This method waits until all the threads have completed IO operations and
then clears any cached information about the files on disk. This
replaces the deactivation of threading by means of zeroing the buffer
size when writing and reading of a file happen in sequence. It also
allows paraFoam to update the list of available times.
Patch contributed by Mattijs Janssens
Resolves bug report https://bugs.openfoam.org/view.php?id=2962
Improvements to existing functionality
--------------------------------------
- MPI is initialised without thread support if it is not needed e.g. uncollated
- Use native c++11 threading; avoids problem with static destruction order.
- etc/cellModels now only read if needed.
- etc/controlDict can now be read from the environment variable FOAM_CONTROLDICT
- Uniform files (e.g. '0/uniform/time') are now read only once on the master only
(with the masterUncollated or collated file handlers)
- collated format writes to 'processorsNNN' instead of 'processors'. The file
format is unchanged.
- Thread buffer and file buffer size are no longer limited to 2Gb.
The global controlDict file contains parameters for file handling. Under some
circumstances, e.g. running in parallel on a system without NFS, the user may
need to set some parameters, e.g. fileHandler, before the global controlDict
file is read from file. To support this, OpenFOAM now allows the global
controlDict to be read as a string set to the FOAM_CONTROLDICT environment
variable.
The FOAM_CONTROLDICT environment variable can be set to the content the global
controlDict file, e.g. from a sh/bash shell:
export FOAM_CONTROLDICT=$(foamDictionary $FOAM_ETC/controlDict)
FOAM_CONTROLDICT can then be passed to mpirun using the -x option, e.g.:
mpirun -np 2 -x FOAM_CONTROLDICT simpleFoam -parallel
Note that while this avoids the need for NFS to read the OpenFOAM configuration
the executable still needs to load shared libraries which must either be copied
locally or available via NFS or equivalent.
New: Multiple IO ranks
----------------------
The masterUncollated and collated fileHandlers can now use multiple ranks for
writing e.g.:
mpirun -np 6 simpleFoam -parallel -ioRanks '(0 3)'
In this example ranks 0 ('processor0') and 3 ('processor3') now handle all the
I/O. Rank 0 handles 0,1,2 and rank 3 handles 3,4,5. The set of IO ranks should always
include 0 as first element and be sorted in increasing order.
The collated fileHandler uses the directory naming processorsNNN_XXX-YYY where
NNN is the total number of processors and XXX and YYY are first and last
processor in the rank, e.g. in above example the directories would be
processors6_0-2
processors6_3-5
and each of the collated files in these contains data of the local ranks
only. The same naming also applies when e.g. running decomposePar:
decomposePar -fileHandler collated -ioRanks '(0 3)'
New: Distributed data
---------------------
The individual root directories can be placed on different hosts with different
paths if necessary. In the current framework it is necessary to specify the
root per slave process but this has been simplified with the option of specifying
the root per host with the -hostRoots command line option:
mpirun -np 6 simpleFoam -parallel -ioRanks '(0 3)' \
-hostRoots '("machineA" "/tmp/" "machineB" "/tmp")'
The hostRoots option is followed by a list of machine name + root directory, the
machine name can contain regular expressions.
New: hostCollated
-----------------
The new hostCollated fileHandler automatically sets the 'ioRanks' according to
the host name with the lowest rank e.g. to run simpleFoam on 6 processors with
ranks 0-2 on machineA and ranks 3-5 on machineB with the machines specified in
the hostfile:
mpirun -np 6 --hostfile hostfile simpleFoam -parallel -fileHandler hostCollated
This is equivalent to
mpirun -np 6 --hostfile hostfile simpleFoam -parallel -fileHandler collated -ioRanks '(0 3)'
This example will write directories:
processors6_0-2/
processors6_3-5/
A typical example would use distributed data e.g. no two nodes, machineA and
machineB, each with three processes:
decomposePar -fileHandler collated -case cavity
# Copy case (constant/*, system/*, processors6/) to master:
rsync -a cavity machineA:/tmp/
# Create root on slave:
ssh machineB mkdir -p /tmp/cavity
# Run
mpirun --hostfile hostfile icoFoam \
-case /tmp/cavity -parallel -fileHandler hostCollated \
-hostRoots '("machineA" "/tmp" "machineB" "/tmp")'
Contributed by Mattijs Janssens
When an OpenFOAM simulation runs in parallel, the data for decomposed fields and
mesh(es) has historically been stored in multiple files within separate
directories for each processor. Processor directories are named 'processorN',
where N is the processor number.
This commit introduces an alternative "collated" file format where the data for
each decomposed field (and mesh) is collated into a single file, which is
written and read on the master processor. The files are stored in a single
directory named 'processors'.
The new format produces significantly fewer files - one per field, instead of N
per field. For large parallel cases, this avoids the restriction on the number
of open files imposed by the operating system limits.
The file writing can be threaded allowing the simulation to continue running
while the data is being written to file. NFS (Network File System) is not
needed when using the the collated format and additionally, there is an option
to run without NFS with the original uncollated approach, known as
"masterUncollated".
The controls for the file handling are in the OptimisationSwitches of
etc/controlDict:
OptimisationSwitches
{
...
//- Parallel IO file handler
// uncollated (default), collated or masterUncollated
fileHandler uncollated;
//- collated: thread buffer size for queued file writes.
// If set to 0 or not sufficient for the file size threading is not used.
// Default: 2e9
maxThreadFileBufferSize 2e9;
//- masterUncollated: non-blocking buffer size.
// If the file exceeds this buffer size scheduled transfer is used.
// Default: 2e9
maxMasterFileBufferSize 2e9;
}
When using the collated file handling, memory is allocated for the data in the
thread. maxThreadFileBufferSize sets the maximum size of memory in bytes that
is allocated. If the data exceeds this size, the write does not use threading.
When using the masterUncollated file handling, non-blocking MPI communication
requires a sufficiently large memory buffer on the master node.
maxMasterFileBufferSize sets the maximum size in bytes of the buffer. If the
data exceeds this size, the system uses scheduled communication.
The installation defaults for the fileHandler choice, maxThreadFileBufferSize
and maxMasterFileBufferSize (set in etc/controlDict) can be over-ridden within
the case controlDict file, like other parameters. Additionally the fileHandler
can be set by:
- the "-fileHandler" command line argument;
- a FOAM_FILEHANDLER environment variable.
A foamFormatConvert utility allows users to convert files between the collated
and uncollated formats, e.g.
mpirun -np 2 foamFormatConvert -parallel -fileHandler uncollated
An example case demonstrating the file handling methods is provided in:
$FOAM_TUTORIALS/IO/fileHandling
The work was undertaken by Mattijs Janssens, in collaboration with Henry Weller.
terms of the local barycentric coordinates of the current tetrahedron,
rather than the global coordinate system.
Barycentric tracking works on any mesh, irrespective of mesh quality.
Particles do not get "lost", and tracking does not require ad-hoc
"corrections" or "rescues" to function robustly, because the calculation
of particle-face intersections is unambiguous and reproducible, even at
small angles of incidence.
Each particle position is defined by topology (i.e. the decomposed tet
cell it is in) and geometry (i.e. where it is in the cell). No search
operations are needed on restart or reconstruct, unlike when particle
positions are stored in the global coordinate system.
The particle positions file now contains particles' local coordinates
and topology, rather than the global coordinates and cell. This change
to the output format is not backwards compatible. Existing cases with
Lagrangian data will not restart, but they will still run from time
zero without any modification. This change was necessary in order to
guarantee that the loaded particle is valid, and therefore
fundamentally prevent "loss" and "search-failure" type bugs (e.g.,
2517, 2442, 2286, 1836, 1461, 1341, 1097).
The tracking functions have also been converted to function in terms
of displacement, rather than end position. This helps remove floating
point error issues, particularly towards the end of a tracking step.
Wall bounded streamlines have been removed. The implementation proved
incompatible with the new tracking algorithm. ParaView has a surface
LIC plugin which provides equivalent, or better, functionality.
Additionally, bug report <https://bugs.openfoam.org/view.php?id=2517>
is resolved by this change.
Using
decomposePar -copyZero
The mesh is decomposed as usual but the '0' directory is recursively copied to
the 'processor.*' directories rather than decomposing the fields. This is a
convenient option to handle cases where the initial field files are generic and
can be used for serial or parallel running. See for example the
incompressible/simpleFoam/motorBike tutorial case.
splitMeshRegions: handle flipping of faces for surface fields
subsetMesh: subset dimensionedFields
decomposePar: use run-time selection of decomposition constraints. Used to
keep cells on particular processors. See the decomposeParDict in
$FOAM_UTILITIES/parallel/decomposePar:
- preserveBaffles: keep baffle faces on same processor
- preserveFaceZones: keep faceZones owner and neighbour on same processor
- preservePatches: keep owner and neighbour on same processor. Note: not
suitable for cyclicAMI since these are not coupled on the patch level
- singleProcessorFaceSets: keep complete faceSet on a single processor
- refinementHistory: keep cells originating from a single cell on the
same processor.
decomposePar: clean up decomposition of refinement data from snappyHexMesh
reconstructPar: reconstruct refinement data (refineHexMesh, snappyHexMesh)
reconstructParMesh: reconstruct refinement data (refineHexMesh, snappyHexMesh)
redistributePar:
- corrected mapping surfaceFields
- adding processor patches in order consistent with decomposePar
argList: check that slaves are running same version as master
fvMeshSubset: move to dynamicMesh library
fvMeshDistribute:
- support for mapping dimensionedFields
- corrected mapping of surfaceFields
parallel routines: allow parallel running on single processor
Field: support for
- distributed mapping
- mapping with flipping
mapDistribute: support for flipping
AMIInterpolation: avoid constructing localPoints
These new names are more consistent and logical because:
primitiveField():
primitiveFieldRef():
Provides low-level access to the Field<Type> (primitive field)
without dimension or mesh-consistency checking. This should only be
used in the low-level functions where dimensional consistency is
ensured by careful programming and computational efficiency is
paramount.
internalField():
internalFieldRef():
Provides access to the DimensionedField<Type, GeoMesh> of values on
the internal mesh-type for which the GeometricField is defined and
supports dimension and checking and mesh-consistency checking.
To be used instead of zeroGradientFvPatchField for temporary fields for
which zero-gradient extrapolation is use to evaluate the boundary field
but avoiding fields derived from temporary field using field algebra
inheriting the zeroGradient boundary condition by the reuse of the
temporary field storage.
zeroGradientFvPatchField should not be used as the default patch field
for any temporary fields and should be avoided for non-temporary fields
except where it is clearly appropriate;
extrapolatedCalculatedFvPatchField and calculatedFvPatchField are
generally more suitable defaults depending on the manner in which the
boundary values are specified or evaluated.
The entire OpenFOAM-dev code-base has been updated following the above
recommendations.
Henry G. Weller
CFD Direct
