GEOS icon indicating copy to clipboard operation
GEOS copied to clipboard

HDF5 errors when running with MPI

Open paveltomin opened this issue 1 year ago • 5 comments

Running this case https://geosx-geosx.readthedocs-hosted.com/en/latest/docs/sphinx/basicExamples/multiphaseFlowWithWells/Example.html

Serial runs just fine, when run with mpirun: OMP_NUM_THREADS=1 mpirun -n 2 /data/rpo_ptls/GEOSX/residual_flash/GEOS/GEOS/build-CPU-OPTO2-Hypre-GCC_10.2.0-ompi_hpcx-OMP-relwithdebinfo/bin/geosx -i deadOilEgg_benchmark.xml HDF5 complains at the end of simulation when timeHistoryOutput is triggered:

Cleaning up events
HDF5-DIAG: Error detected in HDF5 (1.12.1) MPI-process 0:
  #000: ../../hdf5/src/H5D.c line 285 in H5Dopen2(): unable to open dataset
    major: Dataset
    minor: Can't open object
  #001: ../../hdf5/src/H5VLcallback.c line 1910 in H5VL_dataset_open(): dataset open failed
    major: Virtual Object Layer
    minor: Can't open object
  #002: ../../hdf5/src/H5VLcallback.c line 1877 in H5VL__dataset_open(): dataset open failed
    major: Virtual Object Layer
    minor: Can't open object
  #003: ../../hdf5/src/H5VLnative_dataset.c line 123 in H5VL__native_dataset_open(): unable to open dataset
    major: Dataset
    minor: Can't open object
  #004: ../../hdf5/src/H5Dint.c line 1483 in H5D__open_name(): not found
    major: Dataset
    minor: Object not found
  #005: ../../hdf5/src/H5Gloc.c line 442 in H5G_loc_find(): can't find object
    major: Symbol table
    minor: Object not found
  #006: ../../hdf5/src/H5Gtraverse.c line 837 in H5G_traverse(): internal path traversal failed
    major: Symbol table
    minor: Object not found
  #007: ../../hdf5/src/H5Gtraverse.c line 613 in H5G__traverse_real(): traversal operator failed
    major: Symbol table
    minor: Callback failed
  #008: ../../hdf5/src/H5Gloc.c line 399 in H5G__loc_find_cb(): object 'wellElementMixtureConnectionRate Time' doesn't exist
    major: Symbol table
    minor: Object not found

Output files contain duplicates: image

paveltomin avatar Sep 27 '23 16:09 paveltomin