Move the fake usnic IBV provider out of common/verbs and into a new
common/verbs_usnic component that is always statically linked into
libopen-pal. The fake provider is registered with libibverbs at run
time, but there is no *un*register IBV API. Hence, we can't let the
code containing this provider be dlclosed -- which means it needs to
be statically linked into libopen-pal.
Fixesopen-mpi/ompi#1060.
libibverbs will complain to stderr if it sees device entries in
/sys/class/infiniband for which it has no userspace plugins.
The Cisco usNIC device no longer exports a verbs interface, thereby
causing libibverbs to emit this annoying stderr warning.
To avoid this, use the public ibv API to register a "fake" libibverbs
driver at run-time (right after we call ibv_fork_init(), but --
critically -- *before* we call ibv_get_device_list()). The purpose of
this driver is solely to convince libibverbs that there *is* a driver
for /sys/class/infininband/usnic_verbs devices. ...although this
driver will never return a valid ibv context (and therefore will never
be used).
call the opal_common_verbs_mca_register function to make sure that
opal_common_verbs_want_fork_support mca parameter is created and therefore
can be used to control the fork support.
In order to have an effect, ibv_fork_init should be called in the
beginning of the verbs initialization flow - before the calls to the
ibv_create_qp and ibv_create_cq verbs.
These functions are called from the oob/ud code and by the time the
other verbs components (btl openib, pml yalla, ...) call ibv_fork_init,
it's too late. This commit forces the call to ibv_fork_init (if it's
requested) right at the beginning of all the components that are using
verbs.
(ibv_fork_init() can be safely called multiple times)
This commit also removes the btl_openib_want_fork_support mca parameter
and adds a new mca parameter instead - opal_verbs_want_fork_support.
Through this new parameter, fork support may be requested for ALL
components.
The default value for this parameter is set to 1.
Before this commit the btl_openib_want_fork_support parameter didn't
provide fork support for the openib btl if its value was set to 1.
(because when openib called ibv_fork_init, it was already after the
calls to ibv_create_* in oob/ud and thereofre it failed).
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
