I/O and memory diagnostic improvements in DistributedClosestPoint driver

skills/building/SKILL.md

@@ -64,3 +64,44 @@ If the user does **not** specify a host-config file, determine the best match by
 ```
 
 Use its output as the `-hc` argument (as shown in the examples above). If the user explicitly provides a host-config file/path, use that instead.
+
+### Symlinked directories in the sandbox
+
+If configure/build commands report that an existing path is missing, inaccessible, or outside the sandbox, check whether the source, build, install, host-config, or TPL paths include symlinks. Compare logical and physical paths with:
+
+```bash
+pwd -P
+readlink -f <path>
+```
+
+Prefer physical paths resolved by `readlink -f` when invoking `config-build.py` (for `-bp`, `-ip`, `-hc`, and any explicit source/TPL paths), or restart the sandbox from the resolved workspace path. A symlinked path may appear outside the sandbox policy even when its resolved target is visible.
+
+### MPI and Slurm in the sandbox
+
+To run MPI-enabled commands from the sandbox, launch Codex with the `--mpi` command-line argument. This starts a Flux instance when needed. MPI through the sandbox is single-node only. If MPI or Slurm commands fail because no Flux allocation is available, stop and ask the user to restart the sandbox with `--mpi`.
+
+On Slurm-based systems, run Slurm commands through the Flux wrapper instead of the system executable, for example:
+
+```bash
+/usr/global/tools/flux_wrappers/bin/srun -n 2 <command>
+```
+
+Loading the flux wrappers before launching the agent allows you to run the srun wrapper, e.g.
+```bash
+module load flux_wrappers
+srun -n 2 <command>
+```
+
+When configuring builds whose MPI tests use `srun`, override CMake's MPI launcher:
+
+```bash
+./config-build.py -hc "$(./skills/building/scripts/determine_host_config)" -DMPIEXEC_EXECUTABLE=/usr/global/tools/flux_wrappers/bin/srun
+```
+
+### Shroud in the sandbox
+
+If CMake configuration has trouble with Shroud in the sandbox, unset the cached Shroud executable at configure time:
+
+```bash
+./config-build.py -hc "$(./skills/building/scripts/determine_host_config)" -USHROUD_EXECUTABLE
+```

src/axom/quest/detail/DistributedClosestPointImpl.hpp

@@ -381,7 +381,7 @@ class DistributedClosestPointImpl
     {
       auto& queryDom = isMultidomain ? queryNode.child(domainNum) : queryNode;
       conduit::Node& xferDom = xferDoms.child(domainNum);
-      conduit::Node& fields = queryDom.fetch_existing("fields");
+      conduit::Node& fields = queryDom.fetch("fields");
 
       conduit::Node genericHeaders;
       genericHeaders["association"] = "vertex";

src/axom/quest/examples/CMakeLists.txt

@@ -381,81 +381,123 @@ if(AXOM_ENABLE_MPI AND AXOM_ENABLE_SIDRE AND HDF5_FOUND)
     if(AXOM_ENABLE_TESTS AND AXOM_DATA_DIR)
         set(_nranks 3)
 
-        # Run the distributed closest point example on N ranks for each enabled policy
-        # Non-zero empty-rank probability tests domain underloading case
+        # Run the distributed closest point example on N ranks for each enabled policy.
+        # Query meshes match the original DCP example. Object meshes were
+        # generated with src/tools/gen-multidom-point-mesh.py.
         set(_meshes "mdmesh.2x1" "mdmesh.2x3" "mdmesh.2x2x1" "mdmeshg.2x2x1")
-        # The mdmesh.* files were generated by these commands:
-        # src/tools/gen-multidom-structured-mesh.py -ml=0,0 -mu=2,2 -ms=100,100 -dc=2,1 -o mdmesh.2x1
-        # src/tools/gen-multidom-structured-mesh.py -ml=0,0 -mu=2,2 -ms=100,100 -dc=2,3 -o mdmesh.2x3
-        # src/tools/gen-multidom-structured-mesh.py -ml=0,0,0 -mu=2,2,2 -ms=20,20,15 -dc=2,2,1 -o mdmeshg.2x2x1 --strided
-        foreach(_pol ${AXOM_EXECUTION_POLICIES})
-            # sets the number of threads for the omp policy; leave empty for non-omp policies
-            set(_num_threads)
-            if(_pol STREQUAL "omp")
-                set(_num_threads ${AXOM_TEST_NUM_OMP_THREADS})
+        foreach(_mesh ${_meshes})
+            string(REGEX MATCH "\\.[0-9]+(x[0-9]+)+$" _sizes "${_mesh}")
+            string(REGEX MATCHALL "[0-9]+" _sizes ${_sizes})
+            list(LENGTH _sizes _ndim)
+
+            if(_ndim EQUAL 2)
+                set(_dim 2)
+                set(_shape circle)
+                set(_object_mesh ${quest_data_dir}/dcp_object_circle.root)
+            elseif(_ndim EQUAL 3)
+                set(_dim 3)
+                set(_shape sphere)
+                set(_object_mesh ${quest_data_dir}/dcp_object_sphere.root)
             endif()
 
-            foreach(_mesh ${_meshes})
-                # Determine problem dimension by mesh filename.
-                # and set dimension-dependent arguments.
-                string(REGEX MATCH "\\.[0-9]+(x[0-9]+)+$" _sizes "${_mesh}")
-                string(REGEX MATCHALL "[0-9]+" _sizes ${_sizes})
-                list(LENGTH _sizes _ndim)
-
-                if(_ndim EQUAL 2)
-                  set(_center 0.7 0.9)
-                elseif(_ndim EQUAL 3)
-                  set(_center 0.7 0.9 0.5)
+            foreach(_pol ${AXOM_EXECUTION_POLICIES})
+                # sets the number of threads for the omp policy; leave empty for non-omp policies
+                set(_num_threads)
+                if(_pol STREQUAL "omp")
+                    set(_num_threads ${AXOM_TEST_NUM_OMP_THREADS})
                 endif()
 
-                set(_test "quest_distributed_closest_point_run_${_ndim}D_${_pol}_${_mesh}")
+                set(_test "quest_distributed_closest_point_run_${_dim}D_${_pol}_${_mesh}")
                 axom_add_test(
                     NAME    ${_test}
                     COMMAND quest_distributed_distance_query_ex
                                 --mesh-file ${quest_data_dir}/${_mesh}.root
-                                --long-point-count 60
-                                --center ${_center}
-                                --radius 0.9
-                                --lat-point-count 30
-                                --obj-domain-count-range 0 2
+                                --object-mesh-file ${_object_mesh}
                                 --dist-threshold .3
-                                --no-random-spacing
-                                --check-results
                                 --dynamic-distance-filtering
                                 --policy ${_pol}
-                                --object-file dcp_object_mesh_${_ndim}d_${_pol}_${_mesh}
-                                --distance-file dcp_closest_point_2d_${_pol}_${_mesh}
+                                --distance-file dcp_closest_point_${_dim}d_${_pol}_${_mesh}
                     NUM_MPI_TASKS ${_nranks}
                     NUM_OMP_THREADS ${_num_threads})
+                set_tests_properties(${_test}
+                    PROPERTIES
+                    PASS_REGULAR_EXPRESSION "Analytic verification for '${_shape}' found 0 errors")
 
-                if(_pol STREQUAL "seq" AND (_mesh STREQUAL "mdmesh.2x1" OR _mesh STREQUAL "mdmesh.2x2x1"))
+                if(_pol STREQUAL "seq" AND
+                   (_mesh STREQUAL "mdmesh.2x1" OR _mesh STREQUAL "mdmesh.2x2x1"))
                     # Keep fallback coverage for the non-dynamic filtering path
                     # with one 2D and one 3D seq case.
                     set(_static_test "${_test}_no_dynamic_distance_filtering")
                     axom_add_test(
                         NAME    ${_static_test}
                         COMMAND quest_distributed_distance_query_ex
                                     --mesh-file ${quest_data_dir}/${_mesh}.root
-                                    --long-point-count 60
-                                    --center ${_center}
-                                    --radius 0.9
-                                    --lat-point-count 30
-                                    --obj-domain-count-range 0 2
+                                    --object-mesh-file ${_object_mesh}
                                     --dist-threshold .3
-                                    --no-random-spacing
-                                    --check-results
                                     --no-dynamic-distance-filtering
                                     --policy ${_pol}
-                                    --object-file dcp_object_mesh_${_ndim}d_${_pol}_${_mesh}_no_dynamic
-                                    --distance-file dcp_closest_point_2d_${_pol}_${_mesh}_no_dynamic
+                                    --distance-file dcp_closest_point_${_dim}d_${_pol}_${_mesh}_no_dynamic
                         NUM_MPI_TASKS ${_nranks}
                         NUM_OMP_THREADS ${_num_threads})
+                    set_tests_properties(${_static_test}
+                        PROPERTIES
+                        PASS_REGULAR_EXPRESSION "Analytic verification for '${_shape}' found 0 errors")
                 endif()
             endforeach()
         endforeach()
 
-        unset(optional_dependency)
+        foreach(_pol ${AXOM_EXECUTION_POLICIES})
+            # sets the number of threads for the omp policy; leave empty for non-omp policies
+            set(_num_threads)
+            if(_pol STREQUAL "omp")
+                set(_num_threads ${AXOM_TEST_NUM_OMP_THREADS})
+            endif()
+
+            set(_test "quest_distributed_closest_point_run_2D_${_pol}_single_domain_object")
+            axom_add_test(
+                NAME    ${_test}
+                COMMAND quest_distributed_distance_query_ex
+                            --mesh-file ${quest_data_dir}/mdmesh.2x1.root
+                            --object-mesh-file ${quest_data_dir}/dcp_object_circle_single_domain.root
+                            --dist-threshold .3
+                            --policy ${_pol}
+                            --distance-file dcp_closest_point_2d_${_pol}_single_domain_object
+                NUM_MPI_TASKS ${_nranks}
+                NUM_OMP_THREADS ${_num_threads})
+            set_tests_properties(${_test}
+                PROPERTIES
+                PASS_REGULAR_EXPRESSION "Analytic verification for 'circle' found 0 errors")
+        endforeach()
+
+        if("seq" IN_LIST AXOM_EXECUTION_POLICIES)
+            set(_test "quest_distributed_closest_point_memory_instrumentation")
+            axom_add_test(
+                NAME    ${_test}
+                COMMAND quest_distributed_distance_query_ex
+                            --mesh-file ${quest_data_dir}/mdmesh.2x1.root
+                            --object-mesh-file ${quest_data_dir}/dcp_object_circle.root
+                            --dist-threshold .3
+                            --policy seq
+                            --track-memory
+                            --trim-after-query
+                            --sample-memory-ms 1
+                            --distance-file dcp_closest_point_2d_seq_memory_instrumentation
+                NUM_MPI_TASKS ${_nranks})
+            set_tests_properties(${_test}
+                PROPERTIES
+                PASS_REGULAR_EXPRESSION "peak RSS during phase")
+        endif()
+
+        unset(_dim)
+        unset(_mesh)
+        unset(_meshes)
+        unset(_ndim)
+        unset(_num_threads)
+        unset(_object_mesh)
+        unset(_pol)
         unset(_nranks)
+        unset(_shape)
+        unset(_sizes)
         unset(_test)
         unset(_static_test)
     endif()