Original commit message:
------------------------
Parallel IO: New collated file format
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.
e.g. (fvc::interpolate(HbyA) & mesh.Sf()) -> fvc::flux(HbyA)
This removes the need to create an intermediate face-vector field when
computing fluxes which is more efficient, reduces the peak storage and
improved cache coherency in addition to providing a simpler and cleaner
API.
The boundary conditions of HbyA are now constrained by the new "constrainHbyA"
function which applies the velocity boundary values for patches for which the
velocity cannot be modified by assignment and pressure extrapolation is
not specified via the new
"fixedFluxExtrapolatedPressureFvPatchScalarField".
The new function "constrainPressure" sets the pressure gradient
appropriately for "fixedFluxPressureFvPatchScalarField" and
"fixedFluxExtrapolatedPressureFvPatchScalarField" boundary conditions to
ensure the evaluated flux corresponds to the known velocity values at
the boundary.
The "fixedFluxPressureFvPatchScalarField" boundary condition operates
exactly as before, ensuring the correct flux at fixed-flux boundaries by
compensating for the body forces (gravity in particular) with the
pressure gradient.
The new "fixedFluxExtrapolatedPressureFvPatchScalarField" boundary
condition may be used for cases with or without body-forces to set the
pressure gradient to compensate not only for the body-force but also the
extrapolated "HbyA" which provides a second-order boundary condition for
pressure. This is useful for a range a problems including impinging
flow, extrapolated inlet conditions with body-forces or for highly
viscous flows, pressure-induced separation etc. To test this boundary
condition at walls in the motorBike tutorial case set
lowerWall
{
type fixedFluxExtrapolatedPressure;
}
motorBikeGroup
{
type fixedFluxExtrapolatedPressure;
}
Currently the new extrapolated pressure boundary condition is supported
for all incompressible and sub-sonic compressible solvers except those
providing implicit and tensorial porosity support. The approach will be
extended to cover these solvers and options in the future.
Note: the extrapolated pressure boundary condition is experimental and
requires further testing to assess the range of applicability,
stability, accuracy etc.
Henry G. Weller
CFD Direct Ltd.
Moved file path handling to regIOobject and made it type specific so
now every object can have its own rules. Examples:
- faceZones are now processor local (and don't search up anymore)
- timeStampMaster is now no longer hardcoded inside IOdictionary
(e.g. uniformDimensionedFields support it as well)
- the distributedTriSurfaceMesh is properly processor-local; no need
for fileModificationChecking manipulation.
Solver for the magnetic field generated by permanent magnets.
A Poisson's equation for the magnetic scalar potential psi is solved
from which the magnetic field intensity H and magnetic flux density B
are obtained.
deltaT().value() to deltaTValue()
and
deltaT0().value() to deltaT0Value()
across the whole code - faster to return especially if being used
often, in each call to a submodel for example.
- change system/controlDict to use functions {..} instead of functions (..);
* This is internally more efficient
- fixed formatting of system/controlDict functions entry
- pedantic change: use 'return 0' instead of 'return(0)' in the applications,
since return is a C/C++ keyword, not a function.
- this (now deprecated) idiom:
for (runTime++; !runTime.end(); runTime++) { ... }
has a few problems:
* stop-on-next-write will be off-by-one (ie, doesn't work)
* function objects are not executed on exit with runTime.end()
Fixing these problems is not really possible.
- this idiom
while (runTime.run())
{
runTime++;
...
}
works without the above problems.
