\subsection options_smpi_privatization smpi/privatization: Automatic privatization of global variables
-MPI executables are usually meant to be executed in separated processes, but SMPI is
-executed in only one process. Global variables from executables will be placed
-in the same memory zone and shared between processes, causing intricate bugs.
-Several options are possible to avoid this, as described in the main
-<a href="https://hal.inria.fr/hal-01415484">SMPI publication</a>.
-SimGrid provides two ways of automatically privatizing the globals,
-and this option allows to choose between them.
+MPI executables are usually meant to be executed in separated
+processes, but SMPI is executed in only one process. Global variables
+from executables will be placed in the same memory zone and shared
+between processes, causing intricate bugs. Several options are
+possible to avoid this, as described in the main
+<a href="https://hal.inria.fr/hal-01415484">SMPI publication</a> and in
+the @ref SMPI_what_globals "SMPI documentation". SimGrid provides two
+ways of automatically privatizing the globals, and this option allows
+to choose between them.
+
+ - <b>no</b> (default when not using smpirun): Do not automatically privatize variables.
+ Pass \c -no-privatize to smpirun to disable this feature.
+ - <b>mmap</b> or <b>yes</b> (default when using smpirun):
+ Runtime automatic switching of the data segments.
+ - <b>dlopen</b> (faster but less tested): Link multiple times against the binary.
\warning
This configuration option cannot be set in your platform file. You can only
pass it as an argument to smpirun.
- - <b>no</b> (default when not using smpirun): Do not automatically privatize variables.
- - <b>mmap</b> or <b>yes</b> (default when using smpirun): Runtime automatic switching of the data segments.\n
- SMPI stores a copy of each global data segment for each process,
- and at each context switch replaces the actual data with its copy
- from the right process. No copy actually occures as this mechanism
- uses mmap for efficiency. As such, it is for now limited to
- systems supporting this functionnality (all Linux and most BSD).\n
- Another limitation is that SMPI only accounts for global variables
- defined in the executable. If the processes use external global
- variables from dynamic libraries, they won't be switched
- correctly. The easiest way to solve this is to statically link
- against the library with these globals (but you should never
- statically link against the simgrid library itself).
- - <b>dlopen</b> (faster but less tested): Link multiple times against the binary.\n
- Asks SMPI to load several copies of the same binary in memory, so
- that the global variables get naturally duplicated. Since the
- dynamic linker refuses to link the same file several times, the
- binary is copied in a temporary file before being dl-loaded.\n
- This approach greatly speeds up the context switching, down to
- about 40 CPU cycles with our raw contextes, instead of requesting
- several syscalls with the \c mmap approach. Another advantage is
- that it permits to run the SMPI contexts in parallel, which is
- obviously not possible with the \c mmap approach.\n
- Further work may be possible to alleviate the memory and disk
- overconsumption. It seems that we could
- <a href="https://lwn.net/Articles/415889/">punch holes</a>
- in the files before dl-loading them to remove the code and
- constants, and mmap these area onto a unique copy. If done
- correctly, this would reduce the disk- and memory- usage to the
- bare minimum, and would also reduce the pressure on the CPU
- instruction cache.\n
- For now, this still requires any external dependencies to be
- statically linked into your application. We could extend this
- mechanism to change this, but we never felt the need so far.
-
\subsection options_model_smpi_detached Simulating MPI detached send
This threshold specifies the size in bytes under which the send will return