing estimated consumed hours for the …
|
|
|
|
@918
|
11 years |
sdipsl |
Active instrumentation #140 disturbs this kind of call
TarFileLocation?=$( …
|
|
|
|
@912
|
11 years |
sdipsl |
remove machines that are not available anymore
cleanup
|
|
|
|
@909
|
11 years |
mafoipsl |
ada : don't use rsh to find gaya HOME. It breakes script and …
|
|
|
|
@900
|
11 years |
labetoulle |
Remove suffix ${CumulPeriod?} from ${JobName?} when resubmitting (#144).
|
|
|
|
@887
|
11 years |
mafoipsl |
On ada, add a suffix to have a unique jobname for QsubPost.
|
|
|
|
@883
|
11 years |
mafoipsl |
On ada , use STOREHOST variable instead of gaya directly.
|
|
|
|
@882
|
11 years |
mafoipsl |
On ada, since june 18th, tha variable HOME changed. It's like /smphome/... …
|
|
|
|
@881
|
11 years |
mafoipsl |
For LSCE, add asterix* with same treatment as obelix.
|
|
|
|
@880
|
11 years |
mafoipsl |
On curie, define time limit for post-processing jobs : rebuild and …
|
|
|
|
@863
|
11 years |
jgipsl |
Changed to have rebuild in a directory with apropriate name for curie. The …
|
|
|
|
@862
|
11 years |
jgipsl |
Corrections for run at obelix/LSCE.
|
|
|
|
@855
|
11 years |
sdipsl |
First try. Include rabbitMQ C client call within IGCM_debug_PushStack and …
|
|
|
|
@853
|
11 years |
sdipsl |
- Clean up job submission
|
|
|
|
@850
|
11 years |
mafoipsl |
On curie, change RUN_DIR_PATH to have only one additionnal level (instead …
|
|
|
|
@847
|
11 years |
sdipsl |
- small adjustement to be able to run MPI/OpenMP when only one binary is …
|
|
|
|
@845
|
11 years |
labetoulle |
Add function IGCM_sys_RshArchive_NoError to be used in monitoring.job.
See …
|
|
|
|
@839
|
11 years |
sdipsl |
correct a typo
|
|
|
|
@838
|
11 years |
sdipsl |
- Adjust obelix RUN_DIR_PATH. see #111
|
|
|
|
@835
|
11 years |
labetoulle |
Runchecker : add rsh access for monitoring files on Ada. See #128.
|
|
|
|
@834
|
11 years |
labetoulle |
Look for the right string to check rebuild jobs when SpaceName?=TEST. See …
|
|
|
|
@831
|
11 years |
sdipsl |
- ksh exposes its functions to any son processes. Not the case for bash. …
|
|
|
|
@828
|
11 years |
sdipsl |
- Stack file management must be kept in libIGCM_debug
|
|
|
|
@826
|
11 years |
mafoipsl |
On curie, add ${$} in RUN_DIR name to be sure to have an empty temporary …
|
|
|
|
@818
|
11 years |
sdipsl |
- Side effect of the SpaceName?=TEST behaviour implementation at IDRIS …
|
|
|
|
@816
|
11 years |
sdipsl |
- All .doc files has been moved to libIGCM_documentation
|
|
|
|
@813
|
11 years |
sdipsl |
- Update existing .doc files. cat lib* | grep "#D-" | cut -c "4-"
|
|
|
|
@811
|
11 years |
sdipsl |
- see #104 homegenize sys lib so as to ease maintenance.
- all sys lib …
|
|
|
|
@810
|
11 years |
sdipsl |
- see #104 Start with this one so as to ease sys lib maintenance.
- all …
|
|
|
|
@809
|
11 years |
sdipsl |
Activate IGCM_sys_Chmod from DRYRUN=3 and add BoundaryFiles? list in …
|
|
|
|
@808
|
11 years |
mafoipsl |
On curie, modification of EXECUTION command. Pourquoi faire simple quand …
|
|
|
|
@807
|
11 years |
mafoipsl |
On curie, adapt EXECUTION command to stop immediately instead of waiting …
|
|
|
|
@806
|
11 years |
sdipsl |
- Cosmetics
|
|
|
|
@804
|
11 years |
sdipsl |
- Files waiting for rebuild are stored within the relevant simulation …
|
|
|
|
@802
|
11 years |
sdipsl |
Curie as well need adaptation due to STORE issue.
|
|
|
|
@801
|
11 years |
sdipsl |
- Some adaptation so as to find and prepare tared restart on Ada.
|
|
|
|
@800
|
11 years |
sdipsl |
- default and obelix was outdated. They diverged too much from the others.
|
|
|
|
@798
|
11 years |
sdipsl |
Continue to track down SpaceName?=TEST implications at IDRIS
|
|
|
|
@797
|
11 years |
sdipsl |
Bugfix detecting targeted filesystem
|
|
|
|
@796
|
11 years |
sdipsl |
Continu to track down SpaceName?=TEST implications at IDRIS
|
|
|
|
@795
|
11 years |
sdipsl |
Unlike mfput cp don't create parent directory
|
|
|
|
@794
|
11 years |
sdipsl |
Catch the correct return code …
|
|
|
|
@793
|
11 years |
sdipsl |
Continue adaptation to have the correct behaviour when SpaceName?=TEST
…
|
|
|
|
@792
|
11 years |
sdipsl |
Bugfixes ada.
- R_FIG was wrong
- Some adaptation for the test case
|
|
|
|
@791
|
11 years |
mafoipsl |
On ada add /usr/bin/time to have real time usge information. Add …
|
|
|
|
@790
|
11 years |
sdipsl |
bugfix : need to specify poe when executing MPI code
|
|
|
|
@789
|
11 years |
mafoipsl |
On ada delete useless rm.
|
|
|
|
@788
|
11 years |
mafoipsl |
On ada, IGCM_sys_PutBuffer_Out add status initialisation when copy is …
|
|
|
|
@786
|
11 years |
labetoulle |
Cosmetics :
- Tabs replacement, round 2.
|
|
|
|
@785
|
11 years |
labetoulle |
Cosmetics :
- Convert tabs into space for better lisibility with different …
|
|
|
|
@784
|
11 years |
sdipsl |
llsubmit dont support path in standard/error output. Must submit where …
|
|
|
|
@782
|
11 years |
labetoulle |
- Move REBUILD_DIR initialization into IGCM_config_CommonConfiguration …
|
|
|
|
@780
|
11 years |
labetoulle |
Revert to r778.
|
|
|
|
@779
|
11 years |
labetoulle |
Add IGCM_sys_CountJobInQueue (needed by RunChecker?) to Ada and Curie …
|
|
|
|
@777
|
11 years |
sdipsl |
Bugfix building execution file run_file
OpenMP not yet in. Only MPI.
time …
|
|
|
|
@776
|
11 years |
sdipsl |
Check curie's quota while running
|
|
|
|
@774
|
11 years |
sdipsl |
Bugfix in ada lib when settings meaningfull output filenames. DRYRUN is …
|
|
|
|
@773
|
11 years |
sdipsl |
Cosmetics
|
|
|
|
@771
|
11 years |
sdipsl |
Add ada system library. Almost running in DRYRUN mode (post process …
|
|
|
|
@768
|
11 years |
labetoulle |
RunChecker? for IDRIS :
- replace ccc_home by ${HOME} ;
- create …
|
|
|
|
@767
|
11 years |
acosce |
o-This line, and those below, will be ignored--
On Curie : Project …
|
|
|
|
@765
|
11 years |
mafoipsl |
- Consolidation of AA_pack_debug and AA_pack_restart : don't delete …
|
|
|
|
@759
|
11 years |
mafoipsl |
On curie first consolidation for 444 file transfer.
|
|
|
|
@747
|
12 years |
sdipsl |
- correct a typo. Do not affect running simulations
|
|
|
|
