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
Now if a <field> file does not exist first the compressed <field>.gz file is
searched for and if that also does not exist the <field>.orig file is searched
for.
This simplifies case setup and run scripts as now setField for example can read
the <field>.orig file directly and generate the <field> file from it which is
then read by the solver. Additionally the cleanCase function used by
foamCleanCase and the Allclean scripts automatically removed <field> files if
there is a corresponding <field>.orig file. So now there is no need for the
Allrun scripts to copy <field>.orig files into <field> or for the Allclean
scripts to explicitly remove them.
When etc/controlDict::writeJobInfo is set to 1 jobInfo.<pid> files are written
to the case directory containing a summary of the execution of the job containing
startDate
startTime
userName
foamVersion
code
argList
currentDir
PPID
PGID
foamBuild
root
case
nProcs
When the job completes the following additional entries are written:
cpuTime
endDate
endTime
termination
The original etc/controlDict::writeJobInfo control has been renamed writeJobControl and when set
to 1 writes the ~/OpenFOAM/jobControl/runningJobs and finishedJobs files for job control.
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.
with the more general and flexible 'postProcess' utility and '-postProcess' solver option
Rationale
---------
Both the 'postProcess' utility and '-postProcess' solver option use the
same extensive set of functionObjects available for data-processing
during the run avoiding the substantial code duplication necessary for
the 'foamCalc' and 'postCalc' utilities and simplifying maintenance.
Additionally consistency is guaranteed between solver data processing
and post-processing.
The functionObjects have been substantially re-written and generalized
to simplify development and encourage contribution.
Configuration
-------------
An extensive set of simple functionObject configuration files are
provided in
OpenFOAM-dev/etc/caseDicts/postProcessing
and more will be added in the future. These can either be copied into
'<case>/system' directory and included into the 'controlDict.functions'
sub-dictionary or included directly from 'etc/caseDicts/postProcessing'
using the '#includeEtc' directive or the new and more convenient
'#includeFunc' directive which searches the
'<etc>/caseDicts/postProcessing' directories for the selected
functionObject, e.g.
functions
{
#includeFunc Q
#includeFunc Lambda2
}
'#includeFunc' first searches the '<case>/system' directory in case
there is a local configuration.
Description of #includeFunc
---------------------------
Specify a functionObject dictionary file to include, expects the
functionObject name to follow (without quotes).
Search for functionObject dictionary file in
user/group/shipped directories.
The search scheme allows for version-specific and
version-independent files using the following hierarchy:
- \b user settings:
- ~/.OpenFOAM/\<VERSION\>/caseDicts/postProcessing
- ~/.OpenFOAM/caseDicts/postProcessing
- \b group (site) settings (when $WM_PROJECT_SITE is set):
- $WM_PROJECT_SITE/\<VERSION\>/caseDicts/postProcessing
- $WM_PROJECT_SITE/caseDicts/postProcessing
- \b group (site) settings (when $WM_PROJECT_SITE is not set):
- $WM_PROJECT_INST_DIR/site/\<VERSION\>/caseDicts/postProcessing
- $WM_PROJECT_INST_DIR/site/caseDicts/postProcessing
- \b other (shipped) settings:
- $WM_PROJECT_DIR/etc/caseDicts/postProcessing
An example of the \c \#includeFunc directive:
\verbatim
#includeFunc <funcName>
\endverbatim
postProcess
-----------
The 'postProcess' utility and '-postProcess' solver option provide the
same set of controls to execute functionObjects after the run either by
reading a specified set of fields to process in the case of
'postProcess' or by reading all fields and models required to start the
run in the case of '-postProcess' for each selected time:
postProcess -help
Usage: postProcess [OPTIONS]
options:
-case <dir> specify alternate case directory, default is the cwd
-constant include the 'constant/' dir in the times list
-dict <file> read control dictionary from specified location
-field <name> specify the name of the field to be processed, e.g. U
-fields <list> specify a list of fields to be processed, e.g. '(U T p)' -
regular expressions not currently supported
-func <name> specify the name of the functionObject to execute, e.g. Q
-funcs <list> specify the names of the functionObjects to execute, e.g.
'(Q div(U))'
-latestTime select the latest time
-newTimes select the new times
-noFunctionObjects
do not execute functionObjects
-noZero exclude the '0/' dir from the times list, has precedence
over the -withZero option
-parallel run in parallel
-region <name> specify alternative mesh region
-roots <(dir1 .. dirN)>
slave root directories for distributed running
-time <ranges> comma-separated time ranges - eg, ':10,20,40:70,1000:'
-srcDoc display source code in browser
-doc display application documentation in browser
-help print the usage
pimpleFoam -postProcess -help
Usage: pimpleFoam [OPTIONS]
options:
-case <dir> specify alternate case directory, default is the cwd
-constant include the 'constant/' dir in the times list
-dict <file> read control dictionary from specified location
-field <name> specify the name of the field to be processed, e.g. U
-fields <list> specify a list of fields to be processed, e.g. '(U T p)' -
regular expressions not currently supported
-func <name> specify the name of the functionObject to execute, e.g. Q
-funcs <list> specify the names of the functionObjects to execute, e.g.
'(Q div(U))'
-latestTime select the latest time
-newTimes select the new times
-noFunctionObjects
do not execute functionObjects
-noZero exclude the '0/' dir from the times list, has precedence
over the -withZero option
-parallel run in parallel
-postProcess Execute functionObjects only
-region <name> specify alternative mesh region
-roots <(dir1 .. dirN)>
slave root directories for distributed running
-time <ranges> comma-separated time ranges - eg, ':10,20,40:70,1000:'
-srcDoc display source code in browser
-doc display application documentation in browser
-help print the usage
The functionObjects to execute may be specified on the command-line
using the '-func' option for a single functionObject or '-funcs' for a
list, e.g.
postProcess -func Q
postProcess -funcs '(div(U) div(phi))'
In the case of 'Q' the default field to process is 'U' which is
specified in and read from the configuration file but this may be
overridden thus:
postProcess -func 'Q(Ua)'
as is done in the example above to calculate the two forms of the divergence of
the velocity field. Additional fields which the functionObjects may depend on
can be specified using the '-field' or '-fields' options.
The 'postProcess' utility can only be used to execute functionObjects which
process fields present in the time directories. However, functionObjects which
depend on fields obtained from models, e.g. properties derived from turbulence
models can be executed using the '-postProcess' of the appropriate solver, e.g.
pisoFoam -postProcess -func PecletNo
or
sonicFoam -postProcess -func MachNo
In this case all required fields will have already been read so the '-field' or
'-fields' options are not be needed.
Henry G. Weller
CFD Direct Ltd.
Starting from an initial buffer size of 256 it is incremented in steps
of 256 upto the maximum of 4096 as required.
Based on patch provided by Bruno Santos
Resolves bug-report http://www.openfoam.org/mantisbt/view.php?id=1944
This malloc overrides the one provided by GLIBC and calls mallocNan
which initializes the allocated block of memory to NaN if enabled by the
FOAM_SETNAN environment variable.
in particular to pick-up the DebugSwitches from system/controlDict at
global construction time.
Disadvantage is that system/controlDict is only picked-up if the
OpenFOAM application is executed IN the case directory. The directory
provided by the -case option is not yet known as the arguments have not
yet been parsed.
To compile with 64bit labels set
WM_LABEL_SIZE=64
in ~/OpenFOAM/dev/prefs.sh
source ~/.bashrc
then Allwmake in OpenFOAM-dev.
This will build into for example OpenFOAM-dev/platforms/linux64ClangDPInt64Opt
If WM_LABEL_SIZE is unset or set to 32:
WM_LABEL_SIZE=32
the build would be placed into OpenFOAM-dev/platforms/linux64ClangDPInt32Opt
Thus both 32bit and 64bit label builds can coexist without problem.
