Preparation for Transition to C6 (#78)

* Added C6 env and mk files

* added ci_build_driver for c6

* Updated NEP10 CI test driver

* Update NWA and NEP CI driver

* add c6 gha-ci workflow

* Start modifying xmls

* fixed c6 GHA workflow

* revert changes for workflow

* fix build script in CEFI_MOM6_c6-ci.yaml

* Increase NWA CI layout

* Update xml for c6

* fixed diag yaml convert

* Update run script and change default FRE for PPAN

* turn off analysis for now

* revert back platform change

* Update platforms.xml

* add module unload darshan-runtime

* move data folders properties to platforms.xml

* fre/test works on PPAN now

* fre/test does not work on PP

* Update CEFI_NWA12_cobalt.xml

* Update CEFI_NWA12_cobalt_fms2_yaml.xml

* Update CEFI_NWA12_cobalt.xml

* Update CEFI_NWA12_cobalt_fms2_yaml.xml

* change fre version on PPAN

* FRE/test now works on PPAN

* Update CEFI_NWA12_cobalt_fms2_yaml.xml

FRE/test now works on PPAN

.github/workflows/CEFI_MOM6_c6-ci.yaml

@@ -0,0 +1,130 @@
+name: CEFI-MOM6_c6-ci
+
+on:
+  # Triggers this workflow on pull request event with "CEFI_MOM6_RT_gaea_c6" label
+  pull_request:
+    branches: [ "main" ]
+    types: [ labeled ]
+
+#
+env:
+  TEST_DIR: ${{ github.workspace }}/${{ github.run_id }}
+  PR_NUMBER: ${{ github.event.number }}
+
+#
+jobs:
+  checkout-build:
+    if: ${{ github.event.label.name == 'CEFI_MOM6_RT_gaea_c6' }}
+    runs-on: self-hosted
+    timeout-minutes: 600
+    strategy:
+      max-parallel: 1    
+
+    steps:
+    - name: Checkout CEFI-regional-MOM6
+      uses: actions/checkout@v4
+      with:
+        path: ${{ github.run_id }}/CEFI_MOM6_CHECK
+        fetch-depth: 1  
+        submodules: recursive
+
+    - name: Build MOM6SIS2
+      run: |
+        cd ${{ env.TEST_DIR }}/CEFI_MOM6_CHECK/builds
+        jobid=$(sbatch --parsable ci_build_driver_c6.sh | awk -F';' '{print $1}' | cut -f1)
+        #
+        sleep 1
+        while :; do
+            job_status=$(squeue -h -j "$jobid" -o "%T" 2>/dev/null)
+            if [ -z "$job_status" ]; then
+               echo "Job with ID $jobid is not found or completed."
+               break
+            else
+               echo "Job with ID $jobid is still running."
+               echo "Job Status: $job_status"
+            fi
+            sleep 60  # Adjust the sleep duration as needed
+        done
+        #
+        check_file="${{ env.TEST_DIR }}/CEFI_MOM6_CHECK/builds/build/gaea-ncrc6.intel23/ocean_ice/repro/MOM6SIS2"
+        if [ -f "$check_file" ]; then
+            echo "PASSED: $check_file"
+        else
+            echo "FAILED: $check_file"
+            exit 1
+        fi 
+
+  run-CEFI_MOM6-ci:
+    needs: checkout-build
+    runs-on: self-hosted
+    strategy:
+      max-parallel: 2
+      matrix:
+        case: ["NWA12.COBALT"] #["NWA12.COBALT", "NEP10.COBALT"]
+    steps:
+      - name: Run Experiment ${{ matrix.case }}
+        run: |
+          cd ${{ env.TEST_DIR }}/CEFI_MOM6_CHECK/exps/${{ matrix.case }}
+          jobid=$(sbatch --parsable driver.sh | awk -F';' '{print $1}' | cut -f1) 
+          #
+          sleep 1
+          while :; do
+              job_status=$(squeue -h -j "$jobid" -o "%T" 2>/dev/null)
+              if [ -z "$job_status" ]; then
+                 echo "Job with ID $jobid is not found or completed."
+                 break
+              else
+                 echo "Job with ID $jobid is still running."
+                 echo "Job Status: $job_status"
+              fi
+              sleep 60  # Adjust the sleep duration as needed
+          done
+          # 
+          expected_string="All restart files are identical, PASS"
+          check_file="${{ env.TEST_DIR }}/CEFI_MOM6_CHECK/exps/${{ matrix.case }}/${{ matrix.case }}_o.$jobid"
+          if [ -f "$check_file" ]; then
+             if grep -qF "$expected_string" $check_file; then
+                 echo "PASSED: ${{ matrix.case }}"
+             else
+                 echo "FAILED: ${{ matrix.case }}"
+                 exit 1
+             fi
+          else
+             echo "Can not find $check_file. STOP"
+             exit 10
+          fi
+
+  add-pass-label:
+    needs: run-CEFI_MOM6-ci
+    runs-on: self-hosted 
+    if: ${{ needs.run-CEFI_MOM6-ci.result == 'success' }}
+    steps:
+      - name: Add "pass_CEFI_MOM6_RT" label on success
+        run: |
+          TOKEN=${{ secrets.GITHUB_TOKEN }}
+          RT_TEST_LABEL="CEFI_MOM6_RT_gaea_c6"
+          PASS_LABEL="pass_CEFI_MOM6_RT"
+
+          # Remove the "CEFI_MOM6_RT_gaea_c6" label
+          curl -X DELETE \
+            -H "Authorization: Bearer $TOKEN" \
+            -H "Accept: application/vnd.github.v3+json" \
+            "https://api.github.com/repos/$GITHUB_REPOSITORY/issues/${{ env.PR_NUMBER }}/labels/$RT_TEST_LABEL"
+
+          # Add the "pass_CEFI_MOM6_RT" label
+          curl -X POST \
+            -H "Authorization: Bearer $TOKEN" \
+            -H "Accept: application/vnd.github.v3+json" \
+            "https://api.github.com/repos/$GITHUB_REPOSITORY/issues/${{ env.PR_NUMBER }}/labels" \
+            -d "{\"labels\":[\"$PASS_LABEL\"]}"
+
+  clean-up:
+    needs: add-pass-label
+    runs-on: self-hosted 
+    strategy:
+      max-parallel: 1
+    steps:
+      - name: Clean-up
+        run: |
+          cd ${{ github.workspace }}
+          rm -rf ${{ github.run_id }}        

builds/ci_build_driver_c6.sh

@@ -0,0 +1,65 @@
+#!/bin/bash
+#SBATCH --nodes=1
+#SBATCH --time=60
+#SBATCH --job-name="MOM6SIS2_ci_build"
+#SBATCH --output=MOM6SIS2_ci_build_o.%j
+#SBATCH --error=MOM6SIS2_ci_build_e.%j
+#SBATCH --qos=debug
+#SBATCH --partition=batch
+#SBATCH --clusters=c6
+#SBATCH --account=ira-cefi
+
+#
+[ -d "build" ] && rm -rf build
+
+#
+echo "Build MOM6SIS2-COBALT for CI testing started:  " `date`
+
+#
+machine_name="gaea" 
+platform="ncrc6.intel23"
+target="repro"
+flavor="fms1_mom6sis2"
+
+FMSlib_PATH="/ncrc/home2/Yi-cheng.Teng/github/FMS/2024.02_FMS1"
+rootdir=$(pwd)
+abs_rootdir=$rootdir
+
+echo $abs_rootdir
+
+#load modules              
+source $MODULESHOME/init/bash
+source $rootdir/$machine_name/$platform.env
+. $rootdir/$machine_name/$platform.env
+
+makeflags="NETCDF=3"
+
+if [[ $target =~ "repro" ]] ; then
+   makeflags="$makeflags REPRO=1"
+fi
+
+srcdir=$abs_rootdir/../src
+
+#
+sed -i 's/static pid_t gettid(void)/pid_t gettid(void)/g' $srcdir/FMS/affinity/affinity.c
+
+#
+if [[ $flavor == "fms1_mom6sis2" ]] ; then
+    echo "build mom6sis2 with FMS1 cap" 	
+
+    mkdir -p build/$machine_name-$platform/ocean_ice/$target
+    pushd build/$machine_name-$platform/ocean_ice/$target
+    rm -f path_names
+    $srcdir/mkmf/bin/list_paths $srcdir/MOM6/{config_src/infra/FMS1,config_src/memory/dynamic_symmetric,config_src/drivers/FMS_cap,config_src/external/ODA_hooks,config_src/external/database_comms,config_src/external/drifters,config_src/external/stochastic_physics,pkg/GSW-Fortran/{modules,toolbox}/,src/{*,*/*}/} $srcdir/SIS2/{config_src/dynamic_symmetric,config_src/external/Icepack_interfaces,src} $srcdir/icebergs/src $srcdir/FMS/{coupler,include}/ $srcdir/{ocean_BGC/generic_tracers,ocean_BGC/mocsy/src}/ $srcdir/{atmos_null,ice_param,land_null,coupler/shared/,coupler/full/}/
+
+   compiler_options='-DINTERNAL_FILE_NML -DMAX_FIELDS_=600 -DNOT_SET_AFFINITY -Duse_deprecated_io -D_USE_MOM6_DIAG -D_USE_GENERIC_TRACER -DUSE_PRECISION=2 -D_USE_LEGACY_LAND_ -Duse_AM3_physics'
+
+   $srcdir/mkmf/bin/mkmf -t $abs_rootdir/$machine_name/$platform.mk -o "-I${FMSlib_PATH}/shared/$target" -p MOM6SIS2 -l "-L${FMSlib_PATH}/shared/$target -lfms" -c "$compiler_options" path_names
+
+   make $makeflags MOM6SIS2 
+
+fi
+
+
+
+echo "Build MOM6SIS2-COBALT for CI testing ended:  " `date`

builds/gaea/ncrc6.intel23.env

@@ -0,0 +1,11 @@
+source $MODULESHOME/init/tcsh
+module unload cray-netcdf cray-hdf5 fre
+module unload PrgEnv-pgi PrgEnv-intel PrgEnv-gnu PrgEnv-cray
+module load PrgEnv-intel/8.5.0
+module unload intel intel-classic intel-oneapi
+module load intel-classic/2023.2.0
+module load cray-hdf5/1.12.2.11
+module load cray-netcdf/4.9.0.9
+module load libyaml/0.2.5
+module list
+ftn --version