The direct modex operation is slow, especially at scale for even modestly-connected applications. Likewise, blocking in MPI_Init while we wait for a full modex to complete takes too long. However, as George pointed out, there is a middle ground here. We could kickoff the modex operation in the background, and then trap any modex_recv's until the modex completes and the data is delivered. For most non-benchmark apps, this may prove to be the best of the available options as they are likely to perform other (non-communicating) setup operations after MPI_Init, and so there is a reasonable chance that the modex will actually be done before the first modex_recv gets called.
Once we get instant-on-enabled hardware, this won't be necessary. Clearly, zero time will always out-perform the time spent doing a modex. However, this provides a decent compromise in the interim.
This PR changes the default settings of a few relevant params to make "background modex" the default behavior:
* pmix_base_async_modex -> defaults to true
* pmix_base_collect_data -> continues to default to true (no change)
* async_mpi_init - defaults to true. Note that the prior code attempted to base the default setting of this value on the setting of pmix_base_async_modex. Unfortunately, the pmix value isn't set prior to setting async_mpi_init, and so that attempt failed to accomplish anything.
The logic in MPI_Init is:
* if async_modex AND collect_data are set, AND we have a non-blocking fence available, then we execute the background modex operation
* if async_modex is set, but collect_data is false, then we simply skip the modex entirely - no fence is performed
* if async_modex is not set, then we block until the fence completes (regardless of collecting data or not)
* if we do NOT have a non-blocking fence (e.g., we are not using PMIx), then we always perform the full blocking modex operation.
* if we do perform the background modex, and the user requested the barrier be performed at the end of MPI_Init, then we check to see if the modex has completed when we reach that point. If it has, then we execute the barrier. However, if the modex has NOT completed, then we block until the modex does complete and skip the extra barrier. So we never perform two barriers in that case.
HTH
Ralph
Signed-off-by: Ralph Castain <rhc@open-mpi.org>
The usNIC BTL does not use more than 1 iov, so be sure to set it to 1
so that we don't allocate cq/rq/sq entries based on a default (i.e.,
>1) number of iovs per entry.
Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
This commit recategorizes several mpirun arguments,
and moves the information for mpirun --help arguments
to the bottom of the general help message. I also
added the OPAL_CMD_LINE_OTYPE field to two commands
that were missed initially because they were not
in the same area as the others.
Signed-off-by: Nathaniel Graham <ngraham@lanl.gov>
since Open MPI now requires a C99, and ptrdiff_t type is part of C99,
there is no more need for the abstract OPAL_PTRDIFF_TYPE type.
Thanks George, Nathan and Paul for the help.
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
since Open MPI now requires a C99, and ptrdiff_t type is part of C99,
there is no more need for the abstract OPAL_PTRDIFF_TYPE type.
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
* Complete rewrite of opal_pointer_array
Instead of a cache oblivious linear search use a bits array
to speed up the management of the free space. As a result we
slightly increase the memory used by the structure, but we get a
significant boost in performance.
Signed-off-by: George Bosilca <bosilca@icl.utk.edu>
* Do not register datatypes in the f2c translation table.
The registration is now done up into the Fortran layer, by
forcing a call to MPI_Type_c2f.
Signed-off-by: George Bosilca <bosilca@icl.utk.edu>
With this, libs (e.g., "-ldl") are not added to the wrapper LIBS
flags. This may work on some platforms, but on at least RHEL 7.3, it
does not (i.e., compiling MPI applications fails because it can't find
dlopen).
Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
Adds:
- enabling/disabling of timings throught environment variable `OMPI_TIMING_ENABLE`
- output format: [file name]:[function name]:[description]: avg/min/max
- dynamically extending array of results for case then inited size was exhausted
- catch and collect errors
- cleanup
Note:
For use feature need to configure with `--enable-timings`
and set env `OMPI_TIMING_ENABLE = 1`
Signed-off-by: Boris Karasev <karasev.b@gmail.com>
This commit adds new timing feature that uses environment variables to
expose timing information. This allows easy access to this data (if
timing is enabled) from any other part of the application for the subsequent
postprocessing.
In particular this will be integrated with OMPI-level timing framework that
whill use MPI_Reduce functionality to provide more compact and easy-to use
information.
This commit also adds the example of usage of this framework by annotating
rte_init function. The result is not used anywhere for now. It will be
postprocessed in subsequent commits.
NOTE: that functionality is currently disabled untill it will be verified at runtime
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
This commit adds a "parsable" option to the help
arguments, which prints out a machine readable
list of all the mpirun options.
Fixes#3279
Signed-off-by: Nathaniel Graham <ngraham@lanl.gov>
This commit modifies the output from the mpirun --help
command. The options have been split into groups, to
make the output smaller and more readable. The groups
are: general, debug, output, input, mapping, ranking,
binding, devel, compatibility, launch, dvm, and
unsupported. There is also a special "full" command
that can be used to get the old behaviour of printing
out all of the options. Unsupported options may only
be seen with this full output.
This commit also adds a special case for the help
argument. It makes it possible for the user to
enter 0 or 1 arguments instead of having to always
enter an argument. This defaults to printing out
the "general" help options so the user can then
see what help arguments there are.
Signed-off-by: Nathaniel Graham <ngraham@lanl.gov>
Set the daemons' state to "running" and mark them as "alive" by default when constructing the nidmap
Get the DVM running again
Fix direct modex by eliminating race condition caused by releasing data while sending it
Up the size limit before compressing
Signed-off-by: Ralph Castain <rhc@open-mpi.org>
Commit fec519a793a2afcfd1ebcb3fa7c151bd30893835 broke the ability to
run autogen.pl in a distribution tarball. This commit restores that
ability by also distributing opal/mca/hwloc/autogen.options in the
tarball.
Skipping CI because CI does not test this functionality:
[skip ci]
bot:notest
Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
Several component-specific functions were named with a prefix of
"opal_timer_base", which was quite confusing. Rename them to have a
prefix "opal_timer_linux" to make it clear that they are here in this
component (and different than *actual* opal_timer_base symbols).
Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
This commit makes datagram checks time based and reduces their
frequency when only the wildcard datagram is posted. This change
improves latency on knl systems.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
This commit removes the local operation count check from the local SMSG
completion queue. This check was leading to hangs due to an undocumented
feature of the ugni library. The local SMSG CQ is used to send credit
return messages back to the sender. The ugni library never checks for
the completion itself but relying on the SMSG user to periodically
check the CQ.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
This commit updates the ugni btl to make use of multiple device
contexts to improve the multi-threaded RMA performance. This commit
contains the following:
- Cleanup the endpoint structure by removing unnecessary field. The
structure now also contains all the fields originally handled by the
common/ugni endpoint.
- Clean up the fragment allocation code to remove the need to
initialize the my_list member of the fragment structure. This
member is not initialized by the free list initializer function.
- Remove the (now unused) common/ugni component. btl/ugni no longer
need the component. common/ugni was originally split out of
btl/ugni to support bcol/ugni. As that component exists there is no
reason to keep this component.
- Create wrappers for the ugni functionality required by
btl/ugni. This was done to ease supporting multiple device
contexts. The wrappers are thread safe and currently use a spin
lock instead of a mutex. This produces better performance when
using multiple threads spread over multiple cores. In the future
this lock may be replaced by another serialization mechanism. The
wrappers are located in a new file: btl_ugni_device.h.
- Remove unnecessary device locking from serial parts of the ugni
btl. This includes the first add-procs and module finalize.
- Clean up fragment wait list code by moving enqueue into common
function.
- Expose the communication domain flags as an MCA variable. The
defaults have been updated to reflect the recommended setting for
knl and haswell.
- Avoid allocating fragments for communication with already
overloaded peers.
- Allocate RDMA endpoints dyncamically. This is needed to support
spreading RMA operations accross multiple contexts.
- Add support for spreading RMA communication over multiple ugni
device contexts. This should greatly improve the threading
performance when communicating with multiple peers. By default the
number of virtual devices depends on 1) whether
opal_using_threads() is set, 2) how many local processes are in the
job, and 3) how many bits are available in the pid. The last is
used to ensure that each CDM is created with a unique id.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
This commit exposes ugni statistics for use with MPI_T. There is
no overhead to providing these counters.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
