fix CI: free disk before NVHPC docker pull, use long-lived container

Port fix from MFlowCode/MFC#1350: the ~25-30GB NVHPC cuda_multi Docker
images exceed GitHub runner disk space when pulled via the container:
directive (which runs before any steps).

Fix: remove container: directive, add explicit steps to free disk space
(remove dotnet/android/ghc/boost/chromium), then docker pull + docker
run -d + docker exec for NVHPC jobs. Non-NVHPC jobs are unchanged.

Also fix: fetch main instead of master for coverage diff.

Author: sbryngelson

.github/workflows/test.yml

@@ -8,7 +8,6 @@ on:
   workflow_dispatch:
 
 concurrency:
-  # PRs: group by branch (new push cancels old). Push to master: unique per SHA (never cancelled).
   group: ${{ github.workflow }}-${{ github.event_name == 'push' && github.sha || github.ref }}
   cancel-in-progress: ${{ github.event_name != 'push' }}
 
@@ -31,7 +30,6 @@ jobs:
 
         include:
           # NVHPC compiler matrix: cpu (build+test), gpu (build-only, acc then omp)
-          # Every release from 23.11 through 26.3 (current)
           - { nvhpc: '23.11', target: cpu }
           - { nvhpc: '23.11', target: gpu }
           - { nvhpc: '24.7',  target: cpu }
@@ -44,35 +42,81 @@ jobs:
       fail-fast: false
     continue-on-error: true
     runs-on: ${{ matrix.nvhpc && 'ubuntu-22.04' || format('{0}-latest', matrix.os) }}
-    container:
-      image: ${{ matrix.nvhpc && format('nvcr.io/nvidia/nvhpc:{0}-devel-cuda_multi-ubuntu22.04', matrix.nvhpc) || '' }}
-      options: ${{ matrix.nvhpc && '--security-opt seccomp=unconfined' || '' }}
     env:
-      CC:  ${{ matrix.nvhpc && 'nvc' || '' }}
-      CXX: ${{ matrix.nvhpc && 'nvc++' || '' }}
-      FC:  ${{ matrix.nvhpc && 'nvfortran' || '' }}
-      OMPI_ALLOW_RUN_AS_ROOT:         ${{ matrix.nvhpc && '1' || '' }}
-      OMPI_ALLOW_RUN_AS_ROOT_CONFIRM: ${{ matrix.nvhpc && '1' || '' }}
-      PMIX_MCA_gds:                   ${{ matrix.nvhpc && 'hash' || '' }}
-      OMPI_MCA_hwloc_base_binding_policy: ${{ matrix.nvhpc && 'none' || '' }}
-      FFLAGS:  ${{ matrix.nvhpc && '-tp=px -Kieee -noswitcherror' || '' }}
-      CFLAGS:  ${{ matrix.nvhpc && '-tp=px' || '' }}
-      CXXFLAGS: ${{ matrix.nvhpc && '-tp=px' || '' }}
+      NVHPC_IMAGE: ${{ matrix.nvhpc && format('nvcr.io/nvidia/nvhpc:{0}-devel-cuda_multi-ubuntu22.04', matrix.nvhpc) || '' }}
 
     steps:
-      - name: Git safe directory
+      # ── NVHPC: free disk before pulling the ~25-30 GB cuda_multi image ──
+      - name: Free disk space
         if:   matrix.nvhpc
-        run:  git config --global --add safe.directory /__w/figr/figr
+        run: |
+          echo "=== Disk before cleanup ==="
+          df -h /
+          sudo rm -rf /usr/share/dotnet /usr/local/lib/android \
+            /opt/ghc /usr/local/share/boost /opt/hostedtoolcache \
+            /usr/local/graalvm /usr/local/.ghcup \
+            /usr/local/share/chromium /usr/local/lib/node_modules
+          sudo docker image prune -af
+          sudo apt-get clean
+          echo "=== Disk after cleanup ==="
+          df -h /
 
       - name: Clone
         uses: actions/checkout@v4
 
-      - name: Fetch master for coverage diff
+      - name: Fetch main for coverage diff
         run: |
-          git fetch origin master:master --depth=1
+          git fetch origin main:main --depth=1
           git fetch --deepen=200
         continue-on-error: true
 
+      # ── NVHPC: pull image and start a long-lived container ──────────────
+      - name: Pull NVHPC container
+        if:   matrix.nvhpc
+        run:  docker pull "$NVHPC_IMAGE"
+
+      - name: Start NVHPC container
+        if:   matrix.nvhpc
+        run: |
+          docker run -d --name nvhpc \
+            --security-opt seccomp=unconfined \
+            -v "${{ github.workspace }}:/workspace" \
+            -w /workspace \
+            -e CC=nvc \
+            -e CXX=nvc++ \
+            -e FC=nvfortran \
+            -e OMPI_ALLOW_RUN_AS_ROOT=1 \
+            -e OMPI_ALLOW_RUN_AS_ROOT_CONFIRM=1 \
+            -e PMIX_MCA_gds=hash \
+            -e OMPI_MCA_hwloc_base_binding_policy=none \
+            -e "FFLAGS=-tp=px -Kieee -noswitcherror" \
+            -e CFLAGS=-tp=px \
+            -e CXXFLAGS=-tp=px \
+            "$NVHPC_IMAGE" sleep infinity
+
+      - name: Setup NVHPC
+        if:   matrix.nvhpc
+        run: |
+          docker exec nvhpc bash -c '
+            set -e
+            apt-get update -y
+            apt-get install -y cmake python3 python3-venv python3-pip \
+                               libfftw3-dev libhdf5-dev hdf5-tools git
+            git config --global --add safe.directory /workspace
+
+            HPCX_DIR=$(dirname "$(find /opt/nvidia/hpc_sdk -path "*/hpcx/hpcx-*/ompi/bin/mpirun" | head -1)")/../..
+            MPI_LIB=$(mpifort --showme:link | grep -oP "(?<=-L)\S+" | head -1)
+
+            cat > /etc/nvhpc-env.sh <<EOF
+          export LD_LIBRARY_PATH=${MPI_LIB}:${HPCX_DIR}/ucx/lib:${HPCX_DIR}/ucc/lib:\$LD_LIBRARY_PATH
+          export OMPI_MCA_rmaps_base_oversubscribe=1
+          EOF
+
+            echo "=== NVHPC Environment ==="
+            nvfortran --version
+          '
+
+      # ── Standard (non-NVHPC) setup ─────────────────────────────────────
       - name: Setup MacOS
         if:   matrix.os == 'macos' && !matrix.nvhpc
         run:  |
@@ -109,30 +153,7 @@ jobs:
           echo "MPICC=mpiicx" >> $GITHUB_ENV
           echo "MPICXX=mpiicpx" >> $GITHUB_ENV
 
-      # --- NVHPC container setup ---
-      - name: Setup NVHPC
-        if:   matrix.nvhpc
-        run: |
-          apt-get update -y
-          apt-get install -y cmake python3 python3-venv python3-pip \
-                             libfftw3-dev libhdf5-dev hdf5-tools git
-          # Set up NVHPC HPC-X MPI runtime paths
-          HPCX_DIR=$(dirname "$(find /opt/nvidia/hpc_sdk -path "*/hpcx/hpcx-*/ompi/bin/mpirun" | head -1)")/../..
-          MPI_LIB=$(mpifort --showme:link | grep -oP '(?<=-L)\S+' | head -1)
-          echo "LD_LIBRARY_PATH=${MPI_LIB}:${HPCX_DIR}/ucx/lib:${HPCX_DIR}/ucc/lib:${LD_LIBRARY_PATH}" >> $GITHUB_ENV
-          # Container MPI fixes: PMIx shared-memory, hwloc binding
-          echo "PMIX_MCA_gds=hash" >> $GITHUB_ENV
-          echo "OMPI_MCA_hwloc_base_binding_policy=none" >> $GITHUB_ENV
-          echo "OMPI_MCA_rmaps_base_oversubscribe=1" >> $GITHUB_ENV
-          # Debug: confirm compiler flags are set
-          echo "=== NVHPC Environment ==="
-          echo "FFLAGS=$FFLAGS"
-          echo "CFLAGS=$CFLAGS"
-          echo "CXXFLAGS=$CXXFLAGS"
-          nvfortran --version
-          cat /proc/cpuinfo | grep "model name" | head -1
-
-      # --- Standard build + test ---
+      # ── Standard build + test ───────────────────────────────────────────
       - name: Build
         if:   '!matrix.nvhpc'
         run:  /bin/bash figr.sh test -v --dry-run -j $(nproc) --${{ matrix.debug }} $PRECISION --test-all
@@ -147,19 +168,34 @@ jobs:
           TEST_PCT: ${{ matrix.debug == 'reldebug' && '-% 20' || '' }}
           ONLY_CHANGES: ${{ github.event_name == 'pull_request' && '--only-changes' || '' }}
 
-      # --- NVHPC build + test ---
+      # ── NVHPC build + test (via docker exec into long-lived container) ──
       - name: Build (NVHPC)
         if:   matrix.nvhpc && matrix.target == 'cpu'
-        run:  /bin/bash figr.sh test -v --dry-run -j $(nproc) --test-all
+        run: |
+          docker exec nvhpc bash -c '
+            source /etc/nvhpc-env.sh
+            /bin/bash figr.sh test -v --dry-run -j $(nproc) --test-all
+          '
 
       - name: Build (NVHPC GPU)
         if:   matrix.nvhpc && matrix.target == 'gpu'
-        run:  |
-          /bin/bash figr.sh test -v --dry-run -j 2 --test-all --gpu acc
-          /bin/bash figr.sh test -v --dry-run -j 2 --test-all --gpu mp
+        run: |
+          docker exec nvhpc bash -c '
+            source /etc/nvhpc-env.sh
+            /bin/bash figr.sh test -v --dry-run -j 2 --test-all --gpu acc
+            /bin/bash figr.sh test -v --dry-run -j 2 --test-all --gpu mp
+          '
 
       - name: Test (NVHPC)
         if:   matrix.nvhpc && matrix.target == 'cpu'
-        run:  |
-          ulimit -s unlimited || ulimit -s 65536 || true
-          /bin/bash figr.sh test -v --max-attempts 3 -j $(nproc) --test-all
+        run: |
+          docker exec nvhpc bash -c '
+            source /etc/nvhpc-env.sh
+            ulimit -s unlimited || ulimit -s 65536 || true
+            /bin/bash figr.sh test -v --max-attempts 3 -j $(nproc) --test-all
+          '
+
+      # ── Cleanup ─────────────────────────────────────────────────────────
+      - name: Stop NVHPC container
+        if:   always() && matrix.nvhpc
+        run:  docker rm -f nvhpc || true