From 19d6b606c4d2ddd29e3cfa8e20d72a43e171fbf5 Mon Sep 17 00:00:00 2001 From: Matthew Whitlock Date: Tue, 9 Dec 2025 11:01:34 -0600 Subject: [PATCH 1/4] Test against fixed OMPI versions --- .github/workflows/ci_checks.yaml | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/.github/workflows/ci_checks.yaml b/.github/workflows/ci_checks.yaml index a11ed54..0ad0f7a 100644 --- a/.github/workflows/ci_checks.yaml +++ b/.github/workflows/ci_checks.yaml @@ -11,10 +11,8 @@ jobs: matrix: ompi_version: - main - - 5.0.3 - - git.v5.0.5 - - git.v5.0.7 - git.v5.0.x + - git.v6.0.x steps: - name: Checkout @@ -40,4 +38,4 @@ jobs: *.args.OMPI_VERSION=${{ matrix.ompi_version }} - name: Test Fenix - run: docker run fenix ctest --output-on-failure --timeout 20 --repeat after-timeout:3 + run: docker run fenix ctest --output-on-failure --timeout 20 From b772d8ebc0477351b8b4ac4037b654dbdf052c7a Mon Sep 17 00:00:00 2001 From: Matthew Whitlock Date: Thu, 11 Dec 2025 14:19:37 -0600 Subject: [PATCH 2/4] Test with async_mpi_finalize --- .github/docker-compose.yml | 4 ++-- .github/workflows/ci_checks.yaml | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/.github/docker-compose.yml b/.github/docker-compose.yml index 5291752..5e2f248 100644 --- a/.github/docker-compose.yml +++ b/.github/docker-compose.yml @@ -39,7 +39,7 @@ services: -DCMAKE_C_COMPILER=mpicc \ -DBUILD_EXAMPLES=ON \ -DBUILD_TESTING=ON \ - -DMPIEXEC_PREFLAGS="--allow-run-as-root;--map-by;:oversubscribe" && \ + -DMPIEXEC_PREFLAGS="--allow-run-as-root;--map-by;:oversubscribe;--mca;async_mpi_finalize;1" && \ make -j ENV OMPI_MCA_coll=^han @@ -47,7 +47,7 @@ services: WORKDIR /fenix/build ENTRYPOINT ["/entrypoint.sh"] - CMD ["ctest", "--output-on-failure", "--timeout", "60"] + CMD ["ctest", "--output-on-failure", "--timeout", "20"] args: OMPI_VERSION: main pull_policy: build diff --git a/.github/workflows/ci_checks.yaml b/.github/workflows/ci_checks.yaml index 0ad0f7a..6182558 100644 --- a/.github/workflows/ci_checks.yaml +++ b/.github/workflows/ci_checks.yaml @@ -38,4 +38,4 @@ jobs: *.args.OMPI_VERSION=${{ matrix.ompi_version }} - name: Test Fenix - run: docker run fenix ctest --output-on-failure --timeout 20 + run: docker run fenix ctest --output-on-failure --timeout 20 --repeat until-fail:5 From 8139042921834b2269e3b32de06807b728297475 Mon Sep 17 00:00:00 2001 From: Matthew Whitlock Date: Thu, 11 Dec 2025 14:22:07 -0600 Subject: [PATCH 3/4] Verbose test output --- .github/workflows/ci_checks.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/ci_checks.yaml b/.github/workflows/ci_checks.yaml index 6182558..ce14b05 100644 --- a/.github/workflows/ci_checks.yaml +++ b/.github/workflows/ci_checks.yaml @@ -38,4 +38,4 @@ jobs: *.args.OMPI_VERSION=${{ matrix.ompi_version }} - name: Test Fenix - run: docker run fenix ctest --output-on-failure --timeout 20 --repeat until-fail:5 + run: docker run fenix ctest -V --timeout 20 --repeat until-fail:5 From eb66aa3b0df90ccbb20542a6fda6420ee01bf4db Mon Sep 17 00:00:00 2001 From: Matthew Whitlock Date: Thu, 11 Dec 2025 14:27:07 -0600 Subject: [PATCH 4/4] Speed up failed spares test --- test/failed_spares/fenix_failed_spares.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/test/failed_spares/fenix_failed_spares.c b/test/failed_spares/fenix_failed_spares.c index 6b202aa..c06d791 100644 --- a/test/failed_spares/fenix_failed_spares.c +++ b/test/failed_spares/fenix_failed_spares.c @@ -66,7 +66,7 @@ const int kKillID = 1; void* exitThread(void* should_exit){ - sleep(1); + usleep(10000); if( ((intptr_t)should_exit) == 1){ pid_t pid = getpid(); kill(pid, SIGTERM); @@ -114,7 +114,7 @@ int main(int argc, char **argv) { if (recovered == 0) { //Give time for exit thread to work (which needed to give time for fenix init) - sleep(2); + usleep(100000); } MPI_Barrier(new_comm);